Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS data
Accurate prediction of Public Transport (PT) mobility is important for intelligent transportation. Nowadays, mobility data have become increasingly available with the General Transit Feed Specification (GTFS) being the format for PT agencies to disseminate such data. Estimated Time of Arrival (ETA)...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | International Journal of Information Management Data Insights |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667096822000295 |
| _version_ | 1797986775126245376 |
|---|---|
| author | Eva Chondrodima Harris Georgiou Nikos Pelekis Yannis Theodoridis |
| author_facet | Eva Chondrodima Harris Georgiou Nikos Pelekis Yannis Theodoridis |
| author_sort | Eva Chondrodima |
| collection | DOAJ |
| description | Accurate prediction of Public Transport (PT) mobility is important for intelligent transportation. Nowadays, mobility data have become increasingly available with the General Transit Feed Specification (GTFS) being the format for PT agencies to disseminate such data. Estimated Time of Arrival (ETA) of PT is crucial for the public, as well as the PT agency for logistics, route-optimization, maintenance, etc. However, prediction of PT-ETA is a challenging task, due to the complex and non-stationary urban traffic. This work introduces a novel data-driven approach for predicting PT-ETA based on RBF neural networks, using a modified version of the successful PSO-NSFM algorithm for training. Additionally, a novel pre-processing pipeline (CR-GTFS) is designed for cleansing and reconstructing the GTFS data. The combination of PSO-NSFM and CR-GTFS introduces a complete framework for predicting PT-ETA accurately with real-world data feeds. Experiments on GTFS data verify the proposed approach, outperforming state-of-the-art in prediction accuracy and computational times. |
| first_indexed | 2024-04-11T07:38:30Z |
| format | Article |
| id | doaj.art-5a6220091add4fb68530a333adfc27bb |
| institution | Directory Open Access Journal |
| issn | 2667-0968 |
| language | English |
| last_indexed | 2024-04-11T07:38:30Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Information Management Data Insights |
| spelling | doaj.art-5a6220091add4fb68530a333adfc27bb2022-12-22T04:36:39ZengElsevierInternational Journal of Information Management Data Insights2667-09682022-11-0122100086Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS dataEva Chondrodima0Harris Georgiou1Nikos Pelekis2Yannis Theodoridis3Corresponding author.; Department of Informatics, University of Piraeus, GreeceDepartment of Informatics, University of Piraeus, GreeceDepartment of Statistics and Insurance Science, University of Piraeus, GreeceDepartment of Informatics, University of Piraeus, GreeceAccurate prediction of Public Transport (PT) mobility is important for intelligent transportation. Nowadays, mobility data have become increasingly available with the General Transit Feed Specification (GTFS) being the format for PT agencies to disseminate such data. Estimated Time of Arrival (ETA) of PT is crucial for the public, as well as the PT agency for logistics, route-optimization, maintenance, etc. However, prediction of PT-ETA is a challenging task, due to the complex and non-stationary urban traffic. This work introduces a novel data-driven approach for predicting PT-ETA based on RBF neural networks, using a modified version of the successful PSO-NSFM algorithm for training. Additionally, a novel pre-processing pipeline (CR-GTFS) is designed for cleansing and reconstructing the GTFS data. The combination of PSO-NSFM and CR-GTFS introduces a complete framework for predicting PT-ETA accurately with real-world data feeds. Experiments on GTFS data verify the proposed approach, outperforming state-of-the-art in prediction accuracy and computational times.http://www.sciencedirect.com/science/article/pii/S2667096822000295Estimated time of arrival (ETA)Fuzzy meansGeneral transit feed specification (GTFS)Intelligent transportation systemsNeural networks (NN)Particle swarm optimization (PSO) |
| spellingShingle | Eva Chondrodima Harris Georgiou Nikos Pelekis Yannis Theodoridis Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS data International Journal of Information Management Data Insights Estimated time of arrival (ETA) Fuzzy means General transit feed specification (GTFS) Intelligent transportation systems Neural networks (NN) Particle swarm optimization (PSO) |
| title | Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS data |
| title_full | Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS data |
| title_fullStr | Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS data |
| title_full_unstemmed | Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS data |
| title_short | Particle swarm optimization and RBF neural networks for public transport arrival time prediction using GTFS data |
| title_sort | particle swarm optimization and rbf neural networks for public transport arrival time prediction using gtfs data |
| topic | Estimated time of arrival (ETA) Fuzzy means General transit feed specification (GTFS) Intelligent transportation systems Neural networks (NN) Particle swarm optimization (PSO) |
| url | http://www.sciencedirect.com/science/article/pii/S2667096822000295 |
| work_keys_str_mv | AT evachondrodima particleswarmoptimizationandrbfneuralnetworksforpublictransportarrivaltimepredictionusinggtfsdata AT harrisgeorgiou particleswarmoptimizationandrbfneuralnetworksforpublictransportarrivaltimepredictionusinggtfsdata AT nikospelekis particleswarmoptimizationandrbfneuralnetworksforpublictransportarrivaltimepredictionusinggtfsdata AT yannistheodoridis particleswarmoptimizationandrbfneuralnetworksforpublictransportarrivaltimepredictionusinggtfsdata |