Description

             In this paper, we provide a solution to effectively improve Naive Bayes Prediction-based traffic classifier with a small set of training samples.Here,Propose a new traffic classification scheme to utilize the information among the correlated traffic flows generated by an application.Statistical features are extracted and used to represent traffic flows.To apply Correlation based feature selection to remove irrelevant and redundant features from the feature set with high class-specific correlation and low inter correlation.Naive Bayes Prediction can effectively demonstrate the classification capability of various traffic classification methods.