Enhancing Internet of Things Security Through Optimization Algorithms and Machine Learning

Abstract

IoT network traffic classification is an approach used to analyze IoT network traffic, revealing various network activities. The network traffic analysis process involves several steps: data input, preprocessing, feature extraction, classification, and performance analysis. Although various machine learning algorithms have been proposed in recent years, they have failed to achieve high accuracy and effectively extract features from datasets. This research aims to develop an algorithm that can extract features and achieve high accuracy in network traffic classification.To accomplish this, a hybrid optimization algorithm combining genetic algorithms and Particle Swarm Optimization (PSO) is proposed. This hybrid algorithm extracts features, which are then classified using Random Forest. The proposed model is implemented in Python, and its performance is evaluated in terms of accuracy, precision, and recall.