Scipedia: Collection of open conferences in research transport

Scalable Electric-Motor-in-the-Loop Testing for Vehicle Powertrains

Scipedia content — Thu, 28 Jan 2021 17:26:47 +0100

Model-Based System Testing (MBST) combines physical testing and simulation models to enable the validation of complex systems early-on in their design cycle. Therefore, it shows great potential for the validation of increasingly complex Electric Vehicle (EV) powertrains. In this work, the MBST methodology is applied to a downscaled powertrain, including a Permanent-Magnet Synchronous Machine (PMSM) and a 3-phase switch-mode inverter. This System-under-Test (SuT) is integrated into an X-in-the-Loop (XiL) test bench, where real-time simulation models of the rest of the vehicle are used to impose realistic boundary conditions to the SuT. These include the emulation of the vehicle inertia, its friction losses and the regenerative braking controller. Both hardware and software architectures required to achieve this setup are presented. Subsequently, a methodology used for computing scaling factors that match the power levels of the full vehicle to the miniature test bench is proposed. Finally, the combined physical-virtual system is evaluated on a driving cycle to validate its behaviour. The usage of a downscaled SuT constitutes the first step towards full-scale E-powertrain-in-the-loop testing, as well as a valuable multi-purpose didactical XiL setup.

info:eu-repo/semantics/published

Capacity Subscription Tariffs for Electricity Distribution Networks: Design Choices and Congestion Management

Scipedia content — Thu, 28 Jan 2021 17:40:18 +0100

Residential distribution networks in Europe are undergoing rapid changes. As high-power flexible loads, such as electric vehicle (EV) chargers, become more prevalent, the risk of network congestion increases. This is exacerbated by tariff structures which do not give incentives to limit simultaneous power consumption. Network charges in this case may not reflect the true costs of usage, as network costs are driven mainly by simultaneous load peaks.We present a systematic assessment of a new class of tariffs that is currently gaining attention in the Netherlands: capacity subscription models. We argue that this tariff structure is more cost-reflective and fair than the current fixed network fee and show how it helps to prevent transformer overloading in a simple simulation model of a neighborhood of 100 households constrained by a LV transformer, where a varying number of EVs are added.

Consumer Behavior Choice in the Era of Shared Mobility: The Role of Proximity, Competition, and Quality

Scipedia content — Thu, 28 Jan 2021 17:44:29 +0100

New Traffic Congestion Analysis Method in Developing Countries (India)

Scipedia content — Thu, 28 Jan 2021 17:49:04 +0100

Sustainable Transportation Reform Development through Partnerships Based on Bounded Rationality and Incremental Model

Scipedia content — Thu, 28 Jan 2021 17:50:08 +0100

A multi-criteria model for evaluating sustainable transportation system in West Sumatra

Scipedia content — Thu, 28 Jan 2021 17:57:42 +0100

Sustainability has become a major concern for transportation planning and policy around the world. This study develops a multi-criteria model to evaluate the sustainable transportation system in West Sumatra. A literature study is carried out to identify the indicators and then validated by the experts. As a result, a total of sixteen indicators divided into six indicators of the economic aspect, five indicators of the social aspect, and five indicators of the environmental aspect are proposed as the indicators of sustainable transportation evaluation. Next, the relationships among the indicators are determined using the Interpretive Structural Modeling (ISM) method. The results show that six indicators consist of accessibility of region, management of public transportation, the infrastructure of public transportation, transportation for people with special needs, level of traffic congestion, and land use to improve transportation facilities identified as the most influencing indicators. On the other hand, passenger convenience is suggested as the most dependent indicator. The importance weight of indicators is then determined using the Analytic Network Process (ANP) method. The land use to improve transportation facilities is regarded as the most important indicator, followed by the level of traffic congestion, and transportation for people with special needs. The model is expected to help the policymaker in improving the performance of a sustainable transportation system.

Extraction and Use of Geometry Data to Obtain 3D Buildings on a Web Map

Scipedia content — Thu, 28 Jan 2021 18:11:26 +0100

The Fifth International Conference on Advances in Computation, Communications and Services ACCSE 2020, 27/09/2020-01/10/2020, Lisboa, Portugal This work shows a comparison between two different techniques to obtain 3D buildings on a web map. The first one is based on the XYZ Tiles server of OSM Buildings and the second one is based on the Overpass servers of the collaborative project OpenStreetMap. Several simulations have been carried out to analyze their performance. Benefits and limitations of both methods are discussed. Comunidad de Madrid Universidad de Alcalá

Recruiting Apprentices - The Experience of On-boarding Practices in the Swiss Public Transportation Sector

Scipedia content — Thu, 28 Jan 2021 18:24:34 +0100

The professional socialization in a training company is a great challenge for young people. At the same time, they have to adapt to new organizational structures, integrate into a new workplace and competently master new tasks. Successful vocational socialization depends not only on the interests, abilities, and expectations of the young people but also on the company and its on-boarding practices. The aim of on-boarding measures is to help newcomers to get to know the company's structures and to facilitate their socialization into the culture of the company. Based on findings of an in-depth explorative case study within the public transportation sector in Switzerland, that included interviews with all stakeholders involved in apprenticeship training, the paper will address the practice of on-boarding in apprenticeship training and arrive at conclusions about innovative approaches.

Renewable Energy Generation and Impacts on E-Mobility

Scipedia content — Thu, 28 Jan 2021 18:30:17 +0100

This paper gives information about Renewable Energy Generation and its impacts on E-Mobility. By 2050, the two pillars of modern transformation are E-Mobility and Renewable Energy. This transformation requires adaptation to meet demographic and economic growth without increasing pollution and congestion. The modern world needs affordable, secure and inclusive, sustainable and integrated with customer-centric infrastructure and services. There is a great fundamental change needed in road transportation sector, which is to achieve its objective of a long term transition to a low-carbon economy. Electric Vehicles when charged with the electricity generated from Renewable Energy Sources can reduce future emissions of greenhouse gases and air pollutants from road transport. Electric Vehicles combined with renewable energy paint a different picture from the oversimplification of gas miles versus electric miles.Smart Mobility and Smart Grid technologies make people live more sustainable and efficiently.

Intuitive, Interactive Beard and Hair Synthesis with Generative Models

Scipedia content — Thu, 28 Jan 2021 18:34:02 +0100

We present an interactive approach to synthesizing realistic variations in facial hair in images, ranging from subtle edits to existing hair to the addition of complex and challenging hair in images of clean-shaven subjects. To circumvent the tedious and computationally expensive tasks of modeling, rendering and compositing the 3D geometry of the target hairstyle using the traditional graphics pipeline, we employ a neural network pipeline that synthesizes realistic and detailed images of facial hair directly in the target image in under one second. The synthesis is controlled by simple and sparse guide strokes from the user defining the general structural and color properties of the target hairstyle. We qualitatively and quantitatively evaluate our chosen method compared to several alternative approaches. We show compelling interactive editing results with a prototype user interface that allows novice users to progressively refine the generated image to match their desired hairstyle, and demonstrate that our approach also allows for flexible and high-fidelity scalp hair synthesis.

Comment: To be presented in the 2020 Conference on Computer Vision and Pattern Recognition (CVPR 2020, Oral Presentation). Supplementary video can be seen at: https://www.youtube.com/watch?v=v4qOtBATrvM

Materials Cloud, a platform for open computational science

Scipedia content — Thu, 28 Jan 2021 18:38:07 +0100

Materials Cloud is a platform designed to enable open and seamless sharing of resources for computational science, driven by applications in materials modelling. It hosts 1) archival and dissemination services for raw and curated data, together with their provenance graph, 2) modelling services and virtual machines, 3) tools for data analytics, and pre-/post-processing, and 4) educational materials. Data is citable and archived persistently, providing a comprehensive embodiment of the FAIR principles that extends to computational workflows. Materials Cloud leverages the AiiDA framework to record the provenance of entire simulation pipelines (calculations performed, codes used, data generated) in the form of graphs that allow to retrace and reproduce any computed result. When an AiiDA database is shared on Materials Cloud, peers can browse the interconnected record of simulations, download individual files or the full database, and start their research from the results of the original authors. The infrastructure is agnostic to the specific simulation codes used and can support diverse applications in computational science that transcend its initial materials domain.

Comment: 19 pages, 8 figure

Document type: Article

ComplexTrans – global land transportation system: the best way ahead for railways and roads is coherent cooperation, not the competition

Scipedia content — Thu, 28 Jan 2021 18:42:54 +0100

The land-transportation cannot meet its demands anymore. Jammed highways and cities, dangerous emissions, omnipresent traffic accidents, delays, expensive railways. Solutions are being sought to transfer a large part of passenger- and especially freight-traffic to (high-speed) rail and the efforts are shifting towards electromobility, car-sharing, 5G-connectivity, autonomous ride, MaaS-transport-coordination or Hyperloop-type solutions. However, all these solutions have further problems and limitations. Solutions are not sought where they really exist - in the mutual adaptation of the road and rail vehicles and their deep cooperation. The ComplexTrans-project shows that simply adapting dimensions and functions of the road and rail vehicles can eliminate (or at least substantially reduce) all the problems of existing land transport. The main features of the ComplexTrans system are sufficient parking spaces, reduced traffic density inside and outside of the cities, electric-vehicles with unlimited range and cheaper than the standard cars, cheaper and affordable recharging of batteries, autonomous ride, self-financing rail-transport, transfer of intercity freight to rail, replacement of part of the continental air-transport and many others.

Editorial : OpenStreetMap research in the COVID-19 era

Scipedia content — Thu, 28 Jan 2021 18:44:38 +0100

Minghini, M., Coetzee, S., Grinberger, A. Y., Yeboah, G., Juhász, L., & Mooney, P. (2020). Editorial: OpenStreetMap research in the COVID-19 era In: Minghini, M., Coetzee, S., Juhász, L., Yeboah, G., Mooney, P., Grinberger, A.Y. (Eds.). Proceedings of the Academic Track at the State of the Map 2020 Online Conference, July 04-05 2020. Available at https://zenodo.org/communities/sotm-2020

Group-In: Group Inference from Wireless Traces of Mobile Devices

Scipedia content — Thu, 28 Jan 2021 18:57:04 +0100

This paper proposes Group-In, a wireless scanning system to detect static or mobile people groups in indoor or outdoor environments. Group-In collects only wireless traces from the Bluetooth-enabled mobile devices for group inference. The key problem addressed in this work is to detect not only static groups but also moving groups with a multi-phased approach based only noisy wireless Received Signal Strength Indicator (RSSIs) observed by multiple wireless scanners without localization support. We propose new centralized and decentralized schemes to process the sparse and noisy wireless data, and leverage graph-based clustering techniques for group detection from short-term and long-term aspects. Group-In provides two outcomes: 1) group detection in short time intervals such as two minutes and 2) long-term linkages such as a month. To verify the performance, we conduct two experimental studies. One consists of 27 controlled scenarios in the lab environments. The other is a real-world scenario where we place Bluetooth scanners in an office environment, and employees carry beacons for more than one month. Both the controlled and real-world experiments result in high accuracy group detection in short time intervals and sampling liberties in terms of the Jaccard index and pairwise similarity coefficient.

Comment: This work has been funded by the EU Horizon 2020 Programme under Grant Agreements No. 731993 AUTOPILOT and No.871249 LOCUS projects. The content of this paper does not reflect the official opinion of the EU. Responsibility for the information and views expressed therein lies entirely with the authors. Proc. of ACM/IEEE IPSN'20, 2020

AUTOTRACKER: Autonomous inspection — capabilities and lessons learned in offshore operations

Scipedia content — Thu, 28 Jan 2021 19:01:05 +0100

This paper presents AUTOTRACKER, an autonomous pipeline inspection system that operates as a dynamic mission payload for an Autonomous Underwater Vehicle (AUV). The paper describes the mode of operation, together with the validation & trial operations AUTOTRACKER has undertaken over the years, and how this valuable experience has been fed back into the future development of the system.

On the Use of Smartphone Sensors for Developing Advanced Driver Assistance Systems

Scipedia content — Thu, 21 Jan 2021 13:27:50 +0100

Technological evolution impacts several industries, including automotive. The combination of software with advancements in sensory capabilities results in new Advanced Driver Assistance System (ADAS). The pervasiveness of smartphones and their sensory capabilities makes them an solid platform for the development of ADAS. Our work is motivated by concerns on the reliability of data acquired from such devices for developing ADAS. We performed a number of controlled experiments to understand which factors impact the collection of accelerometer data with smartphones. We conclude that the quality of data acquired is not significantly affected by using different smartphones, car mounts, rates of sampling, or vehicles for the purpose of developing ADAS. Our results indicate that smartphone sensors can be used to develop ADAS. Research sponsored by the Portugal Incentive System for Research and TechnologicalDevelopment. Project in co-promotion no. 002797/2015 (INNOVCAR 2015-2018).

Learning multiview 3D point cloud registration

Scipedia content — Thu, 28 Jan 2021 19:38:05 +0100

We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm. Registration of multiple scans typically follows a two-stage pipeline: the initial pairwise alignment and the globally consistent refinement. The former is often ambiguous due to the low overlap of neighboring point clouds, symmetries and repetitive scene parts. Therefore, the latter global refinement aims at establishing the cyclic consistency across multiple scans and helps in resolving the ambiguous cases. In this paper we propose, to the best of our knowledge, the first end-to-end algorithm for joint learning of both parts of this two-stage problem. Experimental evaluation on well accepted benchmark datasets shows that our approach outperforms the state-of-the-art by a significant margin, while being end-to-end trainable and computationally less costly. Moreover, we present detailed analysis and an ablation study that validate the novel components of our approach. The source code and pretrained models are publicly available under https://github.com/zgojcic/3D_multiview_reg.

Comment: CVPR2020 - Camera Ready

UAS Based Methodology for Measuring Glide Slope Angles of Airport Precision Approach Path Indicators (PAPI)

Scipedia content — Thu, 28 Jan 2021 19:39:22 +0100

The Precision Approach Path Indicator (PAPI) is a Visual Glide Slope Indicator that uses a two-color light projector system to produce a visual glidepath for pilots approaching a runway. This paper reports on a methodology for using an Unmanned Aircraft System (UAS) to measure angles where PAPI lights transition from white to red to assess compliance with the US Federal Aviation Administration (FAA) Order JO6850.2B. The UAS captured images from a series of elevations at varying distances from the PAPI lights on runway 10 at the Purdue University Airport on June 27, 2019. Precise location of each image was obtained by mounting a survey prism on the UAS and using ground-based surveying total stations to record the x, y, z location of the UAS. Two 15-minute UAS missions collected 70 images that were synchronized with total station readings. UAS images were classified by the number of white and red PAPI lights visible. A logit model was used to estimate the glidepath transition angle of the four PAPI Light Housing Assemblies, which were compared with the angle and tolerance of transition angles defined in FAA Order JO6850.2B. A second independent robotic total station measured the location of the UAS when images were taken. Comparing the two independent total station measurements, the root mean squared error of the UAS position on the glide slope was 1.3 arc-min. The paper concludes that low cost UAS with a total station can quickly and accurately evaluate PAPI lights to determine if they are aimed within the prescribed FAA tolerance.

Withdrawal: Initial Validation of a Simulation System for Studying Interoperability in Future Air Traffic Management Systems

Scipedia content — Thu, 28 Jan 2021 19:59:20 +0100

LiDAR-enhanced Structure-from-Motion

Scipedia content — Thu, 28 Jan 2021 20:12:49 +0100

hough Structure-from-Motion (SfM) as a maturing technique has been widely used in many applications, state-of-the-art SfM algorithms are still not robust enough in certain situations. For example, images for inspection purposes are often taken in close distance to obtain detailed textures, which will result in less overlap between images and thus decrease the accuracy of estimated motion. In this paper, we propose a LiDAR-enhanced SfM pipeline that jointly processes data from a rotating LiDAR and a stereo camera pair to estimate sensor motions. We show that incorporating LiDAR helps to effectively reject falsely matched images and significantly improve the model consistency in large-scale environments. Experiments are conducted in different environments to test the performance of the proposed pipeline and comparison results with the state-of-the-art SfM algorithms are reported.

Acceleration of the Pair-HMM forward algorithm on FPGA with cloud integration for GATK

Scipedia content — Thu, 28 Jan 2021 20:37:37 +0100

The Pair-HMM forward algorithm is an essential algorithm found in many genomic related analyses. The high number of floating point operations in the algorithm makes it one of the main contributors to the compute time of analysis pipelines. To speed-up computations we propose an FPGA-based hardware accelerator for the Amazon AWS F1 Cloud platform. The accelerator is open source and has been tested within the popular Genomic Analysis Toolkit (GATK) pipeline. The accelerator achieved up to 15 × speed-up against the software implementation when used in-pipeline. The accelerator has also been tested in the experimental Spark (distributed) version of the GATK HaplotypeCaller tool. An in-depth analysis of the compute time contributions allowed to point out the main bottlenecks for accelerators in the GATK pipeline, resulting in a hybrid CPU-FPGA solution to best exploit both resources.

Coordination of Power and Natural Gas Systems: Convexification Approaches for Linepack Modeling

Scipedia content — Thu, 28 Jan 2021 20:38:12 +0100

Utilizing operational flexibility from natural gas networks can foster the integration of uncertain and variable renewable power production. We model a combined power and natural gas dispatch to reveal the maximum potential of linepack, i.e., energy storage in the pipelines, as a source of flexibility for the power system. The natural gas flow dynamics are approximated by a combination of steady-state equations and varying incoming and outgoing flows in the pipelines to account for both natural gas transport and linepack. This steady-state natural gas flow results in a nonlinear and nonconvex formulation. To cope with the computational challenges, we explore convex quadratic relaxations and linear approximations. We propose a novel mixed-integer second-order cone formulation including McCormick relaxations to model the bidirectional natural gas flow accounting for linepack. Flexibility is quantified in terms of system cost compared to a dispatch model that either neglects linepack or assumes infinite storage capability.

Dead-lock in the introduction of ERS-systems - a case of true uncertainty

Scipedia content — Thu, 28 Jan 2021 20:46:26 +0100

a major contributor to reaching the goals of de-carbonization of the transport sector, the introduction of ERS-systems for heavy vehicles is a prioritized action, with Sweden as an example. Even if de-carbonization is asked for by policymakers, and part of the medium to long term strategy for many transport market players, it is very difficult to get the transition to take off. Hindrances related to current roles on the market, regulation and the ability to find new ways to finance and foster new business models can be observed. This resembles a ‘true uncertainty’-situation. The result might be a dead-lock where the introduction of ERS-systems is delayed. It is argued here that platforms and frameworks for testing new systems, where “regimes” supporting shared risk mitigation, faster innovation, and deployment of ERS-technology could be supported. We discuss possible ways for establishing such platforms and crucial policy content for these.

Comparative Analysis of Vehicle-to-Vehicle (V2V) Power Transfer Configurations without Additional Power Converters

Scipedia content — Thu, 28 Jan 2021 20:49:43 +0100

This paper presents a comparative analysis of power transfer configurations towards vehicle-to-vehicle (V2V) battery charging operation without using additional power converters, i.e., using just the on-board battery chargers of two electric vehicles (EVs). Three access interfaces were considered, namely the ac power grid interface, the dc-link interface and the dc battery interface, which allow the establishment of eight V2V configurations. The defined configurations are described and verified through computational simulations. A comparison is performed based on quantitative data, i.e., power transfer efficiency for a given output power range, and qualitative data, i.e., flexibility and safety. According to the obtained results, it can be concluded that each V2V configuration has its pros and cons regarding efficiency, number of possible quadrant operation and need for additional equipment. This work has been supported by FCT –Fundação para a Ciência e Tecnologiawith-in the Project Scope: UID/CEC/00319/2019. This work has been supported by the FCT Project DAIPESEV PTDC/EEI-EEE/30382/2017, and by FCTProject new-ERA4GRIDs PTDC/EEI-EEE/30283/2017. Mr. Tiago J. C. Sousa is supported by the doctoral scholarship SFRH/BD/134353/2017 granted by the Portuguese FCT agency.

Squeeze-and-Excitation SqueezeNext: An Efficient DNN for Hardware Deployment

Scipedia content — Thu, 28 Jan 2021 20:53:50 +0100

Convolution neural network is being used in field of autonomous driving vehicles or driver assistance systems (ADAS), and has achieved great success. Before the convolution neural network, traditional machine learning algorithms helped the driver assistance systems. Currently, there is a great exploration being done in architectures like MobileNet, SqueezeNext & SqueezeNet. It improved the CNN architectures and made it more suitable to implement on real-time embedded systems. This paper proposes an efficient and a compact CNN to ameliorate the performance of existing CNN architectures. The intuition behind this proposed architecture is to supplant convolution layers with a more sophisticated block module and to develop a compact architecture with a competitive accuracy. Further, explores the bottleneck module and squeezenext basic block structure. The state-of-the-art squeezenext baseline architecture is used as a foundation to recreate and propose a high performance squeezenext architecture. The proposed architecture is further trained on the CIFAR-10 dataset from scratch. All the training and testing results are visualized with live loss and accuracy graphs. Focus of this paper is to make an adaptable and a flexible model for efficient CNN performance which can perform better with the minimum tradeoff between model accuracy, size, and speed. Having a model size of 0.595MB along with accuracy of 92.60% and with a satisfactory training and validating speed of 9 seconds, this model can be deployed on real-time autonomous system platform such as Bluebox 2.0 by NXP.

Debugging Machine Learning Pipelines

Scipedia content — Thu, 28 Jan 2021 21:08:46 +0100

Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous or uninformative outputs, the pipeline may fail or produce incorrect results. Inferring the root cause of failures and unexpected behavior is challenging, usually requiring much human thought, and is both time-consuming and error-prone. We propose a new approach that makes use of iteration and provenance to automatically infer the root causes and derive succinct explanations of failures. Through a detailed experimental evaluation, we assess the cost, precision, and recall of our approach compared to the state of the art. Our source code and experimental data will be available for reproducibility and enhancement.

Comment: 10 page

Impact of Electric Vehicle Charging Infrastructure Expansion on Microgrid Economics: A Case Study

Scipedia content — Thu, 28 Jan 2021 21:52:15 +0100

The operation of public and semi-public charging infrastructure is often not profitable yet. However, the integration of charging infrastructure in microgrids enables the introduction of innovative business models, e.g. by local renewable energy generation and storage units. Another driver to improve profitability is to adapt the charging infrastructure expansion according to its usage characteristics. This study presents a method to optimize the charging infrastructure expansion. Therefore, a mixed integer linear program with the aim to minimize costs is formulated and applied on real-world data. Via the optimization, different scenarios are developed and the microgrid integration is simulated in an operation optimization algorithm. Different business models such as PV and battery storage integration are computed and the economics of the business models in the different scenarios are evaluated. It can be concluded that microgrid integration can be a significant driver of charging infrastructure operation profitability. Integrating PV generation shortens the payback period in all scenarios. Also, PV generation and battery storage combined improve profitability, but not to the same extent than without storage unit. Furthermore, the optimization of the charging infrastructure expansion leads to a significant improvement of profitability. Combining both the microgrid integration, as well as the expansion optimization, the payback period can be decreased by up until 67 %.

Should I Stay or Should I Go? Automated Vehicles in the Age of Climate Change

Scipedia content — Thu, 28 Jan 2021 22:08:20 +0100

Will automated driving help or hurt our efforts to remedy climate change? The overall impact of transportation and mobility on the global ecosystem is clear: changes to that system can greatly affect climate outcomes. The design of mobility and automotive systems will influence key factors such as driving style, fuel choice, ride sharing, traffic patterns, and total mileage. However, to date, there are few research efforts that explicitly focus on these overlapping themes (automated driving & climate changes) within the HCI and AutomotiveUI communities. Our intention is to grow this community and awareness of the related problems. Specifically, in this workshop, we invite designers, researchers, and practitioners from the sustainable HCI, persuasive design, AutomotiveUI, and mobility communities to collaborate in finding ways to make future mobility more sustainable. Using embodied design improvisation and design fiction methods, we will explore the ways that systems affect behavior which then affect the environment.

Exploring Spiking Neural Networks for Prediction of Traffic Congestion in Networks-on-Chip

Scipedia content — Thu, 28 Jan 2021 22:12:28 +0100

Developing a Traffic Congestion Model based on Google Traffic Data: A Case Study in Ecuador

Scipedia content — Thu, 28 Jan 2021 22:13:16 +0100

Applying Enterprise Architecture for Digital Transformation of Electro Mobility towards Sustainable Transportation

Scipedia content — Thu, 28 Jan 2021 22:27:24 +0100

Electro Mobility (eMobility) involves deploying Information and Communication Technologies (ICT) and electric technologies in vehicles to enable electric propulsion of vehicles referred to as Electric Vehicles (EVs). EVs are key infrastructure for achieving a sustainable energy future since EV usage can support in achieving CO2 reduction. However, the deployment of EVs for eMobility is highly dependent on data integration of mobility solutions from different stakeholders involved in urban transportation. Respectively, data integration from different mobility services will result to cost reduction and create valued added services to citizens. Therefore, there is need to achieve data integration not only for physical systems but for all domains in providing mobility related services that can be synergically applied to citizens and stakeholders in order to develop innovative solutions at district and urban level. Therefore, this study adopts Enterprise Architecture (EA) for digital transformations of eMobility services for sustainable transportation. Action research methodology was employed and secondary data from the literature was presented in the industrial data space reference architecture to initially validate digital transformation of electro mobility. Findings from this study reveal that EA support digital transformation of eMobility in managing data integration to support cities to implement sustainable transportation services. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Permissions@acm.org. SIGMIS-CPR '20, June 19–21, 2020, Nuremberg, Germany © 2020 Association for Computing Machinery. ACM ISBN 978-1-4503-7130-8/20/06…$15.00 https://doi.org/10.1145/3378539.3393858

Recharge at lunch, an alternative to handle the range issues of electric vehicles

Scipedia content — Thu, 28 Jan 2021 22:34:43 +0100

International audience

ANALYSIS OF EXISTING PASSENGER TRAFFIC BY MODE OF TRANSPORT AND ASSESSMENT THE COMPETITIVENESS HIGH-SPEED TRAFFIC IN UKRAINE

Scipedia content — Thu, 28 Jan 2021 22:51:14 +0100

The article analyses the volume of passenger traffic from 1990 to 2019 for land, water and air transport. From the materials obtained and the experience of the networks of European and world high-speed railways, goals are set. High-speed lines designed exclusively for passenger traffic. This moment plays an important role in reducing the cost of construction, increasing the market and economic profitability. According to the data from the State Statistics Service of Ukraine, it is possible to calculate the passenger flow based on the known parameters for 2020–2032 in the direction of Kiev-Lviv. The design of high-speed lines should meet general requirements aimed at satisfying the basic characteristics of a high-speed railway system, which works in conjunction with the European High-Speed Railway network. The compatibility of the parameters of high-speed lines with the parameters of traditional lines is part of the operational requirements for the gradual introduction of a network of high-speed railways. Possible scenarios to achieve the required compatibility should cover all subsystems. DOI: https://doi.org/10.3846/enviro.2020.689

A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images

Scipedia content — Thu, 28 Jan 2021 23:02:46 +0100

Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process. Cycle consistency loss and a patched discriminator are utilized to further improve the performance. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.

O-007 An analysis of stroke thrombectomy interhospital transportation modality

Scipedia content — Thu, 28 Jan 2021 23:08:36 +0100

Objective Expeditious interhospital transport of patients with potential large-vessel occlusions is key in the hub and spoke model, where patients are first taken to a local primary hospital to be evaluated for intravenous thrombolysis, and then subsequently transferred to an endovascular capable stroke center. The decision on transport modality—air versus ground transportation—may be multifactorial, dependent upon dispatch times, availability, and cost. This study aims to evaluate and quantify the presumed reduction in time to thrombectomy with air compared to ground transport. Methods Patients undergoing mechanical thrombectomy for carotid circulation occlusion within 6 hours at an urban, comprehensive stroke center were retrospectively analyzed. Multivariable linear regression evaluated the relationship between transport modality and the time from last known well to groin puncture after adjusting for distance from the comprehensive stroke center. Results From January 2015 to March 2018, 133 mechanical thrombectomy interhospital transfers were identified; transportation modality was air in 30.8% (n=41) and ground in 69.2% (n=92). The mean inter-hospital distance was 24.1 (standard deviation 16.4, range 0–62) miles. Among patients travelling greater than 10 miles, the use of air transport was associated with a significantly shorter time between last known well and groin puncture when compared to ground (by 26.3 minutes, 95% CI: 1.1–51.9 minutes, p=0.04). The benefit of air transport was greater with increasing distances, with a significantly shorter time to thrombectomy of 35.1 minutes (p=0.02) if an inter-hospital distance of greater than 20 miles, and of 42.2 minutes (p=0.03) if greater than 30 miles. Within 10 miles however, all patients were transported by ground. Conclusions In this single-center analysis, helicopter emergency medical service lead to a shorter time to thrombectomy compared with ground transport. Given the known benefit to earlier revascularization on stroke outcomes, these data support the use of emergency aeromedical services when logistically feasible for stroke thrombectomy interhospital transfers greater than 10 miles. Disclosures H. Dasenbrock: None. A. Beer-Furlan: None. A. Vargas: None. J. Connors: None. R. Crowley: None. M. Chen: 2; C; Genentech, Pneumbra, Stryker, Medtronic.

Application of game theory in planning passenger rail and road transport on parallel routes

Scipedia content — Thu, 28 Jan 2021 23:17:49 +0100

Online Variant of Parcel Allocation in Last-Mile Delivery

Scipedia content — Thu, 28 Jan 2021 23:35:26 +0100

We investigate the problem of last-mile delivery, where a large amount of crowd-workers have performed a great quantity of location-specific urban logistics parcels. Current existing approaches mainly focus on offline scenarios, where all the spatial-temporal information of parcels and workers are given. However, the offline scenarios can be impractical since parcels and workers appear dynamically in reality, and the information of workers is unknown in advance. In this paper, we study the problem of last-mile delivery on online scenarios to resolve the shortcomings of the offline setting. We first formalize the online parcel allocation in last-mile delivery problem, where all parcels were put in pop-stations in advance, and workers arrive dynamically. Then we propose a baseline algorithm with no competitive ratio, and an algorithm providing theoretical guarantee for the parcel allocation in last-mile delivery. Finally, we verify the effectiveness and efficiency of proposed algorithms through extensive experiments on real and synthetic datasets.

Travel Time Prediction using Machine Learning and Weather Impact on Traffic Conditions

Scipedia content — Thu, 28 Jan 2021 23:46:04 +0100

The growth of Intelligent Traffic System (ITS) have recently been quite fast and impressive. Analysis and prediction of network traffic has become a priority in day to day planning in social, economic and more widespread set of areas. With a vision to further contribute to this vast field of research, we propose an approach to forecast level of traffic congestion on the basis of a time series analysis of collected data using machine learning. Moreover, the proposed approach allows us to find a correlation between varying parameter of weather and level of traffic congestion. Traffic data collected from Uber Movement for the city of Mumbai, India was fed to multiple of pre assessed machine learning algorithm. Comparative analysis of the results of the different machine learning algorithms used have shown us that logistic regression works best with an accuracy of 85% on the collected Uber data. Thus our model can accurately predict the time to travel between different nodes (locations) in Mumbai city based on the data collected from Uber Movement.

High precision indoor positioning by means of LiDAR

Scipedia content — Thu, 28 Jan 2021 23:51:55 +0100

The trend towards autonomous driving and the continuous research in the automotive area, like Advanced Driver Assistance Systems (ADAS), requires an accurate localization under all circumstances. An accurate estimation of the vehicle state is a basic requirement for any trajectory-planning algorithm. Still, even when the introduction of the GPS L5 band promises lane-accuracy, coverage limitations in roofed areas still have to be addressed. In this work, a method for high precision indoor positioning using a LiDAR is presented. The method is based on the combination of motion models with LiDAR measurements, and uses infrastructural elements as positioning references. This allows to estimate the orientation, velocity over ground and position of a vehicle in a Local Tangent Plane (LTP) reference frame. When the outputs of the proposed method are compared to those of an Automotive Dynamic Motion Analyzer (ADMA), mean errors of 1 degree, 0.1 m/s and of 4.7 cm respectively are obtained. The method can be implemented by using a LiDAR sensor as a stand-alone unit. A median runtime of 40.77 us on an Intel i7-6820HQ CPU signals the possibility of real-time processing.

Development of Methodological Approaches to the Planning of Operation of Road Transport Systems

Scipedia content — Fri, 29 Jan 2021 00:02:23 +0100

Estimating Model Uncertainty of Neural Networks in Sparse Information Form

Scipedia content — Fri, 29 Jan 2021 00:13:41 +0100

We present a sparse representation of model uncertainty for Deep Neural Networks (DNNs) where the parameter posterior is approximated with an inverse formulation of the Multivariate Normal Distribution (MND), also known as the information form. The key insight of our work is that the information matrix, i.e. the inverse of the covariance matrix tends to be sparse in its spectrum. Therefore, dimensionality reduction techniques such as low rank approximations (LRA) can be effectively exploited. To achieve this, we develop a novel sparsification algorithm and derive a cost-effective analytical sampler. As a result, we show that the information form can be scalably applied to represent model uncertainty in DNNs. Our exhaustive theoretical analysis and empirical evaluations on various benchmarks show the competitiveness of our approach over the current methods.

Comment: Accepted to the Thirty-seventh International Conference on Machine Learning (ICML) 2020

Efficient Transport Logistics : An Approach for Urban Freight Transport in Austria

Scipedia content — Fri, 29 Jan 2021 00:18:12 +0100

To alleviate traffic congestion that results from the growth of e-commerce we propose an approach in the city of Linz, Austria by relying on shared distribution centers from different companies. We develop two algorithms to find out the optimal location for the hubs and calculate the shortest path between locations. Results showed that in an urban environment, the implementation of hubs results in a reduction of the number of delivery vehicles. It reduces driving distances from hub to the customers, and also benefits the drivers that need to return home every day.

Comment: 6 pages, 5 figures, 2 Tables, accepted for publication in the proceedings of the CISTI'2020 - 15th Iberian Conference on Information Systems and Technologie

Semantic Management of Urban Traffic Congestion

Scipedia content — Fri, 29 Jan 2021 00:24:36 +0100

Increasing Traffic Flows with DSRC Technology: Field Trials and Performance Evaluation

Scipedia content — Fri, 29 Jan 2021 00:53:05 +0100

traffic congestion becomes a huge problem for most developing and developed countries across the world, intelligent transportation systems (ITS) are becoming a hot topic that is attracting attention of researchers and the general public alike. In this paper, we demonstrate a specific implementation of an ITS system whereby traffic lights are actuated by DSRC radios installed in vehicles. More specifically, we report the design of prototype of a DSRC-Actuated Traffic Lights (DSRC-ATL) system. It is shown that this system can reduce the travel time and commute time significantly, especially during rush hours. Furthermore, the results reported in this paper do not assume or require all vehicles to be equipped with DSCR radios. Even with low penetration ratios, e.g., when only 20% of all vehicles in a city are equipped with DSRC radios, the overall performance of the designed system is superior to the current traffic control systems.

Comment: 5 pages, 9 figures, submitted to the 44th Annual Conference of the IEEE Industrial Electronics Society (IECON 2018), special session of Connected-and-Automated Vehicle Integration, Safety, and Environment Design, on June 30, 2018

A Methodological Framework of Human-Machine Co-Evolutionary Intelligence for Decision-Making Support of ATM

Scipedia content — Mon, 01 Feb 2021 16:06:44 +0100

International audience; Despite of the success of artificial intelligent (AI) methods in many domains, there is big dilemma for AI when applying to air traffic management (ATM). That is AI researchers have long stated their AI methods are effective and reliable enough to handle many ATM problems, while human controllers still refuse to adopt such AI methods. We believe the dilemma is not about whether AI methods is effective or reliable enough, but about why human controllers should be replaced by AI methods. In other words, as long as an AI method aims to compete and replace human controllers, it will be confronted with the difficulty of not being accepted by human controllers. To address this dilemma, this paper proposes a new thinking about applying AI methods, i.e., an AI method should be developed in such a way of assisting human controllers, but never in the way of competing and replacing human controllers. This new thinking is called human-machine coevolutionary intelligence (HMCEI). A methodological framework of HMCEI is further developed for decision-making support of ATM, in order to demonstrate the concept of HMCEI is practicably possible.

Solving Aircraft Conflicts: data resources

Scipedia content — Mon, 01 Feb 2021 16:24:22 +0100

International audience; In the domain of air traffic, two planes are considered as in a conflict situation when their trajectoriescross each other in certain circumstances of distance at the same time. Air Traffic Management(ATM) has adopted some rules to avoid such conflicts but the increasing density of aircraft flightsmakes conflict situations more and more difficult to anticipate and solve in an optimal way. Decisionsto solve conflicts are made manually in real-time and consist of changing aircraft trajectories tomaintain a safe distance between planes. When a conflict is identified, the Air Traffic Controller(ATCO) has to make a quick decision about the best possible solution using his/her knowledge andexperience. ATCOs have to take into account all the aircraft flight parameters such as its speed,positioning coordinate, destination, flight plan, as well as its environment, for example, weather,wind direction, military zone, etc. and the other flights. The air traffic growth is so that the ATCOs willnot be able to face conflict solving in the future if they are not assisted effectively. Moreconsideration should thus be given to (a) identifying conflict situations (b) assist ATCOs in conflictsolving. Many organizations keep data that could serve these challenges but data from similators canalso be used.In this communication, we will present the context of aircraft conflicts. We will detail the datasources that are available and that could be used for conflict detection and automated conflictsolving. Moreover, we will present the data collection we built as a new resource for simulated datathat we intend to deliver to the scientific community as a shared data source.

Reconfigurable Stationary Battery with Adaptive Cell Switching for Electric Vehicle Fast-Charging

Scipedia content — Mon, 01 Feb 2021 19:34:45 +0100

In this study, we introduce a battery energy storage system (BESS) with reconfigurable cell topology as the direct power source for fast-charging of electric vehicles (EVs). In the proposed scenario, the BESS is following the charging request of the EV by changing its cell topology in a real time fashion. The BESS is modelled at the cell level in order to demonstrate the reconfigurable design, and linked with an EV model. The simulation results confirm that the BESS can maintain a balanced level of its cell states while following the voltage request of the EV with satisfactory precision. However, the approach of adaptive cell switching shows to be not sufficient for fulfilling the current request. Therefore, complementary solutions are necessary to achieve a suitable control of the charging current.

Dynamic Hot Spot Prediction by Learning Spatial- Temporal Utilization of Taxiway Intersections

Scipedia content — Mon, 01 Feb 2021 19:41:19 +0100

International audience; Airports across the world are expanding by building multiple ground control towers and resorting to complex taxiway and runway system, in response to growing air traffic. Current outcome- based ground safety management at the airside may impede our potential to learn from and adapt to evolving air traffic scenarios, owing to the sparsity of accidents when compared with number of daily airside operations. To augment airside ground safety at Singapore Changi airport, in this study, we predict dynamic hot spots- areas where multiple aircraft may come in close vicinity on taxiways, as pre-cursor events to airside conflicts. We use airside infrastructure and A-SMGCS operations data of Changi airport to model aircraft arrival at different taxiway intersections both in temporal and spatial dimensions. The statistically learnt spatial-temporal model is then used to compute conflict probability at identified intersections, in order to evaluate conflict coefficients or hotness values of hot spots. These hot spots are then visually displayed on the aerodrome diagram for heightened attention of ground ATCOs. In the Subjective opinion of Ground Movement Air Traffic Controller, highlighted Hot Spots make sense and leads to better understanding of taxiway movements and increased situational awareness. Future research shall incorporate detailed human-in-the-loop validation of the dynamic hot spot model by ATCOs in 360 degree tower simulator.

Approach and landing aircraft on-board parameters estimation with LSTM networks

Scipedia content — Mon, 01 Feb 2021 19:52:33 +0100

International audience; This paper addresses the problem of estimating aircraft on-board parameters using ground surveillance available parameters. The proposed methodology consists in training supervised Neural Networks with Flight Data Records to estimate target parameters. This paper investigates the learning process upon three case study parameters: the fuel flow rate, the flap configuration, and the landing gear position. Particular attention is directed to the generalization to different aircraft types and airport approaches. From the Air Traffic Management point of view, these additional parameters enable a better understanding and awareness of aircraft behaviors. These estimations can be used to evaluate and enhance the air traffic management system performance in terms of safety and efficiency.

Learning by Analogy: Reliable Supervision From Transformations for Unsupervised Optical Flow Estimation

Scipedia content — Mon, 01 Feb 2021 20:08:51 +0100

Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods. However, the objective of unsupervised learning is likely to be unreliable in challenging scenes. In this work, we present a framework to use more reliable supervision from transformations. It simply twists the general unsupervised learning pipeline by running another forward pass with transformed data from augmentation, along with using transformed predictions of original data as the self-supervision signal. Besides, we further introduce a lightweight network with multiple frames by a highly-shared flow decoder. Our method consistently gets a leap of performance on several benchmarks with the best accuracy among deep unsupervised methods. Also, our method achieves competitive results to recent fully supervised methods while with much fewer parameters.

Comment: Accepted to CVPR 2020, https://github.com/lliuz/ARFlow

High-Resolution Augmentation for Automatic Template-Based Matching of Human Models

Scipedia content — Mon, 01 Feb 2021 20:12:04 +0100

We propose a new approach for 3D shape matching of deformable human shapes. Our approach is based on the joint adoption of three different tools: an intrinsic spectral matching pipeline, a morphable model, and an extrinsic details refinement. By operating in conjunction, these tools allow us to greatly improve the quality of the matching while at the same time resolving the key issues exhibited by each tool individually. In this paper we present an innovative High-Resolution Augmentation (HRA) strategy that enables highly accurate correspondence even in the presence of significant mesh resolution mismatch between the input shapes. This augmentation provides an effective workaround for the resolution limitations imposed by the adopted morphable model. The HRA in its global and localized versions represents a novel refinement strategy for surface subdivision methods. We demonstrate the accuracy of the proposed pipeline on multiple challenging benchmarks, and showcase its effectiveness in surface registration and texture transfer.

Data-Driven Location Annotation for Fleet Mobility Modeling

Scipedia content — Mon, 01 Feb 2021 20:20:25 +0100

The large availability of mobility data allows studying human behavior and human activities. However, this massive and raw amount of data generally lacks any detailed semantics or useful categorization. Annotations of the locations where the users stop may be helpful in a number of contexts, including user modeling and profiling, urban planning, activity recommendations, and can even lead to a deeper understanding of the mobility evolution of an urban area. In this paper, we foster the expressive power of individual mobility networks, a data model describing users' behavior, by defining a data-driven procedure for locations annotation. The procedure considers individual, collective, and contextual features for turning locations into annotated ones. The annotated locations own a high expressiveness that allows generalizing individual mobility networks, and that makes them comparable across different users. The results of our study on a dataset of trucks moving in Greece show that the annotated individual mobility networks can enable detailed analysis of urban areas and the planning of advanced mobility applications.

Exploring the Potential of Traffic Index Data to Analyze Essential Traffic Impact in Developing Cities

Scipedia content — Mon, 01 Feb 2021 20:31:14 +0100

Abstract. In developing countries, metropolitan cities, due to their economic activities, attract an increasing amount of commuters on a daily basis. This has led to major freeways and roads experiencing high levels of congestion and consequently high pollution levels. In 2020, due to a global pandemic of an outbreak of Corona Virus (COVID-19), the national government declared a national shutdown with only essential traffic being allowed to operate. Given the scenario of the national lock-down this allows for the statistical analysis of the impact of essential traffic on the overall transportation system. Consequently the aim of the paper was to assess the congestion and CO2 emission impact of essential traffic for the City of Johannesburg. Using an exploratory approach, we monitored and collected traffic congestion data from the Tomtom traffic index for the metropolitan city of Johannesburg, South Africa. We develop a relationship between congestion and pollution to visualise the daily variations in pollution and congestion levels. We demonstrate this by comparing variations in congestion levels in two epochs, viz the period without movement restrictions and the period whereby movement is restricted. The results reveal essential traffic on the congestion index to be below 22 percent for both weekends and weekdays. A scenario common only during weekends in 2019. Whilst for the emission index, CO2 levels are approximately less than 45 percent throughout the week. The paper concludes the investment into mining and analysing traffic data has a significantly role for future mobility planning in both the developed and developing world and, more generally, improving the quality of commuting trips in the city.

Document type: Article

Agent based simulation for the design of a mobility service in the Paris-Saclay area

Scipedia content — Mon, 01 Feb 2021 20:56:06 +0100

International audience; Autonomous vehicles promise an important opportunity for a complete paradigm shift for the design of transportation systems. These systems will become more flexible and efficient by adapting to the travelers' demand. On the other hand, multi agent systems offer an intuitive and powerful way to design complex distributed systems and agent based simulation has proved to be well suited for studying the performance of mobility services and their impact on the users and the traffic in general. In this study, we use an Agent-Based modeling approach to design a mobility system based on a fleet of autonomous vehicles (robo-taxis and shuttles) and connected road side units, each of these elements represented by intelligent collaborative agents. In our model, the control is distributed among the agents and the global behaviour of the system emerges from local decisions. We then used a microsimulation tool to test the model on the real road network of the Paris-Saclay area. Since this area is planned to become a center for technology, innovation and education and is currently under constant development, it offers an opportunity for the design and the implementation of new models of transportation services. We designed our mobility system in an incremental manner by introducing more components and more intelligent behaviour and testing its performance at each step. Our results suggest that for our area of study, a mobility service that relies on autonomous vehicles aided by connected road side units that allow to retrieve information about the traffic would perform better than a regular service.

Uncertainty Based Camera Model Selection

Scipedia content — Mon, 01 Feb 2021 21:07:46 +0100

The quality and speed of Structure from Motion (SfM) methods depend significantly on the camera model chosen for the reconstruction. In most of the SfM pipelines, the camera model is manually chosen by the user. In this paper, we present a new automatic method for camera model selection in large scale SfM that is based on efficient uncertainty evaluation. We first perform an extensive comparison of classical model selection based on known Information Criteria and show that they do not provide sufficiently accurate results when applied to camera model selection. Then we propose a new Accuracy-based Criterion, which evaluates an efficient approximation of the uncertainty of the estimated parameters in tested models. Using the new criterion, we design a camera model selection method and fine-tune it by machine learning. Our simulated and real experiments demonstrate a significant increase in reconstruction quality as well as a considerable speedup of the SfM process.

Document type: Conference object

Vehicle Localization Based on Visual Lane Marking and Topological Map Matching

Scipedia content — Mon, 01 Feb 2021 21:28:03 +0100

urate and reliable localization is crucial to autonomous vehicle navigation and driver assistance systems. This paper presents a novel approach for online vehicle localization in a digital map. Two distinct map matching algorithms are proposed: i) Iterative Closest Point (ICP) based lane level map matching is performed with visual lane tracker and grid map ii) decision-rule based approach is used to perform topological map matching. Results of both the map matching algorithms are fused together with GPS and dead reckoning using Extended Kalman Filter to estimate vehicle’s pose relative to the map. The proposed approach has been validated on real life conditions on an equipped vehicle. Detailed analysis of the experimental results show improved localization using the two aforementioned map matching algorithms.

Video Based Vehicle Counting Using Deep Learning Algorithms

Scipedia content — Mon, 01 Feb 2021 21:31:54 +0100

Traffic density in roads has been increasing day by day which needs intelligent transportation system that can handle the traffic. Traffic management has become inevitable for smart cities. The enormous increase in vehicle numbers has generated more pressure to manage traffic congestion especially during peak hours. If the traffic congestion at a particular point of time can be found, then that information can be useful for managing the traffic in different lanes and change the traffic light cycle dynamically according to the vehicle count in different lanes. In recent years video surveillance and monitoring has been gaining importance. Video can be analyzed which can be used to find the traffic density. Many useful information can be obtained by video processing like real time traffic density. Vehicle counting can be done by detecting the object, tracking it and then finally counting the objects. Many different techniques are available for object detection and tracking. Deep learning techniques for object detection led to remarkable improvements compared to conventional image processing techniques by removing the weakness in the conventional techniques. This paper provides a survey on various techniques available for vehicle detection and tracking.

Designing a fusion of visible and infra-red camera streams for remote tower operations

Scipedia content — Mon, 01 Feb 2021 21:54:08 +0100

The research project INVIDEON evaluated requirements, technical solutions and the benefit of fusing visible (VIS) and infra-red (IR) spectrum camera streams into a single panorama video stream. In this paper, the design process for developing a usable and accepted fusion is described. As both sensors have strengthens and weaknesses, INVIDEON proposes a fused panorama optimized out of both sensors to be presented to the ATC officer (ATCO). This paper gives an overview of the project and reports results of acceptance and usability of the INVIDEON solution. The process of supporting the definition of requirements by means of rapid prototyping and taking a user-centered approach is described. Main findings of requirements for fusing VIS and IR camera data for remote tower operations are highlighted and set into context with the air traffic controller's tasks. A specific fusion approach was developed within the project and evaluated by means of recorded IR and VIS data. For evaluation, a testbed was set up at a regional airport and data representing different visibility conditions were selected out of 70 days data recordings. Five air traffic controllers participated in the final evaluation. Subjective data on perceived usability, situational awareness and trust in automation was assessed. Furthermore, qualitative data on HMI design and optimization potential from debriefings and comments was collected and clustered.

Security aspects of communications in VANETs

Scipedia content — Mon, 01 Feb 2021 22:10:47 +0100

The Fourth Industrial Revolution has begun and it promises breakthroughs in Artificial Intelligence, robotics, Machine Learning, Internet of Things, Digital Twin, and many other technologies that tackle advancements in the industries. The trend is headed towards automation and connectivity. In the automotive industry, advancements have been made towards integrating autonomous driving vehicles into Intelligent Transport Systems (ITS) with the use of Vehicular Ad-Hoc Networks (VANETs). The purpose of this type of network is to enable efficient communication between vehicles (V2V communication) or vehicles and infrastructure (V2I communication), to improve driving safety, to avoid traffic congestion, and to better coordinate transport networks. This direction towards limited (or lack of) human intervention implies vulnerability to cyber attacks. In this context, this paper provides a comprehensive classification of related state-of-the-art approaches following three key directions: 1) privacy, 2) authentication and 3) message integrity within VANETs. Discussions, challenges and open issues faced by the current and next generation of vehicular networks are also provided.

Road Infrastructure Requirements for Improved Performance of Lane Assistance Systems

Scipedia content — Mon, 01 Feb 2021 22:17:41 +0100

There is a pressing need for road authorities to take a proactive role in the deployment of automated vehicles on the existing road network. This requires a comprehensive understanding of the road infrastructure requirements that would lead to safe operation of automated vehicles. In this context, a field test with Lane Departure Warning and Lane Keeping Systems-enabled vehicles was conducted in the province of North Holland, The Netherlands. The performance of these automated systems was evaluated using performance indicators such as Mean Lateral Position and Standard Deviation of Lane Position. In this study, the Systems Theoretic Accident Modelling and Processes (STAMP) model was adopted to understand the relationships between the various components of the “Road System”, which in this study include the road authority, the automated vehicle system, elements of the road infrastructure, and weather conditions. Empirical data from the experiment is used to estimate the relationships between the different components, followed by the assessment of their impact on the performance of the automated vehicles. It was found that visibility conditions have a significant effect on detection performance, which worsens in rainy conditions especially under streetlights. It has been also observed that there is a significant difference in Lane Position between Left Curves and Straight sections, and between lane widths less than 250 cms and those that have larger widths. These findings are combined with the results from the STAMP analysis to formulate a set of road infrastructure requirements that would lead to safe performance of Lane Assistance Systems.

Innovative Geoinformation Systems for the Design of Communication Paths

Scipedia content — Mon, 01 Feb 2021 22:41:09 +0100

The article analyses the volume of passenger traffic from 1990 to 2019 for land, water and air transport. From the materials obtained and the experience of the networks of European and world high-speed railways, goals are set. High-speed lines designed exclusively for passenger traffic. This moment plays an important role in reducing the cost of construction, increasing the market and economic profitability. According to the data from the State Statistics Service of Ukraine, it is possible to calculate the passenger flow based on the known parameters for 2020–2032 in the direction of Kiev–Lviv. The design of high-speed lines should meet general requirements aimed at satisfying the basic characteristics of a high-speed railway system, which works in conjunction with the European High-Speed Railway network. The compatibility of the parameters of high-speed lines with the parameters of traditional lines is part of the operational requirements for the gradual introduction of a network of high-speed railways. Possible scenarios to achieve the required compatibility should cover all subsystems. DOI: https://doi.org/10.3846/enviro.2020.693

Two-Phase Slug Flow Correlations for Severe Slugging in Subsea Pipelines

Scipedia content — Mon, 01 Feb 2021 22:41:22 +0100

Resilience of Air Traffic Controllers in control tower

Scipedia content — Mon, 01 Feb 2021 22:41:36 +0100

Traffic optimization at the Application Level Proof of Concept, development and usefulness evaluation of the ALTO solution

Scipedia content — Mon, 01 Feb 2021 22:47:26 +0100

This paper presents an overview, proof of concept, and a preliminary demonstrative benchmarking study of the Application-Layer Traffic Optimization (ALTO) architecture proposed by the IETF ALTO Working Group. The main ALTO system purpose is to allow applications to get a more complete view of the underlying network infrastructure, allowing for wellreasoned connection decisions in situations of service redundancy. This paper first begins with a technical description of the ALTO project, and afterwards evaluates how P2P applications, guided by our proposed prototype implementation of the ALTO architecture, perform in comparison to traditional peer selection algorithms on the task of downloading a file in a typical file-sharing P2P network environment. The obtained results from our developed ALTO prototype system state that an application guided by the ALTO solution reduced overall network usage by around 40% with no significant impact in the application performance. FCT - Fundação para a Ciência e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020

Characterizing Radar Network Traffic: a first step towards spoofing attack detection

Scipedia content — Mon, 01 Feb 2021 22:54:28 +0100

International audience; An Air Traffic Management (ATM) Surveillance System is used to provide services to perform Air Traffic Control (ATC) (e.g., horizontal separation between aircraft). This sytem carries messages containing aircraft's position from a collection of radars of an Air Navigation Service Provider (ANSP) through its network. Then Radar traffic is one of the most important sources of information for this system. The format of the radar messages is defined by a specific application-layer protocol entitled ASTERIX. The evolution of the security policy and technologies used makes existing radar systems, once considered safe, now potentially open to attack. Both safety and security of ATM system could be impacted by any kind of attack into the network traffic, who could maliciously modified information about aicrafts, in particular thanks to Spoofing Attack. To counter this risk, there is need to detect intrusion and then to have anomaly detection modules for this safety-critical network traffic, that can be deployed in a security appliance. In order to design this module, we did a statistical analysis to have an overview of the traffic to better know what we need to protect. Specifically, we studied radar network traffic in order to extract high level statistic characteristics of normal radar traffic. This allowed us to identify a trend in the evolution of this traffic. We were then able to inject a spoofing attack (when a malicious party impersonates another device or network user for the purpose of altering the data) into this traffic to modify the nominal traffic. Thereafter, we were able to detect this attack using our method, which consists of the use of a machine learning detection method, using a Long-Short Term Memory (LSTM) mechanism. This is the subject of our paper, an overview of radar traffic and a method to detect spoofing attack in this traffic. This would help to develop an ATM IDS especially as this type of attack could remain invisible for air traffic controller.

Road Grade Estimation Using Crowd-Sourced Smartphone Data

Scipedia content — Mon, 01 Feb 2021 23:01:29 +0100

Estimates of road grade/slope can add another dimension of information to existing 2D digital road maps. Integration of road grade information will widen the scope of digital map's applications, which is primarily used for navigation, by enabling driving safety and efficiency applications such as Advanced Driver Assistance Systems (ADAS), eco-driving, etc. The huge scale and dynamic nature of road networks make sensing road grade a challenging task. Traditional methods oftentimes suffer from limited scalability and update frequency, as well as poor sensing accuracy. To overcome these problems, we propose a cost-effective and scalable road grade estimation framework using sensor data from smartphones. Based on our understanding of the error characteristics of smartphone sensors, we intelligently combine data from accelerometer, gyroscope and vehicle speed data from OBD-II/smartphone's GPS to estimate road grade. To improve accuracy and robustness of the system, the estimations of road grade from multiple sources/vehicles are crowd-sourced to compensate for the effects of varying quality of sensor data from different sources. Extensive experimental evaluation on a test route of ~9km demonstrates the superior performance of our proposed method, achieving $5\\times$ improvement on road grade estimation accuracy over baselines, with 90\\% of errors below 0.3$^\\circ$.

Comment: Proceedings of 19th ACM/IEEE Conference on Information Processing in Sensor Networks (IPSN'20)

INTEGRATED TRAFFIC CONTROL FOR FREEWAYS USING VARIABLE SPEED LIMITS AND LANE CHANGE CONTROL ACTIONS

Scipedia content — Mon, 01 Feb 2021 23:06:11 +0100

The wide deployment of vehicle automation and communication systems (VACS) in the next decade is expected to influence traffic performance on freeways. Apart from safety and comfort, one of the goals is the alleviation of traffic congestion which is a major and challenging problem for modern societies. The paper investigates the combined use of two feedback control strategies utilizing VACS at different penetration rates, aiming to maximize throughput at bottleneck locations. The first control strategy employs mainstream traffic flow control using appropriate variable speed limits as an actuator. The second control strategy delivers appropriate lane-changing actions to selected connected vehicles using a feedback-feedforward control law. Investigations of the proposed integrated scheme have been conducted using a microscopic simulation model for a hypothetical freeway featuring a lane-drop bottleneck. The results demonstrate significant improvements even for low penetration rates of connected vehicles.

Document type: Article

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Scipedia content — Mon, 01 Feb 2021 23:13:25 +0100

Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) input image is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of camera sensors. In contrast to existing learning-based methods, our core idea is to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDRto-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We then propose to learn three specialized CNNs to reverse these steps. By decomposing the problem into specific sub-tasks, we impose effective physical constraints to facilitate the training of individual sub-networks. Finally, we jointly fine-tune the entire model end-to-end to reduce error accumulation. With extensive quantitative and qualitative experiments on diverse image datasets, we demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms.

Comment: CVPR 2020. Project page: https://www.cmlab.csie.ntu.edu.tw/~yulunliu/SingleHDR Code: https://github.com/alex04072000/SingleHDR

Simulator for the reproduction of "Low Sonic Boom"-signatures

Scipedia content — Mon, 01 Feb 2021 23:15:21 +0100

Supersonic aircraft produce a sonic boom when flying faster than the speed of sound. In order to rule out detrimental"br" e ects for inhabitants of overflown areas, civil supersonic flights (like the Concorde) were allowed to fly over water only."br" Due to progress in aircraft design, the super sonic boom may be reduced considerably in the future. Such ”Low Sonic"br" Boom”-signatures will be considerably quieter and sound completely di erent compared to conventional sonic booms."br" Currently, the sensation and the subjective response of humans to future ”Low Sonic Boom”-signatures is not known."br" For an assessment of human responses to ”Low Sonic Boom”-signatures, a Sonic-Boom simulator has been built at the"br" University of Oldenburg as a pressure chamber with a volume of about 9 m"sup"3"/sup". Two 18” loudspeaker chassis enable the"br" production of an overpressure of up to 20 Pa for a signature duration of 200 ms. The background noise level in the"br" chamber is very low (21 dB(A)) and the chamber has a very small reverberation time of T"sub"20"/sub"=0.2 s averaged over octave"br" bands from 63 Hz to 8 kHz. A vibration platform is installed in the chamber to simulate whole-body vibration that may"br" occur in connection with ”Low Sonic Boom”-signatures.

A safety oriented decision support tool for the remanufacturing and recycling of post-use H&EVs Lithium-Ion batteries

Scipedia content — Mon, 01 Feb 2021 23:28:36 +0100

The battery is a key component of electric vehicles. To reach the needed voltage and capacity, single Lithium-Ion cells are assembled into modules, then assembled into the pack. Their disassembly, which unlocks both remanufacturing or recycling and which nowadays is made mainly manually, has high electric hazards. Decision tools have not yet been developed to minimize these risks. This work presents a mathematical model to determine the disassembly sequence with the minimal exposure of the operator to hazardous voltages. The model considers the mechanical and electrical architecture of the battery and the tasks needed to reach the desired disassembly level.

Sustainable Development as a Basic Concept Development of Cities

Scipedia content — Mon, 01 Feb 2021 23:46:05 +0100

The development of cities by their volume and dynamics generated many conflicting places in both conceptual as well as in the implementation part. The sensibility of our time, public sensitivity to the quality of life and environmental quality required in consideration of development concepts for the new approaches. A special dimension to the issue of giving and awareness of the scarcity of resources. The doctrine of sustainable development manifests itself as an epoch-making, and the only way out of the above dilemma. Dimensions that reflect doctrines are improving urban infrastructure and urban infrastructure, support the development of social services and civil society, support local development, energy efficient development - reducing CO2 emissions, preservation and development of cultural heritage, sustainable transport and networking, development cooperation, improving governance. It is necessary to find an answer to the growing needs of urban communities and local governments to take over the role of the driver of economic activity in their communities, organizers of social inclusion and advocate of environmental protection and the fight against climate change. In times of reduced fiscal capacity and growing obligations, the EU structural funds and investment funds are proving to be an important and accessible source of funding for a range of public needs at the local level.

Thickened and Paste Tailings Pipeline Systems: Design Procedure – Part 1

Scipedia content — Mon, 01 Feb 2021 23:56:30 +0100

The design methodology for pipeline systems conveying thickened and paste tailings systems has been well developed over the last decade. This series of papers outlines the process for designing and implementing a typical surface tailings or underground backfill pipeline system. The papers comprise the following parts: Part 1 (this paper) discusses: o development of the design criteria document, o issues to be considered for the test work, and o pipeline flow behaviour modelling, friction loss calculation and pipe diameter selection. Part 2, to be presented at Paste and Thickened Tailings 2007, will include: o centrifugal pump performance derating, o hydraulic and mechanical design, o operational and control considerations, and o specific considerations for thickener underflow and gravity flow systems. 1.1 Terminology Our company classifies tailings and backfills according to the following criteria: The upper limit for conventional tailings is considered to correspond to the freely settled packing concentration. This typically corresponds to yield stresses of between 5 and 20 Pa. High concentration tailings or thickened tailings is considered to cover the range from the freely settled concentration to the concentration at which the mixture has a fully sheared yield stress corresponding to 100 Pa. Figure 1 illustrates the slump of a mixture with a 100 Pa yield stress. Paste tailings and fill are considered to be mixtures with yield stresses greater than 100 Pa. The practical upper limit for pipeline transport is about 800 Pa. These mixtures may be transported in turbulent or laminar flow: Paste\u00192006\u0019–\u0019R.J.\u0019Jewell,\u0019S.\u0019Lawson,\u0019P.\u0019Newman\u0019(eds)\u0019 ©\u00192006\u0019Australian\u0019Centre\u0019for\u0019Geomechanics,\u0019Perth,\u0019ISBN\u00190-9756756-5-6 Paste\u00192006,\u0019Limerick,\u0019Ireland\u0019 371 Turbulent flow – inertial forces dominate and the friction losses are relatively insensitive to the tailings rheology. Laminar flow – viscous forces dominate and the friction losses are directly related to the tailings rheology, which in turn is strongly effected by the tailings material properties, water chemistry and solids concentration. The transition zone from laminar flow occurs over a range of pipeline flow rates and is characterised by fluctuating pressure gradients. Thickened tailings are typically transported in laminar flow, but turbulent flow operation is possible for low yield stress mixtures, large diameter pipes and high operating velocities. Paste tailings are always transported in laminar flow. Iron ore tailings 64%m, 100 Pa yield stress Figure 1 Slump at transition from high concentration tailings to paste 1.2 Design process The procedure outlined in this paper is a guideline defining the typical steps to be followed when designing a pipeline system transporting thickened tailings or paste. It is not a definitive procedure that can be followed without a suitable background in the field and a proper understanding of thickened and paste tailings flow behaviour. It is also important to note that the design process is iterative in nature. So while the steps have been laid out in an ideal linear path, the reality is that the process will be more chaotic with frequent jumps between the various steps of the process.

Assessing global OpenStreetMap building completeness to generate large-scale 3D city models

Scipedia content — Mon, 01 Feb 2021 23:59:52 +0100

Biljecki, F., & Ang, M. L. (2020). Assessing Global OpenStreetMap building completeness to generate large-scale 3D city models In: Minghini, M., Coetzee, S., Juhász, L., Yeboah, G., Mooney, P., Grinberger, A.Y. (Eds.). Proceedings of the Academic Track at the State of the Map 2020 Online Conference, July 4-5 2020. Available at https://zenodo.org/communities/sotm-2020

Global and Secured UAV Authentication System based on Hardware-Security

Scipedia content — Tue, 02 Feb 2021 00:03:10 +0100

UAVs are gaining traction outside their usual markets of hobbyists, areal recordings, and surveillance services with cloud computing enabled applications and their massive combined computing power. These applications rapidly grow the UAV market, consequently raising the priority of safety solutions. Tremendous incidents, such as the air traffic interruption in London (Dec. 2018), raised awareness and demand for UAV identification, authentication, and tracking. To prevent these type of incidents, aviation authorities, such as the FAA or EASA, are currently working on proper regulations. The implementation of the regulations demands dependable technical solutions. This paper proposes a secured and globally operative UAV authentication system, based on reliable security mechanisms and standardized protocols. Therefore, this system must provide mutual and strong cryptographic authentication. First, the TLS protocol is used for mutual authentication and for protecting the communication. Then, hardware-security is implemented to store the necessary keys and certificates in a protected storage, thus supporting the TLS handshake to avoid common attacks against pure software implementations. Lastly, a concept for protected sensor values is introduced. The proposed UAV authentication concept is demonstrated by a proof-of-concept implementation, evaluated for performance and compared to existing solutions.

Getting ready for the future: How can we reach user-centric mobility in Europe by 2030?

Scipedia content — Tue, 02 Feb 2021 00:03:44 +0100

The Mobility4EU project created a vision for a user-centric and cross-modal European transport system in 2030 and an action plan to implement that vision. We used a combination of creative and analytical methods to come from problem identification to the action plan applying a user-centric methodology that included stakeholders in each step of the process. The Action Plan details measures that address technical topics but especially refer to societal aspects and issues for multi-stakeholder interaction, as e.g. policy, user acceptance, standardization, collaboration and the integration of the user perspective into the R&D&I process. The Action Plan adds to the other similar initiatives by providing recommendations on mainstreaming of universal design and user-centric design processes, synergies and collaboration potential between modes and the combination of transport of passengers and freight building on the quadruple helix model of collaboration between academia, users, industry and policy makers.

BENTO: A Visual Platform for Building Clinical NLP Pipelines Based on CodaLab

Scipedia content — Tue, 02 Feb 2021 00:06:37 +0100

CodaLab is an open-source web-based platform for collaborative computational research. Although CodaLab has gained popularity in the research community, its interface has limited support for creating reusable tools that can be easily applied to new datasets and composed into pipelines. In clinical domain, natural language processing (NLP) on medical notes generally involves multiple steps, like tokenization, named entity recognition, etc. Since these steps require different tools which are usually scattered in different publications, it is not easy for researchers to use them to process their own datasets. In this paper, we present BENTO, a workflow management platform with a graphic user interface (GUI) that is built on top of CodaLab, to facilitate the process of building clinical NLP pipelines. BENTO comes with a number of clinical NLP tools that have been pre-trained using medical notes and expert annotations and can be readily used for various clinical NLP tasks. It also allows researchers and developers to create their custom tools (e.g., pre-trained NLP models) and use them in a controlled and reproducible way. In addition, the GUI interface enables researchers with limited computer background to compose tools into NLP pipelines and then apply the pipelines on their own datasets in a “what you see is what you get” (WYSIWYG) way. Although BENTO is designed for clinical NLP applications, the underlying architecture is flexible to be tailored to any other domains.

ENVIRONMENTAL RISK ASSESSMENT FROM OPERATION OF GAS PIPELINES

Scipedia content — Tue, 02 Feb 2021 00:14:27 +0100

Extracting User Behavior at Electric Vehicle Charging Stations with Transformer Deep Learning Models

Scipedia content — Thu, 21 Jan 2021 15:24:27 +0100

[EN] Mobile applications have become widely popular for their ability to access real-time information. In electric vehicle (EV) mobility, these applications are used by drivers to locate charging stations in public spaces, pay for charging transactions, and engage with other users. This activity generates a rich source of data about charging infrastructure and behavior. However, an increasing share of this data is stored as unstructured textâinhibiting our ability to interpret behavior in real-time. In this article, we implement recent transformer-based deep learning algorithms, BERT and XLnet, that have been tailored to automatically classify short user reviews about EV charging experiences. We achieve classification results with a mean accuracy of over 91% and a mean F1 score of over 0.81 allowing for more precise detection of topic categories, even in the presence of highly imbalanced data. Using these classification algorithms as a pre-processing step, we analyze a U.S. national dataset with econometric methods to discover the dominant topics of discourse in charging infrastructure. After adjusting for station characteristics and other factors, we find that the functionality of a charging station is the dominant topic among EV drivers and is more likely to be discussed at points-of-interest with negative user experiences. Marchetto, D.; Ha, S.; Dharur, S.; Asensio, O. (2020). Extracting User Behavior at Electric Vehicle Charging Stations with Transformer Deep Learning Models. Editorial Universitat PolitÃ¨cnica de ValÃ¨ncia. 153-162. https://doi.org/10.4995/CARMA2020.2020.11613 OCS 153 162

Task Measures for Air Traffic Display Operations

Scipedia content — Tue, 02 Feb 2021 00:23:57 +0100

With rising growth in air traffic globally, advanced technologies are being developed to aid ATCOs in the managing and control of a foreseeable denser airspace. The need to perform holding stack management, a potential challenge to ATCO, especially during heavy traffic congestion owing to weather and runway conditions is expected to be more frequent. To mitigate this challenge, the use of 3D displays was suggested. This paper examines the performance impacts resulting from the adoption of 3D instead of 2D radar displays with regards to visual search and relative vertical positioning identification. Observations relating perceived increased in stress and workload by the participants are also made.

An Adaptive and Near Parameter-free Evolutionary Computation Approach Towards True Automation in AutoML

Scipedia content — Tue, 02 Feb 2021 00:46:25 +0100

common claim of evolutionary computation methods is that they can achieve good results without the need for human intervention. However, one criticism of this is that there are still hyperparameters which must be tuned in order to achieve good performance. In this work, we propose a near "parameter-free" genetic programming approach, which adapts the hyperparameter values throughout evolution without ever needing to be specified manually. We apply this to the area of automated machine learning (by extending TPOT), to produce pipelines which can effectively be claimed to be free from human input, and show that the results are competitive with existing state-of-the-art which use hand-selected hyperparameter values. Pipelines begin with a randomly chosen estimator and evolve to competitive pipelines automatically. This work moves towards a truly automatic approach to AutoML.

Comment: 18 pages (single column), 2 figure

The future of urban freight transport: Shifting the cities role from observation to operative steering

Scipedia content — Tue, 02 Feb 2021 00:59:06 +0100

An Artificial Intelligence Approach to Estimate Travel Time along Public Transportation Bus Lines

Scipedia content — Tue, 02 Feb 2021 01:13:43 +0100

Public transportation sectors have played significant roles in accommodating passengers and commodities efficiently and effectively. The modes of public transportation often follow pre-defined operation schedules and routes. Therefore, planning these schedules and routes requires extensive efforts in analyzing the built environment and collecting demand data. Once a transit route is operational as an example, collecting and maintaining real-life information becomes an important task to evaluate service quality using different Key Performance Indicators (KPIs). One of these KPIs is transit travel time along the route. This paper aims to develop a transit travel time prediction model using an artificial intelligence approach. In this study, 12 public bus routes serving the Greater City of Doha were selected. While the ultimate goal is to predict transit travel time from the start to the end of the journeys collected over a period of one-year, routespecific inputs were used as inputs for this prediction. To develop a generalized model, the input variables for the transit route included the number and type of intersections, number of each type of turning movements and the built environment. An Artificial Neural Networks (ANN) model is used to process 78,004 valid datasets. The results indicate that the ANN model is capable of providing reliable and accurate transit travel time estimates, with a coefficient of determination (R2) of 0.95. Transportation planners and public transportation operators can use the developed model as a tool to estimate the transit travel time.

Data-Driven Approach for Aircraft Arrival Sequencing Investigation at Terminal Maneuvering Area

Scipedia content — Tue, 02 Feb 2021 01:22:21 +0100

International audience; Recent air traffic management aims to provide a safety-first operation to support the aircraft approaching and landing procedures. Due to the complexity of air traffic in the terminal control area (also known as the terminal maneuvering area or TMA), simultaneous consideration of aviation economics, environmental concerns, and safety operations in decision makings can be challenging. To improve air traffic controllers' work efficiency and reduce the adverse environmental impact, it is crucial to establish a robust arrival strategy that incorporates weather conditions and flight trajectory configuration. The current state-of-the-art solutions for arrival sequencing and scheduling problem focus more on the operation research aspect, which neglects the airway configuration. Also, no wind condition is assumed to simplify the weather condition. Furthermore, many research efforts have not properly considered practical phenomenon such as holding patterns in their arrival sequencing model, which affects the accuracy of fuel burnt consumption. In this work, we will construct a study on aircraft arrival flow based on historical data at Hong Kong International Airport (HKIA). By extracting features from the data, our results include the spatiotemporal pattern recognition for aircraft arrival transit time and congestion inside HKIA TMA. Besides delivering the statistical analysis on the HKIA aircraft arrival flow, an arrival transit time prediction based on random forest regression is also converted. Results show that our methodologies are not only advantageous in extracting crucial hidden information from historical data for air traffic controllers but also can increase the accuracy of arrival transit time prediction under most of the circumstances.

Advanced Driver-Assistance Systems for City Bus Applications

Scipedia content — Tue, 02 Feb 2021 01:41:13 +0100

The bus sector is currently lagging behind when it comes to implementing autonomous systems for improved vehicle safety. However, in cities such as London, public transport strategies are changing, with requirements being made for advanced driver-assistance systems (ADAS) on buses. This study discusses the adoption of ADAS systems within the bus sector. A review of the on-road ADAS bus trials shows that passive forward collision warning (FCW) and intelligent speed assistance (ISA) systems have been successful in reducing the number of imminent pedestrian/vehicle collision events and improving speed limit compliance, respectively. Bus accident statistics for Great Britain have shown that pedestrians account for 82% of all fatalities, with three quarters occurring with frontal bus impacts. These statistics suggest that the bus forward collision warning system is a priority for inclusion in future vehicles to enhance the driver’s direct vision, and to increase reaction time for earlier brake application. Almost 80% of bus occupant casualties occurred in non-impact situations, mainly during acceleration/deceleration events. Therefore, care must be taken in implementing autonomous braking in buses, to ensure that it does not cause an increased number of deceleration events beyond the safe stability limits for passengers. Real on-road drive cycle data has shown that while instances of unsafe braking events do not occur regularly, there are instances of braking events that would present a hazard to both seated and standing passengers, therefore systems that would mitigate these issues would have real benefits to both passenger comfort and safety. During tests to simulate the use of the vehicle retarder for an autonomous braking system, deceleration rates largely remained safely within standee and seated passenger stability limits, whereas an emergency stop test showed a peak deceleration 3.5 times the limit of a standee supported by a vertical handrail, and 4 times the limit for a forward/backward facing seated passenger.

OpenStreetMap: an opportunity for Citizen Science

Scipedia content — Tue, 02 Feb 2021 01:51:17 +0100

OpenStreetMap (OSM, https://www.openstreetmap.org) is currently the largest, richest, most complete and most up-to-date open geospatial database as well as the most participated crowdsourced geographic information project in the world. While it was initially started (in 2004) with an exclusive focus on road network, it now covers any real-world feature that is verifiable on the ground. The project currently counts more than 5.5 million registered users, with an average of about 5,000 users contributing to the map on a daily basis [1]."br" Currently, the relation between OSM and science is mostly focused on studying various aspects of OSM such as data quality, collaboration patterns, integration between OSM and authoritative data, use of OSM data in specific domains and applications, reuse of tools created around the project (e.g. for the collaborative mapping) etc. [2], more than directly shaping Citizen Science (CS) projects around OSM. However, despite OSM and (geographical) CS projects have many points of intersection [3] and examples of direct contribution of OSM mappers to CS initiatives exist, the link between them is still largely unexplored. Such link might be relevant in a number of different directions, e.g. the exploration of how OSM data may assist in the development of CS initiatives and complement/enrich data collected by citizens; how CS data may, in turn, be included and improve the OSM database; how OSM best practices and lessons learned throughout the project’s 10+ years of development (about issues such as quality, governance, licensing, sustainability, etc.) may assist in organizing and running CS initiatives."br" This session wants to stimulate the attention and interest from the CS community to the OSM database, its ecosystem of tools and services [4] as well as the OSM community as a fertile ground where CS can build and grow projects from local to international scales."br" The session will be organised as an interactive session where a few panellists will first introduce OSM and its main characteristics and then will present a few use cases where data in OSM can be used in support of CS projects. After that, participants will be encouraged to bring data relevant to their own use cases and work in groups, together with panellists, to evaluate the potential to use OSM with their specific data and projects as well as to contribute data gathered in their CS projects back to the OSM database.

User Equilibrium and System Optimum with Incomplete Information In Traffic Congestion

Scipedia content — Tue, 02 Feb 2021 02:07:01 +0100

By providing more information about traffic network, such as more feasible paths via intelligent navigation systems (INS), users in the network may change their choices of the path from a source to a destination. This paper investigates a traffic congestion model with incomplete information, in which different users have different information about the network. We introduce the notions of user equilibrium of incomplete information (UEII) and system optimum of incomplete information (SOII). Then, we prove a theorem about the effect of the change of traffic amount on each couple paths in SOII for the model. Finally, based on this theorem and a property of UEII, we reveal a relationship between UEII and SOII on the cost function.

The Automotive Take on Continuous Experimentation: A Multiple Case Study

Scipedia content — Tue, 02 Feb 2021 02:12:35 +0100

Recently, an increasingly growing number of companies is focusing on achieving self-driving systems towards SAE level 3 and higher. Such systems will have much more complex capabilities than today's advanced driver assistance systems (ADAS) like adaptive cruise control and lane-keeping assistance. For complex software systems in the Web-application domain, the logical successor for Continuous Integration and Deployment (CI/CD) is known as Continuous Experimentation (CE), where product owners jointly with engineers systematically run A/B experiments on possible new features to get quantifiable data about a feature's adoption from the users. While this methodology is increasingly adopted in software-intensive companies, our study is set out to explore advantages and challenges when applying CE during the development and roll-out of functionalities required for self-driving vehicles. This paper reports about the design and results from a multiple case study that was conducted at four companies including two automotive OEMs with a long history of developing vehicles, a Tier-1 supplier, and a start-up company within the area of automated driving systems. Unanimously, all expect higher quality and fast roll-out cycles to the fleet; as major challenges, however, safety concerns next to organizational structures are mentioned.

Specific Air Traffic Management Cybersecurity Challenges

Scipedia content — Tue, 02 Feb 2021 02:23:55 +0100

The Optimal Deployment of Recharging Stations for Electric Vehicles Based on Mobility Flows and Electric Grid Specifications

Scipedia content — Tue, 02 Feb 2021 02:31:54 +0100

International audience; With the increasing interest in using electric vehicles (EVs) in future transportation systems, the need for deploying fast charging infrastructures becomes essential. In order to fulfil this need, it is important to anticipate EV future charging demands and requirements, and optimize their deployment. In this paper, we develop an optimization model to solve the problem of positioning fast-charging stations for EVs. The proposed model takes into account the different mobility flows and recharging demands as well as the constraints imposed by the available electric grid. In addition, the model considers the availability of alternative energy sources (i.e. photo-voltaic). For this purpose, we provide a mathematical formulation for the considered problem aiming at maximizing the covered recharging demand while respecting investment budget limits and the available capacities provided by the electric grid. Through a case study on Paris-Saclay area, we obtain the optimal locations for deploying EV charging stations as well as the number of chargers that need to be installed at each charging station. Results also highlight the benefits of integrating locally-produced photo-voltaic energy on EV recharging service.

A methodology to design and assess scenarios within SULPs: the case of Bologna

Scipedia content — Tue, 02 Feb 2021 02:33:38 +0100

The paper, focusing on the importance to develop sustainable urban logistics plan (SULP) and to implement a demand model system for the assessment of future scenarios, presents a methodology for setting up a SULP modelling, using different sources of data (i.e. automatic traffic counts, floating car data, surveys with retailers and transport operators). The methodology is applied to the functional urban area (FUA) of Bologna (Italy). In particular, it was used for assessing the new city logistics scenarios of the Bologna’s SULP where a set of measures have been proposed for improving city sustainability and livability.

Performance Improvement of Hardware By Series Duplicating Data Buffer for High-level Synthesis

Scipedia content — Tue, 02 Feb 2021 02:37:26 +0100

To occupy appropriate the expanding market share of embedded image processing systems, it is important to quickly develop and launch a high-performance and low-power product onto the market tracking the short life cycle of recent products. To achieve high performance and low-power produce quickly, it is effective to develop the hardware module of high computational software processing using high-level synthesis technology automatically converting software to hardware. However, high-level synthesis cannot convert software not taking into hardware organization to the efficient hardware with high-performance and low-power. This paper proposes a software description method for high-level synthesis that replicates histograms in series and pipelines the pre and post processing across the histogram. The experimental result on the real machine demonstrates the effects of the proposed method.

Photonic Physical Unclonable Functions: From the Concept to Fully Functional Device Operating in the Field

Scipedia content — Tue, 02 Feb 2021 02:39:44 +0100

The scope of this paper is to demonstrate a fully working and compact photonic Physical Unclonable Function (PUF) device capable of operating in real life scenarios as an authentication mechanism and random number generator. For this purpose, an extensive experimental investigation of a Polymer Optical Fiber (POF) and a diffuser as PUF tokens is performed and the most significant properties are evaluated using the proper mathematical tools. Two different software algorithms, the Random Binary Method (RBM) and Singular Value Decomposition (SVD), were tested for optimized key extraction and error correction codes have been incorporated for enhancing key reproducibility. By taking into consideration the limitations and overall performance derived by the experimental evaluation of the system, the designing details towards the implementation of a miniaturized, energy efficient and low-cost device are extensively discussed. The performance of the final device is thoroughly evaluated, demonstrating a long-term stability of 1 week, an operating temperature range of 50C, an exponentially large pool of unique Challenge-Response Pairs (CRPs), recovery after power failure and capability of generating NIST compliant true random numbers.

UNICARagil - Where We Are and Where We Are Going

Scipedia content — Tue, 02 Feb 2021 02:45:25 +0100

Experimental investigation on traffic congestion control and maintenance system using internet of things

Scipedia content — Tue, 02 Feb 2021 03:24:17 +0100

Research on the impact of high-speed railway operation on the lower culvert stability of municipal pipelines

Scipedia content — Tue, 02 Feb 2021 04:01:01 +0100

n urban natural gas high-pressure pipeline culvert is located below the subgrade of a high-speed railway passenger train ring line. Due to the loads generated by the operation of high-speed railway trains, the pipeline may be deformed or even damaged, causing safety accidents. Therefore, its research is of great significance. Based on the field survey and design data, FLAC3D was used to construct a high-simulation 3D mechanical model, and the deformation and stress state of the rock and soil around the lower natural gas pipeline culvert caused by high-speed railway train operation was calculated. The results show that after the operation of the high-speed railway train, the stress on the pipeline structure does not reach the ultimate strength, and the deformation of the pipeline culvert and surrounding rock and soil is small, which will not affect the use of natural gas pipeline culverts and the normal operation of high-speed railway lines. The research results provide references for the normal use of natural gas pipeline culverts and the safe operation of high-speed railways.

On Urban Traffic Flow Benefits of Connected and Automated Vehicles

Scipedia content — Tue, 02 Feb 2021 04:06:23 +0100

utomated Vehicles are an integral part of Intelligent Transportation Systems (ITSs) and are expected to play a crucial role in the future mobility services. This paper investigates two classes of self-driving vehicles: (i) Level 4&5 Automated Vehicles (AVs) that rely solely on their on-board sensors for environmental perception tasks, and (ii) Connected and Automated Vehicles (CAVs), leveraging connectivity to further enhance perception via driving intention and sensor information sharing. Our investigation considers and quantifies the impact of each vehicle group in large urban road networks in Europe and in the USA. The key performance metrics are the traffic congestion, average speed and average trip time. Specifically, the numerical studies show that the traffic congestion can be reduced by up to a factor of four, while the average flow speeds of CAV group remains closer to the speed limits and can be up to 300% greater than the human-driven vehicles. Finally, traffic situations are also studied, indicating that even a small market penetration of CAVs will have a substantial net positive effect on the traffic flows.

Comment: Accepted to IEEE VTC-Spring 2020, Antwerp, Belgium

Discrete Event Simulation of Driver’s Routing Behavior Rule at a Road Intersection

Scipedia content — Tue, 02 Feb 2021 04:12:22 +0100

Several factors influence traffic congestion and overall traffic dynamics. Simulation modelling has been utilized to understand the traffic performance parameters during traffic congestions. This paper focuses on driver behavior of route selection by differentiating three distinguishable decisions, which are shortest distance routing, shortest time routing and less crowded road routing. This research generated 864 different scenarios to capture various traffic dynamics under collective driving behavior of route selection. Factors such as vehicle arrival rate, behaviors at system boundary and traffic light phasing were considered. The simulation results revealed that shortest time routing scenario offered the best solution considering all forms of interactions among the factors. Overall, this routing behavior reduces traffic wait time and total time (by 69.5% and 65.72%) compared to shortest distance routing.

PointNet++ Grasping: Learning An End-to-end Spatial Grasp Generation Algorithm from Sparse Point Clouds

Scipedia content — Tue, 02 Feb 2021 04:31:51 +0100

Grasping for novel objects is important for robot manipulation in unstructured environments. Most of current works require a grasp sampling process to obtain grasp candidates, combined with local feature extractor using deep learning. This pipeline is time-costly, expecially when grasp points are sparse such as at the edge of a bowl. In this paper, we propose an end-to-end approach to directly predict the poses, categories and scores (qualities) of all the grasps. It takes the whole sparse point clouds as the input and requires no sampling or search process. Moreover, to generate training data of multi-object scene, we propose a fast multi-object grasp detection algorithm based on Ferrari Canny metrics. A single-object dataset (79 objects from YCB object set, 23.7k grasps) and a multi-object dataset (20k point clouds with annotations and masks) are generated. A PointNet++ based network combined with multi-mask loss is introduced to deal with different training points. The whole weight size of our network is only about 11.6M, which takes about 102ms for a whole prediction process using a GeForce 840M GPU. Our experiment shows our work get 71.43% success rate and 91.60% completion rate, which performs better than current state-of-art works.

Comment: Accepted at the International Conference on Robotics and Automation (ICRA) 2020

Enhanced Demand and Capacity Balancing based on Alternative Trajectory Options and Traffic Volume Hotspot Detection

Scipedia content — Tue, 02 Feb 2021 05:03:16 +0100

Nowadays, regulations in Europe are applied at traffic volume (TV) level consisting in a reference location, i.e. a sector or an airport, and in some traffic flows, which act as directional traffic filters. This paper presents an enhanced demand and capacity balance (EDCB) formulation based on constrained capacities at traffic volume level. In addition, this approach considers alternative trajectories in order to capture the user driven preferences under the trajectory based operations scope. In fact, these alternative trajectories are assumed to be generated by the airspace users for those flights that cross regulated traffic volumes, where the demand is above the capacity. For every regulated trajectory the network manager requests two additional alternative trajectories to the airspace users, one for avoiding the regulated traffic volumes laterally and another for avoiding it vertically. This paper considers that the network manager allows more flexibility for the new alternative trajectories by removing restrictions in the Route Availability Document (RAD). All the regulated trajectories (and their alternatives) are considered together by the EDCB model in order to perform a centralised optimisation minimising the the cost deviation with respect to the initial traffic situation, considering fuel consumption, route charges and cost of delay. The EDCB model, based on Mixed-Integer Linear Programming (MILP), manages to balance the network applying ground delay, using alternative trajectories or both. A full day scenario over the ECAC area is simulated. The regulated traffic volumes are identified using historical data (based on 28th July of 2016) and the results show that the EDCB could reduce the minutes of delay by 70%. The cost of the regulations is reduced by 11.7%, due to the reduction of the delay, but also because of the savings in terms of fuel and route charges derived from alternative trajectories.

Peer Reviewed

Document type: Conference object

Mission-Aware Spatio-Temporal Deep Learning Model for UAS Instantaneous Density Prediction

Scipedia content — Tue, 02 Feb 2021 05:08:18 +0100

The number of daily sUAS operations in uncontrolled low altitude airspace is expected to reach into the millions in a few years. Therefore, UAS density prediction has become an emerging and challenging problem. In this paper, a deep learning-based UAS instantaneous density prediction model is presented. The model takes two types of data as input: 1) the historical density generated from the historical data, and 2) the future sUAS mission information. The architecture of our model contains four components: Historical Density Formulation module, UAS Mission Translation module, Mission Feature Extraction module, and Density Map Projection module. The training and testing data are generated by a python based simulator which is inspired by the multi-agent air traffic resource usage simulator (MATRUS) framework. The quality of prediction is measured by the correlation score and the Area Under the Receiver Operating Characteristics (AUROC) between the predicted value and simulated value. The experimental results demonstrate outstanding performance of the deep learning-based UAS density predictor. Compared to the baseline models, for simplified traffic scenario where no-fly zones and safe distance among sUASs are not considered, our model improves the prediction accuracy by more than 15.2% and its correlation score reaches 0.947. In a more realistic scenario, where the no-fly zone avoidance and the safe distance among sUASs are maintained using A* routing algorithm, our model can still achieve 0.823 correlation score. Meanwhile, the AUROC can reach 0.951 for the hot spot prediction.

HOG, LBP and SVM based Traffic Density Estimation at Intersection

Scipedia content — Tue, 02 Feb 2021 05:21:45 +0100

Increased amount of vehicular traffic on roads is a significant issue. High amount of vehicular traffic creates traffic congestion, unwanted delays, pollution, money loss, health issues, accidents, emergency vehicle passage and traffic violations that ends up in the decline in productivity. In peak hours, the issues become even worse. Traditional traffic management and control systems fail to tackle this problem. Currently, the traffic lights at intersections aren't adaptive and have fixed time delays. There's a necessity of an optimized and sensible control system which would enhance the efficiency of traffic flow. Smart traffic systems perform estimation of traffic density and create the traffic lights modification consistent with the quantity of traffic. We tend to propose an efficient way to estimate the traffic density on intersection using image processing and machine learning techniques in real time. The proposed methodology takes pictures of traffic at junction to estimate the traffic density. We use Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP) and Support Vector Machine (SVM) based approach for traffic density estimation. The strategy is computationally inexpensive and can run efficiently on raspberry pi board. Code is released at https://github.com/DevashishPrasad/Smart-Traffic-Junction.

Comment: paper accepted at IEEE PuneCon 2019

A Stochastic Theoretical Game Approach for Resource Allocation in Vehicular Fog Computing

Scipedia content — Tue, 02 Feb 2021 05:23:51 +0100

International audience; Mobile devices have usually limited capabilities in terms of computation power, battery lifetime, storage size and available bandwidth. Thus, to address these limitations and to continue supporting the ever-increasing application requirements, service providers use powerful servers in order to offer services through the cloud. However, due to latency and QoS limitations, cloud computing still does not solve all the problems of newly emerging mobile applications demands. Thus, a more recent development is to push the storage and processing capabilities to the edge of access network closer to end users, which introduce the new concept of fog computing. Fog computing is a decentralized computation framework which essentially extends cloud computing resources and services to the edge of access network [2].

DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering

Scipedia content — Tue, 02 Feb 2021 05:51:25 +0100

utomatic machine learning (AutoML) is an area of research aimed at automating machine learning (ML) activities that currently require human experts. One of the most challenging tasks in this field is the automatic generation of end-to-end ML pipelines: combining multiple types of ML algorithms into a single architecture used for end-to-end analysis of previously-unseen data. This task has two challenging aspects: the first is the need to explore a large search space of algorithms and pipeline architectures. The second challenge is the computational cost of training and evaluating multiple pipelines. In this study we present DeepLine, a reinforcement learning based approach for automatic pipeline generation. Our proposed approach utilizes an efficient representation of the search space and leverages past knowledge gained from previously-analyzed datasets to make the problem more tractable. Additionally, we propose a novel hierarchical-actions algorithm that serves as a plugin, mediating the environment-agent interaction in deep reinforcement learning problems. The plugin significantly speeds up the training process of our model. Evaluation on 56 datasets shows that DeepLine outperforms state-of-the-art approaches both in accuracy and in computational cost.

Automated Decision-making in Automated Driving: Striking a Balance between Individual Autonomy and General Road Safety

Scipedia content — Tue, 02 Feb 2021 06:14:23 +0100

In an attempt to increase road safety, car manufacturers turn their attention to the interior of the vehicle. If the driver falls asleep, or is intoxicated, this will be picked up by sensors and cameras inside the vehicle. If it is deemed unsafe for the driver to continue the trip, the vehicle will pull over and bring itself to a stop so as to prevent endangering other road users. This automated decision-making process is not only affecting the autonomy of the driver, it is also challenging law as it gives rise to many legal and ethical questions. When does the autonomy of the individual and its right to data protection weigh heavier than the public interest of road safety? This research aims to answer that question and fill the existing gap in legal literature.

Low-Overhead Near-Real-Time Flow Statistics Collection in SDN

Scipedia content — Tue, 02 Feb 2021 06:14:41 +0100

International audience; In Software-Defined Networking, near-real-time collection of flow-level statistics provided by OpenFlow (e.g. byte count) is needed for control and management applications like traffic engineering, heavy hitters detection, attack detection, etc. The practical way to do this near-real-time collection is a periodic collection at high frequency. However, periodic polling may generate a lot of overheads expressed by the number of OpenFlow request and reply messages on the control network. To handle these overheads, adaptive techniques based on the pull model were proposed. But we can do better by detaching from the classical OpenFlow request-reply model for the particular case of periodic statistics collection. In light of this, we propose a push and prediction based adaptive collection to handle efficiently periodic OpenFlow statistics collection while maintaining good accuracy. We utilize the Ryu Controller and Mininet to implement our solution and then we carry out intensive experiments using real-world traces. The results show that our proposed approach can reduce the number of pushed messages up to 75% compared to a fixed periodic collection with a very good accuracy represented by a collection error of less than 0.5%.

Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio

Scipedia content — Tue, 02 Feb 2021 06:17:43 +0100

utomatic designing computationally efficient neural networks has received much attention in recent years. Existing approaches either utilize network pruning or leverage the network architecture search methods. This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs, so that under each network configuration, one can estimate the FLOPs utilization ratio (FUR) for each layer and use it to determine whether to increase or decrease the number of channels on the layer. Note that FUR, like the gradient of a non-linear function, is accurate only in a small neighborhood of the current network. Hence, we design an iterative mechanism so that the initial network undergoes a number of steps, each of which has a small 'adjusting rate' to control the changes to the network. The computational overhead of the entire search process is reasonable, i.e., comparable to that of re-training the final model from scratch. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach, which consistently outperforms the pruning counterpart. The code is available at https://github.com/danczs/NetworkAdjustment.

5G Network Performance Experiments for Automated Car Functions

Scipedia content — Tue, 02 Feb 2021 06:22:43 +0100

This article discusses the results of supporting transition towards fully automated driving with remote operator support via the novel V2X channels. Automated passenger cars are equipped with multiple sensors (radars, cameras, LiDARs, inertia, GNSS, etc.), the operation of which is limited by weather, detection range, processing power and resolution. The study explores the use of a dedicated network for supporting automated driving needs. The MEC server latencies and bandwidths are compared between the Tampere, Finland test network and studies conducted in China to support remote passenger car operation. In China the main aim is to evaluate the network latencies in different communication planes, whereas the European focus is more on associated driving applications, thus making the two studies mutually complementary.5G revolutionizes connected driving, providing new avenues due to having lower and less latency variation and higher bandwidths. However, due to higher operating frequencies, network coverage is a challenge and one base station is limited to a few hundred meters and thus they deployed mainly to cities with a high population density. Therefore, the transport solutions are lacking so-called C-V2X (one form of 5G RAT) to enable data exchanges between vehicles (V2V) and also between vehicles and the digital infrastructure (V2I). The results of this study indicate that new edge-computing services do not cause a significant increase in latencies $(\\lt 100$ ms), but that latency variation (11 - 192 ms) remains a problem in the first new network configurations.

Self-Adapting Trajectory Segmentation

Scipedia content — Tue, 02 Feb 2021 06:48:53 +0100

Identifying the portions of trajectory data where movement ends and a significant stop starts is a basic, yet fundamental task that can affect the quality of any mobility analytics process. Most of the many existing solutions adopted by researchers and practitioners are simply based on fixed spatial and temporal thresholds stating when the moving object remained still for a significant amount of time, yet such thresholds remain as static parameters for the user to guess. In this work we study the trajectory segmentation from a multi-granularity perspective, looking for a better understanding of the problem and for an automatic, parameter-free and user-adaptive solution that flexibly adjusts the segmentation criteria to the specific user under study. Experiments over real data and comparison against simple competitors show that the flexibility of the proposed method has a positive impact on results.

Towards Alleviating Traffic Congestion: Optimal Route Planning for Massive-Scale Trips

Scipedia content — Tue, 02 Feb 2021 06:56:18 +0100

We investigate the problem of optimal route planning for massive-scale trips: Given a traffic-aware road network and a set of trip queries Q, we aim to find a route for each trip such that the global travel time cost for all queries in Q is minimized. Our problem is designed for a range of applications such as traffic-flow management, route planning and congestion prevention in rush hours. The exact algorithm bears exponential time complexity and is computationally prohibitive for application scenarios in dynamic traffic networks. To address the challenge, we propose a greedy algorithm and an epsilon-refining algorithm. Extensive experiments offer insight into the accuracy and efficiency of our proposed algorithms.

ADAM & EV: Developing an Adoption Dynamics Analysis Model for Electric Vehicles

Scipedia content — Tue, 02 Feb 2021 07:01:43 +0100

This work describes the development of an agent-based simulation that is an Adoption Dynamics Analysis Model for Electric Vehicles (ADAM & EV). ADAM & EV supports stakeholders in understanding the electric mobility landscape and the possible effects on policies. The model takes a consumer perspective by focusing in-depth on the consumer decision making process following the Theory of Planned Behaviour. In this work, we discuss the structure and interface of the model, and shortly discuss a few initial outcomes such as the consequence that stimulating BEVs increases emissions in the short-term when taking into account manufacturing emissions.

The Ups and Downs of Paste Transport

Scipedia content — Tue, 02 Feb 2021 07:12:26 +0100

Mineral tailings pipelines have to traverse undulating terrain. Paste and high concentration tailings lines convey non-Newtonian slurries and usually contain coarse particles, i.e. " 20 m, that are conveyed as a burden. In presentations at previous Paste conferences papers have been presented that demonstrated that such flows, while appearing to behave homogenously in fact stratify and require higher transport pressure gradients and more care when conveying than their true homogenous paste counterparts, (Pullum and Graham 2000, Pullum 2003, Talmon and Mastbergen 2004). The flows are most readily described using a stratified model and a non-Newtonian version of this type of model has been shown to predict such flows quite well (Pullum et al., 2004). While suitable non-Newtonian models have been devised for transport in horizontal lines the effect of incline on such hybrid suspension flows is yet to be established. A new tilting pipeline rig has been constructed at CSIRO to investigate the behaviour of these complex suspensions and this paper describes this new test facility and reports on preliminary results obtained with a visco-plastic suspension, typical of many non-Newtonian co-disposal systems, e.g. (Houman 2003).

Scalable Performance Awareness for In Situ Scientific Applications

Scipedia content — Tue, 02 Feb 2021 07:14:14 +0100

Part of the promise of exascale computing and the next generation of scientific simulation codes is the ability to bring together time and spatial scales that have traditionally been treated separately. This enables creating complex coupled simulations and in situ analysis pipelines, encompassing such things as "whole device" fusion models or the simulation of cities from sewers to rooftops. Unfortunately, the HPC analysis tools that have been built up over the preceding decades are ill suited to the debugging and performance analysis of such computational ensembles. In this paper, we present a new vision for performance measurement and understanding of HPC codes, MonitoringAnalytics (MONA). MONA is designed to be a flexible, high performance monitoring infrastructure that can perform monitoring analysis in place or in transit by embedding analytics and characterization directly into the data stream, without relying upon delivering all monitoring information to a central database for post-processing. It addresses the trade-offs between the prohibitively expensive capture of all performance characteristics and not capturing enough to detect the features of interest. We demonstrate several uses of MONA; capturing and indexing multi-executable performance profiles to enable later processing, extraction of performance primitives to enable the generation of customizable benchmarks and performance skeletons, and extracting communication and application behaviors to enable better control and placement for the current and future runs of the science ensemble. Relevant performance information based on a system for MONA built from ADIOS and SOSflow technologies is provided for DOE science applications and leadership machines.

QEBA: Query-Efficient Boundary-Based Blackbox Attack

Scipedia content — Tue, 02 Feb 2021 07:29:18 +0100

Machine learning (ML), especially deep neural networks (DNNs) have been widely used in various applications, including several safety-critical ones (e.g. autonomous driving). As a result, recent research about adversarial examples has raised great concerns. Such adversarial attacks can be achieved by adding a small magnitude of perturbation to the input to mislead model prediction. While several whitebox attacks have demonstrated their effectiveness, which assume that the attackers have full access to the machine learning models; blackbox attacks are more realistic in practice. In this paper, we propose a Query-Efficient Boundary-based blackbox Attack (QEBA) based only on model's final prediction labels. We theoretically show why previous boundary-based attack with gradient estimation on the whole gradient space is not efficient in terms of query numbers, and provide optimality analysis for our dimension reduction-based gradient estimation. On the other hand, we conducted extensive experiments on ImageNet and CelebA datasets to evaluate QEBA. We show that compared with the state-of-the-art blackbox attacks, QEBA is able to use a smaller number of queries to achieve a lower magnitude of perturbation with 100% attack success rate. We also show case studies of attacks on real-world APIs including MEGVII Face++ and Microsoft Azure.

Comment: Accepted by CVPR 2020

Data-driven Conflict Detection Enhancement in 3D Airspace with Machine Learning

Scipedia content — Tue, 02 Feb 2021 07:53:48 +0100

International audience; Trajectory prediction with Closest Point of Approach (CPA) concept is a fundamental element of aircraft Conflict Detection (CD) problem. Conventional motion-based CPA prediction model generally assumes that aircraft is flying in straight line with constant speed. But due to environment uncertainties and ground speed changes, this conventional method frequently lacks accuracy in the real world with a high rate of false alarms and missed detections. In this paper, we introduce a novel automated data-driven CD framework with Machine Learning (ML) for 3D CPA prediction in a lookahead time of less than 20 minutes. Firstly, a 3D CPA model with cylindrical norm is proposed as the baseline. Then, data preparation with Mode-S observation data in France is explained, including data collection and data processing, to convert raw Mode-S data to the close-to-reality dataset. Furthermore, feature engineering is applied to build up a feature set with 16 features. Finally, four prevailing ML models are used to predict the time, horizontal distance and vertical distance of CPA in 3D airspace. CD is conducted based on the predicted values. The prediction and CD results show that all proposed ML models outperform the baseline model. Especially, GBM and FFNNs could strongly enhance the performance of CD.

Approach to increase flexibility in automobile body shops through component-integrated fixture functions

Scipedia content — Tue, 02 Feb 2021 08:03:31 +0100

Due to shorter product life-cycles, increasing product customization and the co-existence of electric and combustion engine vehicles, variant flexibility is gaining importance in the automobile production. The automobile body shop is characterized by inflexible, rigid fixture systems dedicated to meet the geometrical requirements of specific body parts. Changes in part geometry or dimension require the development of new fixture systems, thus increasing product variety results in higher fixture costs. This paper presents an approach for a fixtureless body shop based on component-integrated fixture-functions, increasing variant flexibility and reducing fixture costs. The approach is implemented using a body part assembly of an electric vehicle.

Document type: Article

Enabling automated driving by ICT infrastructure : a reference architecture

Scipedia content — Wed, 03 Feb 2021 15:29:55 +0100

Information and communication technology (ICT) is an enabler for establishing automated vehicles (AVs) in today's traffic systems. By providing complementary and/or redundant information via radio communication to the AV's perception by on-board sensors, higher levels of automated driving become more comfortable, safer, or even possible without interaction by the driver, especially in complex scenarios. Additionally, communication between vehicles and/or a central service can improve the efficiency of traffic flow. This paper presents a reference architecture for such an infrastructure-based support of AVs. The architecture combines innovative concepts and technologies from different technological fields like communication, IT environment and data flows, and cyber-security and privacy. Being the basis for the EU-funded project ICT4CART, exemplary implementations of this architecture will show its power for a variety of use cases on highways and in urban areas in test sites in Austria, Germany, and Italy, including cross-border interoperability.

Comment: Proceedings of 8th Transport Research Arena TRA 2020 (Conference cancelled), April 27-30, 2020, Helsinki, Finland

Facilitating Electric Vehicle Adoption with Vehicle Cost Calculators

Scipedia content — Wed, 03 Feb 2021 15:51:05 +0100

Consumer education regarding the costs of electric vehicles (EVs), particularly in comparison with similar gasoline vehicles, is important for adoption. However, the complexity of comparing gasoline and electricity prices, and balancing long-term return-on-investment from fuel and maintenance savings with purchase premiums for EVs, makes it difficult for consumers to assess potential economic advantages. Online vehicle cost calculators (VCCs) may help consumers navigate this complexity by providing tailored estimates of different types of vehicles costs for users and enabling comparisons across multiple vehicles. However, VCCs range widely and there has been virtually no behavioral research to identify functionalities and features that determine their usefulness in engaging and educating consumers and promoting EV adoption. This research draws on a behavioral theory, systematic review of available VCCs, and user research with three VCCs to articulate design recommendations for effective VCCs.View the NCST Project Webpage

TensorFlow Data Validation: Data Analysis and Validation in Continuous ML Pipelines

Scipedia content — Wed, 03 Feb 2021 15:54:56 +0100

MeshPipe: a Python-based tool for easy automation and demonstration of geometry processing pipelines

Scipedia content — Wed, 03 Feb 2021 15:57:05 +0100

The popularization of inexpensive 3D scanning, 3D printing, 3D publishing and AR/VR display technologies have renewed the interest in open-source tools providing the geometry processing algorithms required to clean, repair, enrich, optimize and modify point-based and polygonal-based models. Nowadays, there is a large variety of such open-source tools whose user community includes 3D experts but also 3D enthusiasts and professionals from other disciplines. In this paper we present a Python-based tool that addresses two major caveats of current solutions: the lack of easy-to-use methods for the creation of custom geometry processing pipelines (automation), and the lack of a suitable visual interface for quickly testing, comparing and sharing different pipelines, supporting rapid iterations and providing dynamic feedback to the user (demonstration). From the user's point of view, the tool is a 3D viewer with an integrated Python console from which internal or external Python code can be executed. We provide an easy-to-use but powerful API for element selection and geometry processing. Key algorithms are provided by a high-level C library exposed to the viewer via Python-C bindings. Unlike competing open-source alternatives, our tool has a minimal learning curve and typical pipelines can be written in a few lines of Python code. Peer Reviewed

Economic Value and User Remuneration for EV Based Distribution Grid Services

Scipedia content — Wed, 03 Feb 2021 16:01:59 +0100

This paper describes a method to estimate the monetary remuneration for the EV user support in distribution grids. The economic expenses of the conservative reinforcement solution are used for developing the methodology which is first derived and afterwards applied to a piece of Danish distribution grid consisting of 127 customers. In the conservative scenario the DSO should invest approx. 388718 DKK (52000e ) on new upgraded components. With EV support service the potential"br/"available money for the EV support remuneration is evaluated to be 187 DKK/week (25e /week). Considering a customer with an average EV load consumption, the annual remuneration would be 77 DKK (10e ). It is concluded that, if the components are severely overloaded, for the DSO it is more cost effective to invest in components upgrade. Conversely if the components are barely overloaded or close to their limit, the EV user support can benefit both the DSO and the users."br

Modelling one-way electric carsharing in the city of Shanghai, China

Scipedia content — Wed, 03 Feb 2021 16:14:13 +0100

carsharing is developing rapidly worldwide, carsharing demand estimation becomes a more and more important issue, especially for an area that just introduces this service. Station-based one-way carsharing, as a new carsharing type, recently developed rapidly in China. Both policy-maker and operator want to know how the demand changes with increasing supply. To enrich understanding of these problems, this paper aims to make use of the muti-agent simulation tool (MATSim) to model and simulate one-way carsharing. The largest carsharing project in Shanghai, Evcard, is explicitly analyzed. Specifically, it intends to integrate the mobile phone GSM (Global System for Mobile Communications) data, point of interest data, network data and travel survey data to build a base simulation scenario with about 160,000 agents in the Jiading district, Shanghai. More data, for example the empirical data of operator, are used to calibrate the model. Some special functions, for example, the carsharing vehicles in simulation are pure battery electric vehicles, have been integrated into MATSim. Some preliminary results are presented and validated.

DOPS: Learning to Detect 3D Objects and Predict Their 3D Shapes

Scipedia content — Wed, 03 Feb 2021 16:25:51 +0100

We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In contrast, we propose a general-purpose method that works on both indoor and outdoor scenes. The core novelty of our method is a fast, single-pass architecture that both detects objects in 3D and estimates their shapes. 3D bounding box parameters are estimated in one pass for every point, aggregated through graph convolutions, and fed into a branch of the network that predicts latent codes representing the shape of each detected object. The latent shape space and shape decoder are learned on a synthetic dataset and then used as supervision for the end-to-end training of the 3D object detection pipeline. Thus our model is able to extract shapes without access to ground-truth shape information in the target dataset. During experiments, we find that our proposed method achieves state-of-the-art results by ~5% on object detection in ScanNet scenes, and it gets top results by 3.4% in the Waymo Open Dataset, while reproducing the shapes of detected cars.

Comment: To appear in CVPR 2020

Ship-iceberg detection & classification in sentinel-1 SAR images

Scipedia content — Wed, 03 Feb 2021 16:36:49 +0100

The European Space Agency Sentinel-1 satellites provide good resolution all weather SAR images. We describe algorithms for detection and classification of ships, icebergs and other objects at sea. Sidelobes from strongly reflecting objects as large ships are suppressed for better determination of ship parameters. The resulting improved ship lengths and breadths are larger than the ground truth values known from Automatic Identification System (AIS) data due to the limited resolution in the processing of the SAR images as compared to previous analyses of Sentinel-2 optical images. The limited resolution in SAR imagery degrades spatial classification algorithms but it is found that the backscatter horizontal and vertical polarizations can be exploited to distinguish icebergs in the Arctic from large ships but not small boats or wakes.

Leveraging Personal Navigation Assistant Systems Using Automated Social Media Traffic Reporting

Scipedia content — Wed, 03 Feb 2021 16:37:51 +0100

Modern urbanization is demanding smarter technologies to improve a variety of applications in intelligent transportation systems to relieve the increasing amount of vehicular traffic congestion and incidents. Existing incident detection techniques are limited to the use of sensors in the transportation network and hang on human-inputs. Despite of its data abundance, social media is not well-exploited in such context. In this paper, we develop an automated traffic alert system based on Natural Language Processing (NLP) that filters this flood of information and extract important traffic-related bullets. To this end, we employ the fine-tuning Bidirectional Encoder Representations from Transformers (BERT) language embedding model to filter the related traffic information from social media. Then, we apply a question-answering model to extract necessary information characterizing the report event such as its exact location, occurrence time, and nature of the events. We demonstrate the adopted NLP approaches outperform other existing approach and, after effectively training them, we focus on real-world situation and show how the developed approach can, in real-time, extract traffic-related information and automatically convert them into alerts for navigation assistance applications such as navigation apps.

Comment: This paper is accepted for publication in IEEE Technology Engineering Management Society International Conference (TEMSCON'20), Metro Detroit, Michigan (USA)

A Tele-Visit System for ACTIVAGE Project

Scipedia content — Wed, 03 Feb 2021 16:52:33 +0100

The document concerns the development of a remote communication system that allows a remote visit between older patients and healthcare professionals in situations that do not allow hospital transport.

Guideline to measure service provided by, and resilience of, transport infrastructure

Scipedia content — Wed, 03 Feb 2021 17:00:07 +0100

In order to optimally allocate resources to help ensure that transport infrastructure networks continue to provide acceptable levels of service immediately, or as fast as possible, following the occurrence of extreme events, the resilience of the infrastructure need to be estimated. In this paper, a guideline is presented, based on (Adey et al., 2019), that allows managers to measure the resilience of infrastructure networks. The guideline emphasizes that to this scope it is required to define clearly: (i) the transport system, and the way to consistently measure (ii) the service and (iii) the resilience. Particular attention is paid on the fact that resilience can be measured with various degrees of precision depending on the specific problem to be addressed, the time-frame at disposition and the expertise available. Guide are then given on how to do this either using simulation, indicators, or the percentage of fulfilment of the resilience indicators.

Formal Semantics of Predictable Pipelines: a Comparative Study

Scipedia content — Wed, 03 Feb 2021 17:03:00 +0100

Computer architectures used in safety-critical domains are subjected to worst-case execution time analysis. The presence of performance-driven microarchitectures may trigger undesired timing phenomena, called timing anomalies, and complicate the timing analysis. This paper investigates pipelines speciﬁcally designed to simplify the worst-case execution time analysis (also called predictable pipelines). We propose formal and executable models of four research-oriented pipelines and one industrial pipeline to validate some of their claims related to their timing behavior. We indeed validate, via bounded model checking, the absence of a type of timing anomalies called ampliﬁcation timing anomalies, or its potential presence by identifying prerequisite to situations where they can occur."br

MIMIC-Extract

Scipedia content — Wed, 03 Feb 2021 17:11:14 +0100

Robust machine learning relies on access to data that can be used with standardized frameworks in important tasks and the ability to develop models whose performance can be reasonably reproduced. In machine learning for healthcare, the community faces reproducibility challenges due to a lack of publicly accessible data and a lack of standardized data processing frameworks. We present MIMIC-Extract, an open-source pipeline for transforming raw electronic health record (EHR) data for critical care patients contained in the publicly-available MIMIC-III database into dataframes that are directly usable in common machine learning pipelines. MIMIC-Extract addresses three primary challenges in making complex health records data accessible to the broader machine learning community. First, it provides standardized data processing functions, including unit conversion, outlier detection, and aggregating semantically equivalent features, thus accounting for duplication and reducing missingness. Second, it preserves the time series nature of clinical data and can be easily integrated into clinically actionable prediction tasks in machine learning for health. Finally, it is highly extensible so that other researchers with related questions can easily use the same pipeline. We demonstrate the utility of this pipeline by showcasing several benchmark tasks and baseline results.

Red Alert: a cognitive countermeasure to mitigate attentional tunneling

Scipedia content — Wed, 03 Feb 2021 17:17:40 +0100

International audience; Attentional tunneling, that is the inability to detect unexpected changes in the environment, has been shown to have critical consequences in air traffic control. The motivation of this study was to assess the design of a cognitive countermeasure dedicated to mitigate such failure of attention. The Red Alert cognitive countermeasure relies on a brief orange-red flash (300 ms) that masks the entire screen with a 15% opacity. Twenty-two air traffic controllers faced two demanding scenarios, with or without the cognitive countermeasure. The volunteers were not told about the Red Alert so as to assess the intuitiveness of the design without prior knowledge. Behavioral results indicated that the cognitive countermeasure reduced reaction time and improved the detection of the notification when compared to the classical operational design. Further analyses showed this effect was even stronger for half of our participants (91.7% detection rate) who intuitively understood the purpose of this design.

A Deeply Pipelined, Highly Parallel and Flexible LDPC Decoder

Scipedia content — Wed, 03 Feb 2021 17:18:57 +0100

International audience; A deeply pipelined and parallel LDPC decoder architecture is proposed in this paper. The main feature of this architecture is the ∆-update scheme, which relaxes the data dependency requirement and allows for deeper pipelines than typical decoders. The proposed architecture also has the flexibility to handle a large number of codes. Frame error rate performance is shown for three codes with different quantization parameters. Finally, the impact of pipeline depth on processing time and on the energy-delay product (EDP) is evaluated from post-synthesis results. The results show that the ability to have deeper pipelines can lead to large reductions in EDP.

Online Calibration of Microscopic Road Traffic Simulator

Scipedia content — Wed, 03 Feb 2021 17:22:32 +0100

Microscopic road traffic simulator is a powerful tool to analyze and evaluate various transportation systems due to its efficiency and risk-free operation. It is, therefore, widely used in traffic engineering field along with the gradual implementation of novel intelligent transportation systems. A reliable microscopic traffic simulator is able to accurately represent the real-world traffic situation when it is effectively calibrated with the combination of field data and proper simulation settings. Based on the existing theoretical calibration framework for the microscopic traffic simulator, this paper proposes an online calibration procedure using genetic algorithm as well as a specific implementation method to provide real-time performance measures that adequately mimic the field traffic situation. The proposed method was tested based on loop detector data demonstrating that real-time traffic modeling can be run in parallel with the real-world traffic process.

A global map of Amenities: Public Goods, Ethnic Divisions and Decentralization

Scipedia content — Wed, 03 Feb 2021 17:37:04 +0100

I analyze the effects of ethnic divisions on the provision of public goods. Using OpenStreetMap data, I construct a new global dataset of locations of public amenities, such as schools, hospital and libraries. I allow for the possibility that the data may be systematically incomplete using two new proxies for mapping completeness. I provide strong evidence that more autonomous subnational regions with a high degree of ethnic fractionalization provide significantly fewer productive public goods. Therefore, my findings indicate that decentralization can lead to a failure in the provision of local public goods when it increases ethnical fractionalization among the policy makers responsible for collectively supplying public goods.

A novel cost-effective Pressure Sensor based Smart Car park system

Scipedia content — Wed, 03 Feb 2021 17:37:54 +0100

With the increase in number of people using vehicles for transportation since last decade, traffic congestion is a major problem that requires to be solved effectively. Smart car park system is considered as one of the strategic solutions to this problem, which involves use of sensors to collect data. This paper proposes a novel low-cost smart car monitoring system to detect number of incoming and outgoing cars in and/or out of the car park using pressure sensors. This system also provides the data for the number of spaces available in the car park. Additionally, the paper also demonstrates the algorithm used to process the data obtained by the sensors to use it as a useful information.

A Burst and Congestion-Aware Routing Metric for RPL Protocol in IoT Network

Scipedia content — Wed, 03 Feb 2021 17:43:13 +0100

The packet loss and power consumption are the main issues considered once congestion occurs in any network, such as the Internet of Things (IoT) with a huge number of sensors and applications. Since IPv6 Routing Protocol for Low Power and Lossy Networks (RPL) is not initially designed for high stream traffic load, this restricts the application domain of RPL in several IoT scenarios such as burst traffic scenarios. The performance of RPL suffers in a network with burst traffic load, which leads to reducing the lifetime of the network and causing traffic congestion among the neighbour nodes. Therefore, to address this issue, we proposed a Burst and Congestion-Aware Metric for RPL called BCA-RPL, which calculates the rank, considering the number of packets. Also, the proposed mechanism includes congestion avoiding and load balancing techniques by switching the best parent selection to avoid the congested area. Our scheme is built and compared to the original RPL routing protocol for low power and lossy network with OF0 (OF0-RPL). Simulation results based on Cooja simulator shows BCA-RPL performs better than the original RPL-OF0 routing protocol in terms of packet loss, power consumption and packet delivery ratio (PDR) under burst traffic load. The BCA-RPL significantly improves the network where it decreases the packet loss around 50% and power consumption to an acceptable level with an improvement on the PDR of the IoT network.

BugDoc: Algorithms to Debug Computational Processes

Scipedia content — Wed, 03 Feb 2021 18:01:38 +0100

Data analysis for scientific experiments and enterprises, large-scale simulations, and machine learning tasks all entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous outputs, the pipeline may fail to execute or produce incorrect results. Inferring the root cause(s) of such failures is challenging, usually requiring time and much human thought, while still being error-prone. We propose a new approach that makes use of iteration and provenance to automatically infer the root causes and derive succinct explanations of failures. Through a detailed experimental evaluation, we assess the cost, precision, and recall of our approach compared to the state of the art. Our experimental data and processing software is available for use, reproducibility, and enhancement.

Comment: To appear in SIGMOD 2020. arXiv admin note: text overlap with arXiv:2002.04640

The autonomous vehicle for urban collective transport: disrupting business models embedded in the smart city revolution

Scipedia content — Wed, 03 Feb 2021 18:02:17 +0100

The complexity of the automotive sector has grown dramatically in the last years. We are probably witnessing an automobile revolution, combining technology disruptions as well as regulation’s changes which pave the way for a new robomobility. Accordingly, new economic models are about to connect the fourfold product-service-structure-market leading to a responsible and sustainable mobility in connection with the development of smart cities. In this paper, we aim at characterizing the changes that are occurring and try to anticipate which players are about to lead the transition towards the new paradigm of robomobility.

A Morphable Face Albedo Model

Scipedia content — Wed, 03 Feb 2021 18:10:00 +0100

In this paper, we bring together two divergent strands of research: photometric face capture and statistical 3D face appearance modelling. We propose a novel lightstage capture and processing pipeline for acquiring ear-to-ear, truly intrinsic diffuse and specular albedo maps that fully factor out the effects of illumination, camera and geometry. Using this pipeline, we capture a dataset of 50 scans and combine them with the only existing publicly available albedo dataset (3DRFE) of 23 scans. This allows us to build the first morphable face albedo model. We believe this is the first statistical analysis of the variability of facial specular albedo maps. This model can be used as a plug in replacement for the texture model of the Basel Face Model (BFM) or FLAME and we make the model publicly available. We ensure careful spectral calibration such that our model is built in a linear sRGB space, suitable for inverse rendering of images taken by typical cameras. We demonstrate our model in a state of the art analysis-by-synthesis 3DMM fitting pipeline, are the first to integrate specular map estimation and outperform the BFM in albedo reconstruction.

Comment: CVPR 2020

Remanufacturing of electric vehicles: Challenges in production management

Scipedia content — Wed, 03 Feb 2021 18:14:33 +0100

Due to the conceptual degrees of freedom in their product structure, electric vehicles offer high potential for remanufacturing-oriented product design. This potential is, however, not realized yet. Remanufacturing as one fundamental element of a circular economy is characterized by specific challenges caused by uncertain information about the condition and the timing of the returning product. By means of a case study within the remanufacturing industry, the effects of uncertainties on remanufacturing operations are examined and different approaches within the field of production management to meet these specific challenges are pointed out. Based on the result of the case study a production management framework outlining fields of action to deal with remanufacturing specific uncertainties is developed. In this context, the requirements for remanufacturing of electric vehicles are derived by analyzing similarities from other industry sectors. In conclusion, a solution approach for the implementation for electric vehicles is presented for strategic, tactical and operational procurement logistics and remanufacturing operations.

Document type: Article

Design and Evaluation of a Tool to Support Air Traffic Control with 2D and 3D Visualizations

Scipedia content — Wed, 03 Feb 2021 18:29:16 +0100

traffic control officers (ATCOs) are specialized workers responsible to monitor and guide airplanes in their assigned airspace. Such a task is highly visual and mainly supported by 2D visualizations. In this paper, we designed and assessed an application for visualizing air traffic in both orthographic (2D) and perspective (3D) views. A user study was then performed to compare these two types of representations in terms of situation awareness, workload, performance, and user acceptance. Results show that the 3D view yielded both higher situation awareness and less workload than the 2D view condition. However, such a performance does not match the opinion of the ATCOs about the 3D representation.

A Distributed Metaheuristic Approach for Complexity Reduction in Air Traffic for Strategic 4D Trajectory Optimization

Scipedia content — Wed, 03 Feb 2021 18:29:57 +0100

International audience; This paper presents a new challenge on the strategic 4D trajectory optimization problem with the evaluation of air traffic complexity by using the geometric-based intrinsic complexity measure called König metric. The demonstration of König metric shows the potential that the algorithm can capture the disorganized the disorganized traffic which represents the difficulty of maintaining situational awareness as expected by the air traffic controller. We reformulate the optimization problem with two trajectory separation approaches including delaying flight departure time and allocating the new flight level subject to limited delay time of departure, limited changes of flight levels and fuel consumption constraints. We propose our solution to solve daily traffic demands in the regional French airspace. The resolution process uses the distributed metaheuristic algorithm to optimize aircraft trajectories in 4D environment with the objective of finding the optimal air traffic complexity. The experimental results shows the reduction of maximum complexity more than 95 % with average delay of 2.69 minutes. The optimized trajectories can save fuel more than 80000 kg. The proposed algorithm not only reduces the air traffic complexity but also maintain its distribution in traffic. The research results represent further steps towards taking other trajectory separations methods and aircraft trajectory uncertainties into account, developing our approach at the continental scale as well as adapting it in the pre-tactical and tactical planning phase.

Optimizing Geometry Compression using Quantum Annealing

Scipedia content — Wed, 03 Feb 2021 18:30:55 +0100

The compression of geometry data is an important aspect of bandwidth-efficient data transfer for distributed 3d computer vision applications. We propose a quantum-enabled lossy 3d point cloud compression pipeline based on the constructive solid geometry (CSG) model representation. Key parts of the pipeline are mapped to NP-complete problems for which an efficient Ising formulation suitable for the execution on a Quantum Annealer exists. We describe existing Ising formulations for the maximum clique search problem and the smallest exact cover problem, both of which are important building blocks of the proposed compression pipeline. Additionally, we discuss the properties of the overall pipeline regarding result optimality and described Ising formulations.

Comment: 6 pages, 3 figure

Ant Colony Systems for Optimizing Sequences of Airspace Partitions

Scipedia content — Wed, 03 Feb 2021 18:38:01 +0100

International audience; In this paper, we introduce an Ant Colony System algorithm which finds optimal or near-optimal sequences of airspace partitions, taking into account some constraints on the transitions between two successive airspace configurations. The transitions should be simple enough to allow air traffic controllers to maintain their situation awareness during the airspace configuration changes. For the same reason, once a sector is opened it should remain so for a minimum duration. The Ant Colony System (ACS) finds a sequence of airspace configurations minimizing a cost related to the workload and the usage of manpower resources, while satisfying the transition constraints. This approach shows good results in a limited time when compared with a previously proposed $A$ * algorithm on some instances from the french air traffic control center of Aix (East qualification zone) where the $A$ * algorithm exhibited high computation times.00

Simultaneous Stabilization of Traffic Flow on Two Connected Roads

Scipedia content — Wed, 03 Feb 2021 18:39:31 +0100

International audience; In this paper we develop a boundary state feedback control law for a cascaded traffic flow network system: one incoming and one outgoing road connected by a junction. The macroscopic traffic dynamics on each road segment are governed by Aw-Rascle-Zhang (ARZ) model, consisting of second-order nonlinear partial differential equations (PDEs) for traffic density and velocity. Different equilibrium road conditions are considered for the two segments. For stabilization of stop-and-go traffic congestion on the two roads, we consider a ramp metering located at the connecting junction. The traffic flow rate entering from the on-ramp to the mainline junction is actuated. The objective is to simultaneously stabilize the upstream and downstream traffic to given spatially-uniform constant steady states. We design a full state feedback control law for this under-actuated network of two systems of two hetero-directional linear first-order hyperbolic PDEs interconnected through the junction boundary. Exponential Convergence to steady states in L 2 sense is validated by a numerical simulation.

Stop & Go a Cooperative Maneuver for Automated Vehicles Based on Virtual and Real Environment

Scipedia content — Wed, 03 Feb 2021 18:42:28 +0100

[Resumen] La implementación de maniobras cooperativas entre vehículos automatizados es una necesidad dentro del progreso de los Sistemas Avanzado de Asistencia al Conductor (ADAS). Sin embargo, el desarrollo de estas estrategias en vehículos reales depende de la disponibilidad de un mínimo de plataformas experimentales, que involucran elevados costos y tiempos de pruebas. En este sentido, el presente trabajo presenta una herramienta para el diseño de la maniobra cooperativa Stop & Go, haciendo uso de un entorno virtual para la simulación de un vehículo líder, junto con un vehículo eléctrico automatizado que realiza el seguimiento dentro de un circuito cerrado. Para el diseño de la maniobra se establecerá comunicación V2V entre ambas plataformas, las cuales ejecutan una arquitectura general de conducción automatizada. El algoritmo de seguimiento está basado en un controlador de lógica difusa dependiente de la velocidad del vehículo líder y la distancia entre ambos coches. Los resultados demuestran la utilidad de combinar ambos entornos de prueba para la validación de maniobras cooperativas reduciendo el costo y el tiempo en comparación con pruebas reales [Abstract] The implementation of cooperative maneuvers between automated vehicles is a necessary for the improvement of the Advanced Driver Assistence Systems (ADAS). However, the development of these strategies in real vehicles depends on the availability of experimentals platforms, which involves high costs and a lot of testing time. In this line of thought, the present work shows a tool for the design of the Stop & Go cooperative maneuver, making use of a virtual environment for the simulation of a leading vehicle, along with an automated electric vehicle that performs the tracking within a closed circuit. For the design of the maneuver, a V2V communication system bet- ween the two platforms will be established, bearing in mind that they execute an automated driving general arhcitecture. The tracking algorithm is based on a fuzzy logic controller, dependent on the leading vehicle speed and the distance between the two vehicles. The results show the usefulness of combining the two test environments for the validation of the cooperative maneuver, reducing the cost and the time in comparison with the real test environment.

Using real sensors data to calibrate a traffic model for the city of Modena

Scipedia content — Mon, 25 Jan 2021 11:57:37 +0100

In Italy, road vehicles are the preferred mean of transport. Over the last years, in almost all the EU Member States, the passenger car fleet increased. The high number of vehicles complicates urban planning and often results in traffic congestion and areas of increased air pollution. Overall, efficient traffic control is profitable in individual, societal, financial, and environmental terms. Traffic management solutions typically require the use of simulators able to capture in detail all the characteristics and dependencies associated with real-life traffic. Therefore, the realization of a traffic model can help to discover and control traffic bottlenecks in the urban context. In this paper, we analyze how to better simulate vehicle flows measured by traffic sensors in the streets. A dynamic traffic model was set up starting from traffic sensors data collected every minute in about 300 locations in the city of Modena. The reliability of the model is discussed and proved with a comparison between simulated values and real values from traffic sensors. This analysis pointed out some critical issues. Therefore, to better understand the origin of fake jams and incoherence with real data, we approached different configurations of the model as possible solutions.

Challenges of compressing hydrogen for pipeline transportation with centrifugal-compressors

Scipedia content — Wed, 03 Feb 2021 18:52:16 +0100

Analyzing the Sensitivity of GPU Pipeline Registers to Single Events Upsets

Scipedia content — Wed, 03 Feb 2021 19:28:49 +0100

Graphics processing units are available solutions for high-performance safety-critical applications, such as self-driving cars. In this application domain, functional-safety and reliability are major concerns. Thus, the adoption of fault tolerance techniques is mandatory to detect or correct faults, since these devices must work properly, even when faults are present. GPUs are designed and implemented with cutting-edge technologies, which makes them sensitive to faults caused by radiation interference, such as single event upsets. These effects can lead the system to a failure, which is unacceptable in safety-critical applications. Therefore, effective detection and mitigation strategies must be adopted to harden the GPU operation. In this paper, we analyze transient effects in the pipeline registers of a GPU architecture. We run four applications at three GPU configurations, considering the source of the fault, its effect on the GPU, and the use of software-based hardening techniques. The evaluation was performed using a general-purpose soft-core GPU based on the NVIDIA G80 architecture. Results can guide designers in building more resilient GPU architectures.

Faster and More Accurate Measurement through Additive-Error Counters

Scipedia content — Wed, 03 Feb 2021 19:36:17 +0100

Counters are a fundamental building block for networking applications such as load balancing, traffic engineering, and intrusion detection, which require estimating flow sizes and identifying heavy hitter flows. Existing works suggest replacing counters with shorter multiplicative error \\emph{estimators} that improve the accuracy by fitting more of them within a given space. However, such estimators impose a computational overhead that degrades the measurement throughput. Instead, we propose \\emph{additive} error estimators, which are simpler, faster, and more accurate when used for network measurement. Our solution is rigorously analyzed and empirically evaluated against several other measurement algorithms on real Internet traces. For a given error target, we improve the speed of the uncompressed solutions by $5\\times$-$30\\times$, and the space by up to $4\\times$. Compared with existing state-of-the-art estimators, our solution is $ 9\\times$-$35\\times$ faster while being considerably more accurate.

Comment: To appear in IEEE INFOCOM 2020

Description of Non-Intrusive Sonar Array-Based Technology and its Application to Unique and Difficult Slurry and Paste Flow Measurements

Scipedia content — Wed, 03 Feb 2021 19:51:27 +0100

In this presentation, CiDRA’s patented technology platform and its applications will be described. CiDRA's non-invasive, passive sonar array-based flow meter technology performs two independent measurements – flow rate and fluid characterization. Firstly, the meter provides the volumetric flow rate of the mixture by measuring the speed at which naturally occurring structures such as turbulent eddies or density variations convect with the flow past an axial array of sensors. Secondly, the meter uses similar sonar-based processing techniques and naturally occurring sound in the process slurry to measure entrained air levels and in some cases fluid composition. The result is a unique ability to measure the flow rate and entrained air level of most fluids – clean liquids, high solids content slurries, pastes, and liquids and slurries with entrained air. Also to be presented is the application of this array-based technology platform in a variety of hydrotransport and minerals beneficiation applications. Examples of these situations include volume flow measurements in tailings lines, thickener discharge, high solids contents pipelines, slurry lines with magnetite and other magnetic ore, slurry lines with abrasive or corrosive materials, high pressure lines, and slurry and nonslurry lines exhibiting scale buildup. The operational advantages and value of these measurements, even in the presence of scale buildup, will be discussed. Recent developments in extending this technology to solve other unique measurement problems such as valve movement confirmation, non-invasive slurry profiling, and sanding detection will be covered.

Towards more environmentally sustainable intercontinental freight transport

Scipedia content — Wed, 03 Feb 2021 20:02:43 +0100

In a world where the population and many economies are expanding rapidly the demand for freight transport keeps rising accordingly. As more goods are transported by a growing number of freight vehicles, in particular trucks and sea vessels, their already considerable negative environmental impact also rises. Technology advances, but demand growth (partially) counteracts its positive impact on fuel consumption and emissions. In road transport, CO2-emissions keep rising, while emissions of NOx and PM10 have been reduced, at least in those countries where the most advanced engine technologies are used, although locally serious problems may remain. In areas where such technologies are not available, more freight transport means higher emissions and negative health effects. Sea shipping sees increasing emission levels overall. Maritime transport and trucking dominate intercontinental freight transport. Modernisation of railways and roads offers opportunities to reduce emissions by using rail for part of the journey. In a market setting, this means that transport providers have to redesign transport chains. Some have done this already, while others are increasingly interested. To assess the potential, the following main research question was addressed: Is it possible to reduce emissions of CO2, NOx and PM10 by replacing the maritime leg of a transport service by road and/or rail transport in the corridor Antwerp (Belgium) – Shanghai (China) without logistic penalties? Various combinations of trucking, sea and rail transport were fed into a simulation model to estimate the accompanying emissions and trip times. The"br/"new services offer a complex range of positive and negative impacts; hence governments should carefully consider their support. In a simulation study only a very stylised representation of these services can be modelled. This leads to an advice for a more in-depth study to include additional (technical, service and cost) data.

The need for data management plans to enable the resilience analysis of transport infrastructure systems

Scipedia content — Wed, 03 Feb 2021 20:23:55 +0100

To be helpful in developing recommendations to support the standardization of infrastructure resilience assessment, members of the FORESEE project have studied the data requirements of a case study through its lifecycle phases, and asset management perspectives. This paper introduces key results in these analysis, including concepts and objectives for infrastructure data management plans, to accomplish future resilience governance optimizations and enable the broad variety of assessment methods.

Parallel Multi-Hypothesis Algorithm for Criticality Estimation in Traffic and Collision Avoidance

Scipedia content — Wed, 03 Feb 2021 20:24:50 +0100

Due to the current developments towards autonomous driving and vehicle active safety, there is an increasing necessity for algorithms that are able to perform complex criticality predictions in real-time. Being able to process multi-object traffic scenarios aids the implementation of a variety of automotive applications such as driver assistance systems for collision prevention and mitigation as well as fall-back systems for autonomous vehicles. We present a fully model-based algorithm with a parallelizable architecture. The proposed algorithm can evaluate the criticality of complex, multi-modal (vehicles and pedestrians) traffic scenarios by simulating millions of trajectory combinations and detecting collisions between objects. The algorithm is able to estimate upcoming criticality at very early stages, demonstrating its potential for vehicle safety-systems and autonomous driving applications. An implementation on an embedded system in a test vehicle proves in a prototypical manner the compatibility of the algorithm with the hardware possibilities of modern cars. For a complex traffic scenario with 11 dynamic objects, more than 86 million pose combinations are evaluated in 21 ms on the GPU of a Drive PX~2.

What drives the usage of shared transport services?: An impact analysis of supply and utilization of mobility services in German cities

Scipedia content — Wed, 03 Feb 2021 20:31:31 +0100

Shared mobility is widely discussed, yet only few travelers actually make use of shared services. Apart from personal characteristics, the supply and more specific the supply density of shared vehicles is assumed to be crucial for a widespread shared mobility usage. In this paper, we test this hypothesis. Moreover we provide insights into the impact of current mobility behavior on the usage intention for shared transport services. For this purpose, we combine existing transport usage data with the real supply of shared vehicles in selected cities in Germany. We investigate free-floating and station-based car- and bikesharing, free-floating e-scootersharing, as well as ridesharing. To do so, we collected data on the vehicles supplied per service for beginning of 2020. In a first step, we analyze group differences in terms of intended usage between people living in cities where the services are offered and those who live in cities without access to such services. This information is used in a second step when we analyze to what extent the supply density is driving usage intention for a specific trip purpose obtained from the first analysis step. Therefore, we apply logistic regression analyses that focus on socio-demographics, the users’ possession of mobility tools (e.g. driver’s license, car access, transit pass), their current transport behavior and the availability of services respectively.

Work-in-Progress: Synchronous Intersection Management Protocol for Mixed Traffic Flows

Scipedia content — Wed, 03 Feb 2021 20:32:53 +0100

RTSS 2019 originally postponed from December 2019 (Hong-Kong) to February 2020 (York, UK) was cancelled. Urban traffic management (UTM) is responsible for planning and controlling traffic on road infrastructures, including lane closures, full freeway closures, and pedestrian access. An essential element in UTM is the Intersection Management (IM) that deals with traffic control and is vulnerable to traffic congestion and accidents. In this paper, we propose an intelligent intersection management architecture along with the synchronous intersection management protocol (SIMP) instantiated in two versions. Simulation results show the advantages of SIMP-M (one of the versions) over the well known TraCI IM protocol, in terms of both worst-case and average vehicle speed passing through one intersection. info:eu-repo/semantics/publishedVersion

FORESEE: Future proofing strategies FOr resilient transport networks against Extreme Events

Scipedia content — Wed, 03 Feb 2021 20:45:45 +0100

The overall objective of FORESEE, as an H2020 project inside the resilience to extreme events topic (natural, climate change and man-made), is to provide cost effective and reliable tools to improve the resilience of transport infrastructure networks, as the ability to reduce the probability of occurrence, magnitude and/or duration of possible disruptive events that may affect the security and/or the quality of the services provided by infrastructure operators. FORESEE will address through new innovative technologies, methodologies and resilient schemes the effectiveness of resilient measures to improve the ability to anticipate, absorb, adapt to, and/or rapidly recover from a potentially disruptive event."br

Deep Learning for Pipeline Damage Detection: an Overview of the Concepts and a Survey of the State-of-the-Art

Scipedia content — Wed, 03 Feb 2021 20:47:14 +0100

Pipelines have been extensively implemented to transfer oil as well as gas products at wide distances as they are safe, and suitable. However, numerous sorts of damages may happen to the pipeline, for instance erosion, cracks, and dent. Hence, if these faults are not properly refit will result in the pipeline demolitions having leak or segregation which leads to tremendously environment risks. Deep learning methods aid operators to recognize the earliest phases of threats to the pipeline, supplying them time and information in order to handle the problem efficiently. This paper illustrates fundamental implications of deep learning comprising convolutional neural networks. Furthermore the usages of deep learning approaches for hampering pipeline detriment through the earliest diagnosis of threats are introduced.

Multiform Logical Time & Space for Mobile Cyber-Physical System with Automated Driving Assistance System

Scipedia content — Wed, 03 Feb 2021 20:48:14 +0100

International audience; We study the use of Multiform Logical Time, as embodied in Esterel/SyncCharts and Clock Constraint Specification Language (CCSL), for the specification of assume-guarantee constraints providing safe driving rules related to time and space, in the context of Automated Driving Assistance Systems (ADAS). The main novelty lies in the use of logical clocks to represent the epochs of specific area encounters (when particular area trajectories just start overlapping for instance), thereby combining time and space constraints by CCSL to build safe driving rules specification. We propose the safe specification pattern at high-level that provide the required expressiveness for safe driving rules specification. In the pattern, multiform logical time provides the power of parameterization to express safe driving rules, before instantiation in further simulation contexts. We present an efficient way to irregularly update the constraints in the specification due to the context changes, where elements (other cars, road sections, traffic signs) may dynamically enter and exit the scene. In this way, we add constraints for the new elements and remove the constraints related to the disappearing elements rather than rebuild everything. The multi-lane highway scenario is used to illustrate how to irregularly and efficiently update the constraints in the specification while receiving a fresh scene.

Connectivity and resilience of remote operations: insights from air traffic management

Scipedia content — Wed, 03 Feb 2021 20:52:03 +0100

Towards Transforming OpenFlow Rulesets to Fit Fixed-Function Pipelines

Scipedia content — Wed, 03 Feb 2021 20:53:14 +0100

Multiple path prediction for traffic scenes using LSTMs and mixture density models

Scipedia content — Wed, 03 Feb 2021 21:09:16 +0100

This work presents an analysis of predicting multiple future paths of moving objects in traffic scenes by leveraging Long Short-Term Memory architectures (LSTMs) and Mixture Density Networks (MDNs) in a single-shot manner. Path prediction allows estimating the future positions of objects. This is useful in important applications such as security monitoring systems, Autonomous Driver Assistance Systems and assistive technologies. Normal approaches use observed positions (tracklets) of objects in video frames to predict their future paths as a sequence of position values. This can be treated as a time series. LSTMs have achieved good performance when dealing with time series. However, LSTMs have the limitation of only predicting a single path per tracklet. Path prediction is not a deterministic task and requires predicting with a level of uncertainty. Predicting multiple paths instead of a single one is therefore a more realistic manner of approaching this task. In this work, predicting a set of future paths with associated uncertainty was archived by combining LSTMs and MDNs. The evaluation was made on the KITTI and the CityFlow datasets on three type of objects, four prediction horizons and two different points of view (image coordinates and birds-eye view

Adaptive Strategies of Multi-Objective Optimization For Greener Networks

Scipedia content — Wed, 03 Feb 2021 21:10:41 +0100

Increasing energy costs and environmental issues related to the Internet and wired networks continue to be a major concern. Energy-efficient or power-aware networks continue to gain interest in the research community. Existing energy reduction approaches do not fully address all aspects of the problem. We consider the problem of reducing energy by turning off network links, while achieving acceptable load balance, by adjusting link weights. In this research, we optimize two objectives, which are minimizing network energy consumption by maximizing utilization of shortest paths, and at the same time achieving load-balance by minimizing network Maximum Link Utilization (MLU). Increasing utilization of shortest paths provides the opportunity to switch off nodes and links, thus saving network power. This research proposes a new approach that relies on live data collected from wired networks, and performs Multi Objective Optimization (MOO) using a Non-dominated Sorting Genetic Algorithm (NSGA-II) that applies alternative adaptive strategies in order to optimize both objectives. Research to date has focused on the link level or traffic load balance, to minimize energy consumption, while putting less focus on utilizing adaptive strategic techniques that optimize multi objectives problems. This work proposes a novel approach to select underutilized links to go to sleep using adaptive strategies of MOO that are aware of traffic changes. Re-computing the algorithm should take less than a minute, while network traffic is frequently updated every few minutes. The hybrid approach we proposed was able to reduce the power consumption by 35%, while reducing MLU by 31% for specific traffic pattern used in Abilene network topology.

Sustainable business model archetypes for the electric vehicle battery second use industry: towards a conceptual framework

Scipedia content — Wed, 03 Feb 2021 21:15:37 +0100

This paper explores sustainable business models (SBMs) evolution for the rapidly developing battery second use (B2U) market within the emerging electric vehicle (EV) industry. Previous work identified that SBMs and EV B2U are emerging as major research streams but there is paucity among literature to deliver an overarching framework or a holistic view between these fields and highlight fresh areas for future research. We adopted an inductive multiple-case study approach to unearth new knowledge by comprehending how B2U stakeholders undertake their sustainability-related business activities. These are not only focused on economic profitability but more importantly address wider social and environmental stakeholder value as part of prospective SBMs. The SBM archetypes were adopted as the major lens for our data analysis to study multiple cases of B2U stakeholder roles and comprehend further the scope and ultimate purpose of their operations. Major results indicate that the SBM archetypes as major sustainable innovation strategies have the potential to create a new conception of business models for sustainability in the EV B2U market. In turn, this creates and drives shared sustainable value for multiple stakeholders through cross-sectoral collaborations as part of an entire new and more SBMs. Finally, this study proposes the conceptual sustainable innovation business model (SIBM) framework for the EV B2U industry that includes such shared sustainable value creations which in turn drives forward business performance and sustainability at the same time, eventually creating the business case for sustainability within the EV industry.

Peer Reviewed

Document type: Article

Supervised Machine Learning Model to Help Controllers Solving Aircraft Conflicts

Scipedia content — Wed, 03 Feb 2021 21:18:12 +0100

International audience; When two or more airplanes find themselves less than a minimum distance apart on their trajectory, it is called a conflict situation. To solve a conflict, air traffic controllers use various types of information and decide on actions pilots have to apply on the fly. With the increase of the air traffic, the controllers’ workload increases; making quick and accurate decisions is more and more complex for humans. Our research work aims at reducing the controllers’ workload and help them in making the most appropriate decisions. More specifically, our PhD goal is to develop a model that learns the best possible action(s) to solve aircraft conflicts based on past decisions or examples. As the first steps in this work, we present a Conflict Resolution Deep Neural Network (CR-DNN) model as well as the evaluation framework we will follow to evaluate our model and a data set we developed for evaluation.

Urban Factories – Establishing resource-efficiency in production logistics systems in cities

Scipedia content — Wed, 03 Feb 2021 21:39:35 +0100

Cities are a hotspot for resource consumption and related impacts. This is induced, among others, by transportation, production and the use of products and services. Industrial production is commonly associated with negative impacts, e.g. on the environment or traffic. Through positive integration of production sites into urban surroundings, negative impacts can be eliminated, and even positive impacts achieved. To reach a higher degree of integration of different utilizations in cities, resource-efficiency, new conceptual approaches are required for urban factories, city authorities and further stakeholders. For this purpose, a methodology has been developed that describes the planning processes of the involved disciplines and their interdependencies concerning content and timing. Subsequently, an analysis of Urban Factories within a reference framework called the factory-city-system and its key resources is carried out in an exemplary case study. Measures to enhance resource-efficiency are thus dentified, exemplarily described and examined regarding their potential to raise resource-efficiency.

Near-Optimal Reactive Synthesis Incorporating Runtime Information

Scipedia content — Wed, 03 Feb 2021 21:45:29 +0100

We consider the problem of optimal reactive synthesis - compute a strategy that satisfies a mission specification in a dynamic environment, and optimizes a performance metric. We incorporate task-critical information, that is only available at runtime, into the strategy synthesis in order to improve performance. Existing approaches to utilising such time-varying information require online re-synthesis, which is not computationally feasible in real-time applications. In this paper, we pre-synthesize a set of strategies corresponding to candidate instantiations (pre-specified representative information scenarios). We then propose a novel switching mechanism to dynamically switch between the strategies at runtime while guaranteeing all safety and liveness goals are met. We also characterize bounds on the performance suboptimality. We demonstrate our approach on two examples - robotic motion planning where the likelihood of the position of the robot's goal is updated in real-time, and an air traffic management problem for urban air mobility.

Comment: Presented at ICRA2020

Decentralizing Air Traffic Flow Management with Blockchain-based Reinforcement Learning

Scipedia content — Wed, 03 Feb 2021 21:48:50 +0100

We propose and implement a decentralized, intelligent air traffic flow management (ATFM) solution to improve the efficiency of air transportation in the ASEAN region as a whole. Our system, named BlockAgent, leverages the inherent synergy between multi-agent reinforcement learning (RL) for air traffic flow optimization; and the rising blockchain technology for a secure, transparent and decentralized coordination platform. As a result, BlockAgent does not require a centralized authority for effective ATFM operations. We have implemented several novel distributed coordination approaches for RL in BlockAgent. Empirical experiments with real air traffic data concerning regional airports have demonstrated the feasibility and effectiveness of our approach. To the best of our knowledge, this is the first work that considers blockchain-based, distributed RL for ATFM.

Mechanisms for outsourcing computation via a decentralized market

Scipedia content — Wed, 03 Feb 2021 21:57:27 +0100

the number of personal computing and IoT devices grows rapidly, so does the amount of computational power that is available at the edge. Since many of these devices are often idle, there is a vast amount of computational power that is currently untapped, and which could be used for outsourcing computation. Existing solutions for harnessing this power, such as volunteer computing (e.g., BOINC), are centralized platforms in which a single organization or company can control participation and pricing. By contrast, an open market of computational resources, where resource owners and resource users trade directly with each other, could lead to greater participation and more competitive pricing. To provide an open market, we introduce MODiCuM, a decentralized system for outsourcing computation. MODiCuM deters participants from misbehaving-which is a key problem in decentralized systems-by resolving disputes via dedicated mediators and by imposing enforceable fines. However, unlike other decentralized outsourcing solutions, MODiCuM minimizes computational overhead since it does not require global trust in mediation results. We provide analytical results proving that MODiCuM can deter misbehavior, and we evaluate the overhead of MODiCuM using experimental results based on an implementation of our platform.