Abstract

Passengers on metro platforms can board a train only when the train has surplus capacity and the dwell time is sufficient, while the latter condition is omitted in previous studies. Taking into account the impacts of train capacity and dwell time on passengers boarding, this study develops a model on optimizing metro timetable to reduce passenger travel time and metro operating cost, through regulating trains’ inter-station run-time, dwell time and headway. The NSGA-II algorithm is employed to obtain the near-optimal Pareto Frontier of the proposed model. To address insufficient dwell time scheduled in the timetable, three operating strategies are proposed and compared: a. sticking to nominal timetable; b. extending dwell time only; c. extending dwell time and recovering delay as soon as possible by compressing train inter-station run-time. Case studies on real-life metro line prove that some passengers cannot board the train during peak hours due to insufficient dwell time. In this context, strategy a brings low-quality service because passengers are stranded at platform even though the train has surplus capacity. In contrast, more passengers can board the train with strategies b and c because dwell time is extended for passengers’ boarding when train has surplus capacity. Compared to strategy b, strategy c reduces the average in-vehicle time of passengers by 2.5% through compressing inter-station run-time to recover the delay. The timetable optimized based on strategy c saves total travel time of passengers by 3.1% without increasing operating cost when compared to the practical timetable. Document type: Article

Abstract

The effectiveness of a cardiovascular magnetic resonance (CMR) scan depends on the ability of the operator to correctly tune the acquisition parameters to the subject being scanned and on the potential occurrence of imaging artefacts such as cardiac and respiratory motion. In the clinical practice, a quality control step is performed by visual assessment of the acquired images: however, this procedure is strongly operator-dependent, cumbersome and sometimes incompatible with the time constraints in clinical settings and large-scale studies. We propose a fast, fully-automated, learning-based quality control pipeline for CMR images, specifically for short-axis image stacks. Our pipeline performs three important quality checks: 1) heart coverage estimation, 2) inter-slice motion detection, 3) image contrast estimation in the cardiac region. The pipeline uses a hybrid decision forest method - integrating both regression and structured classification models - to extract landmarks as well as probabilistic segmentation maps from both long- and short-axis images as a basis to perform the quality checks. The technique was tested on up to 3000 cases from the UK Biobank as well as on 100 cases from the UK Digital Heart Project, and validated against manual annotations and visual inspections performed by expert interpreters. The results show the capability of the proposed pipeline to correctly detect incomplete or corrupted scans (e.g. on UK Biobank, sensitivity and specificity respectively 88% and 99% for heart coverage estimation, 85% and 95% for motion detection), allowing their exclusion from the analysed dataset or the triggering of a new acquisition. Document type: Article