AN ENSEMBLE MODEL WITH FEATURE SELECTION TECHNIQUE FOR CLASSIFICATION OF LUNG CANCER DISEASE

Cancer is very serious and dangerous diseases facing by many people in the world. Lung cancer is one of the most dangerous cancer types which directly affected to the human life. These diseases can spread worldwide by uncontrolled cell growth in the tissues of the lung. An identification and classification of lung cancer is very necessary to diagnosis of lung cancer disease. In this paper we have analyzed the lung cancer prediction using data mining based classification algorithm such as J48, LMT, REP Tree, CART, Bayes Net, Naïve Bayes, SVM and its ensemble model. The proposed ensemble of Naïve Bayes and LMT gives better classification accuracy compare to others. We have also applied the various ranking based feature selection techniques on proposed ensemble model and achieved better classification accuracy with less number of features and less computational time.