Data analysis and predictions for public transport using machine learning and artificial intelligence methods
Building and evaluation of the prediction models for public transport data, extended by external data sources, using machine learning and artificial intelligence. Compilation of the models based on different scenarios and problems, followed by assessment of the suitability and accuracy of the models. Later on, deployment of proposed methods in an open environment.
Partners
In cooperation with the Faculty of Management Science and Informatics at the University of Žilina and INPROP company.
Team
Head
Size of the research team
5-9 individuals, from which 1 - 5 students
Students' field of study
Applied informatics, Intelligent information systems
Project purpose
To investigate the determinants of public transport availability, delays and passenger needs and their role in the enhancement of the public transport services.
Project goals
- To apply prediction problems in an open environment with the aim of enhancing passenger awareness.
- Analysis of changes in public transport demand and preferences by passengers over time.
- Creation of functionality to optimize the process of timetable construction.
- Comparison of the proposed timetables in terms of reliability and efficiency.
- The utilization of predictions for compiling courses and shifts in order to optimize the fleet and decrease delays.