One-Class Principal Component Classifier for anomaly detection in wireless sensor network

To ensure the quality of data collected by sensor networks, misbehavior in measurements should be detected efficiently and accurately in each sensor node before relying the data to the base station. In this paper, a novel anomaly detection model is proposed based on the lightweight One Class Principal Component Classifier for detecting anomalies in sensor measurements collected by each node locally. The efficiency and accuracy of the proposed model are demonstrated using two real life wireless sensor networks datasets namely; labeled dataset (LD) and Intel Berkeley Research Lab dataset (IBRL). The simulation results show that our model achieves higher detection accuracy with relatively lower false alarms. Furthermore, the proposed model incurs less energy consumption by reducing the computational complexity in each node.