Traffic Measurement and Route Recommendation System for Mass Rapid Transit (MRT)

Abstract

Understanding how people use public transport is important for the operation and future planning of the underlying transport networks. We have therefore developed and deployed a tra c measurement system for a key player in the transportation industry to gain insights into crowd behavior for planning purposes. The system has been in operation for several months and reports, at hourly intervals, (1) the crowdedness of subway stations, (2) the flows of people inside interchange stations, and (3) the expected travel time for each possible route in the subway network of Singapore. The core of our system is an e cient algorithm which detects individual subway trips from anonymized real-time data generated by the location based system of Singtel, the country's largest telecommunications company. To assess the accuracy of our system, we engaged an independent market research company to conduct a field study-a manual count of the number of passengers boarding and disembarking at a selected station on three separate days. A strong correlation between the calculations of our algorithm and the manual counts was found. One of our key findings is that travelers do not always choose the route with the shortest travel time in the subway network of Singapore. We have therefore also been developing a mobile app which allows users to plan their trips based on the average travel time between stations.

Routing Games in the Wild: Efficiency, Equilibration and Regret

“…The LTA regulates and oversees metro and bus transport, ensuring they meet safety standards. The rich information generated by the use of the EZ-Link card was exploited in the works of [Holleczek et al, 2015;Lee and Kam, 2014;Poonawala et al, 2016;Sun et al, 2012], attempting to find interesting insights for public transit planners.…”

“…In comparison, we perform field work in a particularly noisy field -transportation -but in our case we have acquired several orders of magnitude more clean data. Previous studies in Singapore have also met limitations of different sorts, e.g the works of [Holleczek et al, 2015;Lee and Kam, 2014;Sun et al, 2012] or [Poonawala et al, 2016], are either based on smart card data -focusing only on public transport commuter trips -or GSM (cellular phone) data.…”

Travel mode recognition of urban residents using mobile phone data and MapAPI

“…Calabrese et al (2011) used travel duration or speed to identify the means of travel while Qu et al (2015) used travel distance to identify the means of travel. Other researchers have employed spatial proximity for travel means identification (Doyle et al, 2011;Holleczek et al, 2015;Horn et al, 2017;Poonawala et al, 2016;Wu et al, 2016). A few researchers have used the k-means method to cluster trips based on their duration, such as Wang et al (2010).…”

TRIPDECODER: Study Travel Time Attributes and Route Preferences of Metro Systems from Smart Card Data

“…For instance, predicting vehicle crowdedness and platform commuter intensity can help operators evaluate service quality and design structural improvements for the metro network [8,9,17]; understanding commuters' route choice preferences and route travel time allows operators to provide more accurate route recommendation [3,5]; studying commuters' movement during MRT disruption enables operators to identify potentially overcrowded stations and to take more targeted remedial actions, like arranging alternative transportation modes [11,16,20].…”

“…Data collected via crowdsourcing suffers from similar issues. As a result, alternative data sources are required to be able to more accurately and more comprehensively understand the spatial-temporal characteristics of travel patterns, such as train control sensors [8,9] and GPS data [3].…”