EXTENDED KALMAN FILTER IN BLIND SEPARATION OF NONSTATIONARY SIGNALS (ThuPmPO2)
Author(s) :
Slavica Todorovic-Zarkula (Technical School Nis, Serbia)
Branimir Todorovic (Faculty of Occupational Safety, Serbia)
Miomir Stankovic (Faculty of Occupational Safety, Serbia)
Vlastimir Pavlovic (Faculty of Electronics, Serbia)
Abstract : In this paper we deal with on-line algorithms for blind source separation using second order statistics. We briefly describe separating algorithms based on stochastic gradient, and natural gradient optimization method, and propose an on-line separating algorithm based on the application of the extended Kalman filter. Performance evaluation of the pro-posed algorithm has shown that extended Kalman filter ap-plied as an optimization algorithm can improve convergence speed and estimation accuracy of the separating algorithm.

Menu