Robust incremental adaptive strategies for distributed networks to handle outliers in both input and desired data

Authors:
Upendra Kumar Sahoo;Ganapati Panda;Bernard Mulgrew;Babita Majhi
Affiliations:
-;-;-;-
Venue:
Signal Processing
Year:
2014

Citing 8
Cited 0

Robust regression and outlier detection

Robust regression and outlier detection
Adaptive filter theory (3rd ed.)

Adaptive filter theory (3rd ed.)
Convex Optimization

Convex Optimization
Incremental Adaptive Strategies Over Distributed Networks

IEEE Transactions on Signal Processing
Diffusion Recursive Least-Squares for Distributed Estimation Over Adaptive Networks

IEEE Transactions on Signal Processing
QR-based incremental minimum-Wilcoxon-norm strategies for distributed wireless sensor networks

Signal Processing
Preliminary Study on Wilcoxon Learning Machines

IEEE Transactions on Neural Networks
Consensus-Based Distributed Total Least Squares Estimation in Ad Hoc Wireless Sensor Networks

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.08

Visualization

Abstract

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.