Bus arrival time prediction based on network model

Abstract

Providing accurate information on bus arrival and departure times at bus stops is one of the key parameters of high-quality public transport today. This paper proposes a model for the real-time prediction of arrival times at bus stops. The proposed model is based on information about the current location of the bus, the classification of runs into time periods with respect to the historical data, and the data model of the bus network. We discuss four types of data models: a data model defined by bus stops and crossings of the road network, a data model defined by bus stops, a data model which addresses the individual parts of the network in relation to the potential barriers that affect the travel speed of buses, and a data model with fixed-length links of the bus network. Travel times are classified according to the average travel speed into four time periods: morning, afternoon, early morning or late evening, and weekend. The results of the analysis showed that both the data model of the bus network and classifying runs into time periods affect the accuracy of predictions of bus arrival times at bus stops.