Machine Learning Approaches for Anomaly Detection in IoT Networks
Gotte Ranjith Kumar, Anagha Deepak Kulkarni, B Santhosh Kumar, Navdeep Singh, Valureddi Revathi, T. Ch. Anil Kumar · 2024
The exploration paper explores the application of machine literacy ways for anomaly discovery within Internet of Effects (IoT) networks. With the rapid expansion of IoT bias, icing network security becomes decreasingly grueling. Traditional security measures frequently fall suddenly in detecting arising pitfalls and anomalies in the vast and dynamic IoT terrain. thus, this study investigates the efficacity of colorful machine learning algorithms in relating abnormal geste reflective of implicit security breaches or system malfunctions. Through a comprehensive review of the literature and empirical analysis, the paper examines the strengths and limitations of different machine learning approaches, including supervised, unsupervised, and semisupervised styles, in detecting anomalies within IoT networks. The findings give perceptivity into the feasibility and effectiveness of employing machine literacy for enhancing the security and trustability of IoT ecosystems.