Data aggregation in wireless sensor network using SVM-based failure detection and loss recovery
S Kamalesh, Pawan Kumar · Journal of Experimental & Theoretical Artificial Intelligence · 2016
In wireless sensor network, data aggregation can cause increased transmission overhead, failures, data loss and security-related issues. Earlier works did not concentrate on both fault management and loss recovery issues. In order to overcome these drawbacks, in this paper, a reliable data aggregation scheme is proposed that uses support vector machine (SVM) for performing failure detection and loss recovery. Initially, a group head, selected based on node connectivity, splits the nodes into clusters based on their location information. In each cluster, the cluster member with maximum node connectivity is chosen as the cluster head. When the aggregator receives data from the source, it identifies node failures in the received data by classifying the faulty data using SVM. Furthermore, a reserve node-based fault recovery mechanism is developed to prevent data loss. Through simulations, we show that the proposed technique minimises the transmission overhead and increases reliability.