A fuzzy MLP approach for fault diagnosis in wireless sensor networks

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 is used in the fault detection and classif cation phase of the protocol. The proposed protocol considers the composite fault model such as hard permanent, soft permanent, intermittent, and transient fault. The performance of the proposed algorithm is evaluated by using generic parameters such as detection accuracy, false alarm rate, and false positive rate. The simulation is carried out by 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.