基于块自适应滤波的核最小均方算法

doi:10.3969/j.issn.1000-3428.2017.09.029

计算机工程

基于块自适应滤波的核最小均方算法

赵知劲^1,2,金明明¹

(1.杭州电子科技大学通信工程学院,杭州 310018; 2.中国电子科技集团公司第三十六研究所通信系统信息控制技术国家级重点实验室,浙江嘉兴 314001)

收稿日期:2016-07-28 出版日期:2017-09-15 发布日期:2017-09-15
作者简介:赵知劲(1959—),女,教授、博士、博士生导师,主研方向为认知无线电、信号处理;金明明,硕士。

Kernael Least Mean Square Algorithm Based on Block Adaptive Filtering

ZHAO Zhijin^1,2,JIN Mingming¹

(1.School of Telecommunication Engineering,Hangzhou Dianzi University,Hangzhou 310018,China; 2.State Key Lab of Information Control Technology in Communication System,The 36th Research Institute of China Electronics Technology Group Corporation,Jiaxing,Zhejiang 314001,China)

Received:2016-07-28 Online:2017-09-15 Published:2017-09-15

摘要/Abstract

摘要： 核最小均方(KLMS)算法在非线性系统中收敛性能较好,但其使用瞬时梯度估计均方误差梯度,导致随机性较大。而块自适应滤波理论利用多个输入-输出的误差来估计均方误差梯度,可降低KLMS算法稳态误差。为此,将块自适应滤波理论运用到KLMS算法中,提出核块最小均方(KBLMS)算法,根据最陡下降法原理推导出KBLMS权矢量更新公式,使用核方法计算得到滤波器输出表达式,并通过并行处理减小算法计算复杂度。仿真结果表明,KBLMS算法可有效提高KLMS算法的稳态性能,并且相比块最小均方算法具有更低的误码率。

关键词: 核最小均方算法, 块自适应滤波, 最陡下降法, 核方法, 非线性信道均衡

Abstract: Kernel Least Mean Square(KLMS) algorithm has a good covergence performance in nonlinear systems.But its mean square error gradient is estimated by the instantaneous gradient that results in larger randomness.However,the block adaptive filtering theory can reduce the steady-state error of KLMS algorithm by estimating the mean square error gradient with the multiple input-output errors.For this purpose,the block adaptive filtering theory is applied to the KLMS algorithm,and the Kernel Block Least Mean Square(KBLMS) algorithm is proposed.Based on the basic idea of the steepest descent algorithm,the weight vector update equation of KBLMS is derived.Then the filter output expression is calculated by utilizing the kernel method,and the computational complexity is reduced by using parallel processing.Simulations results show that KBLMS effectively improves the steady-state performance of KLMS and has lower Bit Error Rate(BER) than Block Least mean Square(BLMS) algorithin.

Key words: Kernael Least Mean Square(KLMS) algorithm, block adaptive filtering, steepest descent algorithm, kernel method, nonlinear channel equalization

中图分类号:

TP301.6

赵知劲,金明明. 基于块自适应滤波的核最小均方算法[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2017.09.029.

ZHAO Zhijin,JIN Mingming. Kernael Least Mean Square Algorithm Based on Block Adaptive Filtering[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2017.09.029.

http://www.ecice06.com/CN/Y2017/V43/I9/162

参考文献

参考文献［1］CORTES C,VAPNIK V.Support-vector Networks［J］.Machine Learning,1995,20(3):273-297. ［2］TUIA D,MUNOZ-MARKI J,ROJO-ALVAREZ J L,et al.Explicit Recursive and Adaptive Filtering in Reproducing Kernel Hilbert Spaces［J］.IEEE Transactions on Neural Networks & Learning Systems,2014,25(7):1413-1419. ［3］LIU Weifeng,PRINCIPE J C,HAYKIN S.核自适应滤波［M］.田亚娟,张峰,肖忠祥,等,译.北京:国防工业出版社,2014. ［4］LIU Weifeng,POKHAREL P P,PRINCIPE J C.The Kernel Least Mean Square Algorithm［J］.IEEE Transactions on Signal Processing,2008,56(2):543-554. ［5］YU Shujian,FAN Ziqi,ZHAO Yixiao,et al.Quantized Kernel Least Mean Mixed-norm Algorithm［C］//Proceedings of the 12th International Conference on Signal Processing.Washington D.C.,USA:IEEE Press,2015:199-204. ［6］ZHAO Songlin,CHEN Badong,ZHU Pingping,et al.Fixed Budget Quantized Kernel Least-mean-square Algorithm［J］.Signal Processing,2013,93(9):2759-2770. ［7］TOBAR F A,KUNG S Y,MANDIC D P.Multikernel Least Mean Square Algorithm［J］.IEEE Transactions on Neural Networks & Learning Systems,2014,25(2):265-277. ［8］CLARK G A,MITRA S K,PARKER S.Block Implementation of Adaptive Digital Filters［J］.IEEE Transactions on Acoustics Speech & Signal Processing,1981,28(3):744-752. ［9］HSIEH L S L,WOOD S L.Performance Analysis of Time Domain Block LMS Algorithm［C］//Proceedings of IEEE International Conference on Acoustics.Washington D.C.,USA:IEEE Press,1993:535-538. ［10］STEINWART I,SCOVEL C.Mercer’s Theorem on General Domains:On the Interaction Between Measures,Kernels,and RKHSs［J］.Constructive Approximation,2012,35(3):363-387. ［11］STEINWART I,HUSH D,SCOVEL C.An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels［J］.IEEE Transactions on Information Theory,2006,52(10):4635-4643. ［12］RATSCH G,ONODA T,MULLER K R.Soft Margins for AdaBoost［J］.Machine Learning,2001,42(3):287-320. ［13］张翔,肖小玲,徐光祐.一种确定高斯核模型参数的新方法［J］.计算机工程,2007,33(12):52-53. ［14］Haykin S.自适应滤波器原理［M］.4版.郑宝玉,译.北京:电子工业出版社,2006:270-278. ［15］MITRA R,BHATIA V.A Kernel Based Technique for MSER Equalisation for Non-linear Channels［C］//Proceedings of the 23rd European Signal Processing Conference.Washington D.C.,USA:IEEE Press,2015:1446-1450. 编辑陆燕菲

[1]	袁少锋，王士同. 基于混合Kotz-型分布的多分类人脸识别方法[J]. 计算机工程, 2013, 39(11): 24-30.
[2]	于新星, 王永. 基于在线核聚类的雷达信号分选方法[J]. 计算机工程, 2012, 38(3): 270-272,275.
[3]	蒋砺思, 曾菊玲. 多重QoS的区分业务到无线链路的优化映射[J]. 计算机工程, 2012, 38(15): 77-80.
[4]	王燕, 白万荣. 核邻域保持判别嵌入在人脸识别中的应用[J]. 计算机工程, 2012, 38(01): 163-164,167.
[5]	唐楠, 杨志豪, 林鸿飞, 李彦鹏. 基于多核学习的医学文献蛋白质关系抽取[J]. 计算机工程, 2011, 37(10): 184-186.
[6]	于春梅, 潘泉, 程咏梅, 张洪才. 基于核正则化Fisher判据的故障诊断[J]. 计算机工程, 2010, 36(23): 1-3.
[7]	林健;彭敏晶;. 基于支持向量数据描述的预警技术及其应用[J]. 计算机工程, 2006, 32(20): 7-9,12.
[8]	饶鲜;李斌;杨绍全. 基于核中心距比值法的入侵检测[J]. 计算机工程, 2006, 32(18): 122-124.

选择文件类型/文献管理软件名称

选择包含的内容

基于块自适应滤波的核最小均方算法

Kernael Least Mean Square Algorithm Based on Block Adaptive Filtering

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于块自适应滤波的核最小均方算法

Kernael Least Mean Square Algorithm Based on Block Adaptive Filtering

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价