### 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 language | English |
---|---|

Title of host publication | IEEE Region 10 Annual International Conference, Proceedings/TENCON |

Volume | B |

Publication status | Published - 2004 |

Event | IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering - Chiang Mai Duration: 21 Nov 2004 → 24 Nov 2004 |

### Other

Other | IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering |
---|---|

City | Chiang Mai |

Period | 21/11/04 → 24/11/04 |

### Fingerprint

### Keywords

- Fuzzy c-means
- Optimal clustering
- Similarity measures

### ASJC Scopus subject areas

- Engineering(all)

### Cite this

*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.

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

*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.

}

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 -