IOT NETWORK TRAFFIC CLASSIFICATION USING MACHINE LEARNING ALGORITHMS

In past years there is been a substantial rise in the number of IoT devices and the volume of data they generate.These IoT devices, often limited in terms of computational and power resources, are typically deployed withoutrobust security mechanisms, making them prime targets for cyberattacks. As the number of attack attempts onthese devices grows, conventional intrusion detection systems (IDS) face increasing challenges in promptlydetecting and responding to threats. Accurate classification of IoT-generated data is crucial for variousapplications including anomaly detection, intrusion prevention, resource management, and ensuring Quality ofService (QoS). This paper explores the application of machine learning (ML) techniques for classifying networktraffic in IoT environments. A range of ML models—such as Random Forest, Support Vector Machines, anddeep learning methods—are analyzed for their effectiveness in classifying IoT traffic based on network flowcharacteristics. The study focuses on key elements like feature selection, the datasets utilized, and the evaluationmetrics applied. The results highlight the potential of AI-driven approaches to enhance the accuracy of IoTtraffic classification, revealing the promise of intelligent systems in strengthening IoT network security