Outlier Detection over Distributed Trajectory Streams
Jiali Mao, Pengda Sun, Cheqing Jin, Aoying Zhou · Society for Industrial and Applied Mathematics eBooks · 2018
The wide deployments of GPS-embedded devices have produced multiple rapid voluminous trajectory streams, which needs to be analyzed to extract abnormal behaviors of moving objects in real-time. To date, outlier detection over distributed trajectory streams has not received enough focuses due to the constraint factors like skewness distribution and evolving nature of trajectory data, and on-the-fly execution requirement with minimal communication cost. In this paper, we present the first scalable decentralized outlier detection framework over distributed trajectory streams, called ODDTS. It consists of remote site processing and coordinator processing, with the aim of continuously providing feature-grouping based outliers detection over distributed trajectory streams. Extensive experiments over real data demonstrate high detecting validity, less communication cost and linear scalability of ODDTS method for online identifying outliers upon distributed trajectory streams.