Paper Type
Complete Research Paper
Description
Due to technological innovation in the automotive sector, more and more vehicle data becomes available. Today, historical trip data can be analysed in order to personalise a vehicle´s navigation device. Thus, it is possible to incorporate drivers´ preferences in routing decisions. To describe drivers´ preferences in a navigation context, it is necessary to model driver behaviour appropriately. \ \ In this paper, we develop three models to depict different perspectives of driver behaviour in order to personalise navigation devices. The core point is to investigate edge utilization along the dimensions of time and space. Edges are the foundation for each navigation device´s digital roadmap. The first, time-oriented model examines the observed speeds on the edges. For the second, space-oriented model, a measure considering the entirety of edges is provided as to characterize the coverage of a driver´s mobility network. \ \ The third model analyses routes consisting of paths of edges. Correlation analysis shows that results obtained from the different models confirm each other. Thus, it is possible to build a well-founded two-dimensional model from well-known attributes, which can be "plugged" into existing navigation devices. Possible support of personalized route computation consists of adapted edge weights and a personalized objective function. \
MULTI-PERSPECTIVE DATA ANALYSIS OF DRIVERS´ NAVIGATION BEHAVIOUR
Due to technological innovation in the automotive sector, more and more vehicle data becomes available. Today, historical trip data can be analysed in order to personalise a vehicle´s navigation device. Thus, it is possible to incorporate drivers´ preferences in routing decisions. To describe drivers´ preferences in a navigation context, it is necessary to model driver behaviour appropriately. \ \ In this paper, we develop three models to depict different perspectives of driver behaviour in order to personalise navigation devices. The core point is to investigate edge utilization along the dimensions of time and space. Edges are the foundation for each navigation device´s digital roadmap. The first, time-oriented model examines the observed speeds on the edges. For the second, space-oriented model, a measure considering the entirety of edges is provided as to characterize the coverage of a driver´s mobility network. \ \ The third model analyses routes consisting of paths of edges. Correlation analysis shows that results obtained from the different models confirm each other. Thus, it is possible to build a well-founded two-dimensional model from well-known attributes, which can be "plugged" into existing navigation devices. Possible support of personalized route computation consists of adapted edge weights and a personalized objective function. \