AI-Aided Gait Analysis with a Wearable Device Featuring a Hydrogel Sensor.

Area of Science:

• Materials Science
• Biomedical Engineering
• Artificial Intelligence

Background:

• Wearable devices are crucial for real-time health monitoring but face limitations in flexibility, weight, and accuracy.
• Existing sensors often struggle to balance performance with user comfort and practicality.

Purpose of the Study:

• To develop a novel wearable sensor system for accurate gait monitoring.
• To integrate a flexible hydrogel sensor with artificial intelligence for enhanced biomechanical analysis.

Main Methods:

• Development of a conductive polyacrylamide-lithium chloride-MXene (PLM) hydrogel sensor with polydimethylsiloxane (PDMS) and polyurethane (PU) layers.
• Integration of the PLM sensor into a lightweight (23 g) knee brace to capture motion-generated energy.
• Digitization of sensor signals and analysis using a one-dimensional (1D) convolutional neural network (CNN).

Main Results:

• The PLM sensor demonstrated exceptional stretchability (317% strain) and durability (1000 cycles) with stable signal output.
• The wearable device accurately classified four distinct gait patterns (standing, walking, jogging, running) with 100% accuracy.
• The system effectively converted mechanical knee motion into electrical signals for AI analysis.

Conclusions:

• The developed wearable device offers a lightweight, energy-efficient solution for advanced biomechanical monitoring.
• The combination of advanced hydrogel sensors and AI shows significant potential for sports performance tracking and healthcare applications.
• This technology paves the way for more sophisticated and user-friendly health monitoring systems.