Improving the Accuracy of Classifier with the Ensemble of Centroid Based Algorithms

Abstract

Classification accuracy improvement is an essential process in data analysis problems and large amount of data generated in extra bytes per year are produced by many real world application. There are many enhancement techniques to address the problems as regarding the classification performance, have been proposed previously by many researchers. However, the issues of mislabeling problems that depend on noise dataset, class imbalanced problems and big data problems still have been a challenge of today’s research. In data mining process, the ensemble of classifiers are known to increase the accuracy of single classifiers by combining several of them, but neither of these learning techniques alone solve the above problems. Therefore, this paper analyzes on the problems of data and emphasizes on the ensemble techniques by using centroid based clustering methods. In order to get the more accuracy, filtering process is used by enhancing the simple ensemble ways of classifier.