Development of robust distributed learning strategies for wireless sensor networks using rank based norms

Distributed signal processing is an important area of research in wireless sensor networks (WSNs) which aims to increase the lifetime of the entire network. In WSNs the data collected by nodes are affected by both additive white Gaussian noise (AWGN) and impulsive noise. The classical square error based distributed techniques used for parameter estimation are sensitive to impulse noise and provide inferior estimation performance. In this paper, novel robust distributed learning strategies are proposed based on the Wilcoxon norm and its variants. The Wilcoxon norm based learning strategy provides very slow convergence speed. In order to circumvent this improved distributed learning strategies based on the notion of the Wilcoxon norm are proposed for different types of environmental data. These algorithms require less computational complexity compared to previous ones. In addition these algorithms offer faster convergence rate in the presence of biased input data. Simulation based experiments demonstrate that the proposed techniques provide faster convergence speed than the previously reported techniques in both biased and unbiased input data.