AI-Driven Safety and Health Monitoring System: A Three-Tier Architecture for Industrial Environments

Abstract

This study uses three-tier architecture to explain safety and health monitoring in industrial environments. It attempts to combine wearable sensors, AI-driven models and finally data visualization. Tier-one presents real-time health metrics that are collected using wearable devices; embedded with sensors. Tier-two is set to portray an AI-driven system, utilizing MATLAB’s Aggregate Channel Features (ACF). Tier-three shows how data is integrated and visualized in Power BI dashboards for actionable insights.  AI-driven system is considered important as it predicts Personal Protective Equipment (PPE) requirements to safeguard workers from potential safety risks and ensures compliance with Personal Protective Equipment (PPE) requirements. The suggested three-tier architecture addresses the limitations of manual monitoring by providing real-time, data-driven solutions. It has high potential to significantly improve compliance and proactive safety management. The proposed three-tier architecture highlights the importance of integrating the three levels: to enhance health and safety in an industrial working setting. Active detection and monitoring can facilitate fast responses in emergencies and improve decision making systems