抗冲激干扰的稀疏惩罚约束遗漏最小均方算法

当被识别系统是稀疏系统时,传统的遗漏最小均方(LLMS)自适应算法收敛性能较差,特别在非高斯噪声环境中,该算法性能进一步恶化甚至算法不平稳收敛.为了解决因信道的稀疏性使算法收敛变慢的问题,对LLMS算法的代价函数分别利用加权l1-norm和加权零吸引两种稀疏惩罚项进行改进;为了优化算法的抗冲激干扰的性能,利用符号函数对已改进的算法迭代式作进一步改进.同时,将提出的两个算法运用于非高斯噪声环境下的稀疏系统识别,仿真结果显示提出的算法性能优于现存的同类稀疏算法....

Full description

Saved in:
Bibliographic Details
Published in电讯技术 Vol. 56; no. 10; pp. 1153 - 1158
Main Author 晏国杰 林云
Format Journal Article
LanguageChinese
Published 重庆邮电大学 移动通信技术重庆市重点实验室,重庆,400065 2016
Subjects
Online AccessGet full text
ISSN1001-893X
DOI10.3969/j.issn.1001-893x.2016.10.016

Cover

More Information
Summary:当被识别系统是稀疏系统时,传统的遗漏最小均方(LLMS)自适应算法收敛性能较差,特别在非高斯噪声环境中,该算法性能进一步恶化甚至算法不平稳收敛.为了解决因信道的稀疏性使算法收敛变慢的问题,对LLMS算法的代价函数分别利用加权l1-norm和加权零吸引两种稀疏惩罚项进行改进;为了优化算法的抗冲激干扰的性能,利用符号函数对已改进的算法迭代式作进一步改进.同时,将提出的两个算法运用于非高斯噪声环境下的稀疏系统识别,仿真结果显示提出的算法性能优于现存的同类稀疏算法.
Bibliography:The leaky least mean square(LLMS) adaptive filtering algorithm converges slowly when the identified system is sparse. Especially when the noise is non-Gaussian impulsive interference,the performance ofLLMS algorithm deteriorates severely. To solve the problem that the convergent rate becomes slower becausethe system is sparse,the cost function of the conventional LLMS algorithm is improved by the two penaltyfunctions,the reweighted zero-attracting(the log-sum penalty) and reweighted l1 -norm(RL1),respectively. To address the problem of the impulsive interference,the iterative functions are improved by introducingthe sign function. Simultaneously,the simulations are made for the proposed algorithms to prove to be betterperformances compared with existing leaky-style algorithms in the case of impulsive interference.
sparse system identification;adaptive filtering algorithm;impulsive interference;convergence
YAN Guojie,LIN Yun(Chongqing Key Laboratory of Mobile Communications Technology,Chongqing University of Pos
ISSN:1001-893X
DOI:10.3969/j.issn.1001-893x.2016.10.016