Vulnerability Analysis and Passenger Source Prediction in Urban Rail Transit Networks

Abstract

Based on large-scale human mobility data collected in San Francisco and Boston, the morning peak urban rail transit (URT) ODs (origin-destination matrix) were estimated and the most vulnerable URT segments, those capable of causing the largest service interruptions, were identified. In both URT networks, a few highly vulnerable segments were observed. For this small group of vital segments, the impact of failure must be carefully evaluated. A bipartite URT usage network was developed and used to determine the inherent connections between urban rail transits and their passengers' travel demands. Although passengers' origins and destinations were easy to locate for a large number of URT segments, a few show very complicated spatial distributions. Based on the bipartite URT usage network, a new layer of the understanding of a URT segment's vulnerability can be achieved by taking the difficulty of addressing the failure of a given segment into account. Two proof-of-concept cases are described here: Possible transfer of passenger flow to the road network is here predicted in the cases of failures of two representative URT segments in San Francisco.

Passenger Traffic Forecasting for New Urban Railways in Moscow

“…Firstly, from the analysis of operator data on movements, for example, for a month, you can determine the nature of displacements by the type of "home-work." This is a standard approach, which was used in the earliest works on the analysis of such data [7]. The idea is to relate the time of day and user activity.…”

Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory

“…This often results in suboptimality since transportation activities involve human factors which are difficult to represent or model accurately using mathematics-driven approaches. Previous network-wide congestion studies mainly resort to either complex network theory [ 5 – 11 ] or visualization techniques [ 12 ] to understand the evolution of network-wide traffic congestion. In complex network theory, transportation networks can be abstracted as scale-free networks [ 9 ], and traffic flow dynamics over the network are generated based on the power law distribution [ 11 ] However, these assumptions are not always adherent to the reality, and lack sufficient traffic sensor data to validate their findings.…”

Traffic control approach based on multi‐source data fusion

“…Taxi GPS data were used to obtain real‐time vehicle speed for adjusting the intensity of traffic control. To reduce the influence of traffic control on travellers with limited connections to the bottleneck roads, the sources of vehicles [8, 9, 31, 32] were analysed to pinpoint the effective traffic control intersections. Finally, a genetic algorithm is generated to calculate the dynamic traffic control strength at each control intersection.…”