Model selection for anomaly detection

E. Burnaev, P. Erofeev, D. Smolyakov

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

21 Citations (Scopus)

Abstract

Anomaly detection based on one-class classification algorithms is broadly used in many applied domains like image processing (e.g. detection of whether a patient is 'cancerous' or 'healthy' from mammography image), network intrusion detection, etc. Performance of an anomaly detection algorithm crucially depends on a kernel, used to measure similarity in a feature space. The standard approaches (e.g. cross-validation) for kernel selection, used in two-class classification problems, can not be used directly due to the specific nature of a data (absence of a second, abnormal, class data). In this paper we generalize several kernel selection methods from binary-class case to the case of one-class classification and perform extensive comparison of these approaches using both synthetic and real-world data.

Original languageEnglish
Title of host publicationEighth International Conference on Machine Vision, ICMV 2015
EditorsAntanas Verikas, Petia Radeva, Dmitry Nikolaev
PublisherSPIE
Volume9875
ISBN (Electronic)9781510601161
DOIs
Publication statusPublished - 2015
Externally publishedYes
Event8th International Conference on Machine Vision, ICMV 2015 - Barcelona, Spain
Duration: 19 Nov 201521 Nov 2015

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume9875
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference8th International Conference on Machine Vision, ICMV 2015
Country/TerritorySpain
CityBarcelona
Period19/11/1521/11/15

Keywords

  • anomaly detection
  • empirical risk
  • kernel width
  • model selection
  • one-class classification
  • SVDD

Fingerprint

Dive into the research topics of 'Model selection for anomaly detection'. Together they form a unique fingerprint.

Cite this