AI-based neural network models for bus passenger demand forecasting using smart card data
Accurate short-term forecasting of public transport demand is essential for the operation of on-demand public transport. Knowing where and when future demands for travel are expected allows operators to adjust timetables quickly, which helps improve service quality and reliability and attract more p...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | Journal of Urban Management |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2226585622000280 |
| _version_ | 1818501584962715648 |
|---|---|
| author | Sohani Liyanage Rusul Abduljabbar Hussein Dia Pei-Wei Tsai |
| author_facet | Sohani Liyanage Rusul Abduljabbar Hussein Dia Pei-Wei Tsai |
| author_sort | Sohani Liyanage |
| collection | DOAJ |
| description | Accurate short-term forecasting of public transport demand is essential for the operation of on-demand public transport. Knowing where and when future demands for travel are expected allows operators to adjust timetables quickly, which helps improve service quality and reliability and attract more passengers to public transport. This study addresses this need by developing AI-based deep learning models for prediction of bus passenger demands based on actual patronage data obtained from the smart-card ticketing system in Melbourne. The models, which consider the temporal characteristics of travel demand for some of the heaviest bus routes in Melbourne, were developed using real-world data from 18 bus routes and 1,781 bus stops. LSTM and BiLSTM deep learning models were evaluated and compared with five conventional deep learning models using the same data set. A desktop comparison was also undertaken against a number of established demand forecasting models that have been reported in the literature over the past decade. The comparative evaluation results showed that BiLSTM models outperformed other models tested and was able to predict passenger demands with over 90% accuracy. |
| first_indexed | 2024-12-10T20:58:18Z |
| format | Article |
| id | doaj.art-bb1d659899e8486795b3c56195ac85e7 |
| institution | Directory Open Access Journal |
| issn | 2226-5856 |
| language | English |
| last_indexed | 2024-12-10T20:58:18Z |
| publishDate | 2022-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Urban Management |
| spelling | doaj.art-bb1d659899e8486795b3c56195ac85e72022-12-22T01:33:54ZengElsevierJournal of Urban Management2226-58562022-09-01113365380AI-based neural network models for bus passenger demand forecasting using smart card dataSohani Liyanage0Rusul Abduljabbar1Hussein Dia2Pei-Wei Tsai3Department of Civil and Construction Engineering, Swinburne University of Technology, Australia; Corresponding author. Swinburne University of Technology, Melbourne, Australia.Department of Civil and Construction Engineering, Swinburne University of Technology, AustraliaDepartment of Civil and Construction Engineering, Swinburne University of Technology, AustraliaDepartment of Computer Science and Software Engineering, Swinburne University of Technology, AustraliaAccurate short-term forecasting of public transport demand is essential for the operation of on-demand public transport. Knowing where and when future demands for travel are expected allows operators to adjust timetables quickly, which helps improve service quality and reliability and attract more passengers to public transport. This study addresses this need by developing AI-based deep learning models for prediction of bus passenger demands based on actual patronage data obtained from the smart-card ticketing system in Melbourne. The models, which consider the temporal characteristics of travel demand for some of the heaviest bus routes in Melbourne, were developed using real-world data from 18 bus routes and 1,781 bus stops. LSTM and BiLSTM deep learning models were evaluated and compared with five conventional deep learning models using the same data set. A desktop comparison was also undertaken against a number of established demand forecasting models that have been reported in the literature over the past decade. The comparative evaluation results showed that BiLSTM models outperformed other models tested and was able to predict passenger demands with over 90% accuracy.http://www.sciencedirect.com/science/article/pii/S2226585622000280Artificial intelligenceShort-term predictionNeural networksBus demand predictionDeep learningOn-demand public transport |
| spellingShingle | Sohani Liyanage Rusul Abduljabbar Hussein Dia Pei-Wei Tsai AI-based neural network models for bus passenger demand forecasting using smart card data Journal of Urban Management Artificial intelligence Short-term prediction Neural networks Bus demand prediction Deep learning On-demand public transport |
| title | AI-based neural network models for bus passenger demand forecasting using smart card data |
| title_full | AI-based neural network models for bus passenger demand forecasting using smart card data |
| title_fullStr | AI-based neural network models for bus passenger demand forecasting using smart card data |
| title_full_unstemmed | AI-based neural network models for bus passenger demand forecasting using smart card data |
| title_short | AI-based neural network models for bus passenger demand forecasting using smart card data |
| title_sort | ai based neural network models for bus passenger demand forecasting using smart card data |
| topic | Artificial intelligence Short-term prediction Neural networks Bus demand prediction Deep learning On-demand public transport |
| url | http://www.sciencedirect.com/science/article/pii/S2226585622000280 |
| work_keys_str_mv | AT sohaniliyanage aibasedneuralnetworkmodelsforbuspassengerdemandforecastingusingsmartcarddata AT rusulabduljabbar aibasedneuralnetworkmodelsforbuspassengerdemandforecastingusingsmartcarddata AT husseindia aibasedneuralnetworkmodelsforbuspassengerdemandforecastingusingsmartcarddata AT peiweitsai aibasedneuralnetworkmodelsforbuspassengerdemandforecastingusingsmartcarddata |