Abstract

Deep Learning requires huge amount of data with related labels, that are necessary for proper training. Thanks to modern videogames, which aim at photorealism, it is possible to easily obtain synthetic dataset by extracting information directly from the game engine. The intent is to use data extracted from a videogame to obtain a representation of various scenarios and train a deep neural network to infer the information required for a specific task. In this work we focus on computer vision aids for automotive applications and we target to estimate the distance and speed of the surrounding vehicles by using a single dashboard camera. We propose two network models for distance and speed estimation, respectively. We show that training them by using synthetic images generated by a game engine is a viable solution that turns out to be very effective in real settings. Document type: Part of book or chapter of book

Abstract

The inflexibility and rigidity of the current networking systems in light of the growing number of computing devices that connected to the Internet has led to the need of a new generation of computer networks. In this context, software-defined network has recently emerged as one of the most recognisable solutions to facilitate the network management and decrease the complexity through detaching the control layer from network appliances. Since, each new technology accompanied with new issues and concerns, one of the main challenges that facing the SDNs is the fault tolerance and resilience. Although there are a numerous of studies that have discussed this issue, the after failure repair scenario is remained unclear and have not addressed well yet. For this reason, we specify this paper as a step forward to address the issue of routing changes, which is important for utilising the optimal paths after failure repair. We produced a new network model as well as a compatible framework with SDN architecture to fulfil the routing changes activity. The consequence is estimated based on an analytical model and finally, a case study example is provided in order to conceptualise the concept. Document type: Part of book or chapter of book

Abstract

Micro-simulations for transport planning are becoming increasingly important in traffic simulation, traffic analysis, and traffic forecasting. In the last decades the shift from using typically aggregated data to more detailed, individual based, complex data (e.g. GPS tracking) andthe continuously growing computer performance on fixed price level leads to the possibility of using microscopic models for large scale planning regions. This chapter presents such a micro-simulation. The work is part of the research project MATSim (Multi Agent Transport Simulation, http://matsim.org). In the chapter here the focus lies on design and implementation issues as well as on computational performance of different parts of the system. Based on a study of Swiss daily traffic – ca. 2.3 million individuals using motorized individual transport producing about 7.1 million trips, assigned to a Swiss network model with about 60,000 links, simulated and optimized completely time-dynamic for a complete workday – it is shown that the system is able to generate those traffic patterns in about 36 hours computation time. Document type: Part of book or chapter of book

Abstract

The economic effects of existing and prospective federal policies governing intercity and international freight and passenger transportation enterprises in the economy of the United States are evaluated. The analysis encompasses all modes of transportation, including rail, motor, water, air and intermodal coordinative institutions, and focuses upon the impact of alternative regulatory policies. Volume IV includes: an introduction; transport economics at the network level; airline policy analysis at the industrial level--a preview; demand in airline markets; airline policy analysis at the firm level--a preview; and a summary and conclusions. Document type: Report