关键词: 特征抽取, 降维, 离群点检测

Abstract: This work addresses the problem of feature extraction for boosting the performance of outlier detectors in high-dimensional spaces. Recent years, the prominence of multidimensional data on which traditional detection techniques usually fail to work as expected due to the curse of dimensionality. This paper introduces an efficient feature extraction method can take advantage of both ERE and APCPA which brings nontrivial improvements in detection accuracy in outlier detection. Similar to APCDA, this approach performs engenspace decomposition as well as feature extraction on the weight-adjusted scatter matrices, and applies the strategy of ERE during the eigenspace regularization process to preserve the discriminant information. Experiments carried out on real datasets demonstrate the feasibility of feature extraction in outlier detection.

Key words: feature extraction, dimensionality reduction, outlier detection