论文部分内容阅读
针对在低频信道下多天线信号检测问题,提出一种新型的多维大气噪声模型的参数估计算法.通过推导贝叶斯模型,设计马尔科夫链蒙特卡罗算法,并在迭代中采用Gibbs和Metropolis-Hasting混合抽样的方法,能够有效估计出多维噪声模型的参数.多维大气噪声模型建模为应用广泛的亚高斯分布.仿真实验表明:该算法能迅速收敛于真实值,估计器相对误差能被有效控制,且易于并行实现.
Aiming at the multi-antenna signal detection problem in low-frequency channel, a new parameter estimation algorithm for multi-dimensional atmospheric noise model is proposed.By deriving the Bayesian model, a Markov chain Monte Carlo algorithm is designed and Gibbs and Metropolis -Hasting mixed sampling method can effectively estimate the parameters of the multidimensional noise model.Multi-dimensional atmospheric noise model is modeled as a widely used sub-Gaussian distribution.The simulation results show that the algorithm can quickly converge to the true value, the relative error of the estimator can be Effective control, and easy to implement in parallel.