An Anomaly Detection Scheme Based on Machine Learning for WSN

Security is one of the most important research issues in wireless sensor network (WSN). A Machine Learning (ML) based anomaly detection scheme is proposed, where Bayesian classification algorithm is used to detect anomalous nodes. By the tool NS2, a small number of samples are given and learned, and intrusion detection rules are built, network attack traffic is generated and simulated. And based on this, its detection rate, average detection rate, false positive rate and average false positive rate are evaluated. Experimental results demonstrate that the scheme achieves higher accuracy rate of detection and lower false positive rate than the current important intrusion detection schemes of WSN.