Fatigue monitoring using wearables and AI: Trends, challenges, and future opportunities

Monitoring fatigue is essential for improving safety, particularly for people who work long shifts or in high-demand and high-risk environments such as transportation, construction, healthcare, and manufacturing. The development of wearable technologies, such as fitness trackers and smartwatches, has made it possible to continuously analyze physiological signals in real-time to determine a person's level of exhaustion. This has allowed for timely insights into preventing hazards associated with fatigue. This review focuses on wearable technology and artificial intelligence (AI) integration for fatigue detection, using a systematic approach guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. Studies that used signal processing methods to extract pertinent aspects from physiological data, such as electrocardiogram (ECG), electromyogram (EMG), and electroencephalogram (EEG), among others, were analyzed as part of the systematic review process. These features were then analyzed using models, to detect patterns of fatigue and anticipate its onset. By merging data from several sources, information fusion techniques enhanced the precision and dependability of fatigue evaluation. The findings demonstrate that wearable devices can accurately identify fatigue through multi-modal signal analysis when combined with advanced ML/DL models. Information fusion techniques, which combine data from multiple sensors, significantly improved the accuracy and reliability of fatigue assessments. These developments open the door for more improvements in this field and offer valuable tools for enhancing safety and reducing fatigue-related hazards.