Cargando…

Combining Entropy Measures for Anomaly Detection

The combination of different sources of information is a problem that arises in several situations, for instance, when data are analysed using different similarity measures. Often, each source of information is given as a similarity, distance, or a kernel matrix. In this paper, we propose a new clas...

Descripción completa

Detalles Bibliográficos
Autores principales: Muñoz, Alberto, Hernández, Nicolás, Moguerza, Javier M., Martos, Gabriel
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7513228/
https://www.ncbi.nlm.nih.gov/pubmed/33265787
http://dx.doi.org/10.3390/e20090698
_version_ 1783586339663380480
author Muñoz, Alberto
Hernández, Nicolás
Moguerza, Javier M.
Martos, Gabriel
author_facet Muñoz, Alberto
Hernández, Nicolás
Moguerza, Javier M.
Martos, Gabriel
author_sort Muñoz, Alberto
collection PubMed
description The combination of different sources of information is a problem that arises in several situations, for instance, when data are analysed using different similarity measures. Often, each source of information is given as a similarity, distance, or a kernel matrix. In this paper, we propose a new class of methods which consists of producing, for anomaly detection purposes, a single Mercer kernel (that acts as a similarity measure) from a set of local entropy kernels and, at the same time, avoids the task of model selection. This kernel is used to build an embedding of data in a variety that will allow the use of a (modified) one-class Support Vector Machine to detect outliers. We study several information combination schemes and their limiting behaviour when the data sample size increases within an Information Geometry context. In particular, we study the variety of the given positive definite kernel matrices to obtain the desired kernel combination as belonging to that variety. The proposed methodology has been evaluated on several real and artificial problems.
format Online
Article
Text
id pubmed-7513228
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-75132282020-11-09 Combining Entropy Measures for Anomaly Detection Muñoz, Alberto Hernández, Nicolás Moguerza, Javier M. Martos, Gabriel Entropy (Basel) Article The combination of different sources of information is a problem that arises in several situations, for instance, when data are analysed using different similarity measures. Often, each source of information is given as a similarity, distance, or a kernel matrix. In this paper, we propose a new class of methods which consists of producing, for anomaly detection purposes, a single Mercer kernel (that acts as a similarity measure) from a set of local entropy kernels and, at the same time, avoids the task of model selection. This kernel is used to build an embedding of data in a variety that will allow the use of a (modified) one-class Support Vector Machine to detect outliers. We study several information combination schemes and their limiting behaviour when the data sample size increases within an Information Geometry context. In particular, we study the variety of the given positive definite kernel matrices to obtain the desired kernel combination as belonging to that variety. The proposed methodology has been evaluated on several real and artificial problems. MDPI 2018-09-12 /pmc/articles/PMC7513228/ /pubmed/33265787 http://dx.doi.org/10.3390/e20090698 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Muñoz, Alberto
Hernández, Nicolás
Moguerza, Javier M.
Martos, Gabriel
Combining Entropy Measures for Anomaly Detection
title Combining Entropy Measures for Anomaly Detection
title_full Combining Entropy Measures for Anomaly Detection
title_fullStr Combining Entropy Measures for Anomaly Detection
title_full_unstemmed Combining Entropy Measures for Anomaly Detection
title_short Combining Entropy Measures for Anomaly Detection
title_sort combining entropy measures for anomaly detection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7513228/
https://www.ncbi.nlm.nih.gov/pubmed/33265787
http://dx.doi.org/10.3390/e20090698
work_keys_str_mv AT munozalberto combiningentropymeasuresforanomalydetection
AT hernandeznicolas combiningentropymeasuresforanomalydetection
AT moguerzajavierm combiningentropymeasuresforanomalydetection
AT martosgabriel combiningentropymeasuresforanomalydetection