Privacy-preserving trajectory classification of driving trip data based on pattern discovery techniques

With the rapid growth of the remote sensing technology and its high adoption in automotive domain, identifying patterns in the context of driving trips becomes a promising and interesting area of research and application. Due to privacy concern, user location data in the moving object trajectory are to be anonymized before publishing. To classify the privacy-preserving driving trips in a set of recorded GPS tracks, this paper presents an information theoretic approach to characterize them based on their occurrences of frequently detected patterns. The patterns are discovered through a statistical significance test on a generated set of spatio-temporal data and its associated attributes that represent the characteristics of recorded GPS data. For evaluating the performance of the proposed approach, a real dataset with class information is tested to validate its classificatory power and compare with other approaches. The result indicates the approach is effective and efficient in achieving a good accuracy in the prediction of the class labels of the different driving trips based on the transformed set of attributes.