2019/06/13 by Ali Mohamed AbdelAziz, Amin Shoukry, AbdelAziz, Ali +5
Social Sciences · Engineering · #Transportation Planning and Optimization #Human Mobility and Location-Based Analysis #Transportation and Mobility Innovations
paper · pdf · doi:10.48550/arxiv.1906.07575
Developing countries suffer from traffic congestion, poorly planned road/rail\nnetworks, and lack of access to public transportation facilities. This context\nresults in an increase in fuel consumption, pollution level, monetary losses,\nmassive delays, and less productivity. On the other hand, it has a negative\nimpact on the commuters feelings and moods. Availability of real-time transit\ninformation - by providing public transportation vehicles locations using GPS\ndevices - helps in estimating a passenger's waiting time and addressing the\nabove issues. However, such solution is expensive for developing countries.\nThis paper aims at designing and implementing a crowd-sourced mobile\nphones-based solution to estimate the expected waiting time of a passenger in\npublic transit systems, the prediction of the remaining time to get on/off a\nvehicle, and to construct a real time public transit schedule. Trans-Sense has\nbeen evaluated using real data collected for over 800 hours, on a daily basis,\nby different Android phones, and using different light rail transit lines at\ndifferent time spans. The results show that Trans-Sense can achieve an average\nrecall and precision of 95.35% and 90.1%, respectively, in discriminating\nlightrail stations. Moreover, the empirical distributions governing the\ndifferent time delays affecting a passenger's total trip time enable predicting\nthe right time of arrival of a passenger to her destination with an accuracy of\n91.81%.In addition, the system estimates the stations dimensions with an\naccuracy of 95.71%.\n