RST-Net: a spatio-temporal residual network based on Region-reConStruction algorithm for shared bike prediction
Abstract As a new form of public transportation, shared bikes have greatly facilitated people’s travel in recent years. However, in the actual operation process, the uneven distribution of bicycles at each shared bicycle station has limited the travel experience. In this paper, we propose a deep spa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-06-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-022-00781-y |
| _version_ | 1797863151822176256 |
|---|---|
| author | Yanyan Tan Bin Wang Zeyuan Yan Haoran Liu Huaxiang Zhang |
| author_facet | Yanyan Tan Bin Wang Zeyuan Yan Haoran Liu Huaxiang Zhang |
| author_sort | Yanyan Tan |
| collection | DOAJ |
| description | Abstract As a new form of public transportation, shared bikes have greatly facilitated people’s travel in recent years. However, in the actual operation process, the uneven distribution of bicycles at each shared bicycle station has limited the travel experience. In this paper, we propose a deep spatio-temporal residual network model based on Region-reConStruction algorithm to predict the usage of shared bikes in the bike-sharing system. We first propose an Region-reConStruction algorithm (RCS) to partition the shared bicycle sites within a city into separate areas based on their geographic location information as well as bikes’ migration trends between stations. We then combine the RCS algorithm with a deep spatio-temporal residual network to model the key factors affecting the usage of shared bicycles. RCS makes good use of the migration trend of shared bikes during user usage, thus greatly improving the accuracy of prediction. Experiments performed on New York’s bike-sharing system show that our model’s prediction accuracy is significantly better than that of previous models. |
| first_indexed | 2024-04-09T22:32:01Z |
| format | Article |
| id | doaj.art-b4648b4c11264907a2d8afb237eae185 |
| institution | Directory Open Access Journal |
| issn | 2199-4536 2198-6053 |
| language | English |
| last_indexed | 2024-04-09T22:32:01Z |
| publishDate | 2022-06-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj.art-b4648b4c11264907a2d8afb237eae1852023-03-22T12:44:10ZengSpringerComplex & Intelligent Systems2199-45362198-60532022-06-0191819710.1007/s40747-022-00781-yRST-Net: a spatio-temporal residual network based on Region-reConStruction algorithm for shared bike predictionYanyan Tan0Bin Wang1Zeyuan Yan2Haoran Liu3Huaxiang Zhang4School of Information Science and Engineering, Shandong Normal UniversitySchool of Information Science and Engineering, Shandong Normal UniversitySchool of Information Science and Engineering, Shandong Normal UniversitySchool of Information Science and Engineering, Shandong Normal UniversitySchool of Information Science and Engineering, Shandong Normal UniversityAbstract As a new form of public transportation, shared bikes have greatly facilitated people’s travel in recent years. However, in the actual operation process, the uneven distribution of bicycles at each shared bicycle station has limited the travel experience. In this paper, we propose a deep spatio-temporal residual network model based on Region-reConStruction algorithm to predict the usage of shared bikes in the bike-sharing system. We first propose an Region-reConStruction algorithm (RCS) to partition the shared bicycle sites within a city into separate areas based on their geographic location information as well as bikes’ migration trends between stations. We then combine the RCS algorithm with a deep spatio-temporal residual network to model the key factors affecting the usage of shared bicycles. RCS makes good use of the migration trend of shared bikes during user usage, thus greatly improving the accuracy of prediction. Experiments performed on New York’s bike-sharing system show that our model’s prediction accuracy is significantly better than that of previous models.https://doi.org/10.1007/s40747-022-00781-ySpatio-temporal data miningUrban computingGaussian mixture model clusterCitywide bike usage predictionDeep learning |
| spellingShingle | Yanyan Tan Bin Wang Zeyuan Yan Haoran Liu Huaxiang Zhang RST-Net: a spatio-temporal residual network based on Region-reConStruction algorithm for shared bike prediction Complex & Intelligent Systems Spatio-temporal data mining Urban computing Gaussian mixture model cluster Citywide bike usage prediction Deep learning |
| title | RST-Net: a spatio-temporal residual network based on Region-reConStruction algorithm for shared bike prediction |
| title_full | RST-Net: a spatio-temporal residual network based on Region-reConStruction algorithm for shared bike prediction |
| title_fullStr | RST-Net: a spatio-temporal residual network based on Region-reConStruction algorithm for shared bike prediction |
| title_full_unstemmed | RST-Net: a spatio-temporal residual network based on Region-reConStruction algorithm for shared bike prediction |
| title_short | RST-Net: a spatio-temporal residual network based on Region-reConStruction algorithm for shared bike prediction |
| title_sort | rst net a spatio temporal residual network based on region reconstruction algorithm for shared bike prediction |
| topic | Spatio-temporal data mining Urban computing Gaussian mixture model cluster Citywide bike usage prediction Deep learning |
| url | https://doi.org/10.1007/s40747-022-00781-y |
| work_keys_str_mv | AT yanyantan rstnetaspatiotemporalresidualnetworkbasedonregionreconstructionalgorithmforsharedbikeprediction AT binwang rstnetaspatiotemporalresidualnetworkbasedonregionreconstructionalgorithmforsharedbikeprediction AT zeyuanyan rstnetaspatiotemporalresidualnetworkbasedonregionreconstructionalgorithmforsharedbikeprediction AT haoranliu rstnetaspatiotemporalresidualnetworkbasedonregionreconstructionalgorithmforsharedbikeprediction AT huaxiangzhang rstnetaspatiotemporalresidualnetworkbasedonregionreconstructionalgorithmforsharedbikeprediction |