基于变分稀疏贝叶斯学习的DOA估计  

Direction-of-arrival(DOA) estimation based on variational sparse Bayesian learning

作　　者：郜丽鹏[1] 杜旭华 GAO Lipeng;DU Xuhua(College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《应用科技》2018年第6期32-36,共5页Applied Science and Technology

基　　金：上海航天科技创新基金项目(SAST2017-068)

摘　　要：针对传统稀疏贝叶斯学习的DOA估计算法复杂度较高、收敛速度较慢等问题,提出了一种基于变分稀疏贝叶斯学习的DOA估计算法。首先通过空间网格划分方式建立基于稀疏表示的DOA估计信号模型;其次在此模型基础上为未知待估计参数指定先验分布,得出稀疏信号的后验概率分布;然后利用变分贝叶斯学习算法,通过最小化KL散度寻求后验概率分布的近似分布;最后估计出未知参数,并得到信号的DOA估计值。根据MATLAB仿真图的结果,该算法成功估计出信号的DOA,并达到了预期效果。与传统稀疏贝叶斯学习算法相比,该算法单快拍下具有更高的DOA估计精度以及更快的收敛速度。To solve the problems of high complexity and slow convergence rate of traditional sparse Bayesian learning(SBL)algorithm,this paper proposes a direction-of-arrival(DOA)estimation algorithm based on variational sparse Bayesian learning(VSBL).Firstly,a DOA estimation signal model based on sparse representation was established by spatial gridding.Secondly,based on this model,a priori distribution was specified for unknown parameters to be estimated,then obtain the posterior probability distribution of sparse signal.Then apply the variational Bayesian learning algorithm to find the approximate distribution of the posterior probability distribution by minimizing the KL divergence.Finally,estimate the unknown parameters,and obtain the DOA estimation value of the signal.According to the MATLAB simulation results,the signal DOA was estimated successfully by the algorithm,achieving the expected results.Compared with traditional sparse Bayesian learning algorithm,this algorithm has higher DOA estimation accuracy and faster convergence speed under single snapshot.

关 键 词：DOA估计 贝叶斯学习 变分贝叶斯学习 稀疏表示 相关向量机 MATLAB仿真 估计精度 收敛速度 

分 类 号：TN911.7[电子电信—通信与信息系统]