University of Twente Student Theses
Short-Term Passenger Flow Forecasting in Public Transportation Networks Under Event Conditions
Bakker, Jeffrey (2023) Short-Term Passenger Flow Forecasting in Public Transportation Networks Under Event Conditions.
|
PDF
10MB |
| Abstract: | Public transportation networks are an essential part of public infrastructure and have the potential to reduce society's dependency on personal cars. Making public transportation a more attractive option requires better passenger demand forecasts, as these can be used to guarantee enough seating capacity for everyone, especially under event conditions. This Master thesis looks into short-term passenger flow forecasting under event conditions by comparing the performance of forecasting algorithms under event conditions and looking at the impact of including event features in the forecasting approach. Even though passenger demand in public transportation tends to be quite regular, accurately forecasting the additional peaks of passengers caused by large events has proven to be quite challenging. This research uses the types of events and their venues' capacities as indicators of their actual attendance; however, these indicators have proven to be insufficient in the context of passenger flow forecasting. Some cherry-picked examples show promising results for future works that have access to the correct data. |
| Item Type: | Essay (Master) |
| Clients: | Info Support B.V., Veenendaal, Netherlands |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science MSc (60300) |
| Link to this item: | https://purl.utwente.nl/essays/97536 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page