A Grip Strength Estimation Method Using a Novel Flexible Sensor under Different Wrist Angles.

Area of Science:

• Biomedical Engineering
• Wearable Technology
• Sensor Development

Background:

• Accurate, continuous handgrip strength detection is challenging due to complexity and uncertainty.
• Existing methods may lack precision or adaptability to varying wrist angles.

Purpose of the Study:

• To develop a novel flexible deformation sensor for accurate handgrip strength estimation.
• To enable real-time, continuous grip strength prediction across multiple wrist angles.

Main Methods:

• A flexible deformation sensor was created using a foaming sponge, Hall sensor, LED, and photoresistors (PRs).
• The sensor measures muscle deformation by detecting changes in light intensity within the sponge.
• A grip strength-arm muscle model and a dynamic window-based 1D convolutional neural network (CNN) were employed.

Main Results:

• The flexible deformation sensor accurately detected arm muscle deformation.
• The developed muscle model and CNN successfully predicted hand grip strength in real-time.
• The system demonstrated effectiveness across different wrist angles.

Conclusions:

• The proposed flexible sensor and modeling approach offer a viable solution for accurate, real-time handgrip strength monitoring.
• This technology has potential applications in rehabilitation, sports science, and human-computer interaction.
• The integration of sensor technology and AI enhances the precision of biomechanical measurements.