摘要
从修改传统仿射投影算法(Affine Projection Algorithm,APA)的约束条件出发,推导出了一种新的可变数据重用因子仿射投影算法。该算法解决了传统APA算法收敛速度与稳态失调和计量复杂度之间的矛盾,实现了在初始阶段数据重用因子大,收敛后数据重用因子小的目标。仿真结果表明该算法最终达到了高数据重用因子APA的收敛速度和NLMS算法的计算量和稳态失调。
Based on the changed constraint condition of Affine Projection Algorithm(APA),a novel APA with variable datareuse factor is proposed.The confliction between covergence speed and misalignment or computational complexity is successfully solved.At the beginning of the algorithm a large data-reuse factor is achieved while a small one is achieved after the algorithm has converged.Simulations show the proposed algorithm has as fast convergence speed as APA with high data-reuse factor while its misalignment and computational complexity are as low as NLMS algorithm.
出处
《计算机工程与应用》
CSCD
北大核心
2011年第26期159-161,共3页
Computer Engineering and Applications
关键词
仿射投影算法
可变数据重用因子
收敛速度
稳态失调
计算量
affine projection algorithm
variable data-reuse factor
convergence speed
misalignment
computational complexity