A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep Learning
Traffic flow forecasting has been regarded as a key problem of intelligent transport systems. In this work, we propose a hybrid multimodal deep learning method for short-term traffic flow forecasting, which can jointly and adaptively learn the spatial–temporal correlation features and long temporal...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2020-01-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://www.atlantis-press.com/article/125932622/view |
| _version_ | 1818538178573762560 |
|---|---|
| author | Shengdong Du Tianrui Li Xun Gong Shi-Jinn Horng |
| author_facet | Shengdong Du Tianrui Li Xun Gong Shi-Jinn Horng |
| author_sort | Shengdong Du |
| collection | DOAJ |
| description | Traffic flow forecasting has been regarded as a key problem of intelligent transport systems. In this work, we propose a hybrid multimodal deep learning method for short-term traffic flow forecasting, which can jointly and adaptively learn the spatial–temporal correlation features and long temporal interdependence of multi-modality traffic data by an attention auxiliary multimodal deep learning architecture. According to the highly nonlinear characteristics of multi-modality traffic data, the base module of our method consists of one-dimensional convolutional neural networks (1D CNN) and gated recurrent units (GRU) with the attention mechanism. The former is to capture the local trend features and the latter is to capture the long temporal dependencies. Then, we design a hybrid multimodal deep learning framework for fusing share representation features of different modality traffic data by multiple CNN-GRU-Attention modules. The experimental results indicate that the proposed multimodal deep learning model is capable of dealing with complex nonlinear urban traffic flow forecasting with satisfying accuracy and effectiveness. |
| first_indexed | 2024-12-11T21:25:39Z |
| format | Article |
| id | doaj.art-42b81d9fb46e41b6b734bd6ceb039a51 |
| institution | Directory Open Access Journal |
| issn | 1875-6883 |
| language | English |
| last_indexed | 2024-12-11T21:25:39Z |
| publishDate | 2020-01-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj.art-42b81d9fb46e41b6b734bd6ceb039a512022-12-22T00:50:21ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832020-01-0113110.2991/ijcis.d.200120.001A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep LearningShengdong DuTianrui LiXun GongShi-Jinn HorngTraffic flow forecasting has been regarded as a key problem of intelligent transport systems. In this work, we propose a hybrid multimodal deep learning method for short-term traffic flow forecasting, which can jointly and adaptively learn the spatial–temporal correlation features and long temporal interdependence of multi-modality traffic data by an attention auxiliary multimodal deep learning architecture. According to the highly nonlinear characteristics of multi-modality traffic data, the base module of our method consists of one-dimensional convolutional neural networks (1D CNN) and gated recurrent units (GRU) with the attention mechanism. The former is to capture the local trend features and the latter is to capture the long temporal dependencies. Then, we design a hybrid multimodal deep learning framework for fusing share representation features of different modality traffic data by multiple CNN-GRU-Attention modules. The experimental results indicate that the proposed multimodal deep learning model is capable of dealing with complex nonlinear urban traffic flow forecasting with satisfying accuracy and effectiveness.https://www.atlantis-press.com/article/125932622/viewTraffic flow forecastingMultimodal deep learningGated recurrent unitsAttention mechanismConvolutional neural networks |
| spellingShingle | Shengdong Du Tianrui Li Xun Gong Shi-Jinn Horng A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep Learning International Journal of Computational Intelligence Systems Traffic flow forecasting Multimodal deep learning Gated recurrent units Attention mechanism Convolutional neural networks |
| title | A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep Learning |
| title_full | A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep Learning |
| title_fullStr | A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep Learning |
| title_full_unstemmed | A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep Learning |
| title_short | A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep Learning |
| title_sort | hybrid method for traffic flow forecasting using multimodal deep learning |
| topic | Traffic flow forecasting Multimodal deep learning Gated recurrent units Attention mechanism Convolutional neural networks |
| url | https://www.atlantis-press.com/article/125932622/view |
| work_keys_str_mv | AT shengdongdu ahybridmethodfortrafficflowforecastingusingmultimodaldeeplearning AT tianruili ahybridmethodfortrafficflowforecastingusingmultimodaldeeplearning AT xungong ahybridmethodfortrafficflowforecastingusingmultimodaldeeplearning AT shijinnhorng ahybridmethodfortrafficflowforecastingusingmultimodaldeeplearning AT shengdongdu hybridmethodfortrafficflowforecastingusingmultimodaldeeplearning AT tianruili hybridmethodfortrafficflowforecastingusingmultimodaldeeplearning AT xungong hybridmethodfortrafficflowforecastingusingmultimodaldeeplearning AT shijinnhorng hybridmethodfortrafficflowforecastingusingmultimodaldeeplearning |