基于  l 1 稀疏正则化的信源个数估计新算法

doi:10.11959/j.issn.1000-436x.2016198

通信学报 ›› 2016, Vol. 37 ›› Issue (10): 75-80.doi: 10.11959/j.issn.1000-436x.2016198

基于 $l_{1}$ 稀疏正则化的信源个数估计新算法

金芳晓¹,邱天爽¹,王鹏¹,夏楠²,李景春²

¹ 大连理工大学电子信息与电气工程学部，辽宁大连 116024
² 国家无线电监测中心，北京 100037

出版日期:2016-10-25 发布日期:2016-10-25
基金资助:
国家自然科学基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目;国家科技支撑计划基金资助项目

New source number estimation algorithm based on $l_{1}$ sparse regularization

Fang-xiao JIN¹,Tian-shuang QIU¹,Peng WANG¹,Nan XIA²,Jing-chun LI²

¹ Faculty of Electronic Information and Electrical Engineering,Dalian University of Technology,Dalian 116024,China
² State Radio Monitoring Center,Beijing 100037,China

Online:2016-10-25 Published:2016-10-25
Supported by:
The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Key Technology R＆D Program

摘要/Abstract

摘要：

针对现有信号源个数估计相关算法在低信噪比和较少快拍数下存在欠估计的问题，提出一种适用于空间平稳噪声下基于e₁稀疏正则化的信源个数估计新算法。该算法利用信号协方差矩阵特征值分解得到的特征值序列的稀疏性，选取合适的正则化参数对信号源个数进行估计。理论分析和仿真实验表明，所提算法可以在较低信噪比的空间平稳噪声条件下，实现对较少快拍数下阵列接收数据信源个数的精确估计。

关键词: 稀疏正则化, 信源个数估计, 空间平稳噪声, 正则化参数

Abstract:

In view of the problems of inefficient in low SNR and less snapshots when using existing sources number estimation related algorithms,a new algorithm based on e₁sparse regularization under space stationary noise was proposed to estimate the number of signal sources.The algorithm estimated the sources number by using the sparse representation of eigenvalues vectors with the suitable regularization parameter.Theoretical analysis and simulation results show that the algorithm can realize an accurate sources number estimation in low SNR and less snapshots.

Key words: sparse regularization, sources number estimation, space stationary noise, regularization parameter

金芳晓,邱天爽,王鹏,夏楠,李景春. 基于 $l_{1}$ 稀疏正则化的信源个数估计新算法[J]. 通信学报, 2016, 37(10): 75-80.

Fang-xiao JIN,Tian-shuang QIU,Peng WANG,Nan XIA,Jing-chun LI. New source number estimation algorithm based on $l_{1}$ sparse regularization[J]. Journal on Communications, 2016, 37(10): 75-80.

图/表 5

表1

表2

图1

图2

图3

参考文献 15

[1]	程伟, 左继章 . 基于时空结构的阵列信号三维参数同时估计方法[J]. 通信学报, 2004,25(10): 67-74. CHENG W , ZUO J Z . A new method for simultaneous estimation of 3-D parameters of array signal based on time-space structure[J]. Journal on Communications, 2004,25(10): 67-74.
[2]	CHEN W , WONG K M , REILLY J P . Detection of the number of signals:a predicted eigen-threshold approach[J]. IEEE Transactions on Signal Processing, 1991,39(5): 1088-1098.
[3]	ZHAO L C , KRISHNAIAH P , BAI Z D . Remarks on certain criteria for detection of number of signals[J]. IEEE Transactions on Acoustics,Speech and Signal Processing, 1987,35(2): 129-132.
[4]	WAX M , ZISKIND I . Detection of the number of coherent signals by the MDL principle[J]. IEEE Transactions on Acoustics,Speech and Signal Processing, 1989,37(8): 1190-1196.
[5]	FISHLER E , POOR H V . Estimation of the number of sources in unbalanced arrays via information theoretic criteria[J]. IEEE Transactions on Signal Processing, 2005,53(9): 3543-3553.
[6]	LIU Y , SORAGHAN J , DURRANI T . Detection of number of harmonics by maximum eigenvalue varied rate criteria[C]// International Conference on Acoustics,Speech,and Signal Processing (ICASSP). 1990: 2543-2546.
[7]	WU H T , YANG J F , CHEN F K . Source number estimators using transformed Gerschgorin radii[J]. IEEE Transactions on Signal Processing, 1995,43(6): 1325-1333.
[8]	石光明, 刘丹华, 高大化 . 压缩感知理论及其研究进展[J]. 电子学报, 2009,37(5): 1070-1081. SHI G M , LIU D H , GAO D H . Advances in theory and application of compressed sensing[J]. Chinese Journal of Electronics, 2009,37(5): 1070-1081.
[9]	MALIOUTOV D,?ETIN M , WILLSKY A S . A sparse signal reconstruction perspective for source localization with sensor arrays[J]. IEEE Transactions on Signal Processing, 2005,53(8): 3010-3022.
[10]	RAO B D , ENGAN K , COTTER S F . Subset selection in noise based on diversity measure minimization[J]. IEEE Transactions on Signal Processing, 2003,51(3): 760-770.
[11]	OTTERSTEN B , STOICA P , ROY R . Covariance matching estimation techniques for array signal processing applications[J]. Digital Signal Processing, 1998,8(3): 185-210.
[12]	MILLER A . Subset selection in regression[M]. CRC Press, 2002.
[13]	YARDIBI T , LI J , STOICA P . Source localization and sensing:a nonparametric iterative adaptive approach based on weighted least squares[J]. IEEE Transactions on Aerospace and Electronic Systems, 2010,46(1): 425-443.
[14]	CANDES E , RUDELSON M , TAO T ,et al. Error correction via linear programming[C]// IEEE Symposium on.Foundations of Computer Science (FOCS). 2005: 668-681.
[15]	CHEN W G , REILLY J P , WONG K M . Detection of the number of signals in noise with unknown,non-white covariance matrices[C]// IEEE International Conference on Acoustics,Speech,and Signal Processing (ICASSP). 1992,5: 377-380.

u _i	SNR = ?10 dB	SNR = ?5 dB	SNR = 0 dB	SNR = 5 dB	SNR = 10 dB
u ₁	11.38	10.62	10.66	10.57	10.57
u ₂	6.04	5.91	5.83	5.80	5.77
u ₃	0.63	0.25	0.08	0.08	0.08
u ₄	0.06	5.28×10^{? 9}	7.42×10^{? 10}	2.95×10^{? 10}	2.12×10^{? 10}
u ₅	2.36×10^{? 9}	2.93×10^{? 9}	2.97 ×10^{? 10}	1.32×10^{? 10}	1.04×10^{? 10}
u ₆	2.24×10^{? 29}	5.86×10^{? 29}	5.00×10^{? 31}	5.51×10^{? 31}	6.53×10^{? 31}

正则化参数γ			估计准确率
正则化参数γ	SNR = ?20 dB	SNR = ?10 dB	SNR = 0 dB	SNR = 10 dB	SNR = 20 dB
0.5	66%	52%	0	0	0
0.55	46%	72.5%	0	0	0
0.6	0	30	100%	100%	100%

基于 $l_{1}$ 稀疏正则化的信源个数估计新算法

New source number estimation algorithm based on $l_{1}$ sparse regularization

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 15

相关文章 1

Metrics

推荐阅读 0

基于 l 1 稀疏正则化的信源个数估计新算法

New source number estimation algorithm based on l 1 sparse regularization

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 15

相关文章 1

Metrics

推荐阅读 0

基于 $l_{1}$ 稀疏正则化的信源个数估计新算法

New source number estimation algorithm based on $l_{1}$ sparse regularization