Spatio-temporal outlier detection in streaming trajectory data
Máté Szekér · KTH Publication Database DiVA (KTH Royal Institute of Technology) · 2014
This thesis investigates the problem of detecting spatiotemporalanomalies in streamed trajectory data using both supervised and unsupervised algorithms. Anomaly detection can be understood as an unsupervised classification problem which requires the knowledge of the normal course of events or how the anomalies manifest themselves. To this end, an algorithm is proposed to identify the normative pattern in a streamed dataset. A non-parametric algorithm based on SVM is proposed for classifying trajectories basedon the explicit geometric properties alone. A parametric algorithm based on dynamic Markov Chains is presented for analysing trajectories based on their semantics. Two methods are proposed to fade the Markov Chains so that new behaviours can be modelled and obsolete behaviours can be forgotten. Both the non-parametric and parametric approaches are evaluated using both a synthetic and a real-life dataset. Fading the Markov Chains turns out to be essential in order to accurately detect anomalies in a dynamic dataset.