Enhancing Signal Detection in 6G Networks through LSTM-based MIMO Technology

Artificial intelligence (AI) transforms the multiple input multiple output (MIMO) technology into a promising candidate for beyond-fifth-generation (B5G) and upcoming sixth-generation (6G) networks. However, due to the large number of antennas in the MIMO systems, the detection process becomes very complex and also shows high computational complexity. To address this issue, this paper introduces an optimized AI-based signal detection method based on Long short-term memory (LSTM) called LSTM-based signal detection for MIMO systems. The proposed model works more efficiently in signal detection as compared to the conventional signal detection methods in terms of symbol error rate (SER) at different signal-to-noise ratios (SNR). The optimized simple LSTM architecture provides significant advantages in detecting patterns from input data. This paper goes through the various aspects of signal detection using LSTM, such as system architecture design, data preparation and training process of the neural network, performance evaluation, and future scope. Overall, this paper provides a comprehensive resource for the deployment of an LSTM neural network for signal detection in the upcoming 6G wireless networks.