Detection of variable length anomalous subsequences in data streams

We consider the problem of anomaly detection in data streams, which is the problem of extracting subsequences that do not match an expected behaviour. The main challenge for detecting anomalous subsequences from data streams in the existing techniques is to determine the lengths of the normal and anomalous subsequences. Therefore, creating a robust model for detecting the anomalous subsequences is of critical importance. In this paper, we propose an incremental algorithm based on the dynamic time warping technique to detect anomalous subsequences in data streams. The proposed algorithm is able to detect anomalous subsequences under relaxed length constrains of the normal and/or the anomalous subsequences. That is the proposed algorithm is able to detect variable length anomalous subsequences from among variable length normal sequences. The proposed robust model can be applied in areas such as system health monitoring, event detection in sensor networks, and detecting eco-system disturbances, etc. The cost of the proposed algorithm is linear with time and memory.