A Fuzzy MLP Approach for Fault Diagnosis in Wireless Sensor Networks

Abstract

This paper presents a fault diagnosis protocol for wireless sensor networks (WSNs) based on neural network approach. A particle swarm optimization based fuzzy multilayer perceptron used in the fault detection and classification phase of the protocol. The proposed protocol handled the composite fault model such as hard permanent, soft permanent, intermittent, and transient fault. The performance of proposed algorithm evaluated by using the generic parameter such that detection accuracy, false alarm rate, and false positive rate. The simulation is carried out by the standard network simulator NS-2.35 and the performance is compared with the existing fault diagnosis protocols. The result shows that the proposed protocol performs superior than the existing protocols.