File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.trc.2018.01.022
- Scopus: eid_2-s2.0-85042425665
- WOS: WOS:000429390200002
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Individual mobility prediction using transit smart card data
Title | Individual mobility prediction using transit smart card data |
---|---|
Authors | |
Keywords | Individual mobility Bayesian n-gram model Next trip prediction Smart card data |
Issue Date | 2018 |
Citation | Transportation Research Part C: Emerging Technologies, 2018, v. 89, p. 19-34 How to Cite? |
Abstract | © 2018 Elsevier Ltd For intelligent urban transportation systems, the ability to predict individual mobility is crucial for personalized traveler information, targeted demand management, and dynamic system operations. Whereas existing methods focus on predicting the next location of users, little is known regarding the prediction of the next trip. The paper develops a methodology for predicting daily individual mobility represented as a chain of trips (including the null set, no travel), each defined as a combination of the trip start time t, origin o, and destination d. To predict individual mobility, we first predict whether the user will travel (trip making prediction), and then, if so, predict the attributes of the next trip (t,o,d) (trip attribute prediction). Each of the two problems can be further decomposed into two subproblems based on the triggering event. For trip attribute prediction, we propose a new model, based on the Bayesian n-gram model used in language modeling, to estimate the probability distribution of the next trip conditional on the previous one. The proposed methodology is tested using the pseudonymized transit smart card records from more than 10,000 users in London, U.K. over two years. Based on regularized logistic regression, our trip making prediction models achieve median accuracy levels of over 80%. The prediction accuracy for trip attributes varies by the attribute considered—around 40% for t, 70–80% for o and 60–70% for d. Relatively, the first trip of the day is more difficult to predict. Significant variations are found across individuals in terms of the model performance, implying diverse travel behavior patterns. |
Persistent Identifier | http://hdl.handle.net/10722/286957 |
ISSN | 2023 Impact Factor: 7.6 2023 SCImago Journal Rankings: 2.860 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhao, Zhan | - |
dc.contributor.author | Koutsopoulos, Haris N. | - |
dc.contributor.author | Zhao, Jinhua | - |
dc.date.accessioned | 2020-09-07T11:46:07Z | - |
dc.date.available | 2020-09-07T11:46:07Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Transportation Research Part C: Emerging Technologies, 2018, v. 89, p. 19-34 | - |
dc.identifier.issn | 0968-090X | - |
dc.identifier.uri | http://hdl.handle.net/10722/286957 | - |
dc.description.abstract | © 2018 Elsevier Ltd For intelligent urban transportation systems, the ability to predict individual mobility is crucial for personalized traveler information, targeted demand management, and dynamic system operations. Whereas existing methods focus on predicting the next location of users, little is known regarding the prediction of the next trip. The paper develops a methodology for predicting daily individual mobility represented as a chain of trips (including the null set, no travel), each defined as a combination of the trip start time t, origin o, and destination d. To predict individual mobility, we first predict whether the user will travel (trip making prediction), and then, if so, predict the attributes of the next trip (t,o,d) (trip attribute prediction). Each of the two problems can be further decomposed into two subproblems based on the triggering event. For trip attribute prediction, we propose a new model, based on the Bayesian n-gram model used in language modeling, to estimate the probability distribution of the next trip conditional on the previous one. The proposed methodology is tested using the pseudonymized transit smart card records from more than 10,000 users in London, U.K. over two years. Based on regularized logistic regression, our trip making prediction models achieve median accuracy levels of over 80%. The prediction accuracy for trip attributes varies by the attribute considered—around 40% for t, 70–80% for o and 60–70% for d. Relatively, the first trip of the day is more difficult to predict. Significant variations are found across individuals in terms of the model performance, implying diverse travel behavior patterns. | - |
dc.language | eng | - |
dc.relation.ispartof | Transportation Research Part C: Emerging Technologies | - |
dc.subject | Individual mobility | - |
dc.subject | Bayesian n-gram model | - |
dc.subject | Next trip prediction | - |
dc.subject | Smart card data | - |
dc.title | Individual mobility prediction using transit smart card data | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.trc.2018.01.022 | - |
dc.identifier.scopus | eid_2-s2.0-85042425665 | - |
dc.identifier.volume | 89 | - |
dc.identifier.spage | 19 | - |
dc.identifier.epage | 34 | - |
dc.identifier.isi | WOS:000429390200002 | - |
dc.identifier.issnl | 0968-090X | - |