基于MetropolisHastings抽样短采样宽带信号方位估计AML算法

Journal of Systems Engineering and Electronics ›› 2009, Vol. 31 ›› Issue (12): 2809-2812.

基于MetropolisHastings抽样短采样宽带信号方位估计AML算法

金勇1,2，李捷1，黄建国2

1. 河南大学先进控制与智能信息研究所，河南开封 475004; 2. 西北工业大学航海学院, 陕西西安 710072

出版日期:2009-12-24 发布日期:2010-01-03

AML algorithm for short sampling wideband signal DOA estimation based on MetropolisHastings sampling

JIN Yong1,2,LI Jie1,HUANG Jian-guo2

1. Inst. of Advanced Control and Intelligent Information Processing, Henan Univ.,Kaifeng 475004, China; 2. Coll. of Marine, Northwestern Polytechnical Univ.，Xi’an 710072, China

Online:2009-12-24 Published:2010-01-03

摘要/Abstract

摘要：

针对短采样宽带信号近似最大似然（approximated maximum likelihood,AML）方位估计计算量大的问题，将马尔科夫链〖CD*2〗蒙特卡罗方法与近似最大似然方位估计相结合，提出一种基于MetropolisHastings抽样的近似最大似然方位估计方法（AMLMH）。该方法将AML算法的空间谱函数作为信号的概率分布函数，并利用MetropolisHastings抽样方法从该概率分布函数中抽样。研究结果表明，AMLMH方法不但保持了原近似最大似然方位估计方法的优良性能，而且减小了计算量。

Abstract:

In view of the approximated maximum likelihood (AML)estimation which is suitable to the short time sampling wideband signals DOA estimation, is nonperfect for its very large computation load, a novel approximated maximum likelihood DOA estimation based on MetropolisHasting sampling (AMLMH) is proposed by combining the Markov chain Monte Carlo methods are combined with approximated maximum likelihood DOA estimator. AMLMH regards the power of the AML spectrum function as the target distribution up to a constant proportionality, and uses MetropolisHasting sampler to sample from it. Simulations show that AMLMH not only keeps the excellent performance of the original AML but also reduces the computational load greatly.

金勇1,2，李捷1，黄建国2. 基于MetropolisHastings抽样短采样宽带信号方位估计AML算法[J]. Journal of Systems Engineering and Electronics, 2009, 31(12): 2809-2812.

JIN Yong1,2,LI Jie1,HUANG Jian-guo2. AML algorithm for short sampling wideband signal DOA estimation based on MetropolisHastings sampling[J]. Journal of Systems Engineering and Electronics, 2009, 31(12): 2809-2812.