DSpace Repository

Transit System Prediction for Real-time Weather Conditions: Fleet Management and Weather-related Ridership

Show simple item record

dc.contributor.author Elnoshokaty, Ahmed en
dc.contributor.author Arai, Ismail en
dc.contributor.author El-Tawab, Samy en
dc.contributor.author Salman, Ahmad en
dc.date.accessioned 2022-04-25T02:26:28Z en
dc.date.available 2022-04-25T02:26:28Z en
dc.date.issued 2022-04-20 en
dc.identifier.isbn 978-1-6654-9954-5 en
dc.identifier.uri http://hdl.handle.net/10061/14721 en
dc.description 2022 IEEE International Conference on Smart Mobility (SM),6-7 March 2022,New Alamein, Egypt en
dc.description.abstract The communication technology revolution in this era has increased the use of smartphones in the world of transportation. The public transit system wishes to predict the expected ridership at a specific time. The bus system's dream of dynamic routing (i.e., having no more near-empty buses) is close to reality. Our study collected data from the transit bus system in two different countries (USA and Japan). This paper studies the correlation between ridership and weather conditions using a deep learning algorithm. Empirically, an experiment with several bus routes in Japan, was utilized to confirm a high precision level. We compared our deep learning model against three baseline models: linear regression, regression trees, and a wide neural network in two sub-experiments. First, the deep learning model had 23%, 21%, and 14% better mean squared error (MSE) scores compared to linear regression, regression trees, and wide neural networks when trained on three months of historical data. Second, we ran the models on a larger dataset of two years. The result was that the gap between the baseline models and the deep learning model was almost doubled to 56%, 50%, and 35% better MSE scores for predictions in favor of the deep learning model compared to linear regression, regression trees, and wide neural networks, respectively. en
dc.language.iso en en
dc.publisher IEEE en
dc.relation.isversionof https://ieeexplore.ieee.org/document/9758295 en
dc.rights © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 出版社許諾条件により、本文は2024年4月21日以降に公開 ja
dc.subject Deep learning en
dc.subject Neural networks en
dc.subject Linear regression en
dc.subject Transportation en
dc.subject Predictive models en
dc.subject Routing en
dc.subject Real-time systems en
dc.title Transit System Prediction for Real-time Weather Conditions: Fleet Management and Weather-related Ridership en
dc.type.nii Conference Paper en
dc.contributor.transcription アライ, イスマイル ja
dc.contributor.alternative 新井, イスマイル ja
dc.textversion author en
dc.identifier.spage 14 en
dc.identifier.epage 20 en
dc.relation.doi 10.1109/SM55505.2022.9758295 en
dc.identifier.NAIST-ID 74652785 en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account