SVM and Naïve Bayes Network Traffic Classification using Correlation Information

Traffic classification is an automatic method that categorizes network traffic in line with varied parameters into variety of traffic categories. Many supervised classification algorithms and unsupervised clustering algorithms have been applied to categorise web traffic. Traditional traffic classification strategies embrace the port-based prediction strategies and payload-based deep examination strategies. In current network environment, the traditional strategies suffer from variety of sensible issues, such as dynamic ports and encrypted applications. In order to boost the classification accuracy, Support Vector Machine (SVM) and Naïve Bayes estimator is planned to categorise the traffic by application. In this, traffic flows are represented exploitation the discretized statistical options and flow correlation data is sculptured by bag-of-flow (BoF). This methodology uses flow statistical feature primarily based traffic classification to boost feature discretization. This approach for traffic classification improves the classification performance effectively by incorporating correlated data into the classification method. The experimental results show that the proposed theme will come through far better classification performance than existing progressive traffic classification strategies.