Muscle strength detection device based on hall sensor and gesture recognition method

By combining Hall sensors and convolutional neural networks, the problems of sensor susceptibility to interference and wear in traditional muscle strength measurement are solved, achieving high-precision, low-power, and long-life muscle strength measurement and gesture recognition.

CN122111231APending Publication Date: 2026-05-29NANJING NORMAL UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NANJING NORMAL UNIVERSITY
Filing Date
2026-02-28
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing technologies for muscle strength measurement suffer from problems such as sensor susceptibility to interference and wear, high computational complexity, and insufficient signal processing, resulting in inadequate measurement accuracy and stability.

Method used

A muscle strength detection device based on Hall sensors is used, which combines non-contact mechanical transmission and magnetic field sensing. The Hall sensor senses the changes in magnetic field caused by muscle deformation, and the signal is processed using filtering, analog-to-digital conversion and wireless communication technologies. The one-dimensional time-series signal is converted into a two-dimensional image, and gesture recognition is performed using a convolutional neural network.

Benefits of technology

It achieves high signal-to-noise ratio, good long-term stability, and low power consumption in muscle strength measurement. It can accurately recognize gestures, adapt to different arm circumferences, and has a long system battery life.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122111231A_ABST
    Figure CN122111231A_ABST
Patent Text Reader

Abstract

The application discloses a muscle strength detection device based on a Hall sensor and a gesture recognition method. The device comprises a wearable shell, which is worn on the surface of a target muscle group; a mechanical transmission and sensing unit, which is arranged in the shell and comprises a moving block and a magnet assembly fixed in the moving block, the moving block being in contact with the skin to sense muscle deformation; a Hall sensor, which is fixed in the shell and is arranged in non-contact opposite to the magnet assembly, and is used for detecting the magnetic field change caused by the displacement change of the magnet assembly driven by the moving block; and a circuit system unit, which is connected with the Hall sensor for signal processing and transmission. The algorithm encodes the collected muscle strength signals into two-dimensional images by using Gram angle fields and Markov transition fields after pretreatment, and then inputs the two-dimensional images into a convolutional neural network to realize gesture recognition. The application can capture low-noise muscle strength signals, fully excavate the space-time information in the signals, and realize high-precision gesture recognition. Moreover, the device can be adjusted to adapt to different arm circumferences and overcome individual differences.
Need to check novelty before this filing date? Find Prior Art