Multi-Scale Residual Depthwise Separable Convolution for Metro Passenger Flow Prediction
Accurate prediction of metro passenger flow helps operating departments optimize scheduling plans, alleviate passenger flow pressure, and improve service quality. However, existing passenger flow prediction models tend to only consider the historical passenger flow of a single station while ignoring...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/20/11272 |
| _version_ | 1827629362987401216 |
|---|---|
| author | Taoying Li Lu Liu Meng Li |
| author_facet | Taoying Li Lu Liu Meng Li |
| author_sort | Taoying Li |
| collection | DOAJ |
| description | Accurate prediction of metro passenger flow helps operating departments optimize scheduling plans, alleviate passenger flow pressure, and improve service quality. However, existing passenger flow prediction models tend to only consider the historical passenger flow of a single station while ignoring the spatial relationships between different stations and correlations between passenger flows, resulting in low prediction accuracy. Therefore, a multi-scale residual depthwise separable convolution network (MRDSCNN) is proposed for metro passenger flow prediction, which consists of three pivotal components, including residual depthwise separable convolution (RDSC), multi-scale depthwise separable convolution (MDSC), and attention bidirectional gated recurrent unit (AttBiGRU). The RDSC module is designed to capture local spatial and temporal correlations leveraging the diverse temporal patterns of passenger flows, and then the MDSC module is specialized in obtaining the inter-station correlations between the target station and other heterogeneous stations throughout the metro network. Subsequently, these correlations are fed into AttBiGRU to extract global interaction features and obtain passenger flow prediction results. Finally, the Hangzhou metro passenger inflow and outflow data are employed to assess the model performance, and the results show that the proposed model outperforms other models. |
| first_indexed | 2024-03-09T13:50:26Z |
| format | Article |
| id | doaj.art-bbedff4b50364167b357aa4c7205158d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:50:26Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-bbedff4b50364167b357aa4c7205158d2023-11-30T20:51:45ZengMDPI AGApplied Sciences2076-34172023-10-0113201127210.3390/app132011272Multi-Scale Residual Depthwise Separable Convolution for Metro Passenger Flow PredictionTaoying Li0Lu Liu1Meng Li2School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, ChinaSchool of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, ChinaSchool of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, ChinaAccurate prediction of metro passenger flow helps operating departments optimize scheduling plans, alleviate passenger flow pressure, and improve service quality. However, existing passenger flow prediction models tend to only consider the historical passenger flow of a single station while ignoring the spatial relationships between different stations and correlations between passenger flows, resulting in low prediction accuracy. Therefore, a multi-scale residual depthwise separable convolution network (MRDSCNN) is proposed for metro passenger flow prediction, which consists of three pivotal components, including residual depthwise separable convolution (RDSC), multi-scale depthwise separable convolution (MDSC), and attention bidirectional gated recurrent unit (AttBiGRU). The RDSC module is designed to capture local spatial and temporal correlations leveraging the diverse temporal patterns of passenger flows, and then the MDSC module is specialized in obtaining the inter-station correlations between the target station and other heterogeneous stations throughout the metro network. Subsequently, these correlations are fed into AttBiGRU to extract global interaction features and obtain passenger flow prediction results. Finally, the Hangzhou metro passenger inflow and outflow data are employed to assess the model performance, and the results show that the proposed model outperforms other models.https://www.mdpi.com/2076-3417/13/20/11272metro passenger flow predictionspatiotemporal dependenciesgraph convolutional networkresidual network |
| spellingShingle | Taoying Li Lu Liu Meng Li Multi-Scale Residual Depthwise Separable Convolution for Metro Passenger Flow Prediction Applied Sciences metro passenger flow prediction spatiotemporal dependencies graph convolutional network residual network |
| title | Multi-Scale Residual Depthwise Separable Convolution for Metro Passenger Flow Prediction |
| title_full | Multi-Scale Residual Depthwise Separable Convolution for Metro Passenger Flow Prediction |
| title_fullStr | Multi-Scale Residual Depthwise Separable Convolution for Metro Passenger Flow Prediction |
| title_full_unstemmed | Multi-Scale Residual Depthwise Separable Convolution for Metro Passenger Flow Prediction |
| title_short | Multi-Scale Residual Depthwise Separable Convolution for Metro Passenger Flow Prediction |
| title_sort | multi scale residual depthwise separable convolution for metro passenger flow prediction |
| topic | metro passenger flow prediction spatiotemporal dependencies graph convolutional network residual network |
| url | https://www.mdpi.com/2076-3417/13/20/11272 |
| work_keys_str_mv | AT taoyingli multiscaleresidualdepthwiseseparableconvolutionformetropassengerflowprediction AT luliu multiscaleresidualdepthwiseseparableconvolutionformetropassengerflowprediction AT mengli multiscaleresidualdepthwiseseparableconvolutionformetropassengerflowprediction |