A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic Prediction
Traffic prediction is crucial for urban planning and transportation management, and deep learning techniques have emerged as effective tools for this task. While previous works have made advancements, they often overlook comprehensive analyses of spatio-temporal distributions and the integration of...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2024.9020020 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572899544793088 |
|---|---|
| author | Bodong Zhou Jiahui Liu Songyi Cui Yaping Zhao |
| author_facet | Bodong Zhou Jiahui Liu Songyi Cui Yaping Zhao |
| author_sort | Bodong Zhou |
| collection | DOAJ |
| description | Traffic prediction is crucial for urban planning and transportation management, and deep learning techniques have emerged as effective tools for this task. While previous works have made advancements, they often overlook comprehensive analyses of spatio-temporal distributions and the integration of multimodal representations. Our research addresses these limitations by proposing a large-scale spatio-temporal multimodal fusion framework that enables accurate predictions based on location queries and seamlessly integrates various data sources. Specifically, we utilize Convolutional Neural Networks (CNNs) for spatial information processing and a combination of Recurrent Neural Networks (RNNs) for final spatio-temporal traffic prediction. This framework not only effectively reveals its ability to integrate various modal data in the spatio-temporal hyperspace, but has also been successfully implemented in a real-world large-scale map, showcasing its practical importance in tackling urban traffic challenges. The findings presented in this work contribute to the advancement of traffic prediction methods, offering valuable insights for further research and application in addressing real-world transportation challenges. |
| format | Article |
| id | doaj-art-b7aea8e64ffd4ef186406265f307ed24 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-b7aea8e64ffd4ef186406265f307ed242025-02-02T06:29:07ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-09-017362163610.26599/BDMA.2024.9020020A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic PredictionBodong Zhou0Jiahui Liu1Songyi Cui2Yaping Zhao3Technical Consulting Department, Shanghai EchoBlend Internet Technology Co. Ltd., Shanghai 201111, ChinaDepartment of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong 999077, ChinaDepartment of Industrial and Manufacturing Systems Engineering, The University of Hong Kong, Hong Kong 999077, ChinaDepartment of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong 999077, ChinaTraffic prediction is crucial for urban planning and transportation management, and deep learning techniques have emerged as effective tools for this task. While previous works have made advancements, they often overlook comprehensive analyses of spatio-temporal distributions and the integration of multimodal representations. Our research addresses these limitations by proposing a large-scale spatio-temporal multimodal fusion framework that enables accurate predictions based on location queries and seamlessly integrates various data sources. Specifically, we utilize Convolutional Neural Networks (CNNs) for spatial information processing and a combination of Recurrent Neural Networks (RNNs) for final spatio-temporal traffic prediction. This framework not only effectively reveals its ability to integrate various modal data in the spatio-temporal hyperspace, but has also been successfully implemented in a real-world large-scale map, showcasing its practical importance in tackling urban traffic challenges. The findings presented in this work contribute to the advancement of traffic prediction methods, offering valuable insights for further research and application in addressing real-world transportation challenges.https://www.sciopen.com/article/10.26599/BDMA.2024.9020020spatio-temporaltraffic predictionmultimodal fusionlearning representation |
| spellingShingle | Bodong Zhou Jiahui Liu Songyi Cui Yaping Zhao A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic Prediction Big Data Mining and Analytics spatio-temporal traffic prediction multimodal fusion learning representation |
| title | A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic Prediction |
| title_full | A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic Prediction |
| title_fullStr | A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic Prediction |
| title_full_unstemmed | A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic Prediction |
| title_short | A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic Prediction |
| title_sort | large scale spatio temporal multimodal fusion framework for traffic prediction |
| topic | spatio-temporal traffic prediction multimodal fusion learning representation |
| url | https://www.sciopen.com/article/10.26599/BDMA.2024.9020020 |
| work_keys_str_mv | AT bodongzhou alargescalespatiotemporalmultimodalfusionframeworkfortrafficprediction AT jiahuiliu alargescalespatiotemporalmultimodalfusionframeworkfortrafficprediction AT songyicui alargescalespatiotemporalmultimodalfusionframeworkfortrafficprediction AT yapingzhao alargescalespatiotemporalmultimodalfusionframeworkfortrafficprediction AT bodongzhou largescalespatiotemporalmultimodalfusionframeworkfortrafficprediction AT jiahuiliu largescalespatiotemporalmultimodalfusionframeworkfortrafficprediction AT songyicui largescalespatiotemporalmultimodalfusionframeworkfortrafficprediction AT yapingzhao largescalespatiotemporalmultimodalfusionframeworkfortrafficprediction |