Recognition of Human Lower Limb Motion and Muscle Fatigue Status Using a Wearable FES-sEMG System

Area of Science:

• Biomedical Engineering
• Rehabilitation Technology
• Wearable Sensors

Background:

• Existing functional electrical stimulation (FES) devices lack wearability and user intention recognition.
• Current limitations hinder the integration of FES into daily life for rehabilitation and training.

Purpose of the Study:

• To develop a novel wearable FES system with enhanced wearability and user intention detection.
• To enable accurate identification of motion type and muscle fatigue status during FES application.

Main Methods:

• Development of a wearable FES system utilizing customized textile electrodes.
• Integration of surface electromyography (sEMG) for capturing movement intention.
• Implementation of a parallel deep learning model for motion and fatigue analysis.

Main Results:

• The proposed system demonstrated high accuracy in lower limb motion recognition.
• Accurate detection of muscle fatigue status was achieved, unaffected by electrical stimulation.
• Preliminary experiments with five subjects validated the system's effectiveness.

Conclusions:

• The novel wearable FES system shows significant potential for improving FES-assisted rehabilitation and training.
• Customized textile electrodes and deep learning enhance user experience and functional outcomes.
• The system effectively addresses limitations of current FES devices for daily application.