Enhancing the Performance of LibSVM Classifier by Kernel F-Score Feature Selection

Medical Data mining is the search for relationships and patterns within the medical datasets that could provide useful knowledge for effective clinical decisions. The inclusion of irrelevant, redundant and noisy features in the process model results in poor predictive accuracy. Much research work in data mining has gone into improving the predictive accuracy of the classifiers by applying the techniques of feature selection. Feature selection in medical data mining is appreciable as the diagnosis of the disease could be done in this patient-care activity with minimum number of significant features. The objective of this work is to show that selecting the more significant features would improve the performance of the classifier. We empirically evaluate the classification effectiveness of LibSVM classifier on the reduced feature subset of diabetes dataset. The evaluations suggest that the feature subset selected improves the predictive accuracy of the classifier and reduce false negatives and false positives.