基于雷达与PPG信号的睡眠觉醒检测、评估方法及设备
By combining multi-scale feature extraction and fusion of radar echo and photoplethysmography (PPG) signals, and utilizing deep neural networks for sleep wakefulness detection, the problems of insufficient detection accuracy and stability in existing technologies are solved, achieving efficient and accurate sleep wakefulness detection and assessment.
CN121533701BActive Publication Date: 2026-07-17BEIJING TSINGRAY TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING TSINGRAY TECH CO LTD
- Filing Date
- 2026-01-21
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing sleep-wake detection technologies, which rely on electroencephalogram (EEG) signals and cardiovascular and autonomic nervous system signals, suffer from inconvenient equipment, susceptibility to interference, and individual differences, resulting in insufficient accuracy and stability.
Method used
By combining radar echo signals and photoplethysmography (PPG) signals, multi-scale feature extraction and fusion are performed using deep neural networks. Segment proposal networks and fragment of interest head networks are then used to detect and evaluate sleep-wake events.
Benefits of technology
It improves the stability and accuracy of sleep-wake detection, reduces the false detection rate, and enhances the reliability and accuracy of detection in complex environments.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121533701B_ABST
Abstract
本发明提供一种基于雷达与PPG信号的睡眠觉醒检测、评估方法及设备。应用于雷达与生物信号数据处理技术领域。该方法包括：获取在目标对象睡眠期间采集的雷达回波信号和光电容积脉搏波信号；利用第一多尺度特征提取网络对雷达谱图进行多尺度特征提取，利用第二多尺度特征提取网络对光电容积脉搏波时频图进行多尺度特征提取，利用融合层将雷达多尺度特征图和脉搏多尺度特征图进行融合；利用片段提议网络任务头对多尺度融合特征图进行回归分类，得到候选特征图片段；利用感兴趣片段头部网络将候选特征图片段进行睡眠觉醒事件预测，得到目标特征图片段。本发明提高了睡眠觉醒事件检测的准确性。
Need to check novelty before this filing date? Find Prior Art