Secured Aggregation Based on Learning Procedure in Wireless Sensor Networks

Wireless Sensor Networks (WSNs) is one of the important areas in research center, causing major impact on technology improvement. In a Wireless Sensor Network, attacks are usually based on the signature in a centralized approach which detects the anomalies. In this paper the existing Extended Kalman Filter (EKF) mechanism that can be used to find the malicious node which sends the false information with the constant threshold value. Each node in a network contains the normal value if any emergency event occurs then there will be a change in value of node. For this purpose system monitoring module (SMM) can be used, that will oversees the network behavior. In this paper, we proposed k-nearest neighbor (k-NN) algorithm for secure wireless network. This algorithm uses two methods such as distance and density in addition to this it also uses cluster summary aggregated from local and parent node to the base station which is used to identify the anomalies. We use centralized detection is useful for network anomalies, while network data can be piggybacked in packets, providing the centralized anomaly detector with a comprehensive view of network state.