Article’s

Operational efficiency within defence research organizations depends heavily on the physical and cognitive readiness of personnel. Fatigue among officers and staff can lead to reduced concentration, impaired decision-making, and increased operational risks. Traditional fatigue assessment methods are largely reactive and lack predictive capabilities. This research presents a Machine Learning-based Health and Fatigue Prediction System designed for defence personnel. A synthetic dataset was generated using physiological and operational parameters such as working hours, sleep duration, heart rate, stress level, workload intensity, and recovery time. Data preprocessing techniques, including Label Encoding and Standard Scaling, were applied to prepare the dataset for model training. Two ensemble learning algorithms, Random Forest and XGBoost, were implemented and evaluated using Accuracy Score, Confusion Matrix, and Classification Report. Experimental results demonstrated strong predictive performance, validating the feasibility of AI-driven fatigue monitoring systems in defence environments. The proposed system can support proactive intervention, enhance workforce management, and improve operational readiness through predictive analytics.