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

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.