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

摘要

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.