Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data
Passengers of public transportation nowadays expect reliable and accurate travel information. The need for occupancy information is becoming more prevalent in intelligent public transport systems as people started avoiding overcrowded vehicles during the COVID-19 pandemic. Furthermore, public transp...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10057448/ |
| _version_ | 1827986541087031296 |
|---|---|
| author | Josef Hoppe Felix Schwinger Henrik Haeger Jonas Wernz Matthias Jarke |
| author_facet | Josef Hoppe Felix Schwinger Henrik Haeger Jonas Wernz Matthias Jarke |
| author_sort | Josef Hoppe |
| collection | DOAJ |
| description | Passengers of public transportation nowadays expect reliable and accurate travel information. The need for occupancy information is becoming more prevalent in intelligent public transport systems as people started avoiding overcrowded vehicles during the COVID-19 pandemic. Furthermore, public transportation companies require accurate occupancy forecasts to improve service quality. We present a novel approach to improve the prediction of passenger numbers that enhances a day-ahead prediction with real-time data. We first train a baseline predictor on historical automatic passenger counting data. Next, we train a real-time model on the deviations between baseline prediction and observed values, thus capturing events not addressed by the baseline. For the forecast, we attempt to detect emerging patterns in real time and adjust the baseline prediction with deviations from the patterns. Our experiments with data from Germany show that the proposed model improves the forecast of the baseline model and is only outperformed by artificial neural networks in some instances. If the training sets only cover a limited period of up to four months, our approach outperforms competing methods. For larger training sets, there are mixed results in the sense that for some test cases, certain types of neural networks yield slightly better results, but our method still performs well with less training effort, is explainable along the whole prediction process and can be applied to existing prediction methods. |
| first_indexed | 2024-04-09T23:33:00Z |
| format | Article |
| id | doaj.art-76c764c8f0944511bfa334f9ce9c3ad8 |
| institution | Directory Open Access Journal |
| issn | 2687-7813 |
| language | English |
| last_indexed | 2024-04-09T23:33:00Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj.art-76c764c8f0944511bfa334f9ce9c3ad82023-03-20T23:00:51ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132023-01-01415317410.1109/OJITS.2023.325156410057448Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy DataJosef Hoppe0https://orcid.org/0000-0003-4383-7049Felix Schwinger1https://orcid.org/0000-0001-7754-3933Henrik Haeger2https://orcid.org/0009-0006-0530-4128Jonas Wernz3Matthias Jarke4https://orcid.org/0000-0001-6169-2942Computational Network Science, RWTH Aachen University, Aachen, GermanyChair for Information Systems, RWTH Aachen University, Aachen, GermanyDevelopment Operations, IVU Traffic Technology AG, Aachen, GermanyDevelopment Operations, IVU Traffic Technology AG, Aachen, GermanyChair for Information Systems, RWTH Aachen University, Aachen, GermanyPassengers of public transportation nowadays expect reliable and accurate travel information. The need for occupancy information is becoming more prevalent in intelligent public transport systems as people started avoiding overcrowded vehicles during the COVID-19 pandemic. Furthermore, public transportation companies require accurate occupancy forecasts to improve service quality. We present a novel approach to improve the prediction of passenger numbers that enhances a day-ahead prediction with real-time data. We first train a baseline predictor on historical automatic passenger counting data. Next, we train a real-time model on the deviations between baseline prediction and observed values, thus capturing events not addressed by the baseline. For the forecast, we attempt to detect emerging patterns in real time and adjust the baseline prediction with deviations from the patterns. Our experiments with data from Germany show that the proposed model improves the forecast of the baseline model and is only outperformed by artificial neural networks in some instances. If the training sets only cover a limited period of up to four months, our approach outperforms competing methods. For larger training sets, there are mixed results in the sense that for some test cases, certain types of neural networks yield slightly better results, but our method still performs well with less training effort, is explainable along the whole prediction process and can be applied to existing prediction methods.https://ieeexplore.ieee.org/document/10057448/Clustering algorithmspredictive modelspublic transportationtime series analysis |
| spellingShingle | Josef Hoppe Felix Schwinger Henrik Haeger Jonas Wernz Matthias Jarke Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data IEEE Open Journal of Intelligent Transportation Systems Clustering algorithms predictive models public transportation time series analysis |
| title | Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data |
| title_full | Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data |
| title_fullStr | Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data |
| title_full_unstemmed | Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data |
| title_short | Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data |
| title_sort | improving the prediction of passenger numbers in public transit networks by combining short term forecasts with real time occupancy data |
| topic | Clustering algorithms predictive models public transportation time series analysis |
| url | https://ieeexplore.ieee.org/document/10057448/ |
| work_keys_str_mv | AT josefhoppe improvingthepredictionofpassengernumbersinpublictransitnetworksbycombiningshorttermforecastswithrealtimeoccupancydata AT felixschwinger improvingthepredictionofpassengernumbersinpublictransitnetworksbycombiningshorttermforecastswithrealtimeoccupancydata AT henrikhaeger improvingthepredictionofpassengernumbersinpublictransitnetworksbycombiningshorttermforecastswithrealtimeoccupancydata AT jonaswernz improvingthepredictionofpassengernumbersinpublictransitnetworksbycombiningshorttermforecastswithrealtimeoccupancydata AT matthiasjarke improvingthepredictionofpassengernumbersinpublictransitnetworksbycombiningshorttermforecastswithrealtimeoccupancydata |