Modified support vector novelty detector using training data with outliers

This paper proposes the modified support vector novelty detector (SVND) for novelty detection which addresses the problem of detecting outliers from normal data patterns. While the original SVND [Neural Comput. 13 (2001) 1443] attempts to estimate a function to separate the region of normal data patterns from that of outliers based on normal data patterns, the modified SVND generalizes it to take into account the outliers in the training set by separating both the normal data patterns and the outliers from the origin with maximal margin. By examining several artificial and real data sets. the experiment shows that there is significant improvement in the performance of the modified SVND in comparison with the original SVND. Furthermore, the original SVND is sensitive to the outliers, with the performance deteriorating when outliers are included in the training set. (C) 2003 Published by Elsevier B.V.