Fault Diagnosis Based on Support Vector Machines and Convex Hulls

被引：0

作者：

Han Li ^{[1
]}

Zheng Yuan-yuan ^{[1
]}

Dong Ru-yi ^{[1
]}

机构：

[1] NE Dianli Univ, Sch Automat Engn, Jilin, Peoples R China

来源：

PROCEEDINGS OF THE 2009 WRI GLOBAL CONGRESS ON INTELLIGENT SYSTEMS, VOL III | 2009年

关键词：

support vector machines; convex hull; fault diagnosis;

D O I：

10.1109/GCIS.2009.312

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Through the analysis of support vector machines principle, the theory of convex hull based on support vector machines is used for the fault diagnosis, with acme-set of convex hull replacing the entire sample set to train, then, use actual data to do the simulation. The simulation results show that this method has the same performance as learning by the entire sample set, but reduces the storage space and improves the learning speed.

引用

页码：534 / 538

页数：5

共 8 条

[1]

Cristianini N., 2000, INTRO SUPPORT VECTOR

[2] Mixture of experts for classification of gender, ethnic origin, and pose of human faces [J].

Gutta, S ;

Huang, JRJ ;

Jonathon, P ;

Wechsler, H .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (04) :948-960

[3] Comments on password-based private key download protocol of NDSS'99 [J].

Kim, S ;

Kim, B ;

Park, S .

ELECTRONICS LETTERS, 1999, 35 (22) :1937-1938

[4] Nonlinear kernel-based statistical pattern analysis [J].

Ruiz, A ;

López-de-Teruel, PE .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (01) :16-32

[5] Support vector machine techniques for nonlinear equalization [J].

Sebald, DJ ;

Bucklew, JA .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2000, 48 (11) :3217-3226

[6] Support vector machine for regression and applications to financial forecasting [J].

Trafalis, TB ;

Ince, H .

IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL VI, 2000, :348-353

[7]

Vapnik V.N., 1963, Automation and Remote Control, V24, P774

[8] An overview of statistical learning theory [J].

Vapnik, VN .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05) :988-999

← 1 →