Automatic clustering of generalized regression neural network by similarity index based fuzzy c-means clustering

Hafizah Husain, Marzuki Khalid, Rubiyah Yusof

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

In general regression neural networks (GRNN), one drawback is that the number of training vectors is proportional to the number of hidden nodes, thus a large number of training vectors will produce a larger architecture, which is a major disadvantage for many applications. In this paper we proposed an efficient clustering technique referred to as 'similarity index fuzzy c-means clustering'. This technique uses the conventional fuzzy c-means clustering preceded by a technique based on similarity indexing to automatically cluster input data which are relevant to the system. The technique employs a one-pass similarity measures on the data to calculate the similarity index. This index indicates the degree of similarity in which data will be clustered. Similar data then undergoes fuzzy c-means iterative process to determine their cluster centers. We applied the technique for system identification and modeling and found the results to be encouraging and efficient.

Original languageEnglish
Title of host publicationIEEE Region 10 Annual International Conference, Proceedings/TENCON
VolumeB
Publication statusPublished - 2004
EventIEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering - Chiang Mai
Duration: 21 Nov 200424 Nov 2004

Other

OtherIEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering
CityChiang Mai
Period21/11/0424/11/04

Fingerprint

Neural networks
Identification (control systems)

Keywords

  • Fuzzy c-means
  • Optimal clustering
  • Similarity measures

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Husain, H., Khalid, M., & Yusof, R. (2004). Automatic clustering of generalized regression neural network by similarity index based fuzzy c-means clustering. In IEEE Region 10 Annual International Conference, Proceedings/TENCON (Vol. B)

Automatic clustering of generalized regression neural network by similarity index based fuzzy c-means clustering. / Husain, Hafizah; Khalid, Marzuki; Yusof, Rubiyah.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. B 2004.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Husain, H, Khalid, M & Yusof, R 2004, Automatic clustering of generalized regression neural network by similarity index based fuzzy c-means clustering. in IEEE Region 10 Annual International Conference, Proceedings/TENCON. vol. B, IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering, Chiang Mai, 21/11/04.
Husain H, Khalid M, Yusof R. Automatic clustering of generalized regression neural network by similarity index based fuzzy c-means clustering. In IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. B. 2004
Husain, Hafizah ; Khalid, Marzuki ; Yusof, Rubiyah. / Automatic clustering of generalized regression neural network by similarity index based fuzzy c-means clustering. IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. B 2004.
@inproceedings{0cd6cce7f6bc417486610269ec0d04c1,
title = "Automatic clustering of generalized regression neural network by similarity index based fuzzy c-means clustering",
abstract = "In general regression neural networks (GRNN), one drawback is that the number of training vectors is proportional to the number of hidden nodes, thus a large number of training vectors will produce a larger architecture, which is a major disadvantage for many applications. In this paper we proposed an efficient clustering technique referred to as 'similarity index fuzzy c-means clustering'. This technique uses the conventional fuzzy c-means clustering preceded by a technique based on similarity indexing to automatically cluster input data which are relevant to the system. The technique employs a one-pass similarity measures on the data to calculate the similarity index. This index indicates the degree of similarity in which data will be clustered. Similar data then undergoes fuzzy c-means iterative process to determine their cluster centers. We applied the technique for system identification and modeling and found the results to be encouraging and efficient.",
keywords = "Fuzzy c-means, Optimal clustering, Similarity measures",
author = "Hafizah Husain and Marzuki Khalid and Rubiyah Yusof",
year = "2004",
language = "English",
volume = "B",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

}

TY - GEN

T1 - Automatic clustering of generalized regression neural network by similarity index based fuzzy c-means clustering

AU - Husain, Hafizah

AU - Khalid, Marzuki

AU - Yusof, Rubiyah

PY - 2004

Y1 - 2004

N2 - In general regression neural networks (GRNN), one drawback is that the number of training vectors is proportional to the number of hidden nodes, thus a large number of training vectors will produce a larger architecture, which is a major disadvantage for many applications. In this paper we proposed an efficient clustering technique referred to as 'similarity index fuzzy c-means clustering'. This technique uses the conventional fuzzy c-means clustering preceded by a technique based on similarity indexing to automatically cluster input data which are relevant to the system. The technique employs a one-pass similarity measures on the data to calculate the similarity index. This index indicates the degree of similarity in which data will be clustered. Similar data then undergoes fuzzy c-means iterative process to determine their cluster centers. We applied the technique for system identification and modeling and found the results to be encouraging and efficient.

AB - In general regression neural networks (GRNN), one drawback is that the number of training vectors is proportional to the number of hidden nodes, thus a large number of training vectors will produce a larger architecture, which is a major disadvantage for many applications. In this paper we proposed an efficient clustering technique referred to as 'similarity index fuzzy c-means clustering'. This technique uses the conventional fuzzy c-means clustering preceded by a technique based on similarity indexing to automatically cluster input data which are relevant to the system. The technique employs a one-pass similarity measures on the data to calculate the similarity index. This index indicates the degree of similarity in which data will be clustered. Similar data then undergoes fuzzy c-means iterative process to determine their cluster centers. We applied the technique for system identification and modeling and found the results to be encouraging and efficient.

KW - Fuzzy c-means

KW - Optimal clustering

KW - Similarity measures

UR - http://www.scopus.com/inward/record.url?scp=27944468751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27944468751&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:27944468751

VL - B

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

ER -