IJIES - International Journal of Information Engineering and Science - Vol. 1 Issue. 1 (2024)

IoT, Anomaly Detection, Machine Learning, K-Nearest Neighbors, Random Forest, Real-Time Detection

James Anderson, Emily Johnson, Michael Brown,

Abstract

The increase in connected IoT devices causes increased vulnerability to cyber attacks. This research develops a hybrid machine learning model to detect real-time anomalies in IoT networks. This model combines the K-Nearest Neighbors (KNN) and Random Forest (RF) algorithms to increase accuracy and efficiency. Evaluation was carried out using the UNSW-NB15 dataset to test model performance. The results show that this hybrid approach is able to detect anomalies with high accuracy and a low false positive rate.