Abstract

Fouling build up is a well-known problem in the offshore industry. Accumulation of fouling occurs in different structures, e.g. offshore pipes, ship hulls, floating production platforms. The type of fouling that accumulates is dependent on environmental conditions surrounding the structure itself. Current methods deployed for fouling removal span across hydraulic, chemical and manual, all sharing the common disadvantage of necessitating halting production for the cleaning process to commence. Conventionally, ultrasound is used in ultrasonic baths to clean a submerged component by the generation and implosion of cavitation bubbles on the fouled surface; this method is particularly used in Reverse Osmosis applications. However, this requires the submersion of the fouled structure and thus may require a halt to production. Large fouled structures such as pipelines may not be accommodated. The application of high power ultrasonics is proposed in this work as a means to remove fouling on a structure whilst in operation. The work presented in this paper consists of the development of a finite element analysis model based on successful cleaning results from a pipe fouled with calcite on the inner pipe wall. A Polytec 3D Laser Doppler Vibrometer was used in this investigation to study the fouling removal process. Results show the potential of high power ultrasonics for fouling removal in pipe structures from the wave propagation across the structure under excitation, and are used to validate a COMSOL model to determine cleaning patterns based on pressure and displacement distributions for future transducer array design and optimization.

Abstract

Purpose Precision cancer medicine is dependent on accurate prediction of disease and treatment outcome, requiring integration of clinical, imaging and interventional knowledge. User controlled pipelines are capable of feature integration with varied levels of human interaction. In this work we present two pipelines designed to combine clinical, radiomic (quantified imaging), and RTx-omic (quantified radiation therapy (RT) plan) information for prediction of locoregional failure (LRF) in head and neck cancer (HN and 2) a pipeline with minimal user input that utilizes deep learning convolutional neural networks to extract and combine CT imaging, RT dose and clinical features for model development. Results Clinical features with logistic regression in our highly user-driven pipeline had the highest precision recall area under the curve (PR-AUC) of 0.66 (0.33–0.93), where a PR-AUC = 0.11 is considered random. CONCLUSIONS: Our work demonstrates the potential to aggregate features from multiple specialties for conditional-outcome predictions using pipelines with varied levels of human interaction. Most importantly, our results provide insights into the importance of data curation and quality, as well as user, data and methodology bias awareness as it pertains to result interpretation in user controlled pipelines.

Abstract

© 2020, © 2020 Informa UK Limited, trading as Taylor & Francis Group. Markerless motion capture would permit the study of human biomechanics in environments where marker-based systems are impractical, e.g. outdoors or underwater. The visual hull tool may enable such data to be recorded, but it requires the accurate detection of the silhouette of the object in multiple camera views. This paper reviews the top-performing algorithms available to date for silhouette extraction, with the visual hull in mind as the downstream application; the rationale is that higher-quality silhouettes would lead to higher-quality visual hulls, and consequently better measurement of movement. This paper is the first attempt in the literature to compare silhouette extraction algorithms that belong to different fields of Computer Vision, namely background subtraction, semantic segmentation, and multi-view segmentation. It was found that several algorithms exist that would be substantial improvements over the silhouette extraction algorithms traditionally used in visual hull pipelines. In particular, FgSegNet v2 (a background subtraction algorithm), DeepLabv3+ JFT (a semantic segmentation algorithm), and Djelouah 2013 (a multi-view segmentation algorithm) are the most accurate and promising methods for the extraction of silhouettes from 2D images to date, and could seamlessly be integrated within a visual hull pipeline for studies of human movement or biomechanics.