An Asymptotically Optimal Approximation of the Conditional Mean Channel Estimator Based on Gaussian Mixture Models
An Asymptotically Optimal Approximation of the Conditional Mean Channel Estimator Based on Gaussian Mixture Models
复制标题
DOI：
10.1109/icassp43922.2022.9747226
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
M. Koller;B. Fesl;N. Turan;W. Utschick
中科院分区：
文献类型：
--
作者：
M. Koller;B. Fesl;N. Turan;W. Utschick
本文研究了一种基于高斯混合模型的信道估计器。我们拟合GMM到给定的信道样本，以获得近似真实信道概率密度函数（PDF）的解析概率密度函数（PDF）。然后，一个条件均值估计（CME）对应于这个近似的PDF计算在封闭的形式，并作为一个近似的最佳CME的基础上真正的信道PDF。这个最佳估计器不能解析计算，因为真实的信道PDF通常不可用。为了激励基于GMM的估计，我们表明，它收敛到最佳的CME的GMM组件的数量增加。在数值实验中，合理数量的GMM分量已经显示出有希望的估计结果。
This paper investigates a channel estimator based on Gaussian mixture models (GMMs). We fit a GMM to given channel samples to obtain an analytic probability density function (PDF) which approximates the true channel PDF. Then, a conditional mean estimator (CME) corresponding to this approximating PDF is computed in closed form and used as an approximation of the optimal CME based on the true channel PDF. This optimal estimator cannot be calculated analytically because the true channel PDF is generally not available. To motivate the GMM-based estimator, we show that it converges to the optimal CME as the number of GMM components is increased. In numerical experiments, a reasonable number of GMM components already shows promising estimation results.