Online novelty detection on temporal sequences

Junshui Ma, Simon Perkins
2003 Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '03  
Novelty detection, or anomaly detection, on temporal sequences has increasingly attracted attention from researchers in different areas. In this paper, we present a new framework for online novelty detection on temporal sequences. This framework includes a mechanism for associating each detection result with a confidence value. Based on this framework, we develop a concrete online detection algorithm, by modeling the temporal sequence using an online support vector regression algorithm.
more » ... nts on both synthetic and real world data are performed to demonstrate the promising performance of our proposed detection algorithm. The main contributions of this paper are (a) It proposes an online novelty detection framework for temporal sequences. This online framework is capable of associating a confidence level with each detection result. (b) It proposes a concrete online novelty detection algorithm based on the framework, and describes experiments to test the new algorithm.
doi:10.1145/956750.956828 dblp:conf/kdd/MaP03 fatcat:dos7xoiwmrfkfh7sh5syzxr7iq