IDR @ IIT Bhubaneswar
Permanent URI for this communityhttps://idr.iitbbs.ac.in/handle/2008/1
Browse
4 results
Search Results
Item Robust incremental adaptive strategies for distributed networks to handle outliers in both input and desired data(2014) Sahoo U.K.; Panda G.; Mulgrew B.; Majhi B.Conventional distributed strategies based on least error squares cost function are not robust against outliers present in the desired and input data. This manuscript employs the generalized-rank (GR) technique as a cost function instead of least error squares cost function to control the effects of outliers present both in input and desired data. A novel indicator function and median based approach are proposed to decrease the computational complexity requirement at the sensor nodes. Further to increase the convergence speed a sign regressor GR norm is also proposed and used. Simulation based experiments show that the performance obtained using proposed methods is robust against outliers in the desired and input data. � 2013 Elsevier B.V.Item Development of robust distributed learning strategies for wireless sensor networks using rank based norms(2014) Sahoo U.K.; Panda G.; Mulgrew B.; Majhi B.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. � 2014 Elsevier B.V.Item QR-based incremental minimum-Wilcoxon-norm strategies for distributed wireless sensor networks(2012) Sahoo U.K.; Panda G.; Mulgrew B.; Majhi B.When outliers are present in the desired data, the conventional distributed adaptive estimation algorithms exhibit poor performance. To alleviate this shortcoming a novel distributed robust incremental strategy based on QR decomposition and the Wilcoxon score is proposed which convergence speed is faster than the other previous techniques. To demonstrate the potential of this algorithm simulation study is carried out for the distributed estimation of parameters in the presence of weak to strong outliers in the desired data. The results show that the performance of the new algorithm is robust against outliers compared to conventional incremental RLS algorithm. Further to achieve low communication overhead, a new scheme is introduced and its performance has been assessed through simulation study. It is observed that the proposed scheme even though exhibits slightly inferior performance but offers substantially reduction in terms of communication overhead. � 2012 Elsevier B.V. All rights reserved.Item New robust forecasting models for exchange rates prediction(2012) Majhi B.; Rout M.; Majhi R.; Panda G.; Fleming P.J.This paper introduces two robust forecasting models for efficient prediction of different exchange rates for future months ahead. These models employ Wilcoxon artificial neural network (WANN) and Wilcoxon functional link artificial neural network (WFLANN). The learning algorithms required to train the weights of these models are derived by minimizing a robust norm called Wilcoxon norm. These models offer robust exchange rate predictions in the sense that the training of weight parameters of these models are not influenced by outliers present in the training samples. The Wilcoxon norm considers the rank or position of an error value rather than its amplitude. Simulation based experiments have been conducted using real life data and the results indicate that both models, unlike conventional models, demonstrate consistently superior prediction performance under different densities of outliers present in the training samples. Further, comparison of performance between the two proposed models reveals that both provide almost identical performance but the later involved low computational complexity and hence is preferable over the WANN model. � 2012 Elsevier Ltd. All rights reserved.