IDR Logo

Please use this identifier to cite or link to this item: http://idr.iitbbs.ac.in/jspui/handle/2008/649
Title: Robust incremental adaptive strategies for distributed networks to handle outliers in both input and desired data
Authors: Sahoo U.K.
Panda G.
Mulgrew B.
Majhi B.
Keywords: Generalized rank norm
Incremental strategy
Minimum volume ellipsoid
Wilcoxon norm
Issue Date: 2014
Citation: 6
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. � 2013 Elsevier B.V.
URI: http://dx.doi.org/1016/j.sigpro.2013.09.006
http://10.10.32.48:8080/jspui/handle/2008/649
Appears in Collections:Research Publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.