Continuous Angle-based Outlier Detection on High-dimensional Data Streams

Abstract

Outlier detection over data streams is an increasingly important task in data mining. Traditional distance-based data stream outlier detection is unsuitable for high-dimensional data sets, since the discrimination of distances between different data points becomes rather poor in high dimensional space. ABOD (Angle-based Outlier Detection) is an effective approach to detecting outliers in high-dimensional space. In this paper, the problem of continuous ABOD over data streams is studied. Generally, only a few data objects may change their states during two consecutive timestamps. Therefore, we propose several incremental angle-based outlier detection approaches over data streams based on ABOD and its variants that provide visible speed-up without loss of accuracy. Firstly, the basic ideas of these incremental algorithms are introduced. Then, we explain the time complexity of them. Finally, we use synthetic data streams to prove their efficiency.