A multi-scale attributes attention model for transport mode identification
Transport mode identification (TMI), which infers the travel modes of user trajectories, is essential to facilitate an understanding of urban mobility patterns and passengers’ choice behaviors with the goal of improving urban transportation systems. To achieve higher accuracy, existing TMI methods u...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/179465 |
| _version_ | 1824457090730557440 |
|---|---|
| author | Jiang, Guiyuan Lam, Siew-Kei He, Peilan Ou, Changhai Ai, Dihao |
| author2 | College of Computing and Data Science |
| author_facet | College of Computing and Data Science Jiang, Guiyuan Lam, Siew-Kei He, Peilan Ou, Changhai Ai, Dihao |
| author_sort | Jiang, Guiyuan |
| collection | NTU |
| description | Transport mode identification (TMI), which infers the travel modes of user trajectories, is essential to facilitate an understanding of urban mobility patterns and passengers’ choice behaviors with the goal of improving urban transportation systems. To achieve higher accuracy, existing TMI methods usually rely on mobility features obtained from densely sampled GPS trajectory points (e.g. 1 second per GPS point) or data measurements of additional inertial measurement unit (IMU) sensors (e.g. accelerometer, gyroscope, rotation vector). However, these lead to high energy consumption of the users’ mobile devices. In this paper, we propose a novel deep learning framework, Multi-Scale Attributes Attention (MSAA) model, to extract discriminating trajectory features from GPS data only, without the need to increase its sampling rate. The proposed model first partitions the trajectories into different scales and extract the latent representation of local attributes at each scale. The MSAA model relies on Convolutional Neural Network (CNN) to capture the spatial correlation of different trajectory segments, and utilizes attention mechanism to select the most suitable local attributes on the different trajectory scales that can effectively characterize the various transport modes. Since the learned latent local attributes are significantly different from the global features (e.g. average/min/max travel speeds which are measurable quantities), an ensemble model based on Neural Decision Forest (NDF) is employed to fuse the heterogeneous features consisting of both measurable quantities and non-measurable elements for determining the transport mode. Experiments on real-world datasets demonstrate the competitive performance of the proposed approach compared to several state-of-the-art baselines, with average improvements in accuracy ranging from 0.76% to 6.4%. In addition, the proposed multi-scale local attributes well complement the global features. Our results show that by incorporating the local attributes, the detection performance improved by 2.3% on average compared to using only global features. |
| first_indexed | 2025-02-19T04:04:28Z |
| format | Journal Article |
| id | ntu-10356/179465 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T04:04:28Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1794652024-08-05T05:29:29Z A multi-scale attributes attention model for transport mode identification Jiang, Guiyuan Lam, Siew-Kei He, Peilan Ou, Changhai Ai, Dihao College of Computing and Data Science School of Computer Science and Engineering Computer and Information Science Travel mode identification GPS trajectory Transport mode identification (TMI), which infers the travel modes of user trajectories, is essential to facilitate an understanding of urban mobility patterns and passengers’ choice behaviors with the goal of improving urban transportation systems. To achieve higher accuracy, existing TMI methods usually rely on mobility features obtained from densely sampled GPS trajectory points (e.g. 1 second per GPS point) or data measurements of additional inertial measurement unit (IMU) sensors (e.g. accelerometer, gyroscope, rotation vector). However, these lead to high energy consumption of the users’ mobile devices. In this paper, we propose a novel deep learning framework, Multi-Scale Attributes Attention (MSAA) model, to extract discriminating trajectory features from GPS data only, without the need to increase its sampling rate. The proposed model first partitions the trajectories into different scales and extract the latent representation of local attributes at each scale. The MSAA model relies on Convolutional Neural Network (CNN) to capture the spatial correlation of different trajectory segments, and utilizes attention mechanism to select the most suitable local attributes on the different trajectory scales that can effectively characterize the various transport modes. Since the learned latent local attributes are significantly different from the global features (e.g. average/min/max travel speeds which are measurable quantities), an ensemble model based on Neural Decision Forest (NDF) is employed to fuse the heterogeneous features consisting of both measurable quantities and non-measurable elements for determining the transport mode. Experiments on real-world datasets demonstrate the competitive performance of the proposed approach compared to several state-of-the-art baselines, with average improvements in accuracy ranging from 0.76% to 6.4%. In addition, the proposed multi-scale local attributes well complement the global features. Our results show that by incorporating the local attributes, the detection performance improved by 2.3% on average compared to using only global features. National Research Foundation (NRF) Submitted/Accepted version This work was 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 (TUM) at TUMCREATE Centre. 2024-08-05T05:29:29Z 2024-08-05T05:29:29Z 2020 Journal Article Jiang, G., Lam, S., He, P., Ou, C. & Ai, D. (2020). A multi-scale attributes attention model for transport mode identification. IEEE Transactions On Intelligent Transportation Systems, 23(1), 152-164. https://dx.doi.org/10.1109/TITS.2020.3008469 1524-9050 https://hdl.handle.net/10356/179465 10.1109/TITS.2020.3008469 1 23 152 164 en IEEE Transactions on Intelligent Transportation Systems © 2020 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1109/TITS.2020.3008469. application/pdf |
| spellingShingle | Computer and Information Science Travel mode identification GPS trajectory Jiang, Guiyuan Lam, Siew-Kei He, Peilan Ou, Changhai Ai, Dihao A multi-scale attributes attention model for transport mode identification |
| title | A multi-scale attributes attention model for transport mode identification |
| title_full | A multi-scale attributes attention model for transport mode identification |
| title_fullStr | A multi-scale attributes attention model for transport mode identification |
| title_full_unstemmed | A multi-scale attributes attention model for transport mode identification |
| title_short | A multi-scale attributes attention model for transport mode identification |
| title_sort | multi scale attributes attention model for transport mode identification |
| topic | Computer and Information Science Travel mode identification GPS trajectory |
| url | https://hdl.handle.net/10356/179465 |
| work_keys_str_mv | AT jiangguiyuan amultiscaleattributesattentionmodelfortransportmodeidentification AT lamsiewkei amultiscaleattributesattentionmodelfortransportmodeidentification AT hepeilan amultiscaleattributesattentionmodelfortransportmodeidentification AT ouchanghai amultiscaleattributesattentionmodelfortransportmodeidentification AT aidihao amultiscaleattributesattentionmodelfortransportmodeidentification AT jiangguiyuan multiscaleattributesattentionmodelfortransportmodeidentification AT lamsiewkei multiscaleattributesattentionmodelfortransportmodeidentification AT hepeilan multiscaleattributesattentionmodelfortransportmodeidentification AT ouchanghai multiscaleattributesattentionmodelfortransportmodeidentification AT aidihao multiscaleattributesattentionmodelfortransportmodeidentification |