PROJECT TITLE :

A Systematic Approach to Clustering Whole Trajectories of Mobile Objects in Road Networks - 2017

ABSTRACT:

Most of mobile object trajectory clustering analysis to this point has been centered on clustering the location points or sub-trajectories extracted from trajectory knowledge. This paper presents TraceMob, a scientific approach to clustering whole trajectories of mobile objects traveling in road networks. TraceMob as a whole trajectory clustering framework has 3 unique features. Initial, we have a tendency to style a top quality measure for the distance between 2 whole trajectories. By quality, we mean that the distance measure will capture the advanced characteristics of trajectories as an entire including their varying lengths and their constrained movement within the road network area. Second, we have a tendency to develop an algorithm that transforms whole trajectories in a very road network area into multidimensional knowledge points in a euclidean house while preserving their relative distances within the remodeled metric house. This transformation allows us to effectively shift the clustering task for whole mobile object trajectories in the complicated road network house to the ancient clustering task for multidimensional knowledge in an exceedingly euclidean space. Third, we have a tendency to develop a cluster validation method for evaluating the clustering quality in each the remodeled metric area and therefore the road network space. Extensive experimental analysis with trajectories generated on real road network maps of different cities shows that TraceMob produces higher quality clustering results and outperforms existing approaches by an order of magnitude.