Enhanced Elman Spike Neural Network fostered intrusion detection framework for securing wireless sensor network

One of the essential elements of the cyber-physical system is the wireless sensor network (WSN), which is a multi-hop, self-organizing wireless network made up of numerous stationary or moving sensors. It collaborates, collects, processes and transmits the information of objects sensed in the geographic area enclosed by the network, and transmits this data to the network user. Several common WSN attacks exist, including Blackhole, Gray hole, Flooding, and Scheduling, which can quickly harm the WSN system. Owing to sensor node's constrained resources, extensive redundancy, and strong correlation of network data, the intrusion detection schemes for WSN have low detection rate, high rates of false alarms, and substantial calculation overhead. To overwhelm these issues, an Enhanced Elman Spike Neural Network fostered Intrusion detection framework (IDS-WSN-EESNN) is proposed in this manuscript. First, the Balancing Composite Motion Optimization Algorithm (BCMOA) is employed to lessen the data dimension and computational overhead in original traffic data's feature space. Then, EESNN is applied to identify different network attacks. WSN-DS dataset based the experimental results prove that the proposed IDS-WSN-EESNN approach attains 30.42%, 28.24%, 23.03% and 32.63% higher accuracy, 95.02%, 91.52%, 92.67% and 92.9% lower error rate and 25.13%, 21.75%, 27.54% and 23.08% lower computation time compared with the existing methods.