DeepHeart

作者
Xiangmao Chang,Gangkai Li,Guoliang Xing,Kun Zhu,Linlin Tu
出处
期刊:ACM Transactions on Sensor Networks [Association for Computing Machinery]
卷期号:17 (2): 1-18 被引量:57
标识
DOI:10.1145/3441626
摘要

Heart rate (HR) estimation based on photoplethysmography (PPG) signals has been widely adopted in wrist-worn devices. However, the motion artifacts caused by the user’s physical activities make it difficult to get the accurate HR estimation from contaminated PPG signals. Although many signal processing methods have been proposed to address this challenge, they are often highly optimized for specific scenarios, making them impractical in real-world settings where a user may perform a wide range of physical activities. In this article, we propose DeepHeart, a new HR estimation approach that features deep-learning-based denoising and spectrum-analysis-based calibration. DeepHeart generates clean PPG signals from electrocardiogram signals based on a training data set. Then a set of denoising convolutional neural networks (DCNNs) are trained with the contaminated PPG signals and their corresponding clean PPG signals. Contaminated PPG signals are then denoised by an ensemble of DCNNs and a spectrum-analysis-based calibration is performed to estimate the final HR. We evaluate DeepHeart on the IEEE Signal Processing Cup training data set with 12 records collected during various physical activities. DeepHeart achieves an average absolute error of 1.61 beats per minute (bpm), outperforming a state-of-the-art deep learning approach (4 bpm) and a classical signal processing approach (2.34 bpm).

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
11完成签到,获得积分10
1秒前
1秒前
song完成签到 ,获得积分10
1秒前
王敏完成签到 ,获得积分10
1秒前
山里万重完成签到,获得积分10
2秒前
Juvenilesy的应助被傻傻的起眸采纳,获得10
2秒前
2秒前
2秒前
和谐的寒风完成签到,获得积分20
2秒前
王长长完成签到,获得积分10
3秒前
3秒前
英姑的应助被brokey采纳,获得10
4秒前
xuhangming完成签到,获得积分20
6秒前
6秒前
jack完成签到,获得积分10
6秒前
8秒前
糜康发布了新的文献求助10
9秒前
10秒前
10秒前
10秒前
小艾同学发布了新的文献求助10
11秒前
坦率碧蓉完成签到 ,获得积分10
13秒前
13秒前
endlessloop发布了新的文献求助10
15秒前
WZJ发布了新的文献求助50
15秒前
Juvenilesy的应助被傻傻的起眸采纳,获得10
15秒前
Cc完成签到 ,获得积分10
15秒前
乌龙茶发布了新的文献求助10
17秒前
美菇完成签到 ,获得积分10
17秒前
王慧琳完成签到 ,获得积分10
17秒前
17秒前
19秒前
cuihanhan0824关注了科研通微信公众号
19秒前
彭于晏的应助被我的djwhjja采纳,获得10
21秒前
endlessloop完成签到,获得积分10
22秒前
hoohoo完成签到 ,获得积分10
22秒前
22秒前
积极的逍遥完成签到,获得积分10
22秒前
23秒前
huyangliu完成签到 ,获得积分10
24秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181658
求助须知:如何正确求助?哪些是违规求助? 9571454
关于积分的说明 21818081
捐赠科研通 7777987
什么是DOI,文献DOI怎么找? 3433508
关于科研通互助平台的介绍 2557696
邀请新用户注册赠送积分活动 2479568