Enhanced Fox Optimizer for Internet of Things Powered Personalized Healthcare Systems

Abstract

The Internet of Things (IoT) paradigm has recently opened up new research opportunities in many academic and industrial fields, particularly medicine. IoT-enabled technology has transformed healthcare from a centralized model to a personalized healthcare system driven by ubiquitous wearable devices and smartphones. The implementation of IoT in healthcare faces critical challenges, including energy efficiency, network reliability, task response time, and availability of services. An Adaptive Fox Optimizer (AFO) is proposed as a novel IoT-supported method for providing healthcare services. The zero-orientation nature of AFO is mitigated by quasi-oppositional learning. A reinitialization plan is also presented to improve exploration skills. Furthermore, an additional stage is implemented with two novel movement techniques to optimize search capabilities. In addition, a multi-best methodology is used to deviate from the local optimum and manage the population more efficiently. Ultimately, greedy selection accelerates convergence and exploitability. The proposed AFO was rigorously evaluated, demonstrating significant improvements across key performance metrics. Compared to conventional approaches, AFO enhances system availability by 83.33%, reliability by 11.32%, reduces energy consumption by 19.12%, and decreases task response times by 25.14%. These results highlight AFO's ability to optimize resource allocation, enhance fault tolerance, and prolong network lifespan in IoT healthcare environments. By addressing critical challenges, this research contributes to developing more efficient, reliable, and responsive IoT-enabled healthcare systems, paving the way for advancements in wearable health monitoring, telemedicine, and smart hospital management.