The BusGrid system architecture
Estimating passenger avg. waiting time for a specific bus stop
Passenger demand prediction for a specific day
Optimized bus schedules
Passenger demand predictions for specific bus routes

Project Description

The main objective of the BusGrid research project is the design and implementation of a novel information system for the administrators of Public Transport companies. BusGrid is an integrated system for productivity and customer service improvement in the Public Transportation Companies with a two-fold goal of improving both quality of service and productivity of bus routes. The system produces solutions that tackle this trade-off by consistently optimizing vehicle schedules to achieve a relatively stable average number of on-board passengers. Specifically, it receives real time data from installed sensors (AVL & APC) on the vehicles of Public Transportation Companies in order to:

The project was implemented by the Machine Learning & Knowledge Discovery (MLKD) group and Link Technologies S.A.

Research Programme

Industrial Reasearch and Technology
Funded by the Greek R&D General Secretariat, PABET 2013


16 months (3/2014 - 7/2015)


MLKD group, Dept. of Informatics, Aristotle University of Thessaloniki, Greece

Prof. Ioannis Vlahavas, Project Coordination
Assist. Prof. Grigorios Tsoumakas, Scientific Advisor
Anestis Fachantidis, Lead Developer
Patroklos Samaras, Developer


Samaras, P., Fachantidis, A., Tsoumakas, G., & Vlahavas, I. (2015, October). A prediction model of passenger demand using AVL and APC data from a bus fleet. In Proceedings of the 19th Panhellenic Conference on Informatics (pp. 129-134). ACM.