A New Variable Step-Size LMS Adaptive Filtering Algorithm
In this paper, a new variable step-size LMS (FVSSLMS) algorithm in which the step-size parameter is dependent on absolute instantaneous error is proposed. This paper analyses the convergence of proposed algorithm, and presents the choice criterion of various parameters which affect the convergence speed and precision. The performance of proposed algorithm is compared with the fixed step-size LMS (FSSLMS) in several system environments. Computer simulation results validate the theoretical analysis about the proposed algorithm, demonstrate that the proposed algorithm has a good convergence property, overcoming the drawback of FSSLMS during convergence at a certain extent. Furthermore, the presented algorithm has a better tracking capability when the unknown system is disturbed.
Zhang Wenguang Guo Zhenkai Zheng Jiandong
School of Science BeiHang University Beijing, China 100083 School of Astronautics BeiHang University Beijing, China 100083
国际会议
青岛
英文
2006-07-21(万方平台首次上网日期,不代表论文的发表时间)