Similarity Kernels for Nearest Neighbor-Based Outlier Detection

Outlier detection is an important research topic that focuses on detecting abnormal information in data sets and processes. This paper addresses the problem of determining which class of kernels should be used in a geometric framework for nearest neighbor-based outlier detection. It introduces the c...

Full description

Saved in:
Bibliographic Details
Published inAdvances in Intelligent Data Analysis IX pp. 159 - 170
Main Authors Ramirez-Padron, Ruben, Foregger, David, Manuel, Julie, Georgiopoulos, Michael, Mederos, Boris
Format Book Chapter
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2010
SeriesLecture Notes in Computer Science
Subjects
nearest neighbors
outlier detection
similarity kernels
similarity scores
Online AccessGet full text

Cover

More Information
Summary:Outlier detection is an important research topic that focuses on detecting abnormal information in data sets and processes. This paper addresses the problem of determining which class of kernels should be used in a geometric framework for nearest neighbor-based outlier detection. It introduces the class of similarity kernels and employs it within that framework. We also propose the use of isotropic stationary kernels for the case of normed input spaces. Two definitions of similarity scores using kernels are given: the k-NN kernel similarity score (kNNSS) and the summation kernel similarity score (SKSS). The paper concludes with preliminary experimental results comparing the performance of kNNSS and SKSS for outlier detection on four data sets. SKSS compared favorably to kNNSS.
ISBN:9783642130618
3642130615
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-642-13062-5_16