Abstract This paper presents a comprehensive framework for the design, modeling, and performance evaluation of an AI-driven Visible Light Communication (VLC) system for smart hospital and healthcare Internet of Things (HIoT) applications. The proposed approach integrates VLC physical-layer modeling, patient-priority-aware scheduling, power and resource allocation, and machine learning–based link adaptation and anomaly detection. Analytical formulations are developed for optical channel and noise characteristics, achievable capacity under reliability constraints, and optimization problems for power control and resource assignment, along with learning-based models for adaptive transmission in dynamic hospital environments. Closed-form approximations and practical design guidelines are also provided to support efficient deployment. The proposed framework targets ultra-reliable and low-latency communication (URLLC) requirements of critical medical devices while ensuring secure telemetry and scalable resource sharing. Simulation results show that the system achieves stable data rates of 5–10 Mbps per device with an end-to-end latency of approximately 0.2 ms, even under dense and mobile operating conditions.
Verma et al. (Fri,) studied this question.