Implementation of the deep learning method for signal detection in massive-MIMO-NOMA systems.

The integration of Non-Orthogonal Multiple Access (NOMA) with massive Multiple-Input Multiple-Output (MIMO) systems represents a pivotal advancement for next-generation wireless networks, offering enhanced spectral efficiency and massive connectivity. However, joint signal detection in massive-MIMO-NOMA systems presents significant computational challenges due to severe inter-user interference and high-dimensional channel matrices. Traditional detection algorithms, such as Minimum Mean Square Error (MMSE) and Successive Interference Cancellation (SIC), often suffer from high computational complexity or performance degradation under non-ideal channel conditions. This research direction explores the implementation of deep learning-based architectures to optimize signal detection in massive-MIMO-NOMA configurations. By modeling the detection process as a supervised learning or deep unfolding task, neural networks can learn

the complex mapping between received signals and transmitted data symbols. The proposed methodology evaluates the bit error rate (BER) performance, computational complexity, and convergence behavior of deep learning detectors under varying signal-to-noise ratios (SNR) and user densities. The simulation framework provides a comprehensive comparative analysis against conventional detection schemes, validating the robustness and efficiency of deep learning models in highly dense, interference-limited wireless environments.

Message: Hi FE, I need help with “Implementation of the deep learning method for signal detection in massive-MIMO-NOMA systems.” in “Electronics & Communication Engineering”