Healthcare Internet of Things (HIoT) systems play a pivotal role in continuous patient monitoring, yet they face persistent challenges related to limited energy capacity and strict latency requirements. This study proposes an adaptive, energy-aware communication strategy for HIoT devices that minimizes energy consumption while ensuring rapid data delivery during critical health events. Using the publicly available UCI Smart Heart Monitoring System dataset (2,200 real patient records), a Python 3.11-based simulation framework was developed utilizing NumPy, Pandas, and Matplotlib libraries. The proposed adaptive transmission model dynamically adjusts data transmission frequency in response to real-time physiological states and is directly compared with a baseline fixed-interval model. Quantitative evaluation was conducted using key performance metrics—total energy consumption, average communication latency, packet delivery success rate, and response time to critical events. Experimental findings reveal that the adaptive strategy achieved a 28% reduction in total energy consumption and 75% faster response times to critical events compared to the baseline (p < 0.05), while maintaining a packet delivery success rate exceeding 96%. Statistical validation across multiple simulation runs confirmed the robustness and reproducibility of the results. These outcomes demonstrate that the proposed context-aware communication mechanism effectively enhances energy efficiency and responsiveness in resource-constrained HIoT environments, making it suitable for real-time wearable and telemedicine applications.
Huthaifa Ayad Al-Ani (Mon,) studied this question.