Indian Journal of Automation and Artificial Intelligence

Open Access Open Access  Restricted Access Subscription Access

Clustering of Disease Data Base using Self Organizing Maps and Logical Inferences


Affiliations
1 Department of Statistics, NIRT(ICMR), Chennai, India
2 Department of Mathematics, Ethiraj College For Women, Chennai, India
 

Disease classification requires an expertise in handling the uncertainty. ANNs emerge as a powerful tool in this regard. ANNs have featured in a wide range of applications with promising results in biomedical sciences. The self-organized maps (SOM) use unsupervised learning to produce low dimensional discretized representation of the input space. SOMs are different from other neural networks in the sense that they use neighborhood function to preserve the topological properties of the input space. This paper compares Kohanen's SOM network with other clustering method. The SOM gives faster and accurate results in clustering the data. The results were presented and compared.

Keywords

Medical Diagnosis, Artificial Intelligence (AI), Neural Network, Self Organizing Map(SOM), Best Matching Unit(BMU),Tuberculosis (TB)
User
Notifications

  • Brause, R.W.,(2001). Medical analysis and diagnosis by neural networks.Proceeings of Second International Symposium on Medical data Analysis. Oct 08-09, Springer-Verlag, Lonon, UK.,pp: 1-13

  • Gordon A.D, (1994). Identifying Genuine Clusters in a Classification, Computational Statistics and Data Analysis 18 ,pp: 561-581

  • Hartigan J. A & Wong M. A, (1979). A K-means Clustering Algorithm, Applied Statistics,28,pp: 100-108

  • Kohonen, T. (1982) Self-organizing formation of topologically correct feature maps, Biological Cyberbetics. Volume 43, 1982, pp:59-96

  • Kohonen, T. (1995) Self-Organizing Maps, Springer Series in Information Sciences, Vol. 30, Springer, Berlin, Heidelberg, New York, 1995

  • Lippman R.P (1987) An Introduction to Computing with Neural Nets, IEEE, ASSP Magazine, April 1987, pp: 4-22

  • Spath H (1980) Cluster Analysis Algorithms,Chichester, UK, 1980

  • Ultsch A &Siemon H. P(1989) Exploratory Data Analysis: Using Kohonen Networks on Transputers, Research Report No. 329, University of Dortmund, 1989

  • Victor Alves, Paulo Novais, Luis Nelas, Moreira Maia & Victor Ribeiro (2003) Case based reasoning versus artificial neural networks in medical diagnosis. Proceedings of IASTED International Conference Artificial Intelligence and Applications. pp: 1-5


Abstract Views: 636

PDF Views: 354




  • Clustering of Disease Data Base using Self Organizing Maps and Logical Inferences

Abstract Views: 636  |  PDF Views: 354

Authors

P. Venkatesan
Department of Statistics, NIRT(ICMR), Chennai, India
M. Mullai
Department of Mathematics, Ethiraj College For Women, Chennai, India

Abstract


Disease classification requires an expertise in handling the uncertainty. ANNs emerge as a powerful tool in this regard. ANNs have featured in a wide range of applications with promising results in biomedical sciences. The self-organized maps (SOM) use unsupervised learning to produce low dimensional discretized representation of the input space. SOMs are different from other neural networks in the sense that they use neighborhood function to preserve the topological properties of the input space. This paper compares Kohanen's SOM network with other clustering method. The SOM gives faster and accurate results in clustering the data. The results were presented and compared.

Keywords


Medical Diagnosis, Artificial Intelligence (AI), Neural Network, Self Organizing Map(SOM), Best Matching Unit(BMU),Tuberculosis (TB)

References