Feature Selection and Dynamic Network Traffic Congestion Classification based on Machine Learning for Internet of Things

Abstract

The network traffic congestion classifier is essential for network monitoring systems. Network traffic characterization is a methodology to classify traffic into several classes supporting various attributes. In this paper, payload-based classification is suggested for network traffic characterization. It has a broad scope of utilization like network security assessment, intrusion identification, QoS supplier, et cetera; furthermore, it has significance in investigating different suspicious movements in the network. Numerous supervised classification techniques like Support Vector Machines and unsupervised clustering methods like K-Means connected are used in traffic classification. In current network conditions, minimal supervised data and unfamiliar applications influence the usual classification procedure's performance. This paper implements a methodology for network traffic classification using clustering, feature extraction, and variety for the Internet of Things (IoT). Further, K-Means is used for network traffic clustering datasets, and feature extraction is performed on grouped information. KNN, Naïve Bayes, and Decision Tree classification methods classify network traffic because of extracted features, which presents a performance measurement between these classification algorithms. The results discuss the best machine learning algorithm for network congestion classification. According to the outcome, clustering (k-means) with network classification (Decision Tree) generates a higher accuracy, 86.45 %, than other clustering and network classification