Genetic algorithm based CFS and naive bayes algorithm to enhance the predictive accuracy

Abstract

For better classification accuracy in the area of data mining, feature selection techniques are applied to medical data sets. In this work genetic algorithm and Particle Swarm Optimization search techniques and correlation based feature selection is used for evaluation and naive bayes classifier for classification purpose. The hepatitis data set, taken from the UCI machine learning repository, is applied in this work. Accuracy and time is the outcome of the classification model and also various measures like sensitivity, specificity, precision and recall are also calculated.