Multipurpose wearable sensor-based platform for weight training

In recent years, there has been a growing interest in automated tracking and detection of sports activities. Researchers have shown that tracking and monitoring the workout activities aids in keeping the individuals' motivation by providing feedback and information about their progress and achievement throughout their exercise program. In this regard,wearable devices are great tools for monitoring the exercise without imposing any additional limitation on users' performance. This study presents a novel multipurpose wearable device for automatic weight detection, activity type recognition and count repetition in sports activities such as weight training using various classification technique. The autonomous weight detection and activity recognition device wouldmaximize workout efficiency and prevent overreaching and overtraining. The device monitors weights and activities by using anInertial Measurement Unit(IMU), an accelerometer and three force sensors mounted in the glove and classifies them by utilizing developed machine learning models. For weight detection, different classifiers including Linear Discriminant Analysis (LDA), Support Vector Machine (SVM),and Multi-layer Perceptron Neural Networks (MLP) were investigated. For activity recognition, we utilized K Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF),and SVM models. Experimental results indicate that SVM classifier can achieve the highest accuracy for weight detection application and RF can outperform other classifiers for activity recognition application.The results reveal that the suggested wearable device can provide in-situ accurate information regarding the lifted weight and activity type with minimum physical intervention.