Hybrid signal algorithm detection in NOMA 5G waveform: Transforming smart healthcare connectivity by reducing latency

Abstract

The detection of hybrid signal algorithms in Non-Orthogonal Multiple Access (NOMA) 5G waveforms is changing the face of smart healthcare. The integration of NOMA allows multiple simultaneous connections in a given system, which significantly enhances spectral efficiency, ensuring unmatched communication between different medical devices and monitoring systems. Interference mitigation is guaranteed by the proper employment of hybrid signal algorithms that improve correct data interpretation, and are important for maintaining robust connectivity among healthcare facilities with heavy demands. These developments have overcome some of the key challenges in the domain of smart healthcare such as real-time data transmission for remote monitoring, telemedicine, and emergency response. Lowering latency and improving signal reliability will support rapid decision making and patient safety in critical situations. In this paper, we propose a hybrid signal detection algorithm that combines a zero-forcing equalizer (ZFE) and minimum mean square error (MMSE) for the NOMA-MIMO structure with Rician and Rayleigh channels, highlighting its role in empowering next-generation healthcare solutions through enhanced connectivity, reliability, and efficiency. For 16 × 16 and 64 × 64 MIMO-NOMA, the Bit error rate (BER) was evaluated and compared for Long Short-Term Memory (LSTM), ZFE, MMSE, and Maximum likelihood (ML) detection, and the proposed ZFE-MMSE algorithms. The simulation results revealed that the projected LSTM obtains a better BER at a low SNR with high complexity. However, ZFE-MMSE effectively detects the signal at a low SNR, outperforming contemporary algorithms at complexity similar to MMSE and ZFE, and can enhance the latency performance for smart health care applications.