部分均匀环境中训练样本不足时的贝叶斯子空间检测器

Bayesian subspace detector with limited training data in partially homogeneous environments

摘要:

为了解决部分均匀环境中训练数据不足时的子空间信号检测难题，采用贝叶斯理论，将噪声协方差矩阵建模为逆威沙特分布，并采用广义似然比准则（generalized likelihood ratio test，GLRT）、Rao准则和Wald准则设计自适应检测器，结果表明3种准则得到相同的结果。基于仿真及实测数据验证了所提检测器的有效性，并得出了影响检测性能的关键物理量。

Abstract:

To solve the problem of subspace signal detection in partially homogeneous environment with limited training data, the Bayesian theory was adopted by modelling the unknown covariance matrix as an inverse Wishart distribution. Then, an adaptive detector was designed according to the generalized likelihood ratio test (GLRT), Rao test and Wald test. Numerical examples of simulations and real data have demonstrated that the proposed detector can provide better detection performance than those existing detectors. The key physical quantities that affect the detection performance were also obtained.