A Deep Learning Approach for Predicting Bus Passenger Demand Based on Weather Conditions
This work apply a deep learning artificial neural network model – the Multilayer Perceptron – as a regression model to estimate the demand of bus passengers. Transit bus ridership and weather conditions were collected over a year from a medium-size European metropolitan area and linked under the ass...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2020-12-01
|
| Series: | Transport and Telecommunication |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/ttj-2020-0020 |
| _version_ | 1828852402865831936 |
|---|---|
| author | Fontes Tânia Correia Ricardo Ribeiro Joel Borges José Luís |
| author_facet | Fontes Tânia Correia Ricardo Ribeiro Joel Borges José Luís |
| author_sort | Fontes Tânia |
| collection | DOAJ |
| description | This work apply a deep learning artificial neural network model – the Multilayer Perceptron – as a regression model to estimate the demand of bus passengers. Transit bus ridership and weather conditions were collected over a year from a medium-size European metropolitan area and linked under the assumption: individuals choose the travel mode based on the weather conditions that are observed during (a) the departure hour, (b) the hour before or (c) two hours prior to the travel start. The transit ridership data were also labelled according to the hour of the day, day of the week, month, and whether there was a strike and/or holiday or not. The results show that the prediction error of the model decrease by ~9% when the weather conditions observed two hours before travel start is taken into account. The model sensitivity analyses reveals that the worst performance is obtained for a strike day of a weekday in spring (typically Wednesdays or Thursdays). |
| first_indexed | 2024-12-12T23:52:24Z |
| format | Article |
| id | doaj.art-3e12138bbe5b416c8559c0a3b5c9e304 |
| institution | Directory Open Access Journal |
| issn | 1407-6179 |
| language | English |
| last_indexed | 2024-12-12T23:52:24Z |
| publishDate | 2020-12-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Transport and Telecommunication |
| spelling | doaj.art-3e12138bbe5b416c8559c0a3b5c9e3042022-12-22T00:06:40ZengSciendoTransport and Telecommunication1407-61792020-12-0121425526410.2478/ttj-2020-0020ttj-2020-0020A Deep Learning Approach for Predicting Bus Passenger Demand Based on Weather ConditionsFontes Tânia0Correia Ricardo1Ribeiro Joel2Borges José Luís3INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal, Rua Dr. Roberto Frias, 4200-465INESC TEC and Faculty of Engineering, University of Porto, Porto, Portugal, Rua Dr. Roberto Frias, 4200-465INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal, Rua Dr. Roberto Frias, 4200-465INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal, Rua Dr. Roberto Frias, 4200-465This work apply a deep learning artificial neural network model – the Multilayer Perceptron – as a regression model to estimate the demand of bus passengers. Transit bus ridership and weather conditions were collected over a year from a medium-size European metropolitan area and linked under the assumption: individuals choose the travel mode based on the weather conditions that are observed during (a) the departure hour, (b) the hour before or (c) two hours prior to the travel start. The transit ridership data were also labelled according to the hour of the day, day of the week, month, and whether there was a strike and/or holiday or not. The results show that the prediction error of the model decrease by ~9% when the weather conditions observed two hours before travel start is taken into account. The model sensitivity analyses reveals that the worst performance is obtained for a strike day of a weekday in spring (typically Wednesdays or Thursdays).https://doi.org/10.2478/ttj-2020-0020preditionurban public transportbus passenger demandweather conditionsartificial neural networks |
| spellingShingle | Fontes Tânia Correia Ricardo Ribeiro Joel Borges José Luís A Deep Learning Approach for Predicting Bus Passenger Demand Based on Weather Conditions Transport and Telecommunication predition urban public transport bus passenger demand weather conditions artificial neural networks |
| title | A Deep Learning Approach for Predicting Bus Passenger Demand Based on Weather Conditions |
| title_full | A Deep Learning Approach for Predicting Bus Passenger Demand Based on Weather Conditions |
| title_fullStr | A Deep Learning Approach for Predicting Bus Passenger Demand Based on Weather Conditions |
| title_full_unstemmed | A Deep Learning Approach for Predicting Bus Passenger Demand Based on Weather Conditions |
| title_short | A Deep Learning Approach for Predicting Bus Passenger Demand Based on Weather Conditions |
| title_sort | deep learning approach for predicting bus passenger demand based on weather conditions |
| topic | predition urban public transport bus passenger demand weather conditions artificial neural networks |
| url | https://doi.org/10.2478/ttj-2020-0020 |
| work_keys_str_mv | AT fontestania adeeplearningapproachforpredictingbuspassengerdemandbasedonweatherconditions AT correiaricardo adeeplearningapproachforpredictingbuspassengerdemandbasedonweatherconditions AT ribeirojoel adeeplearningapproachforpredictingbuspassengerdemandbasedonweatherconditions AT borgesjoseluis adeeplearningapproachforpredictingbuspassengerdemandbasedonweatherconditions AT fontestania deeplearningapproachforpredictingbuspassengerdemandbasedonweatherconditions AT correiaricardo deeplearningapproachforpredictingbuspassengerdemandbasedonweatherconditions AT ribeirojoel deeplearningapproachforpredictingbuspassengerdemandbasedonweatherconditions AT borgesjoseluis deeplearningapproachforpredictingbuspassengerdemandbasedonweatherconditions |