Direction of Arrival Estimation Based on Deep Neural Network in MIMO System

Multiple-input multiple-output (MIMO) is the key technology for the fifth-generation (5G) mobile communication system. However, to reduce the hardware cost of the MIMO system, a low-resolution analog to digital converter (ADC) is usually used at the receiver, which reduces the data resolution and males the data recovery more difficult. To address this problem, in this paper, we focus on direction-of-arrival (DOA) estimation and propose a novel deep neural network (DNN) based framework to recover received data effectively. We use the multiple signal classification (MUSIC) algorithm to estimate the DOA of the recovery data and analyze the effect of different SNRs and quantization bits on the performance. The simulation results show that the proposed DNN based framework can achieve much better performance on DOA estimation compared with traditional methods.