Performance Evaluation of Multistage Classifier

Ensemble of classifiers is one of the most researched methods in pattern classification in recency. It’s a well-known fact that multiple phases for evaluation provides more accuracy. In this paper we proposed a multistage classifier approach where we are applying three supervised classifiers for the classification in pattern recognition. Three Classifiers are Multilayer Perceptron (MLP), K-Nearest Neighbour (K-NN) and Naive Bayes Classifier (NB). After evaluation, we realized that as a single stage classifier MLP provides minimum misclassification. When we pass the database through a three stage classifier in the given order, firstly MLP, secondly NB and finally KNN, it provides better result with 3.12% misclassification rate. Keywords—Classification, K-Nearest Neighbour (KNN), Multilayer Perceptron (MLP), Naive Bayes Classifier (NB).