Worker’s physical fatigue classification using neural networks

Physical fatigue is not only an indication of the user’s physical condition and/or need for sleep or rest, but can also be a significant symptom various diseases. This affects performance workers in jobs that involve some continuous activity, and cause large proportion accidents at work. The commonly measured by perceived exertion (RPE). Many previous studies have attempted to continuously monitor order detect level prevent these accidents, most used invasive sensors are difficult place worker from performing their tasks correctly. Other works use activity measurement such as accelerometers, amount information obtained analyse extract characteristics each state. In this work, we dataset contains data inertial several activities during working day, labelled every 10 min based on using questionnaires Borg scale. Applying Machine Learning techniques, design, develop test system neural network capable classifying variation caused collected min; purpose, feature extraction performed after time decomposition done with Discrete Wavelet Transform (DWT). results show proposed has accuracy higher than 92% all cases, being viable its application scenario.