A human activity state recognition method based on a photoelectric volume pulse signal

By employing adaptive denoising and multi-domain feature fusion, the problem of recognizing single-channel PPG signals in complex motion scenarios was solved, achieving high-precision and stable human activity recognition and improving the robustness and generalization ability of the model.

CN122272003APending Publication Date: 2026-06-26FUDAN UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
FUDAN UNIVERSITY
Filing Date
2026-03-27
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

In complex motion scenarios, single-channel PPG signals are susceptible to motion artifacts. Existing methods struggle to effectively denoise these artifacts and distinguish between physiological rhythm information and motion dynamics information, resulting in decreased recognition performance and insufficient generalization ability when applied across subjects.

Method used

A multi-domain feature fusion-based approach is adopted, which uses adaptive denoising, time-frequency feature construction, and bi-branch feature modeling to guide the modeling of activity dynamics information by utilizing stable physiological rhythm information. An adaptive denoising module is constructed and combined with time-frequency domain feature extraction to achieve joint modeling of physiological rhythm and motion dynamics information.

Benefits of technology

It improves the accuracy and stability of human activity recognition, especially in cross-individual application scenarios, demonstrating strong robustness and adaptability, and enhancing the model's recognition performance in complex motion scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122272003A_ABST
    Figure CN122272003A_ABST
Patent Text Reader

Abstract

This invention relates to the field of wearable computing and signal processing technology, specifically to a method for human activity recognition based on photoplethysmography (PPG) signals. It addresses the problem of recognizing single-channel PPG signals under complex motion conditions. The method includes the following steps: acquiring single-channel PPG signals of the human body in different activity states, the signals being derived from existing data sources; performing bandpass filtering on the signals to remove baseline drift and high-frequency noise; and dividing the signals into fixed-length time window samples. An adaptive joint denoising module and a multi-domain feature collaborative modeling structure are constructed. By decomposing, filtering, and reconstructing the PPG signals, and combining time-domain and time-frequency domain feature extraction, joint modeling of physiological rhythm information and motion dynamic information is achieved, thereby improving the accuracy and stability of human activity recognition.
Need to check novelty before this filing date? Find Prior Art