A method, system and storage medium for chronic low back pain surface electromyography discrimination based on fourier analysis neural network

By using Fourier analysis neural networks to process surface electromyography signals, the problems of subjectivity and noise interference in the assessment of chronic low back pain are solved, and efficient and accurate automated discrimination is achieved.

CN121400850BActive Publication Date: 2026-06-19GUANGDONG UNIV OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
GUANGDONG UNIV OF TECH
Filing Date
2025-09-11
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing methods for assessing chronic low back pain rely on professional experience, are subjective and costly, and surface electromyography (EMG) signal assessment methods are difficult to extract discriminative power and maintain model robustness in noisy environments.

Method used

A method based on Fourier analysis neural networks was adopted to extract the latent periodic features of surface electromyography signals through preprocessing and training, construct a loss function and train the neural network to achieve automated identification of chronic low back pain.

Benefits of technology

It improves the accuracy and objectivity of chronic low back pain assessment, enhances the robustness and generalization ability of the model, and can effectively identify chronic low back pain in noisy environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121400850B_ABST
    Figure CN121400850B_ABST
Patent Text Reader

Abstract

This invention provides a method, system, and storage medium for discriminating surface electromyography (EMG) signals in chronic low back pain based on a Fourier analysis neural network. First, a dataset is acquired, containing several EMG signals and their corresponding ground truth labels. The EMG signals are preprocessed to obtain preprocessed EMG signals. These preprocessed EMG signals are then input into a constructed Fourier analysis-based neural network to obtain a predicted label for each EMG signal. A loss function is constructed based on the ground truth labels and predicted labels, and the Fourier analysis-based neural network is trained to obtain a trained Fourier analysis-based neural network. The EMG signal to be detected is then input into the trained Fourier analysis-based neural network to obtain the corresponding predicted label. This invention, by constructing and training a Fourier analysis-based neural network, aims to extract discriminative latent periodic features, achieving automated discrimination of abnormal patterns in EMG signals of chronic low back pain, thus achieving more robust, generalizable, and efficient discrimination.
Need to check novelty before this filing date? Find Prior Art