File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ACCESS.2023.3294345
- Scopus: eid_2-s2.0-85164682137
- WOS: WOS:001040720500001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Deep Encoder Cross Network for Estimated Time of Arrival
Title | Deep Encoder Cross Network for Estimated Time of Arrival |
---|---|
Authors | |
Keywords | deep learning Estimated time of arrival neural network |
Issue Date | 11-Jul-2023 |
Publisher | Institute of Electrical and Electronics Engineers |
Citation | IEEE Access, 2023, v. 11, p. 76095-76107 How to Cite? |
Abstract | Estimated time of arrival (ETA) is essential to enable various intelligent transportation services and reduce passenger waiting time. Estimating the time of arrival of public transport in a highly dynamic and uncertain transportation system could be challenging. Many indirect factors beyond the remaining travel distance could dramatically deviate the time of arrival from the original schedule. Existing distance-based estimation methods disregarding those factors usually result in inaccurate estimations. In this paper, we propose a new deep learning model, called Deep Encoder Cross Network (DECN), to improve the ETA prediction based on multiple non-distance-based factors such as weather, road speed and congestion, and traffic composition. Unlike most regression tasks that output the target directly, we predict the ETA residual over the location-based ETA prediction. To effectively learn in the large and sparse input feature space, we use a new neural network structure consisting of three main components. First, a deep neural network is responsible for modeling explicit feature interactions. Second, an encoder network is constructed to reduce the input feature dimensionality. Third, a cross-network is introduced to learn from the implicit feature interactions. We conduct extensive experiments on a large real-world bus ETA dataset of Hong Kong, which contains about 2.95×108 rows with 27 different features on an 84-dimensional space. The results show that the deep learning approach with the DECN model can improve the ETA error by 11% on average, and 49% for late arrival. The proposed approach can be further improved and extended to estimate other traffic information by incorporating non-distance-based related information. |
Persistent Identifier | http://hdl.handle.net/10722/337337 |
ISSN | 2023 Impact Factor: 3.4 2023 SCImago Journal Rankings: 0.960 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chu, Kai-Fung | - |
dc.contributor.author | Lam, Albert Y S | - |
dc.contributor.author | Tsoi, Ka Ho | - |
dc.contributor.author | Huang, Zhiran | - |
dc.contributor.author | Loo, Becky P Y | - |
dc.date.accessioned | 2024-03-11T10:20:05Z | - |
dc.date.available | 2024-03-11T10:20:05Z | - |
dc.date.issued | 2023-07-11 | - |
dc.identifier.citation | IEEE Access, 2023, v. 11, p. 76095-76107 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | http://hdl.handle.net/10722/337337 | - |
dc.description.abstract | <p>Estimated time of arrival (ETA) is essential to enable various intelligent transportation services and reduce passenger waiting time. Estimating the time of arrival of public transport in a highly dynamic and uncertain transportation system could be challenging. Many indirect factors beyond the remaining travel distance could dramatically deviate the time of arrival from the original schedule. Existing distance-based estimation methods disregarding those factors usually result in inaccurate estimations. In this paper, we propose a new deep learning model, called Deep Encoder Cross Network (DECN), to improve the ETA prediction based on multiple non-distance-based factors such as weather, road speed and congestion, and traffic composition. Unlike most regression tasks that output the target directly, we predict the ETA residual over the location-based ETA prediction. To effectively learn in the large and sparse input feature space, we use a new neural network structure consisting of three main components. First, a deep neural network is responsible for modeling explicit feature interactions. Second, an encoder network is constructed to reduce the input feature dimensionality. Third, a cross-network is introduced to learn from the implicit feature interactions. We conduct extensive experiments on a large real-world bus ETA dataset of Hong Kong, which contains about 2.95×108 rows with 27 different features on an 84-dimensional space. The results show that the deep learning approach with the DECN model can improve the ETA error by 11% on average, and 49% for late arrival. The proposed approach can be further improved and extended to estimate other traffic information by incorporating non-distance-based related information.<br></p> | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.relation.ispartof | IEEE Access | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | deep learning | - |
dc.subject | Estimated time of arrival | - |
dc.subject | neural network | - |
dc.title | Deep Encoder Cross Network for Estimated Time of Arrival | - |
dc.type | Article | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.1109/ACCESS.2023.3294345 | - |
dc.identifier.scopus | eid_2-s2.0-85164682137 | - |
dc.identifier.volume | 11 | - |
dc.identifier.spage | 76095 | - |
dc.identifier.epage | 76107 | - |
dc.identifier.eissn | 2169-3536 | - |
dc.identifier.isi | WOS:001040720500001 | - |
dc.identifier.issnl | 2169-3536 | - |