Integrating Spatial Self-Attention and Convolution Networks for Improved Car-Sharing Demand Forecasting
The core challenge facing the field of car-sharing demand forecasting lies in the innovative construction of models that effectively capture the intricate spatio-temporal variations in the data. Current methods face two particularly significant challenges: first, Current models struggle to capture t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10798450/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536151446355968 |
|---|---|
| author | Shengjun Qin Jiaying Qin Zhi Liu |
| author_facet | Shengjun Qin Jiaying Qin Zhi Liu |
| author_sort | Shengjun Qin |
| collection | DOAJ |
| description | The core challenge facing the field of car-sharing demand forecasting lies in the innovative construction of models that effectively capture the intricate spatio-temporal variations in the data. Current methods face two particularly significant challenges: first, Current models struggle to capture the mutual influences and connections between nearby parking stations; second, when addressing data involving long time series, traditional methods often encounter the dilemma of gradient vanishing or exploding. In view of this, we proposed the SG-SCINet prediction model, which cleverly combines the advantages of the spatial self-attention mechanism and the sample convolution and interaction network (SCINet). By introducing the self-attention module, SG-SCINet effectively analyzes spatial and functional interactions, improving the prediction of car-sharing demand. This series of designs significantly improves the model’s adaptability in complex spatio-temporal environments. Experimental verification shows that the SG-SCINet model shows significant advantages over a single model in terms of prediction accuracy. |
| format | Article |
| id | doaj-art-0ab1c8da54b845359317543fe49ea02f |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-0ab1c8da54b845359317543fe49ea02f2025-01-15T00:01:55ZengIEEEIEEE Access2169-35362024-01-011219089719091110.1109/ACCESS.2024.351676410798450Integrating Spatial Self-Attention and Convolution Networks for Improved Car-Sharing Demand ForecastingShengjun Qin0https://orcid.org/0009-0004-9460-5373Jiaying Qin1Zhi Liu2School of Economics and Management, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Economics and Management, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Economics and Management, Guangxi University of Science and Technology, Liuzhou, ChinaThe core challenge facing the field of car-sharing demand forecasting lies in the innovative construction of models that effectively capture the intricate spatio-temporal variations in the data. Current methods face two particularly significant challenges: first, Current models struggle to capture the mutual influences and connections between nearby parking stations; second, when addressing data involving long time series, traditional methods often encounter the dilemma of gradient vanishing or exploding. In view of this, we proposed the SG-SCINet prediction model, which cleverly combines the advantages of the spatial self-attention mechanism and the sample convolution and interaction network (SCINet). By introducing the self-attention module, SG-SCINet effectively analyzes spatial and functional interactions, improving the prediction of car-sharing demand. This series of designs significantly improves the model’s adaptability in complex spatio-temporal environments. Experimental verification shows that the SG-SCINet model shows significant advantages over a single model in terms of prediction accuracy.https://ieeexplore.ieee.org/document/10798450/Convolution networkscar-sharingdemand forecastingspatio-temporal feature |
| spellingShingle | Shengjun Qin Jiaying Qin Zhi Liu Integrating Spatial Self-Attention and Convolution Networks for Improved Car-Sharing Demand Forecasting IEEE Access Convolution networks car-sharing demand forecasting spatio-temporal feature |
| title | Integrating Spatial Self-Attention and Convolution Networks for Improved Car-Sharing Demand Forecasting |
| title_full | Integrating Spatial Self-Attention and Convolution Networks for Improved Car-Sharing Demand Forecasting |
| title_fullStr | Integrating Spatial Self-Attention and Convolution Networks for Improved Car-Sharing Demand Forecasting |
| title_full_unstemmed | Integrating Spatial Self-Attention and Convolution Networks for Improved Car-Sharing Demand Forecasting |
| title_short | Integrating Spatial Self-Attention and Convolution Networks for Improved Car-Sharing Demand Forecasting |
| title_sort | integrating spatial self attention and convolution networks for improved car sharing demand forecasting |
| topic | Convolution networks car-sharing demand forecasting spatio-temporal feature |
| url | https://ieeexplore.ieee.org/document/10798450/ |
| work_keys_str_mv | AT shengjunqin integratingspatialselfattentionandconvolutionnetworksforimprovedcarsharingdemandforecasting AT jiayingqin integratingspatialselfattentionandconvolutionnetworksforimprovedcarsharingdemandforecasting AT zhiliu integratingspatialselfattentionandconvolutionnetworksforimprovedcarsharingdemandforecasting |