Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency
Short-term traffic prediction (e.g., less than 15 min) is challenging due to severe fluctuations of traffic data caused by dynamic traffic conditions and uncertainties (e.g., in data acquisition, driver behaviors, etc.). Substantial efforts have been undertaken to incorporate spatiotemporal correlat...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162998 |
| _version_ | 1826128994674671616 |
|---|---|
| author | Sun, Yidan Jiang, Guiyuan Lam, Siew-Kei He, Peilan Ning, Fangxin |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Sun, Yidan Jiang, Guiyuan Lam, Siew-Kei He, Peilan Ning, Fangxin |
| author_sort | Sun, Yidan |
| collection | NTU |
| description | Short-term traffic prediction (e.g., less than 15 min) is challenging due to severe fluctuations of traffic data caused by dynamic traffic conditions and uncertainties (e.g., in data acquisition, driver behaviors, etc.). Substantial efforts have been undertaken to incorporate spatiotemporal correlations for improving traffic prediction accuracy. In this paper, we demonstrate that closely located road segments exhibit diverse spatial correlations when characterized using different measurements, and considering these multi-fold correlations can improve prediction performance. We propose new measurements to model multiple spatial correlations among traffic data. We develop a Multi-fold Correlation Attention Network (MCAN) that achieves accurate prediction by capturing multi-fold spatial correlation and multi-fold temporal correlations, and incorporating traffic data of heterogeneous sampling frequencies. The effectiveness of MCAN has been extensively evaluated on two real-world datasets in terms of overall performance, ablation study, sensitivity analysis, and case study, by comparing with several state-of-the-art methods. The results show that MCAN outperforms the best baseline with a reduction in mean absolute error (MAE) by 13% on Singapore dataset and 11% on Beijing dataset. |
| first_indexed | 2024-10-01T07:33:37Z |
| format | Journal Article |
| id | ntu-10356/162998 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:33:37Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1629982022-11-15T02:03:46Z Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency Sun, Yidan Jiang, Guiyuan Lam, Siew-Kei He, Peilan Ning, Fangxin School of Computer Science and Engineering Engineering::Computer science and engineering Multi-Fold Spatial Correlation Multi-Fold Temporal Correlation Short-term traffic prediction (e.g., less than 15 min) is challenging due to severe fluctuations of traffic data caused by dynamic traffic conditions and uncertainties (e.g., in data acquisition, driver behaviors, etc.). Substantial efforts have been undertaken to incorporate spatiotemporal correlations for improving traffic prediction accuracy. In this paper, we demonstrate that closely located road segments exhibit diverse spatial correlations when characterized using different measurements, and considering these multi-fold correlations can improve prediction performance. We propose new measurements to model multiple spatial correlations among traffic data. We develop a Multi-fold Correlation Attention Network (MCAN) that achieves accurate prediction by capturing multi-fold spatial correlation and multi-fold temporal correlations, and incorporating traffic data of heterogeneous sampling frequencies. The effectiveness of MCAN has been extensively evaluated on two real-world datasets in terms of overall performance, ablation study, sensitivity analysis, and case study, by comparing with several state-of-the-art methods. The results show that MCAN outperforms the best baseline with a reduction in mean absolute error (MAE) by 13% on Singapore dataset and 11% on Beijing dataset. National Research Foundation (NRF) This research project is supported in part by the National Research Foundation Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme with the Technical University of Munich at TUMCREATE. 2022-11-15T02:03:46Z 2022-11-15T02:03:46Z 2022 Journal Article Sun, Y., Jiang, G., Lam, S., He, P. & Ning, F. (2022). Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency. Applied Soft Computing, 124, 108977-. https://dx.doi.org/10.1016/j.asoc.2022.108977 1568-4946 https://hdl.handle.net/10356/162998 10.1016/j.asoc.2022.108977 2-s2.0-85130518373 124 108977 en Applied Soft Computing © 2022. Published by Elsevier B.V. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Multi-Fold Spatial Correlation Multi-Fold Temporal Correlation Sun, Yidan Jiang, Guiyuan Lam, Siew-Kei He, Peilan Ning, Fangxin Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency |
| title | Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency |
| title_full | Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency |
| title_fullStr | Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency |
| title_full_unstemmed | Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency |
| title_short | Multi-fold correlation attention network for predicting traffic speeds with heterogeneous frequency |
| title_sort | multi fold correlation attention network for predicting traffic speeds with heterogeneous frequency |
| topic | Engineering::Computer science and engineering Multi-Fold Spatial Correlation Multi-Fold Temporal Correlation |
| url | https://hdl.handle.net/10356/162998 |
| work_keys_str_mv | AT sunyidan multifoldcorrelationattentionnetworkforpredictingtrafficspeedswithheterogeneousfrequency AT jiangguiyuan multifoldcorrelationattentionnetworkforpredictingtrafficspeedswithheterogeneousfrequency AT lamsiewkei multifoldcorrelationattentionnetworkforpredictingtrafficspeedswithheterogeneousfrequency AT hepeilan multifoldcorrelationattentionnetworkforpredictingtrafficspeedswithheterogeneousfrequency AT ningfangxin multifoldcorrelationattentionnetworkforpredictingtrafficspeedswithheterogeneousfrequency |