Identification of noise outliers in clustering by a fuzzy neural network

Surya Pemmaraju; Sunanda Mitra

Identification of noise outliers in clustering by a fuzzy neural network

Surya Pemmaraju, Sunanda Mitra

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

Since most real data sets, encountered in cluster analysis are contaminated with background noise or outliers, it is essential to detect and isolate these noise samples from the data set. A few noisy points can affect the clustering procedure by severely biasing the algorithm. An ideal solution to this problem is to identify all the outliers and form a separate noise cluster. In order to do so, we need a technique by which the noise points are automatically identified and removed from the pattern data. This paper presents a modified Adaptive Fuzzy Leader Clustering (AFLC) algorithm that has been used to detect and eliminate the outliers from the data structure and create a separate cluster of the outliers. The AFLC algorithm has an Adaptive Resonance Theory (ART) like architecture with fuzzy learning rules embedded into it.

Original language	English
Title of host publication	1993 IEEE International Conference on Fuzzy Systems
Publisher	Publ by IEEE
Pages	1269-1274
Number of pages	6
ISBN (Print)	0780306155
State	Published - 1993
Event	Second IEEE International Conference on Fuzzy Systems - San Francisco, CA, USA Duration: Mar 28 1993 → Apr 1 1993

Publication series

Name	1993 IEEE International Conference on Fuzzy Systems

Conference

Conference	Second IEEE International Conference on Fuzzy Systems
City	San Francisco, CA, USA
Period	03/28/93 → 04/1/93

Access to Document

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Identification of noise outliers in clustering by a fuzzy neural network'. Together they form a unique fingerprint.

Cite this

@inproceedings{f23ea1c89c3a459fbc549d80bb26bc0b,

title = "Identification of noise outliers in clustering by a fuzzy neural network",

abstract = "Since most real data sets, encountered in cluster analysis are contaminated with background noise or outliers, it is essential to detect and isolate these noise samples from the data set. A few noisy points can affect the clustering procedure by severely biasing the algorithm. An ideal solution to this problem is to identify all the outliers and form a separate noise cluster. In order to do so, we need a technique by which the noise points are automatically identified and removed from the pattern data. This paper presents a modified Adaptive Fuzzy Leader Clustering (AFLC) algorithm that has been used to detect and eliminate the outliers from the data structure and create a separate cluster of the outliers. The AFLC algorithm has an Adaptive Resonance Theory (ART) like architecture with fuzzy learning rules embedded into it.",

author = "Surya Pemmaraju and Sunanda Mitra",

year = "1993",

language = "English",

isbn = "0780306155",

series = "1993 IEEE International Conference on Fuzzy Systems",

publisher = "Publ by IEEE",

pages = "1269--1274",

booktitle = "1993 IEEE International Conference on Fuzzy Systems",

}

TY - GEN

T1 - Identification of noise outliers in clustering by a fuzzy neural network

AU - Pemmaraju, Surya

AU - Mitra, Sunanda

PY - 1993

Y1 - 1993

N2 - Since most real data sets, encountered in cluster analysis are contaminated with background noise or outliers, it is essential to detect and isolate these noise samples from the data set. A few noisy points can affect the clustering procedure by severely biasing the algorithm. An ideal solution to this problem is to identify all the outliers and form a separate noise cluster. In order to do so, we need a technique by which the noise points are automatically identified and removed from the pattern data. This paper presents a modified Adaptive Fuzzy Leader Clustering (AFLC) algorithm that has been used to detect and eliminate the outliers from the data structure and create a separate cluster of the outliers. The AFLC algorithm has an Adaptive Resonance Theory (ART) like architecture with fuzzy learning rules embedded into it.

AB - Since most real data sets, encountered in cluster analysis are contaminated with background noise or outliers, it is essential to detect and isolate these noise samples from the data set. A few noisy points can affect the clustering procedure by severely biasing the algorithm. An ideal solution to this problem is to identify all the outliers and form a separate noise cluster. In order to do so, we need a technique by which the noise points are automatically identified and removed from the pattern data. This paper presents a modified Adaptive Fuzzy Leader Clustering (AFLC) algorithm that has been used to detect and eliminate the outliers from the data structure and create a separate cluster of the outliers. The AFLC algorithm has an Adaptive Resonance Theory (ART) like architecture with fuzzy learning rules embedded into it.

UR - http://www.scopus.com/inward/record.url?scp=0027228725&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027228725

SN - 0780306155

T3 - 1993 IEEE International Conference on Fuzzy Systems

SP - 1269

EP - 1274

BT - 1993 IEEE International Conference on Fuzzy Systems

PB - Publ by IEEE

Y2 - 28 March 1993 through 1 April 1993

ER -