Analysis of Passenger Flow Characteristics and Origin–Destination Passenger Flow Prediction in Urban Rail Transit Based on Deep Learning
Traditional station passenger flow prediction can no longer meet the application needs of urban rail transit vehicle scheduling. Station passenger flow can only predict station distribution, and the passenger flow distribution in general sections is unknown. Accurate short-term travel origin and des...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/5/2853 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850031386936737792 |
|---|---|
| author | Zhongwei Hou Jin Han Guang Yang |
| author_facet | Zhongwei Hou Jin Han Guang Yang |
| author_sort | Zhongwei Hou |
| collection | DOAJ |
| description | Traditional station passenger flow prediction can no longer meet the application needs of urban rail transit vehicle scheduling. Station passenger flow can only predict station distribution, and the passenger flow distribution in general sections is unknown. Accurate short-term travel origin and destination (OD) passenger flow prediction is the main basis for formulating urban rail transit operation organization plans. To simultaneously consider the spatiotemporal characteristics of passenger flow distribution and achieve high precision estimation of origin and destination (OD) passenger flow quickly, a predictive model based on a temporal convolutional network and a long short-term memory network (TCN–LSTM) combined with an attention mechanism was established to process passenger flow data in urban rail transit. Firstly, according to the passenger flow data of the urban rail transit section, the existing data characteristics were summarized, and the impact of external factors on section passenger flow was studied. Then, a temporal convolutional network and long short-term memory (TCN–LSTM) deep learning model based on an attention mechanism was constructed to predict interval passenger flow. The model combines some external factors such as time, date attributes, weather conditions, and air quality that affect passenger flow in the interval to improve the shortcomings of the original model in predicting origin and destination (OD) passenger flow. Taking Chongqing Rail Transit as an example, the model was validated, and the results showed that the deep learning model had significantly better prediction results than other baseline models. The applicability analysis in scenarios such as high/medium/low passenger flow could achieve stable prediction results. |
| format | Article |
| id | doaj-art-cc753664d06e40a79635071d19c20b51 |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-cc753664d06e40a79635071d19c20b512025-08-20T02:58:58ZengMDPI AGApplied Sciences2076-34172025-03-01155285310.3390/app15052853Analysis of Passenger Flow Characteristics and Origin–Destination Passenger Flow Prediction in Urban Rail Transit Based on Deep LearningZhongwei Hou0Jin Han1Guang Yang2Institute of Future Civil Engineering Science and Technology, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Traffic & Transportation, Chongqing Jiaotong University, Chongqing 400074, ChinaTraditional station passenger flow prediction can no longer meet the application needs of urban rail transit vehicle scheduling. Station passenger flow can only predict station distribution, and the passenger flow distribution in general sections is unknown. Accurate short-term travel origin and destination (OD) passenger flow prediction is the main basis for formulating urban rail transit operation organization plans. To simultaneously consider the spatiotemporal characteristics of passenger flow distribution and achieve high precision estimation of origin and destination (OD) passenger flow quickly, a predictive model based on a temporal convolutional network and a long short-term memory network (TCN–LSTM) combined with an attention mechanism was established to process passenger flow data in urban rail transit. Firstly, according to the passenger flow data of the urban rail transit section, the existing data characteristics were summarized, and the impact of external factors on section passenger flow was studied. Then, a temporal convolutional network and long short-term memory (TCN–LSTM) deep learning model based on an attention mechanism was constructed to predict interval passenger flow. The model combines some external factors such as time, date attributes, weather conditions, and air quality that affect passenger flow in the interval to improve the shortcomings of the original model in predicting origin and destination (OD) passenger flow. Taking Chongqing Rail Transit as an example, the model was validated, and the results showed that the deep learning model had significantly better prediction results than other baseline models. The applicability analysis in scenarios such as high/medium/low passenger flow could achieve stable prediction results.https://www.mdpi.com/2076-3417/15/5/2853passenger flow in urban rail transitorigin–destination passenger flow predictiondeep learninglong short-term memory networksattention mechanism |
| spellingShingle | Zhongwei Hou Jin Han Guang Yang Analysis of Passenger Flow Characteristics and Origin–Destination Passenger Flow Prediction in Urban Rail Transit Based on Deep Learning Applied Sciences passenger flow in urban rail transit origin–destination passenger flow prediction deep learning long short-term memory networks attention mechanism |
| title | Analysis of Passenger Flow Characteristics and Origin–Destination Passenger Flow Prediction in Urban Rail Transit Based on Deep Learning |
| title_full | Analysis of Passenger Flow Characteristics and Origin–Destination Passenger Flow Prediction in Urban Rail Transit Based on Deep Learning |
| title_fullStr | Analysis of Passenger Flow Characteristics and Origin–Destination Passenger Flow Prediction in Urban Rail Transit Based on Deep Learning |
| title_full_unstemmed | Analysis of Passenger Flow Characteristics and Origin–Destination Passenger Flow Prediction in Urban Rail Transit Based on Deep Learning |
| title_short | Analysis of Passenger Flow Characteristics and Origin–Destination Passenger Flow Prediction in Urban Rail Transit Based on Deep Learning |
| title_sort | analysis of passenger flow characteristics and origin destination passenger flow prediction in urban rail transit based on deep learning |
| topic | passenger flow in urban rail transit origin–destination passenger flow prediction deep learning long short-term memory networks attention mechanism |
| url | https://www.mdpi.com/2076-3417/15/5/2853 |
| work_keys_str_mv | AT zhongweihou analysisofpassengerflowcharacteristicsandorigindestinationpassengerflowpredictioninurbanrailtransitbasedondeeplearning AT jinhan analysisofpassengerflowcharacteristicsandorigindestinationpassengerflowpredictioninurbanrailtransitbasedondeeplearning AT guangyang analysisofpassengerflowcharacteristicsandorigindestinationpassengerflowpredictioninurbanrailtransitbasedondeeplearning |