A Fast Non-Unitary Joint Diagonalization Algorithm Based on Utilizations of Parametric Structures

doi:10.7652/xjtuxb201612017

您当前的位置：

首页 >

文章列表页 >

A Fast Non-Unitary Joint Diagonalization Algorithm Based on Utilizations of Parametric Structures

更新时间：2025-07-09

- A Fast Non-Unitary Joint Diagonalization Algorithm Based on Utilizations of Parametric Structures
- Vol. 50, Issue 12, Pages: 106-113(2016)
- 作者机构：
  
  西安电子科技大学雷达信号处理国家重点实验室,西安,710071
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201612017
  CLC： TN911.7
- Online First：10 December 2016，
  
  Published：2016
- 稿件说明：
移动端阅览
A Fast Non-Unitary Joint Diagonalization Algorithm Based on Utilizations of Parametric Structures[J]. 2016, 50(12): 106-113.
DOI：

A Fast Non-Unitary Joint Diagonalization Algorithm Based on Utilizations of Parametric Structures[J]. 2016, 50(12): 106-113. DOI： 10.7652/xjtuxb201612017.

摘要

针对基于快速Frobenius范数对角化(FFDIAG)的盲信号分离算法不能直接处理复数数据从而导致分离性能差的问题

提出一种利用参数结构的快速非酉联合对角化(PSJD)算法。该算法首先将由观测信号的统计量得到的复目标矩阵转化为实对称矩阵; 通过对代价函数的二阶近似

将解联合对角化问题转化为一系列的线性最小二乘问题

直接得到更新矩阵元素的估计。在每次迭代中

通过充分利用转化后的目标矩阵的结构信息

减少估计分离矩阵及更新目标矩阵的计算复杂度。同时

针对FFDIAG算法采用的固定步长难以兼顾收敛速度与更新矩阵严格对角占优性的问题

采用仅由当前更新矩阵的估计值决定的自适应学习率

提高算法的收敛性能。仿真实验表明

在一定的取值范围内

PSJD算法的收敛速度对步长参数的变化不敏感

在步长参数同为0.1的情况下

PSJD算法达到收敛所需的迭代次数比采用固定步长的算法减少了42%左右。

Abstract

A parametric structures based fast joint diagonalization(PSJD)algorithm for non-unitary diagonalization of a set of complex target matrices is presented to cope with the problem that the blind source separation by fast Frobenius diagonalization(FFDIAG)algorithm is not applicable in the complex-valued space and its separation performance is lower. The algorithm firstly transforms the complex target matrices into real-symmetric ones. Secondly

the problem of simultaneous diagonalization of matrices is transformed into a series of linear least-squares problems through second-order approximation to contract functions

and the elements of the updating matrix are directly estimated. The computational complexity for estimating the diagonalizer and for updating the target matrices is significantly reduced by making full use of the structure information of the transformed target matrices. In order to overcome the drawback of fixed step size adopted in the FFDIAG that may not strike a balance between the convergence rate and strictly diagonally dominant property of the update matrix

the proposed algorithm uses the adaptive learning rate determined from the estimation of the update matrix in each iteration to improve the convergence property. Results of numerical simulations show that the convergence rate of PSJD algorithm is not very sensitive in a wide range of step-size values. When the step size is 0.1

the number of iterations required to reach convergence is 42% less than that of the fixed step-size method.

关键词

Keywords

references

CHABRIEL G, KLEINSTEUBER M, MOREAU E, et al. Joint matrices decompositions and blind source separation: a survey of methods, identification, and applications [J]. IEEE Signal Processing Magazine, 2014, 3(31): 34-43.

MESLOUB A, ABED-MERAIM K, BELOUCHRANI A. A new algorithm for complex non orthogonal joint diagonalization based on Shear and Givens rotations [J]. IEEE Transactions on Signal Processing, 2014, 62(8): 1913-1925.

ZIEHE A, LASKOV P, NOLTE G, et al. A fast algorithm for joint diagonalization with non-orthogonal transformations and its application to blind source separation [J]. Journal of Machine Learning Research, 2004, 5(3): 777-800.

XU Xianfeng, FENG Dazheng, ZHENG Weixing. A fast algorithm for nonunitary joint diagonalization and its application to blind source separation [J]. IEEE Transactions on Signal Processing, 2011, 59(7): 3457-3463.

丛丰裕, 雷菊阳, 许海翔, 等. 在线增强型复值混合信号盲分离算法研究 [J]. 西安交通大学学报, 2006, 40(9): 1070-1073.

CONG Fengyu, LEI Juyang, XU Haixiang, et al. Online blind separation of enforced mixed complex-value signal sources [J]. Journal of Xi'an Jiaotong University, 2006, 40(9): 1070-1073.

聂卫科, 冯大政, 刘建强. 二维波达方向估计的非酉联合对角化方法 [J]. 西安交通大学学报, 2008, 42(6): 747-750.

NIE Weike, FENG Dazheng, LIU Jiangiang. Non-unitary joint diagonalization method for estimating two-dimension direction of arrival [J]. Journal of Xi'an Jiaotong University, 2008, 42(6): 747-750.

FENG Dazheng, ZHANG Hua, ZHENG Weixing. Bi-iterative algorithm for extracting independent components from array signals [J]. IEEE Transactions on Signal Processing, 2011, 59(8): 3636-3646.

ZENG Tiaojun, FENG Quanyuan. Non-orthogonal joint diagonalization algorithm based on hybrid trust region method and its application to blind source separation [J]. Neurocomputing, 2014, 133(8): 280-294.

陆建涛, 成玮, 訾艳阳, 等. 变步长等变自适应盲源分离算法 [J]. 西安交通大学学报, 2015, 49(12): 83-89.

LU Jiantao, CHENG Wei, ZI Yanyang, et al. Variable step-size algorithm for equivariant adaptive separation via independent [J]. Journal of Xi'an Jiaotong University, 2015, 49(12): 83-89.

TICHAVSKY P, YEREDOR A. Fast approximate joint diagonalization incorporating weight matrices [J]. IEEE Transactions on Signal Processing, 2009, 57(3): 878-891.

LASALLE J P. The stability of dynamical system [M]. Philadelphia, PA, USA: SIAM Press, 1976: 49-50.

张伟涛, 楼顺天, 张延良. 非对称非正交快速联合对角化算法 [J]. 自动化学报, 2010, 36(6): 829-836.

ZHANG Weitao, LOU Shuntian, ZHANG Yanliang. Non-symmetrical non-orthogonal fast joint diagonalization algorithm [J]. Acta Automatica Sinica, 2010, 36(6): 829-836.

王玉玺,黄国策,李伟,等.非均匀广义对角加载稳健波束形成算法.2016,50(8):64-69.[doi:10.7652/xjtuxb201608011]

刘健伶,陈志刚,王磊.一种自适应广义空间调制及其低复杂度算法.2016,50(4):48-53.[doi:10.7652/xjtuxb201604008]

王富平,水鹏朗.采用多尺度方向微分比率的角点检测算法.2016,50(4):68-75.[doi:10.7652/xjtuxb201604011]

赵凯,王闯,李尊朝,等.结合平衡和滤波技术抑制GaN电源转换器的电磁干扰.2016,50(02):38-42.[doi:10.7652/xjtuxb201602007]

孙黎,徐洪斌.协作式终端直通系统中星座旋转辅助的干扰避免策略.2015,49(12):6-11.[doi:10.7652/xjtuxb201512 002]

张东伟,郭英,齐子森,等.采用空间极化时频分布的跳频信号多参数联合估计算法.2015,49(8):17-23.[doi:10.7652/xjtuxb201508004]

巴斌,郑娜娥,朱世磊,等.利用蒙特卡罗的最大似然时延估计算法.2015,49(8):24-30.[doi:10.7652/xjtuxb201508005]

吴一全,孟天亮,吴诗婳.人工蜂群优化的非下采样Shearlet域引导滤波图像增强.2015,49(6):39-45.[doi:10.7652/xjtuxb201506007]

熊涛,江桦,崔鹏辉,等.应用基扩展模型的混合信号单通道盲分离算法.2015,49(6):60-66.[doi:10.7652/xjtuxb201506 010]

郝雯洁,齐春.一种鲁棒的稀疏信号重构算法.2015,49(4):98-103.[doi:10.7652/xjtuxb201504016]

王云龙,吴瑛.联合时延与多普勒频率的直接定位改进算法.2015,49(4):123-129.[doi:10.7652/xjtuxb201504020]

尚佳栋,王祖林,周丽娜,等.采用随机共振增强的混合扩频信号跳频参数估计.2014,48(10):42-48.[doi:10.7652/xjtuxb201410007]

储颖,牟轩沁,洪伟.采用形状一致性特征的盲图像质量评价方法.2014,48(8):12-17.[doi:10.7652/xjtuxb201408003]

吴仁斌,姚敏立,贾维敏,等.采用幅度响应约束的鲁棒自适应波束形成算法.2014,48(4):109-114.[doi:10.7652/xjtuxb201404019]

郝红侠,刘芳,焦李成,等.采用结构自适应窗的非局部均值图像去噪算法.2013,47(12):71-76.[doi:10.7652/xjtuxb 201312013]

穆为磊,高建民,王昭,等.考虑人眼视觉特性的射线检测数字图像质量评价方法.2013,47(7):91-95.[doi:10.7652/xjtuxb201307017]

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Non-Unitary Joint Diagonalization Method for Estimating Two-Dimension Direction of Arrival

Numerical Simulation of the Energy Conversion Process in Thermoacoustic Engines with Different Stack Materials

Electrothermal Coupling Research on the Evolutionary Law of Anti-Corona Performance for High-Altitude Air-Cooled Generators

Numerical Simulation of Heat-Moisture Barrier Performance of a Horizontal Air Curtain in Cold Storage

Energy Efficiency Optimization of the Cryogenic Air Separation Process for Electronic-Grade Ultra Pure Nitrogen

Related Author

聂卫科

刘建强

Related Institution

National Laboratory Lab for Radar Signal Processing, Xidian University

⁰