A Comprehensive Review of Optimized Graph Transformer with Alpine Skiing Optimization: Improving Initiative IoT in Human Resource Management by Predicting Workers’ Stress

Abstract

The rapid evolution of Internet of Things (IoT) technologies has significantly transformed human resource management (HRM), enabling real-time monitoring and predictive analytics of workforce well-being. Among emerging concerns, occupational stress has become a critical factor affecting productivity, decision-making, and organizational sustainability. This paper presents a comprehensive review of an optimized Graph Transformer integrated with Alpine Skiing Optimization (ASO) for predicting workers’ stress within initiative IoT frameworks. The proposed conceptual framework leverages graph-based deep learning to model complex relationships among physiological, behavioral, and environmental data collected through IoT sensors. Alpine Skiing Optimization is employed to enhance model convergence and feature selection efficiency, addressing challenges such as data heterogeneity, scalability, and prediction accuracy. The study systematically analyzes recent advancements in graph neural networks, transformer architectures, and metaheuristic optimization techniques applied in HR analytics. Furthermore, it explores how the integration of these approaches improves stress prediction performance and supports proactive HR decision-making. The findings highlight the potential of hybrid AI-driven IoT systems in enabling adaptive, personalized, and real-time stress management solutions. This review provides insights into future research directions and practical implications for deploying intelligent HRM systems in smart workplaces.