Intelligent Gait Analysis System Enabled by Liquid Metal-Embedded Sponge Triboelectric Sensor Arrays

Area of Science:

• Biomedical Engineering
• Materials Science
• Artificial Intelligence

Background:

• Gait dynamics are crucial biomarkers for health assessment and disease prediction.
• Existing gait monitoring methods often lack comfort and long-term usability.

Purpose of the Study:

• To develop an intelligent, comfortable, and long-term gait monitoring system.
• To integrate flexible triboelectric nanogenerators with AI for gait analysis.

Main Methods:

• A flexible PDMS/liquid metal sponge triboelectric nanogenerator (PLMFT) array was developed.
• An insole-type monitoring system with five PLMFT sensing units was constructed.
• Convolutional neural networks (CNNs) were employed to analyze gait signals.

Main Results:

• The PLMFT device demonstrated excellent flexibility, high electrical output, and stability over 3000 cycles.
• The insole system offered breathability and wearable comfort.
• CNN analysis achieved a gait recognition accuracy of 98.95%.

Conclusions:

• The proposed system offers a high-precision, lightweight solution for wearable health monitoring.
• This technology has significant potential for gait abnormality detection, motor function assessment, and disease prediction.