Detecting Traffic Anomalies in Urban Areas Using Taxi GPS Data

Abstract

Large-scale GPS data contain hidden information and provide us with the opportunity to discover knowledge that may be useful for transportation systems using advanced data mining techniques. In major metropolitan cities, many taxicabs are equipped with GPS devices. Because taxies operate continuously for nearly 24 hours per day, they can be used as reliable sensors for the perceived traffic state. In this paper, the entire city was divided into subregions by roads, and taxi GPS data were transformed into traffic flow data to build a traffic flow matrix. In addition, a highly efficient anomaly detection method was proposed based on wavelet transform and PCA (principal component analysis) for detecting anomalous traffic events in urban regions. The traffic anomaly is considered to occur in a subregion when the values of the corresponding indicators deviate significantly from the expected values. This method was evaluated using a GPS dataset that was generated by more than 15,000 taxies over a period of half a year in Harbin, China. The results show that this detection method is effective and efficient.