Application of K-Means and Genetic Algorithms for Dimension Reduction by Integrating SVM for Diabetes Diagnosis

Vast amount of data available in health care industry is difficult to handle, hence mining is necessary to find the necessary pattern and relationship among the features available. Medical data mining is one major research area where evolutionary algorithms and clustering algorithms play a vital role. In this research work, K-Means is used for removing the noisy data and genetic algorithms for finding the optimal set of features with Support Vector Machine (SVM) as classifier for classification. The experimental result proves that, the proposed model has attained an average accuracy of 98.79% for reduced dataset of Pima Indians Diabetes from UCI repository. It also shows that the proposed method has attained better results compared to modified K-Means clustering based data preparation method with SVM classifier (96.71%) as described in the literature