Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector Machine

One-class support vector machine (OCSVM) is one of the most popular algorithms in the one-class classification problem, but it has one obvious disadvantage: it is sensitive to noise. In order to solve this problem, the fuzzy membership degree is introduced into OCSVM, which makes the samples with di...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiang He, Qingshuo Zhang, Hengyou Wang, Changlun Zhang
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2020/8853277
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849472865685995520
author Qiang He
Qingshuo Zhang
Hengyou Wang
Changlun Zhang
author_facet Qiang He
Qingshuo Zhang
Hengyou Wang
Changlun Zhang
author_sort Qiang He
collection DOAJ
description One-class support vector machine (OCSVM) is one of the most popular algorithms in the one-class classification problem, but it has one obvious disadvantage: it is sensitive to noise. In order to solve this problem, the fuzzy membership degree is introduced into OCSVM, which makes the samples with different importance have different influences on the determination of classification hyperplane and enhances the robustness. In this paper, a new calculation method of membership degree is proposed and introduced into the fuzzy multiple kernel OCSVM (FMKOCSVM). The combined kernel is used to measure the local similarity between samples, and then, the importance of samples is determined based on the local similarity between training samples, so as to determine the membership degree and reduce the impact of noise. The proposed membership requires only positive data in the calculation process, which is consistent with the training set of OCSVM. In this method, the noise has a smaller membership value, which can reduce the negative impact of noise on the classification boundary. Simultaneously, this method of calculating membership has a higher efficiency. The experimental results show that FMKOCSVM based on proposed local similarity membership is efficient and more robust to outliers than the ordinary multiple kernel OCSVMs.
format Article
id doaj-art-d9a7d400db9d43988e61c760eb3d1337
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-d9a7d400db9d43988e61c760eb3d13372025-08-20T03:24:22ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/88532778853277Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector MachineQiang He0Qingshuo Zhang1Hengyou Wang2Changlun Zhang3School of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaFaculty of Information Technology, Macau University of Science and Technology, Macao 999078, ChinaSchool of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Science, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaOne-class support vector machine (OCSVM) is one of the most popular algorithms in the one-class classification problem, but it has one obvious disadvantage: it is sensitive to noise. In order to solve this problem, the fuzzy membership degree is introduced into OCSVM, which makes the samples with different importance have different influences on the determination of classification hyperplane and enhances the robustness. In this paper, a new calculation method of membership degree is proposed and introduced into the fuzzy multiple kernel OCSVM (FMKOCSVM). The combined kernel is used to measure the local similarity between samples, and then, the importance of samples is determined based on the local similarity between training samples, so as to determine the membership degree and reduce the impact of noise. The proposed membership requires only positive data in the calculation process, which is consistent with the training set of OCSVM. In this method, the noise has a smaller membership value, which can reduce the negative impact of noise on the classification boundary. Simultaneously, this method of calculating membership has a higher efficiency. The experimental results show that FMKOCSVM based on proposed local similarity membership is efficient and more robust to outliers than the ordinary multiple kernel OCSVMs.http://dx.doi.org/10.1155/2020/8853277
spellingShingle Qiang He
Qingshuo Zhang
Hengyou Wang
Changlun Zhang
Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector Machine
Complexity
title Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector Machine
title_full Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector Machine
title_fullStr Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector Machine
title_full_unstemmed Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector Machine
title_short Local Similarity-Based Fuzzy Multiple Kernel One-Class Support Vector Machine
title_sort local similarity based fuzzy multiple kernel one class support vector machine
url http://dx.doi.org/10.1155/2020/8853277
work_keys_str_mv AT qianghe localsimilaritybasedfuzzymultiplekerneloneclasssupportvectormachine
AT qingshuozhang localsimilaritybasedfuzzymultiplekerneloneclasssupportvectormachine
AT hengyouwang localsimilaritybasedfuzzymultiplekerneloneclasssupportvectormachine
AT changlunzhang localsimilaritybasedfuzzymultiplekerneloneclasssupportvectormachine