Ensemble classifier model for health care informatics

Abstract EN

In many circumstances, if a single classifier has a particular level of performance on a problem, a committee of such classifiers will have a better performance on that problem.

Ensemble techniques have been successfully applied in the context of supervised learning to increase the accuracy and stability of classification.

Recently, researches have demonstrated that, by combining a collection of dissimilar algorithms, an improved solution can be obtained more than with a single feature-classifier alone.

The purpose of this study is to demonstrate the benefit of combining common data mining techniques for the classification of benign and malignant patterns for breast cancer disease.

Three classifiers techniques (Naive Bayes Classifier, Rule Based Classifier and the k-Nearest Neighbors Classifier) are the parameters to construct the Ensemble Classifier Model where the accuracy is the measurement tool to e\’aluate the model.