سال انتشار: ۱۳۸۴

محل انتشار: سیزدهیمن کنفرانس مهندسی برق ایران

تعداد صفحات: ۴

نویسنده(ها):

Hadi Sadoghi Yazdi – Department of Electrical Engineering, Tarbiat Modarres University, Tehran, Iran
Mojtaba Lotfizad – Department of Electrical Engineering, Tarbiat Modarres University, Tehran, Iran
Ehsanollah Kabir – Department of Electrical Engineering, Tarbiat Modarres University, Tehran, Iran
Mahmood Fathy – Faculty of Computer Engineering, Iran University of Science and Technology, Tehran, Iran

چکیده:

The LMS algorithm has properties of slow convergence and good tracking in low SNR compared to the RLS algorithm, whereas the RLS has a fast convergence property. A new approach based on a dynamic mixture of the RLS and LMS algorithms, RLMS, is presented. The optimum weights of the mixture are derived and it is proved that the MMSE of the proposed system is reduced compared to those of the RLS and LMS algorithms. RLMS algorithm is configured for identification and chirp tracking problems. Experimental results show better performance compared to both the RLS and LMS algorithms in identification problem and noisy chirp tracking.