A Machine Learning-Based Online Human Motion Recognition System With Multiple Classifier for Exoskeleton

Motion recognition and classification are crucial for exoskeleton applications in rehabilitation, activities of daily living (ADL), and entertainment. Accurate activity analysis is essential to improve human-machine coupling. However, conventional single-task detection systems, which focus on specific requirements, such as finite gait events, mode transitions (such as standing-to-sitting), or locomotion speed, are inadequate and cannot handle the complex and varied walking environments encountered during ADL. This article proposes a real-time, multiclassifier system that incorporates three artificial neural network (ANN) models to simultaneously recognize five gait events, nine activities, and walking speeds ranging from 0 to 8 km/h. Three machine-learning (ML) algorithms were fused and utilized to minimize reliance on manual thresholding methods. The activity detection, speed recognition, and gait detection were performed using a 1-dimension convolutional neural network (1-D-CNN), regression ANN (RANN), and multilayer perceptron (MLP), respectively. The experiment was conducted with five subjects wearing a developing cable-driven exoskeleton. The results demonstrate that the proposed portable motion recognition system accurately detected various movements, including gait events with 99.6% accuracy and a time error of 33 ms, a recognize speed with a mean square error (MSE) of 0.12, and an activity detection with 96.8% accuracy.