Enhancing IoT-Enabled Healthcare Applications by Efficient Cluster Head and Path Selection Using Fuzzy Logic and Enhanced Particle Swarm Optimization

Abstract

Leveraging Internet of Things (IoT) technologies in healthcare, including wireless sensor networks (WSN) and new generation networks, facilitates the integration of diverse medical equipment and enables smart interactions among them. This innovation contributes significantly in meeting the needs of healthcare professionals and improving the quality of life of patients. However, ensuring efficient communication within IoT systems is crucial to meet the critical demands of healthcare, such as real-time monitoring and emergency situations. This paper proposes a novel approach for determining cluster heads and selecting efficient paths in IoT-enabled healthcare applications. The cluster head selection process utilizes a fuzzy logic mechanism, considering factors like energy, distance, and latency. Subsequently, the particle swarm optimization (PSO) technique is employed to identify optimal pathways for routing. MATLAB-based simulations have been conducted to evaluate the proposed approach in terms of several key metrics, including average delay, packet delivery ratio, energy efficiency, and throughput. The results of the evaluation demonstrate significant improvements over comparable works. Specifically, our solution achieves a packet delivery ratio of 91.3%, an average delay of 0.12 s, a throughput of 60.1 bps, and an energy efficiency of 8.9 J/bit. These findings underscore the effectiveness of our proposed approach in meeting the stringent requirements of IoT-enabled healthcare systems, particularly by achieving lower delays and higher throughput.