Mining cell-id trajectory patterns by exploiting handoff features

Abstract

Existing trajectory pattern mining techniques work based on the prerequisite that the trajectory data contain explicit location information. However, it is difficult to collect such trajectory data from mobile phone users due to the high cost of continuously pinpointing the mobile phones' explicit locations. In this poster, we propose a method for mining trajectory patterns from cell-id trajectory data without explicit location information by exploiting handoff features. Experiment results based on real datasets have demonstrated the effectiveness of the proposed method.