Robust one-class SVM for fault detection

被引：58

作者：

Xiao, Yingchao ^{[1
]}

Wang, Huangang ^{[1
]}

Xu, Wenli ^{[1
]}

Zhou, Junwu ^{[2
]}

机构：

[1] Tsinghua Univ, Dept Automat, Inst Control Theory & Technol, Beijing 100084, Peoples R China

[2] State Key Lab Automat Min & Met Proc, Beijing 100160, Peoples R China

来源：

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS | 2016年 / 151卷

关键词：

Robust to outliers; One-class SVM; One-class classification; Fault detection; Tennessee Eastman Process; SUPPORT;

D O I：

10.1016/j.chemolab.2015.11.010

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

One-class SVM (OCSVM) has been widely adopted in many one-class classification (OCC) application fields. However, when there are outliers in OCC training samples, the OCSVM performance will degrade. In order to solve this problem, a new method is proposed in this paper. This method first identifies some "suspected outliers" and removes them so as to obtain the decision boundary enclosing the "cluster core". Then outliers are identified by this boundary and are removed from OCSVM training. The effectiveness of this proposed method is verified by experiments on UCI benchmark data sets and Tennessee Eastman Process data sets. (C) 2015 Elsevier B.V. All rights reserved.

引用

页码：15 / 25

页数：11

共 43 条

[1] A comprehensive survey of numeric and symbolic outlier mining techniques [J].

Agyemang, Malik ;

Barker, Ken ;

Alhajj, Rada .

INTELLIGENT DATA ANALYSIS, 2006, 10 (06) :521-538

[2]

[Anonymous], 2013, P ACM SIGKDD WORKSH

[3]

[Anonymous], 2002, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond

[4]

[Anonymous], 1997, P 14 INT C ONMACHINE

[5]

Barnett V., 1978, Outliers in statistical data

[6] Support vector clustering [J].

Ben-Hur, A ;

Horn, D ;

Siegelmann, HT ;

Vapnik, V .

JOURNAL OF MACHINE LEARNING RESEARCH, 2002, 2 (02) :125-137

[7] Probabilistic Novelty Detection With Support Vector Machines [J].

Clifton, Lei ;

Clifton, David A. ;

Zhang, Yang ;

Watkinson, Peter ;

Tarassenko, Lionel ;

Yin, Hujun .

IEEE TRANSACTIONS ON RELIABILITY, 2014, 63 (02) :455-467

[8]

Dahiel W.W., 1990, APPL NONPARAMETRIC S

[9]

Demsar J, 2006, J MACH LEARN RES, V7, P1

[10] A PLANT-WIDE INDUSTRIAL-PROCESS CONTROL PROBLEM [J].

DOWNS, JJ ;

VOGEL, EF .

COMPUTERS & CHEMICAL ENGINEERING, 1993, 17 (03) :245-255

← 1 2 3 4 5 →