相关实验视频
Updated: Mar 14, 2026

08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
11.2K
从使用深度传感器融合的穿着可穿戴设备中检测睡眠和清醒状态
Yumna Anwar1, Kanika Bansal1,2, Murat Kucukosmanoglu3
1Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, MD, USA.
Scientific reports
|March 13, 2026
概括
这项研究引入了一种新的深度学习方法,使用穿着的可穿戴设备来监测患有注意力缺陷多动症 (ADHD) 的儿童的睡眠. 该方法精确检测睡眠障碍,为临床评估提供了一个有希望的非侵入性替代方案.
科学领域:
- 生物医学工程 生物医学工程
- 神经科学是一个神经科学.
- 睡眠医学 睡眠医学
背景情况:
- 充足的睡眠对整体健康至关重要,但患有注意力缺陷多动症 (ADHD) 的儿童经常经历睡眠障碍.
- 目前的睡眠监测工具,如多睡眠监测和手腕穿戴设备,对于这一群体来说,在成本,复杂性和准确性方面存在重大限制.
研究的目的:
- 开发和验证一种基于深度学习的非侵入性系统,用于准确监测ADHD儿童的睡眠.
- 评估使用穿在腿部的多式可穿戴设备 (RestEaze) 来捕获生理和运动数据的可行性.
主要方法:
- 利用穿着在腿上的可穿戴设备收集14名儿童的光电解剖学 (PPG),运动 (加速计,陀螺仪) 和温度数据,用于ADHD评估.
- 开发并比较了一个支持矢量机 (SVM) 基线模型与两个深度学习模型 (CNN-BiLSTM),使用原始多式联接输入的早期和晚期融合技术.
- 实施了一种时间标签平滑方法,以提高睡眠和清醒状态分类的一致性.
主要成果:
- 晚期融合的CNN-BiLSTM模型实现了高精度,在五倍交叉验证中,ROC曲线下的面积为90.94%.
- 该系统成功地获得了关键的睡眠指标,包括总睡眠时间,入睡后醒来,入睡延迟和唤醒.
- 证明了多式联运数据融合和深度学习的有效性,用于强大的睡眠阶段分类.
结论:
- 基于腿部的多式传感与深度学习相结合,为监测儿科神经发育人口的睡眠提供了一种可行的非侵入性方法.
- 这项技术在诊断和管理ADHD儿童睡眠问题的现有方法上提供了潜在的改进.
- 进一步的研究可以探索将这些发现整合到常规临床实践中,以改善儿科护理.
相关概念视频
Sleep-Wake Cycles
3.2K
Sleep is an essential physiological process vital to maintaining overall well-being. The reticular activating system (RAS), a network of neurons in the brainstem, regulates wakefulness and sleep. While it may seem passive, sleep consists of distinct cycles, each with its unique characteristics and functions. Two key sleep phases are non-rapid eye movement (NREM) and rapid eye movement (REM).
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
3.2K
Pulse Oximetry
1.6K
Pulse oximetry, or SpO2, is a non-invasive method for continuously monitoring arterial oxygen saturation (SaO2). This procedure involves attaching a probe or sensor to the patient's fingertip, forehead, earlobe, or nose bridge. The sensor works by detecting changes in oxygen saturation levels through light signals generated by the oximeter and reflected by the pulsing blood under the probe.
Purpose
Average SpO2 values are greater than 95%. If the readings fall below 90%, it indicates that...
Purpose
Average SpO2 values are greater than 95%. If the readings fall below 90%, it indicates that...
1.6K

