Forecasting Short-Term Passenger Flow of Subway Stations Based on the Temporal Pattern Attention Mechanism and the Long Short-Term Memory Network
Rational use of urban underground space (UUS) and public transportation transfer underground can solve urban traffic problems. Accurate short-term prediction of passenger flow can ensure the efficient, safe, and comfortable operation of subway stations. However, complex and nonlinear interdependenci...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/12/1/25 |
| _version_ | 1827625150399381504 |
|---|---|
| author | Lingxiang Wei Dongjun Guo Zhilong Chen Jincheng Yang Tianliu Feng |
| author_facet | Lingxiang Wei Dongjun Guo Zhilong Chen Jincheng Yang Tianliu Feng |
| author_sort | Lingxiang Wei |
| collection | DOAJ |
| description | Rational use of urban underground space (UUS) and public transportation transfer underground can solve urban traffic problems. Accurate short-term prediction of passenger flow can ensure the efficient, safe, and comfortable operation of subway stations. However, complex and nonlinear interdependencies between time steps and time series complicate such predictions. This study considered temporal patterns across multiple time steps and selected relevant information on short-term passenger flow for prediction. A hybrid model based on the temporal pattern attention (TPA) mechanism and the long short-term memory (LSTM) network was developed (i.e., TPA-LSTM) for predicting the future number of passengers in subway stations. The TPA mechanism focuses on the hidden layer output values of different time steps in history and of the current time as well as correlates these output values to improve the accuracy of the model. The card swiping data from the Hangzhou Metro automatic fare collection system in China were used for verification and analysis. This model was compared with a convolutional neural network (CNN), LSTM, and CNN-LSTM. The results showed that the TPA-LSTM outperformed the other models with good applicability and accuracy. This study provides a theoretical basis for the pre-allocation of subway resources to avoid subway station crowding and stampede accidents. |
| first_indexed | 2024-03-09T12:28:32Z |
| format | Article |
| id | doaj.art-3aa455eb54c6420a8c06f62301bc62b9 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T12:28:32Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-3aa455eb54c6420a8c06f62301bc62b92023-11-30T22:32:03ZengMDPI AGISPRS International Journal of Geo-Information2220-99642023-01-011212510.3390/ijgi12010025Forecasting Short-Term Passenger Flow of Subway Stations Based on the Temporal Pattern Attention Mechanism and the Long Short-Term Memory NetworkLingxiang Wei0Dongjun Guo1Zhilong Chen2Jincheng Yang3Tianliu Feng4Research Center for Underground Space, Army Engineering University of PLA, Nanjing 210007, ChinaResearch Center for Underground Space, Army Engineering University of PLA, Nanjing 210007, ChinaResearch Center for Underground Space, Army Engineering University of PLA, Nanjing 210007, ChinaSchool of Materials Science and Engineering, Yancheng Institute of Technology, Yancheng 224051, ChinaSchool of Materials Science and Engineering, Yancheng Institute of Technology, Yancheng 224051, ChinaRational use of urban underground space (UUS) and public transportation transfer underground can solve urban traffic problems. Accurate short-term prediction of passenger flow can ensure the efficient, safe, and comfortable operation of subway stations. However, complex and nonlinear interdependencies between time steps and time series complicate such predictions. This study considered temporal patterns across multiple time steps and selected relevant information on short-term passenger flow for prediction. A hybrid model based on the temporal pattern attention (TPA) mechanism and the long short-term memory (LSTM) network was developed (i.e., TPA-LSTM) for predicting the future number of passengers in subway stations. The TPA mechanism focuses on the hidden layer output values of different time steps in history and of the current time as well as correlates these output values to improve the accuracy of the model. The card swiping data from the Hangzhou Metro automatic fare collection system in China were used for verification and analysis. This model was compared with a convolutional neural network (CNN), LSTM, and CNN-LSTM. The results showed that the TPA-LSTM outperformed the other models with good applicability and accuracy. This study provides a theoretical basis for the pre-allocation of subway resources to avoid subway station crowding and stampede accidents.https://www.mdpi.com/2220-9964/12/1/25urban underground space (UUS)subway stationshort-term passenger flow forecasttemporal pattern attention (TPA)long short-term memory network (LSTM) |
| spellingShingle | Lingxiang Wei Dongjun Guo Zhilong Chen Jincheng Yang Tianliu Feng Forecasting Short-Term Passenger Flow of Subway Stations Based on the Temporal Pattern Attention Mechanism and the Long Short-Term Memory Network ISPRS International Journal of Geo-Information urban underground space (UUS) subway station short-term passenger flow forecast temporal pattern attention (TPA) long short-term memory network (LSTM) |
| title | Forecasting Short-Term Passenger Flow of Subway Stations Based on the Temporal Pattern Attention Mechanism and the Long Short-Term Memory Network |
| title_full | Forecasting Short-Term Passenger Flow of Subway Stations Based on the Temporal Pattern Attention Mechanism and the Long Short-Term Memory Network |
| title_fullStr | Forecasting Short-Term Passenger Flow of Subway Stations Based on the Temporal Pattern Attention Mechanism and the Long Short-Term Memory Network |
| title_full_unstemmed | Forecasting Short-Term Passenger Flow of Subway Stations Based on the Temporal Pattern Attention Mechanism and the Long Short-Term Memory Network |
| title_short | Forecasting Short-Term Passenger Flow of Subway Stations Based on the Temporal Pattern Attention Mechanism and the Long Short-Term Memory Network |
| title_sort | forecasting short term passenger flow of subway stations based on the temporal pattern attention mechanism and the long short term memory network |
| topic | urban underground space (UUS) subway station short-term passenger flow forecast temporal pattern attention (TPA) long short-term memory network (LSTM) |
| url | https://www.mdpi.com/2220-9964/12/1/25 |
| work_keys_str_mv | AT lingxiangwei forecastingshorttermpassengerflowofsubwaystationsbasedonthetemporalpatternattentionmechanismandthelongshorttermmemorynetwork AT dongjunguo forecastingshorttermpassengerflowofsubwaystationsbasedonthetemporalpatternattentionmechanismandthelongshorttermmemorynetwork AT zhilongchen forecastingshorttermpassengerflowofsubwaystationsbasedonthetemporalpatternattentionmechanismandthelongshorttermmemorynetwork AT jinchengyang forecastingshorttermpassengerflowofsubwaystationsbasedonthetemporalpatternattentionmechanismandthelongshorttermmemorynetwork AT tianliufeng forecastingshorttermpassengerflowofsubwaystationsbasedonthetemporalpatternattentionmechanismandthelongshorttermmemorynetwork |