Feature Grouping-based Outlier Detection upon Streaming Trajectories (Extended abstract)

The existing detection techniques are not tailored to identify the outlier which is close to its neighbors according to some features, but behaves significantly distinct from its neighbors in terms of the other features. In this paper, we propose a feature grouping-based mechanism, and then present two algorithms to detect outliers (TF-outlier and MO-outlier) upon trajectory streams. The effectiveness and efficiency of our proposal are validated by the experiments on real trajectory data.