Hybrid IoT-Edge-Cloud Computing-based Athlete Healthcare Framework: Digital Twin Initiative

Internet of Things (IoT) paradigm has been able to revolutionize ubiquitous healthcare in time-sensitive manner. Conspicuously, the current study proposes an intelligent athlete healthcare framework utilizing IoT-edge computing technology for effective medical care during excessive training and exercise sessions of athletes. Specifically, for analyzing real-time health data during exercises, probabilistic health state susceptibility is detected and quantified. The proposed framework incorporates a probabilistic Bayesian model for the effective classification of health-oriented vitals based on vulnerability. Furthermore, a Multi-scaled Long Term Memory (MLSTM) model is used for predictive purposes. Experimental simulations were conducted to determine validation aspects of the presented framework over challenging datasets. Comparative analysis with state-of-the-art decision-modeling techniques show that the presented framework is better in terms of statistical performance of Temporal Efficacy(62.85%), Classification Efficiency (Precision (95.63%), Specificity (92.32%), and Sensitivity (94.33%)), Predictive Accuracy (95.65%), and Stability (69%).