Intelligent Health Monitoring in 6G Networks: Machine Learning-Enhanced VLC-Based Medical Body Sensor Networks

Recent advances in Artificial Intelligence (AI)-driven wireless communication demand innovative Sixth Generation (6G) solutions, particularly in hospitals where reliability and secure communication are crucial. Visible Light Communication (VLC) leverages existing lighting systems to deliver high data rates while mitigating electromagnetic interference. However, VLC systems in medical settings face fluctuating signal strength and dynamic channel conditions due to patient movement, necessitating advanced optimization techniques. This paper employs a site-specific ray tracing technique in Medical Body Sensor Networks (MBSNs) channel modeling within hospital scenarios to derive channel impulse responses (CIRs) and model path loss (PL) and Root Mean Square (RMS) delay spread in two distinct hospital settings. In the first section, we evaluate Machine Learning (ML)-based adaptive modulation in VLC-enabled MBSNs and introduce a Q-learning technique enabling real-time adaptation without prior environmental knowledge. In the second section, we propose a Long Short Term Memory (LSTM) based approach to estimate PL and RMS delay spread in dynamic hospital environments. The Q-learning method consistently achieved the target symbol error rate (SER), though spectral efficiency (SE) was sometimes lower than optimal due to quantization limits and a cautious approach near the SER threshold. For LSTM-based channel estimation algorithm, simulation studies show that in the Intensive Care Unit (ICU) ward scenario, D1 has the highest Root Mean Squared Error (RMSE) for estimated path loss (1.6797 dB) and RMS delay spread (1.0567 ns), whereas in the Family-Type Patient Rooms (FTPR) scenario, D3 exhibits the highest RMSE for estimated path loss (1.0652 dB) and RMS delay spread (0.7657 ns).