A Multi-Indicator Approach For Enhancing Real-Time Worker Fatigue Monitoring In Mining Environments - SME Annual Meeting 2026

This research developed and simulated a novel multi-indicator Fatigue Detection and Alert System (FDAS) designed to enhance fatigue detection accuracy in mining environments. The system integrates a comprehensive set of inputs: eye blink rate, eye closure duration, yawning frequency, distraction levels, Pre-shift Check-in Scores (Self-report) and Electroencephalography (EEG) Levels. Using MATLAB’s Fuzzy Logic Rule Viewer (FLRV) and Simulink, simulations demonstrated the FDAS’s robust ability to process these diverse physiological and behavioural indicators accurately. It effectively classified operator fatigue into low, moderate, and high fatigue levels, consistently providing appropriate outputs and corresponding intervention recommendations across various mixed-signal scenarios. The system achieved a calculated accuracy of 85.19% across 27 test entries, with a standard deviation of approximately 1.8459, confirming its reliability for real-time fatigue monitoring. These findings highlight the significant potential of this fuzzy logicbased approach to proactively identify early signs of fatigue, substantially enhancing safety and operational efficiency in demanding mining operations.