游康勇^{1, 2},
杨立山^{1, 2},
刘玥良¹,
郭文彬^{1, 2,,},
王文博¹
1.北京邮电大学信息与通信工程学院 ??北京 ??100876
2.通信网信息传输与分发技术重点实验室 ??石家庄 ??050000
基金项目:国家自然科学基金(61271181, 61571054)，通信网信息传输与分发技术重点实验室基金

详细信息

作者简介:游康勇：男，1993年生，博士生，研究方向为压缩感知技术
杨立山：男，1986年生，博士生，研究方向为图信号处理与压缩感知、大数据处理
刘玥良：男，1992年生，博士生，研究方向为图信号处理与压缩感知、大数据处理
郭文彬：男，1971年生，教授，研究方向为信号处理、认知无线电及其关键技术
王文博：男，1965年生，教授，研究方向为通信理论和信号处理

通讯作者:郭文彬　 gwb@bupt.edu.cn

中图分类号:TN911.7

计量

文章访问数:1256
HTML全文浏览量:389
PDF下载量:47
被引次数:0

出版历程

收稿日期:2017-12-28
修回日期:2018-05-23
网络出版日期:2018-07-12
刊出日期:2018-09-01

Adaptive Grid Multiple Sources Localization Based on Sparse Bayesian Learning

Kangyong YOU^{1, 2},
Lishan YANG^{1, 2},
Yueliang LIU¹,
Wenbin GUO^{1, 2,,},
Wenbo WANG¹
1. School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China
2. Science and Technology on Information Transmission and Dissemination in Communication Networks Laboratory, Shijiazhuang 050000, China
Funds:The National Natural Science Foundation of China (61271181, 61571054), The Science and Technology on Information Transmission and Dissemination in Communication Networks Laboratory Foundation


摘要
摘要:多源定位是信号处理中的重要问题。该文针对目标偏离初始网格点引起的基不匹配问题，构建具有Laplace先验的稀疏贝叶斯学习框架，提出基于稀疏贝叶斯学习的网格自适应多源定位算法AGMTL。本质上，AGMTL实现了稀疏信号重建和网格自适应定位字典的学习。仿真结果表明，AGMTL通过网格自适应调整，在定位误差，估计可靠性，抗噪性能上均远远优于传统的压缩感知定位算法。
关键词:多源定位/
压缩感知/
网格自适应模型/
稀疏贝叶斯学习/
Laplace先验
Abstract:Multiple sources localization is an issue of theoretical importance and practical significance in signal processing. The basis mismatch problem caused by target deviation from the initial grid point is addressed. Based on sparse Bayesian learning framework with Laplace prior, a novel iterative Adaptive Grid Multiple Targets Localization (AGMTL) algorithm is proposed to tackle the practical situation in which the targets deviates from the initial grid point. In essence, AGMTL algorithm implements sparse signal reconstruction and adaptive grid localization dictionary learning jointly. The simulation results show that AGMTL algorithm outperforms the traditional Compressive Sensing (CS) based localization algorithm in the terms of localization error, estimation reliability and noise robustness.
Key words:Multiple sources localization/
Compressive Sensing (CS)/
Adaptive grid model/
Sparse Bayesian learning/
Laplace prior



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=e10f4425-5f8d-48a7-ac33-58cdb9cae994