Robust estimation of the number of sources using an MMSE-based MDL method

Teng Long; Lei Huang; Erke Mao

doi:10.1049/cp.2009.0262

Robust estimation of the number of sources using an MMSE-based MDL method

Teng Long^*, Lei Huang, Erke Mao

^*此作品的通讯作者

信息与电子学院

Beijing Institute of Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

2 引用（Scopus）

摘要

In this paper, using the mutual information, we bridge the probability density function and the minimum mean-square error (MMSE) between the observed data and the desired signal, and then employ the MMSE to construct an MMSE-based MDL criterion for accurate source enumeration. The presented numerical results demonstrate that the proposed method is superior to the existing MDL methods in detection performance.

源语言	英语
主期刊名	IET International Radar Conference 2009
版本	551 CP
DOI	https://doi.org/10.1049/cp.2009.0262
出版状态	已出版 - 2009
活动	IET International Radar Conference 2009 - Guilin, 中国期限: 20 4月 2009 → 22 4月 2009

出版系列

姓名	IET Conference Publications
编号	551 CP

会议

会议	IET International Radar Conference 2009
国家/地区	中国
市	Guilin
时期	20/04/09 → 22/04/09

访问文件

10.1049/cp.2009.0262

其它文件与链接

链接到 Scopus 的出版物

引用此

Long, T., Huang, L., & Mao, E. (2009). Robust estimation of the number of sources using an MMSE-based MDL method. 在 IET International Radar Conference 2009 (551 CP 编辑). (IET Conference Publications; 号码 551 CP). https://doi.org/10.1049/cp.2009.0262

@inproceedings{edde9ca4b7aa46888fe0af17ea4beb1a,

title = "Robust estimation of the number of sources using an MMSE-based MDL method",

abstract = "In this paper, using the mutual information, we bridge the probability density function and the minimum mean-square error (MMSE) between the observed data and the desired signal, and then employ the MMSE to construct an MMSE-based MDL criterion for accurate source enumeration. The presented numerical results demonstrate that the proposed method is superior to the existing MDL methods in detection performance.",

keywords = "Eigenvalue decomposition (EVD), Minimum description length (MDL), Sensor array processing, Source number estimation",

author = "Teng Long and Lei Huang and Erke Mao",

year = "2009",

doi = "10.1049/cp.2009.0262",

language = "English",

isbn = "9781849190107",

series = "IET Conference Publications",

number = "551 CP",

booktitle = "IET International Radar Conference 2009",

edition = "551 CP",

note = "IET International Radar Conference 2009 ; Conference date: 20-04-2009 Through 22-04-2009",

}

TY - GEN

T1 - Robust estimation of the number of sources using an MMSE-based MDL method

AU - Long, Teng

AU - Huang, Lei

AU - Mao, Erke

PY - 2009

Y1 - 2009

N2 - In this paper, using the mutual information, we bridge the probability density function and the minimum mean-square error (MMSE) between the observed data and the desired signal, and then employ the MMSE to construct an MMSE-based MDL criterion for accurate source enumeration. The presented numerical results demonstrate that the proposed method is superior to the existing MDL methods in detection performance.

AB - In this paper, using the mutual information, we bridge the probability density function and the minimum mean-square error (MMSE) between the observed data and the desired signal, and then employ the MMSE to construct an MMSE-based MDL criterion for accurate source enumeration. The presented numerical results demonstrate that the proposed method is superior to the existing MDL methods in detection performance.

KW - Eigenvalue decomposition (EVD)

KW - Minimum description length (MDL)

KW - Sensor array processing

KW - Source number estimation

UR - http://www.scopus.com/inward/record.url?scp=70350148375&partnerID=8YFLogxK

U2 - 10.1049/cp.2009.0262

DO - 10.1049/cp.2009.0262

M3 - Conference contribution

AN - SCOPUS:70350148375

SN - 9781849190107

T3 - IET Conference Publications

BT - IET International Radar Conference 2009

T2 - IET International Radar Conference 2009

Y2 - 20 April 2009 through 22 April 2009

ER -

Robust estimation of the number of sources using an MMSE-based MDL method

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此