<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">F. Sun</style></author><author><style face="normal" font="default" size="100%">A. Dubey</style></author><author><style face="normal" font="default" size="100%">C. Samal</style></author><author><style face="normal" font="default" size="100%">H. Baroud</style></author><author><style face="normal" font="default" size="100%">C. Kulkarni</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Short-Term Transit Decision Support System Using Multi-task Deep Neural Networks</style></title><secondary-title><style face="normal" font="default" size="100%">2018 IEEE International Conference on Smart Computing (SMARTCOMP)</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">arrival delay prediction</style></keyword><keyword><style  face="normal" font="default" size="100%">contextual prediction mechanism</style></keyword><keyword><style  face="normal" font="default" size="100%">Data models</style></keyword><keyword><style  face="normal" font="default" size="100%">data sparsity</style></keyword><keyword><style  face="normal" font="default" size="100%">decision support systems</style></keyword><keyword><style  face="normal" font="default" size="100%">deep learning</style></keyword><keyword><style  face="normal" font="default" size="100%">delay prediction</style></keyword><keyword><style  face="normal" font="default" size="100%">Delays</style></keyword><keyword><style  face="normal" font="default" size="100%">Games</style></keyword><keyword><style  face="normal" font="default" size="100%">general transit feed specification</style></keyword><keyword><style  face="normal" font="default" size="100%">GTFS</style></keyword><keyword><style  face="normal" font="default" size="100%">learning (artificial intelligence)</style></keyword><keyword><style  face="normal" font="default" size="100%">multi-task learning</style></keyword><keyword><style  face="normal" font="default" size="100%">multitask deep neural networks</style></keyword><keyword><style  face="normal" font="default" size="100%">neural nets</style></keyword><keyword><style  face="normal" font="default" size="100%">neural networks</style></keyword><keyword><style  face="normal" font="default" size="100%">Predictive models</style></keyword><keyword><style  face="normal" font="default" size="100%">public transport</style></keyword><keyword><style  face="normal" font="default" size="100%">public transportation</style></keyword><keyword><style  face="normal" font="default" size="100%">real-time systems</style></keyword><keyword><style  face="normal" font="default" size="100%">route segment networks</style></keyword><keyword><style  face="normal" font="default" size="100%">short-term transit decision support system</style></keyword><keyword><style  face="normal" font="default" size="100%">traffic information systems</style></keyword><keyword><style  face="normal" font="default" size="100%">Urban areas</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2018</style></year><pub-dates><date><style  face="normal" font="default" size="100%">07/2018</style></date></pub-dates></dates><urls><related-urls><url><style face="normal" font="default" size="100%">https://archive.isis.vanderbilt.edu/sites/default/files/short_term_transit_dnn.pdf</style></url></related-urls></urls><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Taormina, Italy</style></pub-location><pages><style face="normal" font="default" size="100%">155-162</style></pages><isbn><style face="normal" font="default" size="100%">978-1-5386-4705-9</style></isbn><abstract><style face="normal" font="default" size="100%">Unpredictability is one of the top reasons that prevent people from using public transportation. To improve the on-time performance of transit systems, prior work focuses on updating schedule periodically in the long-term and providing arrival delay prediction in real-time. But when no real-time transit and traffic feed is available (e.g., one day ahead), there is a lack of effective contextual prediction mechanism that can give alerts of possible delay to commuters. In this paper, we propose a generic tool-chain that takes standard General Transit Feed Specification (GTFS) transit feeds and contextual information (recurring delay patterns before and after big events in the city and the contextual information such as scheduled events and forecasted weather conditions) as inputs and provides service alerts as output. Particularly, we utilize shared route segment networks and multi-task deep neural networks to solve the data sparsity and generalization issues. Experimental evaluation shows that the proposed toolchain is effective at predicting severe delay with a relatively high recall of 76% and F1 score of 55%.</style></abstract><accession-num><style face="normal" font="default" size="100%">17972176</style></accession-num></record></records></xml>