摘要
提出一种基于双曲函数的变步长最小均方(LMS)算法。通过对双曲余弦函数进行数学变换,建立起误差信号与步长因子的LMS算法,根据误差信号的变化来自动调节步长的大小。仿真结果证明:所提出的LMS算法比标准的LMS算法有着更快的收敛速度等优点。
A variable step least mean square(LMS) algorithm is presented.The LMS algorithm between step size and error signal is established by a mathematical transform of hyperbolic tangent function.According to change of error signal,the step size is adjusted automatically.The simulation results show that the proposed algorithm has faster convergence speed than standard LMS algorithm.
出处
《传感器与微系统》
CSCD
北大核心
2011年第5期127-128,132,共3页
Transducer and Microsystem Technologies
关键词
自适应滤波器
最小均方算法
变步长
双曲函数
adaptive filter
least mean square(LMS) algorithm
variable step size
hyperbolic tangent function