The speed of biometric data generated by health monitoring devices requires real-time processing that conventional cloud systems cannot provide due to the high latency and poor resource allocation. To overcome these dilemmas, the present paper proposes a Crayfish Optimization-based Hadoop MapReduce (CO-HMR) framework. This new fog-big-data architecture optimizes resource allocation for monitoring biological systems. It preprocesses vital-system data at the edge and dynamically allocates fog-layer resources using the Crayfish Optimization Algorithm (COA) to minimize processing delays. Hadoop MapReduce is also used to run large-scale data to deliver reliability and scalability. Experimental findings indicate that CO-HMR achieves 98.21% accuracy, 2.27 s of execution time, 19.1 s of latency, and 2.12 J of energy consumption, surpassing those of existing fog-based healthcare models. The results show the possibilities of CO-HMR to empower efficient, low-latency, and energy-conscious smart healthcare monitoring.
Pal et al. (Thu,) studied this question.