Deep Learning-Based Signal Detection with Soft Information for MISO-NOMA Systems

This paper proposes a deep learning-based receiver scheme with soft information for uplink multiple-input single-output (MISO) non-orthogonal multiple access (NOMA) systems, named by DLSI. In the proposed DLSI, we first perform QL-decomposition for channel matrix and iteratively construct the solution of the objective function for signal detection. Then deep neural networks (DNNs) are used to realize iteration steps and restore the symbols of the transmitted signals one by one. After all symbols of a user are detected, the successive interference cancellation (SIC) algorithm is used to detect the symbols of the next user. The output of each DNN is added with a soft decision layer, and the soft information will be input to the next DNN to improve the accuracy of training. Soft information contains more signal knowledge than hard decision, so it is also used in the SIC step, which reduces error propagation to a certain extent. Simulation results show that the performance of the DLSI is better than other deep learning methods.