Smart data re-sampling for bus fleet management

Abstract

In this paper we focus on bus fleets and propose an application of artificial intelligence (transductive inference for function estimation) which utilizes data from the vehicle tracking system in order to enforce the schedule monitoring of the bus and thus providing more accurate information for decision making activities. This is achieved by estimating the time of arrivals and departures of the buses at certain points of the journey (main bus stops, interchange points, crossroads) which are crucial for the management of the fleet.