贝叶斯高分辨方位估计新方法  

Novel method for Bayesian high-resolution direction finding

作　　者：田力伟[1] 黄建国[1] 侯云山[1] 

机构地区：[1]西北工业大学航海学院,西安710072

出　　处：《计算机工程与应用》2008年第24期9-11,14,共4页Computer Engineering and Applications

基　　金：国家自然科学基金（the National Natural Science Foundation of Chinaunder Grant No.60572098）.

摘　　要：针对贝叶斯方位估计方法计算量大的问题,将马尔可夫蒙特卡罗方法与贝叶斯方位估计方法相结合,提出一种基于Metropolis-Hastings抽样的贝叶斯方位估计方法（Bayesian DOA Estimator Basedon Metropolis-Hasting Sampling,简称MHB）。MHB方法将贝叶斯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,MHB方法不但保持了贝叶斯方位估计方法的优良性能,而且大大减小了计算量。Bayesian estimator is known to have the best performance in DOA estimation of narrowband sources.However,it entails heavy computation.In order to reduce computational complexity,the comhination of Markov Monte Carlo methods with Bayesian estimator is explored.A novel Bayesian DOA Estimator based on Metropolis-Hasting Sampling （MHB） is proposed in this paper. MHB regards the power of the MHB spectrum function ＂as＂ the target distribution up to a constant proportionality,and uses Metropolis-Hasting sampler to sample from it.Simulations show that MHB not only keeps the excellent performance of Bayesian estimator but also reduces computation greatly.

关 键 词：贝叶斯方位估计 Metropolis-Hastings抽样 计算复杂度 

分 类 号：TN911.7[电子电信—通信与信息系统]