Robust fuzzy clustering neural network based on ε-insensitive loss function

Shitong Wang; Fu Lai Korris Chung; Deng Zhaohong; Hu Dewen

doi:10.1016/j.asoc.2006.04.008

Robust fuzzy clustering neural network based on ε-insensitive loss function

Shitong Wang
, Fu Lai Korris Chung
, Deng Zhaohong
, Hu Dewen

Research output: Journal article publication › Journal article › Academic research › peer-review

15 Citations (Scopus)

Abstract

In the paper, as an improvement of fuzzy clustering neural network FCNN proposed by Zhang et al., a novel robust fuzzy clustering neural network RFCNN is presented to cope with the sensitive issue of clustering when outliers exist. This new algorithm is based on Vapnik's ε-insensitive loss function and quadratic programming optimization. Our experimental results demonstrate that RFCNN has much better robustness for outliers than FCNN.

Original language	English
Pages (from-to)	577-584
Number of pages	8
Journal	Applied Soft Computing Journal
Volume	7
Issue number	2
DOIs	https://doi.org/10.1016/j.asoc.2006.04.008
Publication status	Published - 1 Mar 2007

Keywords

ε-Insensitive loss function
Fuzzy clustering
Neural networks
Outliers
Robustness

ASJC Scopus subject areas

Software

More information

10.1016/j.asoc.2006.04.008

Cite this

@article{c6431364770848c0813df04aae4b36d8,

title = "Robust fuzzy clustering neural network based on ε-insensitive loss function",

abstract = "In the paper, as an improvement of fuzzy clustering neural network FCNN proposed by Zhang et al., a novel robust fuzzy clustering neural network RFCNN is presented to cope with the sensitive issue of clustering when outliers exist. This new algorithm is based on Vapnik's ε-insensitive loss function and quadratic programming optimization. Our experimental results demonstrate that RFCNN has much better robustness for outliers than FCNN.",

keywords = "ε-Insensitive loss function, Fuzzy clustering, Neural networks, Outliers, Robustness",

author = "Shitong Wang and Chung, \{Fu Lai Korris\} and Deng Zhaohong and Hu Dewen",

year = "2007",

month = mar,

day = "1",

doi = "10.1016/j.asoc.2006.04.008",

language = "English",

volume = "7",

pages = "577--584",

journal = "Applied Soft Computing Journal",

issn = "1568-4946",

publisher = "Elsevier B.V.",

number = "2",

}

TY - JOUR

T1 - Robust fuzzy clustering neural network based on ε-insensitive loss function

AU - Wang, Shitong

AU - Chung, Fu Lai Korris

AU - Zhaohong, Deng

AU - Dewen, Hu

PY - 2007/3/1

Y1 - 2007/3/1

N2 - In the paper, as an improvement of fuzzy clustering neural network FCNN proposed by Zhang et al., a novel robust fuzzy clustering neural network RFCNN is presented to cope with the sensitive issue of clustering when outliers exist. This new algorithm is based on Vapnik's ε-insensitive loss function and quadratic programming optimization. Our experimental results demonstrate that RFCNN has much better robustness for outliers than FCNN.

AB - In the paper, as an improvement of fuzzy clustering neural network FCNN proposed by Zhang et al., a novel robust fuzzy clustering neural network RFCNN is presented to cope with the sensitive issue of clustering when outliers exist. This new algorithm is based on Vapnik's ε-insensitive loss function and quadratic programming optimization. Our experimental results demonstrate that RFCNN has much better robustness for outliers than FCNN.

KW - ε-Insensitive loss function

KW - Fuzzy clustering

KW - Neural networks

KW - Outliers

KW - Robustness

UR - https://www.scopus.com/pages/publications/33846833888

U2 - 10.1016/j.asoc.2006.04.008

DO - 10.1016/j.asoc.2006.04.008

M3 - Journal article

SN - 1568-4946

VL - 7

SP - 577

EP - 584

JO - Applied Soft Computing Journal

JF - Applied Soft Computing Journal

IS - 2

ER -

Robust fuzzy clustering neural network based on ε-insensitive loss function

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this