3M: Measuring Vital Signs with Markov-Gauss Model

心跳 计算机科学 卡尔曼滤波器 雷达 隐马尔可夫模型 算法 马尔可夫模型 信号(编程语言) 人工智能 马尔可夫链 模式识别(心理学) 机器学习 电信 计算机安全 程序设计语言
作者
Chengyao Tang,Tian Jin,Yongpeng Dai,Zhi Li
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:28 (9): 5113-5123
标识
DOI:10.1109/jbhi.2024.3392250
摘要

Measuring vital signs (VS) contained in the echoes is crucial to the analyses of breathing and heartbeat signals using medical radar. Although many advanced signal processing algorithms have been developed for radar-based VS measurement and make some improved progress, existing schemes cannot achieve a good estimation of echo phases modulated by the respiratory and cardiac activities with high accuracy or low computation, and thus resulting in serious performance degradation on the subsequent separation of breathing and heartbeat patterns as well as the assessment of breathing rate (BR), heart rate (HR), and heart rate variability (HRV). In this paper, we propose a simple yet effective method to measure VS for medical radar, named 3M method. Specifically, our method firstly introduces the Markov-Gauss model to obtain the recursive expression of the echo phases carrying VS, and secondly derive a simple observation equation (SOE) to reflect the relationship between the observed signal and VS of radar measurement. Thirdly, the aforementioned Markov-Gauss model and SOE are fused by Kalman filter to measure VS with accurate estimation. The 3M method demonstrates an elegant structure, low complexity and excellent features introduced by Kalman filter. Simulation results show the superiority of 3M over other methods. Then, we conduct extensive experiments with insightful visualizations to validate the effectiveness of the 3M method. Comparative results on different scenarios illustrate that the 3M method not only achieves state-of-the-art VS measurement performance but also expresses robust properties to HRV analysis.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
迷路小丸子完成签到,获得积分10
刚刚
混世大魔王先生完成签到,获得积分10
刚刚
kiki完成签到,获得积分10
1秒前
zhuozhuo关注了科研通微信公众号
1秒前
2秒前
4秒前
Ade阿德完成签到 ,获得积分10
4秒前
GNY完成签到 ,获得积分10
5秒前
5秒前
自觉的K完成签到,获得积分10
6秒前
6秒前
8788完成签到,获得积分10
7秒前
呆萌芙蓉发布了新的文献求助10
7秒前
酒仙完成签到,获得积分10
7秒前
sasa完成签到,获得积分10
7秒前
Ran-HT完成签到,获得积分10
7秒前
喝到几点完成签到,获得积分10
7秒前
文成发布了新的文献求助10
8秒前
Lucas应助Gavin采纳,获得10
8秒前
8秒前
拉长的初彤完成签到 ,获得积分10
8秒前
卢浩完成签到,获得积分10
9秒前
科研小民工应助PPSlu采纳,获得200
9秒前
10秒前
10秒前
10秒前
wm完成签到,获得积分10
10秒前
隔岸发布了新的文献求助20
10秒前
Kate发布了新的文献求助10
10秒前
呱呱太完成签到,获得积分10
11秒前
ly完成签到,获得积分10
12秒前
拉长的初彤关注了科研通微信公众号
12秒前
王了了完成签到 ,获得积分10
13秒前
赘婿应助专一的书雪采纳,获得10
13秒前
月亮明星完成签到,获得积分10
14秒前
LL发布了新的文献求助10
14秒前
LLC完成签到,获得积分10
15秒前
情怀应助豆兜兜采纳,获得10
15秒前
情怀应助zhouyu采纳,获得50
15秒前
15秒前
高分求助中
Les Mantodea de Guyane Insecta, Polyneoptera 2500
Mobilization, center-periphery structures and nation-building 600
Technologies supporting mass customization of apparel: A pilot project 450
China—Art—Modernity: A Critical Introduction to Chinese Visual Expression from the Beginning of the Twentieth Century to the Present Day 430
Tip60 complex regulates eggshell formation and oviposition in the white-backed planthopper, providing effective targets for pest control 400
A Field Guide to the Amphibians and Reptiles of Madagascar - Frank Glaw and Miguel Vences - 3rd Edition 400
China Gadabouts: New Frontiers of Humanitarian Nursing, 1941–51 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3792971
求助须知:如何正确求助?哪些是违规求助? 3337641
关于积分的说明 10286083
捐赠科研通 3054212
什么是DOI,文献DOI怎么找? 1675888
邀请新用户注册赠送积分活动 803875
科研通“疑难数据库(出版商)”最低求助积分说明 761578