A heuristic method for finding the optimal number of clusters with application in medical data

Author

Bayati, Hamidreza ; Davoudi, Heydar ; Fatemizadeh, Emad

Author_Institution

Biological Signal and Image Processing Laboratory (BiSIPL), Department of Electrical Engineering, Sharif University of Technology, Iran

fYear

2008

fDate

20-25 Aug. 2008

Firstpage

4684

Lastpage

4687

Abstract

In this paper, a heuristic method for determining the optimal number of clusters is proposed. Four clustering algorithms, namely K-means, Growing Neural Gas, Simulated Annealing based technique, and Fuzzy C-means in conjunction with three well known cluster validity indices, namely Davies-Bouldin index, Calinski-Harabasz index, Maulik-Bandyopadhyay index, in addition to the proposed index are used. Our simulations evaluate capability of mentioned indices in some artificial and medical datasets.

Keywords

Biomedical imaging; Clustering algorithms; Image processing; Laboratories; Medical simulation; Partitioning algorithms; Scattering; Signal processing; Simulated annealing; cluster validity index; fuzzy c-means; growing neural gas; k-means; simulated annealing; Algorithms; Artificial Intelligence; Cluster Analysis; Computer Simulation; Data Interpretation, Statistical; Fuzzy Logic; Gene Expression Profiling; Humans; Medical Informatics; Models, Genetic; Models, Statistical; Models, Theoretical; Pattern Recognition, Automated;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE

Conference_Location

Vancouver, BC

ISSN

1557-170X

Print_ISBN

978-1-4244-1814-5

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/IEMBS.2008.4650258

Filename

4650258