Objective physical fatigue evaluation method based on wearable sensor information fusion

By designing a spatiotemporal fusion dual-branch multimodal network and combining IMU and ECG signals, the problem of insufficient single-modal signals in existing physical fatigue assessment methods is solved, and more accurate physical fatigue assessment and real-time monitoring are achieved.

WO2026137265A1PCT designated stage Publication Date: 2026-07-02SHENZHEN INST OF ADVANCED TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
SHENZHEN INST OF ADVANCED TECH
Filing Date
2024-12-25
Publication Date
2026-07-02

AI Technical Summary

Technical Problem

Existing methods for assessing physical fatigue rely on signals from single-modal sensors and lack the fusion of complementary features between heterogeneous modes, resulting in insufficient assessment accuracy and requiring a cumbersome feature selection process.

Method used

A spatiotemporal fusion dual-branch multimodal network was designed, which uses IMU signals and ECG signals for feature extraction and fusion. It captures complex patterns and time-varying information across channels through spatial and temporal branches, and captures the joint representation of various heterogeneous sensors through a multimodal feature fusion module.

Benefits of technology

It improves the classification accuracy of physical fatigue assessment, enables end-to-end real-time assessment without manual feature selection, and enhances the ability to comprehensively assess the fatigue status of athletes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024142409_02072026_PF_FP_ABST
    Figure CN2024142409_02072026_PF_FP_ABST
Patent Text Reader

Abstract

Disclosed in the present invention is an objective physical fatigue evaluation method based on wearable sensor information fusion. The method comprises: using a wearable device to acquire an IMU signal and an ECG signal of a target; and pre-processing the IMU signal and the ECG signal, and then inputting same into a spatio-temporal fusion dual-branch multi-modal network to obtain a fatigue level classification result, wherein the spatio-temporal fusion dual-branch multi-modal network comprises a multi-modal feature extraction module, a spatio-temporal dual-branch feature fusion module, a multi-modal feature fusion module, and a fatigue level classification module. The multi-modal feature extraction module is configured to extract a spatial feature and a temporal feature. The spatio-temporal dual-branch feature fusion module is configured to perform interactive fusion on temporal features and spatial features of sensors of the same category to obtain a joint representation of spatio-temporal features. The multi-modal feature fusion module is configured to capture a joint representation of multi-modal features of signals from various heterogeneous sensors. The fatigue level classification module obtains the fatigue level classification result. The present invention improves the accuracy of physical fatigue classification.
Need to check novelty before this filing date? Find Prior Art