Please use this identifier to cite or link to this item:
|Title:||Robust incremental adaptive strategies for distributed networks to handle outliers in both input and desired data|
|Keywords:||Generalized rank norm|
Minimum volume ellipsoid
|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.|
|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.