In this paper, we study the problem of direction of arrival estimation and model order selection for systems employing subarray sampling. Thereby, we focus on scenarios, where the number of resolvable active sources is not smaller than the number of simultaneously sampled antenna elements, i.e., we operate above the conventional limit for most estimators. For this purpose, we propose new schemes based on neural networks and estimators that combine neural networks with gradient steps on the likelihood function. These methods are able to outperform existing estimators in terms of mean squared error and model selection accuracy, especially in the low snapshot domain, at a drastically lower computational complexity.

中文翻译：

---

具有子阵列采样的天线阵列 DoA 估计和模型阶数选择的机器学习方法

在本文中，我们研究了采用子阵列采样的系统的到达方向估计和模型阶数选择问题。因此，我们专注于可解析有源源的数量不小于同时采样的天线单元的数量的场景，即我们在大多数估计器的常规限制之上运行。为此，我们提出了基于神经网络和估计器的新方案，将神经网络与似然函数的梯度步骤相结合。这些方法能够在均方误差和模型选择精度方面优于现有的估计器，尤其是在低快照域中，计算复杂度大大降低。