摘要
在传统的LMS(LeastMeanSquare)算法中 ,固定步长选取影响收敛速度与稳态误差 ,而且两者不可兼得。为此 ,本文提出了一种改进的LMS算法。在计算机仿真自适应信道均衡中 ,该算法的性能明显优于传统的LMS算法 ,而计算量增加甚少。理论分析与计算机模拟证实了该算法的优越性。
The convergent speed and steady state error are affected by the fixed stepsize and can not be improved simultaneously in classical LMS algorithm. Presents an improved algorithm of LMS. The new algorithm is better than classical LMS that is verified by computer simulation of adaptive channel equalizer, while the computional amount is only increased slightly. Theoretical analysis and computer simulations confirm the excellent properties of this algorithm.
出处
《华东船舶工业学院学报》
2000年第5期18-21,共4页
Journal of East China Shipbuilding Institute(Natural Science Edition)
关键词
自适应滤波
LMS算法
信道均衡
神经网络
adaptive filtering
least mean square algorithm
channel equalizer
