WO2019080728A1 - 一种基于WiFi信号的心率异常检测方法 - Google Patents

一种基于WiFi信号的心率异常检测方法

Info

Publication number
WO2019080728A1
WO2019080728A1 PCT/CN2018/110065 CN2018110065W WO2019080728A1 WO 2019080728 A1 WO2019080728 A1 WO 2019080728A1 CN 2018110065 W CN2018110065 W CN 2018110065W WO 2019080728 A1 WO2019080728 A1 WO 2019080728A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
heart rate
signal
csi
curve
Prior art date
Application number
PCT/CN2018/110065
Other languages
English (en)
French (fr)
Inventor
叶伟
Original Assignee
叶伟
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 叶伟 filed Critical 叶伟
Publication of WO2019080728A1 publication Critical patent/WO2019080728A1/zh

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024Detecting, measuring or recording pulse rate or heart rate
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/0002Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
    • A61B5/0015Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system
    • A61B5/002Monitoring the patient using a local or closed circuit, e.g. in a room or building

Definitions

  • the invention belongs to the technical field of health detection, and particularly relates to a heart rate anomaly detection method based on a Wi-Fi signal.
  • CSI Channel State Information
  • the 802.11n-based WiFi technology uses a MIMO-OFDM system. Using the tool software provided by Daniel Halperin of the University of Washington, it can acquire 30 subcarriers in a wireless communication channel. Finally, a standardized CSI matrix H—n*m* can be obtained. A complex matrix of 30, where n represents the number of transmit antennas, m represents the number of received antennas, and 30 is the number of subcarrier information.
  • a modular matrix of 2*3*30 channel information is as follows:
  • the invention provides a heart rate anomaly detection method based on Wi-Fi signal, which can extract the heart rate data of the user through the WiFi router and establish relevant evaluation indicators, so that the user can find his abnormal heart rate abnormally as soon as possible, and reduce the user because A risk accident caused by a sudden heart attack.
  • a heart rate anomaly detection method based on a WiFi signal comprising the following steps:
  • A1 receiving a wireless signal sent by the indoor WiFi router
  • CSI Channel State Information abbreviation, channel state information
  • step A4 converting the ventricular curve and the atrial curve from the CSI signal data processed in step A3;
  • step A5 comparing and modeling the curve data obtained in step A4 with the arrhythmia data
  • the process of extracting the heart rate curve from the CSI signal data in step A3 includes:
  • B1 data preprocessing including:
  • the WiFi signal data is normalized
  • Multipath suppression that is, transforming CSI from the frequency domain to the time domain (IFFT), and then removing signal components of long delays that are not related to heart rate to mitigate multipath changes caused by environmental changes and human movement;
  • Wavelet filtering that is, using discrete wavelet transform to remove high frequency noise
  • the heart rate is measured using a conventional standard instrument.
  • the heart rate signal during sleep when the user is at rest is recorded. Different data will be tested differently to ensure that the characteristics of the data about the heart rate come from the same large total sample;
  • heart rate data feature extraction including:
  • the machine learning method is used to extract the feature data about the heart rate fluctuation frequency domain data. Firstly, the channel data features that are strongly related to the heart rate change are extracted from the CSI signal, and the small changes related to the breathing are excluded, and the regular change of the heart rate is extracted. Data and do F test;
  • the inverse Fourier transform is performed on the frequency domain signal, and the time domain information of the atrial signal and the ventricular signal is extracted, and a visual display is given;
  • A7, real-time heart rate anomaly detection, specific steps include:
  • the characterization data of the model is continuously optimized based on the test results.
  • the invention realizes heart rate curve recognition and heart rate curve modeling by using a common wireless device, and in a room equipped with a WiFi router, for a slight change such as a human atrial ventricular contraction, by extracting the uploaded CSI data, some regular fluctuations can be obtained. Curve information and find some abnormal heart rate data to alert the user.
  • the user does not need to wear the heart rate detection device to detect the data every day, and can detect the user's heart rate change in real time 24 hours a day, as long as the user is within a certain networking range of the WiFi router.
  • the invention can solve the problem that the user records the daily heart rate data of the user without wearing any hardware products, and alerts the abnormal data, helps the user to find the heart condition as soon as possible, treats as early as possible, and gives the user a healthier life.
  • the accuracy of the CSI signal used in the present invention is much higher than that of the RSSI signal, and the CSI can detect even smaller fluctuations such as heart rate, and can reach the millimeter level. At least 30 channel state fluctuations in each CSI data packet can be analyzed, and characteristic data related to heart rate fluctuations can be extracted from the data due to multipath suppression;
  • the present invention excludes differences in individuality, posture, activity amount, emotional state, and the like, and filters unnecessary noise interference, extracts strongly correlated feature data, and converts into atrial curve, ventricular curve, and Standard heart rate database matching, multi-dimensional test analysis to ensure the accuracy of the model;
  • the invention only needs one CPU and a WiFi router to implement, and mainly relies on data collection, data feature extraction, and algorithm implementation to detect the user's heart rate. Compared with the usual need to wear a conventional heart rate tester for testing, users no longer need to spend time to wear equipment to detect, real-time detection in real time, convenient, time-saving and efficient.
  • FIG. 1 is a flow chart of establishing an arrhythmia index in an embodiment of the present invention.
  • FIG. 2 is a basic flow chart of center rate anomaly detection according to an embodiment of the present invention.
  • FIG. 3 is a flow chart of converting CSI signal data into a heart rate curve in an embodiment of the present invention.
  • the heart rate monitoring scheme based on the CSI signal in WiFi involves simple hardware devices, and the difficulty lies in the extraction and characteristics of the ventricular and atrial variation curves.
  • the process mainly includes the following steps: 1. receiving a wireless signal sent by an indoor WiFi router; 2. extracting a CSI signal from wireless signals of different households that are cumulatively received; 3. preprocessing, modeling, and extracting a heart rate curve of the CSI signal data Characteristics; 4. Extracting ventricular curve and atrial curve from CSI data; 5. Comparing the result data with arrhythmia data, modeling; 6. Establishing indicators such as arrhythmia;
  • the steps for converting CSI signal data into a heart rate curve are as follows:
  • the low frequency data is analyzed, and the high frequency data is filtered by the band pass filter; the second order butterworth filter is used; since the transmission power of different WiFi devices has a certain influence on the CSI data, the data needs to be normalized;
  • Multipath suppression transforming CSI from the frequency domain to the time domain (IFFT), and then removing the signal components of long delays that are not related to heart rate to mitigate multipath changes caused by environmental changes and human movement;
  • Wavelet filtering The high-frequency noise is removed by discrete wavelet transform, in which the threshholding part adopts dynamic threshold and 4 layers of Symlet wavelet;
  • the data in the training sample will exclude individual differences, collect data analysis of three groups of fat and thin people; obtain some basic physiological data before data collection, including some common physiological indicators of the user, height, weight, gender, age, etc.
  • the user's heart rate will be obtained by using the conventional instrument test; when performing the system test, the heart rate signal when the user is at rest and sleeping will be recorded, and different data will be tested differently to ensure that the characteristics of the data about the heart rate come from the same large total. Sample; using the t test method;
  • the machine learning method is used to extract the feature data about the heart rate fluctuation frequency domain data. Firstly, the channel data features that are strongly related to the heart rate change are extracted from the CSI signal, and the small changes related to the breathing are excluded, and the regular change of the heart rate is extracted. Data, and do F test; abnormal heart rate data, do the same treatment;
  • the inverse Fourier transform is performed on the frequency domain signal, and the time domain information of the atrial signal and the ventricular signal is extracted, and a visual display is given;
  • the abnormal data monitoring method is that after the heart rate curve model is trained, it is put into the actual environment application and test, and the accuracy of the model is detected by the actual test result, some parameters of the model are optimized, and the characteristic data of the model is optimized. Wait. After the WiFi device is installed in the room, the process of specific CSI signal analysis and heart rate anomaly detection is shown in Figure 2.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Cardiology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Physiology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

一种基于Wi-Fi信号的心率异常检测方法,步骤有:A1,接收室内WiFi路由器发出的无线信号;A2,从WiFi无线信号提取出CSI信号;A3,对CSI信号数据预处理、建模,提取心率曲线特征;A4,从经过步骤A3处理的CSI信号数据中转化出心室曲线和心房曲线;A5,将步骤A4中获得的曲线数据与心率失常数据比对、建模;A6,建立心率失常指标,A7,进行实时的心率异常检测,判断是否有失常情况发生,提醒用户,同时保持数据记录;根据测试结果不断优化模型的特征数据。

Description

一种基于WiFi信号的心率异常检测方法 技术领域
本发明属于健康检测技术领域,特别涉及一种基于Wi-Fi信号的心率异常检测方法。
背景技术
近些年,各类无线电波被运用到智能硬件设备,用来采集用户的健康、健身数据等等。在智能家居生活中,用户更希望不需要携带任何电子感知设备就能够获取自己的健康数据,这样的一种非侵入式方案正在被更多的开发。另一发面,基于WiFi中CSI(Channel State Information,信道状态信息)信号的室内定位、指纹识别等技术在逐渐被人们所接受。通过对一些CSI信号数据分析,可以得出CSI能够将子载波信息展示的非常丰富,并展示出比较高的多径分辨能力,尤其是对非视距范围内信号微小的变化具有很高的捕获能力,CSI数据具有高灵敏度和感知区域广等特性。
在无线通信领域,CSI(Channel State Information,信道状态信息),是通信链路的信道属性,描述了信号在每条传输路径上的衰弱因子,比如信号散射,环境衰弱,距离衰减等信息。基于802.11n协议的WiFi技术采用MIMO-OFDM系统,利用华盛顿大学的Daniel Halperin提供的工具软件,可以获取一个无线通信信道中的30个子载波;最后可以得到规范化的CSI矩阵H——n*m*30的复数矩阵,其中n表示发射天线个数,m表示接受天线个数,30是子载波信息个数。
一个2*3*30的信道信息的模矩阵如下所示:
Figure PCTCN2018110065-appb-000001
发明内容
本发明提供了一种基于Wi-Fi信号的心率异常检测方法,通过WiFi路由器能够将用户的心率数据提取出来,并建立相关的评估指标,能够尽早让用户发现自己的心率异常情况,减少用户因为心脏突发带来的风险事故。
一种基于WiFi信号的心率异常检测方法,该方法包括以下步骤:
A1,接收室内WiFi路由器发出的无线信号;
A2,从WiFi无线信号提取出CSI(Channel State Information的缩写,信道状态信息)信号;
A3,对CSI信号数据预处理、建模,提取心率曲线特征;
A4,从经过步骤A3处理的CSI信号数据中转化出心室曲线和心房曲线;
A5,将步骤A4中获得的曲线数据与心率失常数据比对、建模;
A6,建立心率失常指标,
其中,步骤A3从CSI信号数据提取心率曲线的过程包括:
B1,数据预处理,包括:
针对心率变动是微小变动的低频数据,使用带通滤波过滤高频数据;
对于不同WiFi设备发送信号对CSI数据的影响,对WiFi信号数据进行归一化处理;
B2,去除环境噪声,包括:
多径抑制,即,将CSI从频域变换到时域(IFFT),再通过移除与心率不相关的长时延的信号成分,以减轻环境变化和人体移动引起的多径变化;
小波滤波,即,利用离散小波变换去除高频噪声;
B3,去除个体因素差异,包括:
为了在训练样本中的数据排除个体性差异,进行数据采集之前先获取基本生理数据,包括不同的体态、身高、体重、性别、年龄、情绪和体力活动差异,并且去除差异数据;
心率使用常规标准仪器测试得到,记录处理用户静止时候,睡觉时候的心率信号,不同的数据之间会做差异化检验,确保数据关于心率的特征来自同一个大的总样本;
使用t检验方法;
B4,心率数据特征提取,包括:
采用机器学习方法对训练数据关于心率变动频域数据做出特征提取,先从CSI信号中提取出和心率变动强相关的信道数据特征,排除呼吸相关的微小变化,提取心率变动这一规律性变化数据,并做F检验;
B5,信号转换,包括:
在将与心跳信号强相关的信道数据提取之后,再对该频域信号进行快速傅里叶反变换,将心房信号,心室信号的时域信息提取出来,并给出可视化展现;
B6,数据匹配,包括:
将数据与MIT的心率失常数据进行曲线比对,分析差异,区分心室、心房的起搏、感知、不适应感、PVAB指标数据,建立相关的模式匹配;
A7,进行实时的心率异常检测,具体步骤包括:
重复步骤A1~A4,计算心率失常评估指标,判断是否有失常情况发生,提醒用户,同时保持数据记录;
根据测试结果不断优化模型的特征数据。
本发明利用普通无线设备实现心率曲线识别,心率曲线建模,在装有WiFi路由器的房间中,对于人的心房心室收缩等微小的变化,通过提取上传的CSI数据,能够得到一些有规律的波动曲线信息,并发现一些心率异常数据,提醒用户。用户不需要每天穿戴心率检测设备检测数据,能够一天24小时实时检测用户的心率变动情况,只要用户在WiFi路由器一定的联网范围内。
本发明可以解决用户在不穿戴任何硬件产品的情况下,记录用户每日的心率数据,对异常数据预警,帮助用户尽早发现心脏病症,尽早治疗,让用户有一个更健康的生活。
与现有技术相比,本发明的技术方案具有以下效果:
1)灵敏性。本发明采用的CSI信号精度远远高于RSSI信号,CSI可以检测到心率等更加微小的波动,能够达到毫米级别水平。可以分析每一个CSI数据包中的至少30个信道状态波动,由于多径抑制,可以就从数据中提取出和心率波动相关的特征数据;
2)准确性。本发明在进行数据处理时,排除了个体性,体态,活动量,情绪 状态等差异性,并且过滤了不必要的噪声干扰,提取强相关的特征数据,转化成心房曲线,心室曲线,并且和标准的心率数据库匹配,多维度测试分析,确保模型的准确性;
3)方便高效。本发明只需要一个CPU和WiFi路由器即可实现,主要依赖数据收集,数据特征提取,算法实现,来检测用户心率。相比于平时需要穿戴常规心率检测仪器进行检测,用户不再需要花时间穿戴设备检测,每天都能够实时检测,方便,省时,高效。
附图说明
通过参考附图阅读下文的详细描述,本发明示例性实施方式的上述以及其他目的、特征和优点将变得易于理解。在附图中,以示例性而非限制性的方式示出了本发明的若干实施方式,其中:
图1是本发明实施例中建立心率失常指标的流程图。
图2是本发明实施例中心率异常检测的基本流程图。
图3是本发明实施例中CSI信号数据转换成心率曲线的流程图。
具体实施方式
如图1所示,基于WiFi中的CSI信号做的心率监测方案,涉及的硬件设备简单,难点在于提取和心室,心房变动曲线的特征。这个过程主要包括如下步骤:1.接收室内WiFi路由器发出的无线信号;2.从累积接收的不同家庭的无线信号中提取出CSI信号;3.对CSI信号数据预处理,建模,提取心率曲线特征;4.从CSI数据中提取出心室曲线,心房曲线;5.将结果数据与心率失常数据比对,建模;6.建立心率失常等指标;
其中,如图3所示,对于CSI信号数据转换成心率曲线的步骤有:
1.数据预处理
由于心率变动是更加微小的变动,分析低频数据,使用带通滤波过滤高频数据;使用2阶butterworth filter;由于不同WiFi设备发送功率对CSI数据有一定影响,需要对数据进行归一化处理;
2.环境噪声去除
多径抑制:将CSI从频域变换到时域(IFFT),再通过移除与心率不相关的长时延的信号成分,以减轻环境变化和人体移动引起的多径变化;
小波滤波:利用离散小波变换去除高频噪声,其中threshholding部分采用动态阈值,4层Symlet小波;
3.个体因素差异去除
训练样本中的数据会排除个体性差异,采集胖中瘦三类人群的数据分析;进行数据采集之前先获取一些基本生理数据,包括用户一些常见的生理指标,身高,体重,性别,年龄等,用户的心率会使用常规仪器测试得到;进行系统测试时,记录处理用户静止时候,睡觉时候的心率信号,不同的数据之间会做差异化检验,确保数据关于心率的特征来自同一个大的总样本;使用t检验方法;
4.心率数据特征提取
采用机器学习方法对训练数据关于心率变动频域数据做出特征提取,先从CSI信号中提取出和心率变动强相关的信道数据特征,排除呼吸相关的微小变化,提取心率变动这一规律性变化数据,并做F检验;非正常心率数据,做同样的处理;
5.信号转换
在将与心跳信号强相关的信道数据提取之后,再对该频域信号进行快速傅里叶反变换,将心房信号,心室信号的时域信息提取出来,并给出可视化展现;
6.数据匹配
再将数据与MIT的心率失常数据进行曲线比对,分析差异,区分心室,心房的起搏,感知,不适应感,PVAB等指标数据,建立相关的模式匹配;
如图2所示,异常数据监测方法是,心率曲线模型训练之后,再放到实际环境应用与测试,并且借助实际测试结果检测模型的准确率,优化模型的一些参数,优化模型的特征数据等等。WiFi设备安装在房间之后,具体的CSI信号分析与心率异常检测的过程见图2。
值得说明的是,虽然前述内容已经参考若干具体实施方式描述了本发明创 造的精神和原理,但是应该理解,本发明并不限于所公开的具体实施方式,对各方面的划分也不意味着这些方面中的特征不能组合,这种划分仅是为了表述的方便。本发明旨在涵盖所附权利要求的精神和范围内所包括的各种修改和等同布置。

Claims (1)

  1. 一种基于WiFi信号的心率异常检测方法,其特征在于,该方法包括以下步骤:
    A1,接收室内WiFi路由器发出的无线信号;
    A2,从WiFi无线信号提取出CSI(Channel State Information的缩写,信道状态信息)信号;
    A3,对CSI信号数据预处理、建模,提取心率曲线特征;
    A4,从经过步骤A3处理的CSI信号数据中转化出心室曲线和心房曲线;
    A5,将步骤A4中获得的曲线数据与心率失常数据比对、建模;
    A6,建立心率失常指标,
    其中,步骤A3从CSI信号数据提取心率曲线的过程包括:
    B1,数据预处理,包括:
    针对心率变动是微小变动的低频数据,使用带通滤波过滤高频数据;
    对于不同WiFi设备发送信号对CSI数据的影响,对WiFi信号数据进行归一化处理;
    B2,去除环境噪声,包括:
    多径抑制,即,将CSI从频域变换到时域(IFFT),再通过移除与心率不相关的长时延的信号成分,以减轻环境变化和人体移动引起的多径变化;
    小波滤波,即,利用离散小波变换去除高频噪声;
    B3,去除个体因素差异,包括:
    为了在训练样本中的数据排除个体性差异,进行数据采集之前先获取基本生理数据,包括不同的体态、身高、体重、性别、年龄、情绪和体力活动差异,并且去除差异数据;
    心率使用常规标准仪器测试得到,记录处理用户静止时候,睡觉时候的心率信号,不同的数据之间会做差异化检验,确保数据关于心率的特征来自同一个大的总样本;
    使用t检验方法;
    B4,心率数据特征提取,包括:
    采用机器学习方法对训练数据关于心率变动频域数据做出特征提取,先从CSI信号中提取出和心率变动强相关的信道数据特征,排除呼吸相关的微小变化,提取心率变动这一规律性变化数据,并做F检验;
    B5,信号转换,包括:
    在将与心跳信号强相关的信道数据提取之后,再对该频域信号进行快速傅里叶反变换,将心房信号,心室信号的时域信息提取出来,并给出可视化展现;
    B6,数据匹配,包括:
    将数据与MIT的心率失常数据进行曲线比对,分析差异,区分心室、心房的起搏、感知、不适应感、PVAB指标数据,建立相关的模式匹配;
    A7,进行实时的心率异常检测,具体步骤包括:
    重复步骤A1~A4,计算心率失常评估指标,判断是否有失常情况发生,提醒用户,同时保持数据记录;
    根据测试结果不断优化模型的特征数据。
PCT/CN2018/110065 2017-10-23 2018-10-12 一种基于WiFi信号的心率异常检测方法 WO2019080728A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710993008.6 2017-10-23
CN201710993008.6A CN107822617B (zh) 2017-10-23 2017-10-23 一种基于WiFi信号的心率异常检测方法

Publications (1)

Publication Number Publication Date
WO2019080728A1 true WO2019080728A1 (zh) 2019-05-02

Family

ID=61648917

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/110065 WO2019080728A1 (zh) 2017-10-23 2018-10-12 一种基于WiFi信号的心率异常检测方法

Country Status (2)

Country Link
CN (1) CN107822617B (zh)
WO (1) WO2019080728A1 (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107822617B (zh) * 2017-10-23 2020-10-16 上海百芝龙网络科技有限公司 一种基于WiFi信号的心率异常检测方法
CN108683467A (zh) * 2018-05-22 2018-10-19 深圳市普威技术有限公司 信号检测方法、通信设备、采集设备和信号检测系统
CN110347583A (zh) * 2019-05-23 2019-10-18 平安科技(深圳)有限公司 一种数据分析系统会诊方法及相关装置
CN110353649B (zh) * 2019-07-03 2020-11-13 北京科技大学 一种心率检测方法
CN110200610A (zh) * 2019-07-04 2019-09-06 合肥工业大学 一种基于WiFi信号的增强呼吸及心率实时监测评估方法系统
CN111174997B (zh) * 2020-01-14 2021-10-22 合肥工业大学 一种基于心率变化的楼板振动舒适度的初步测试方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105232022A (zh) * 2015-09-17 2016-01-13 太原理工大学 基于WiFi中CSI信号强度的非侵入式呼吸心跳检测实现方法
CN106108904A (zh) * 2016-06-23 2016-11-16 华中科技大学 一种非接触式的人体呼吸参数实时测量方法及系统
CN106618497A (zh) * 2016-12-13 2017-05-10 北京理工大学 复杂环境下基于信道状态信息监测睡眠的方法
CN106725488A (zh) * 2016-12-27 2017-05-31 深圳大学 一种无线场强呼吸检测方法、装置及呼吸检测仪
WO2017156492A1 (en) * 2016-03-11 2017-09-14 Origin Wireless, Inc. Methods, apparatus, servers, and systems for vital signs detection and monitoring
CN107822617A (zh) * 2017-10-23 2018-03-23 上海百芝龙网络科技有限公司 一种基于WiFi信号的心率异常检测方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105962946B (zh) * 2016-06-23 2019-01-29 华中科技大学 一种非接触式的人体睡姿安全检测方法及系统
CN106175767A (zh) * 2016-07-01 2016-12-07 华中科技大学 一种非接触式的多人呼吸参数实时检测方法及系统
CN106604394A (zh) * 2016-12-28 2017-04-26 南京航空航天大学 一种基于csi的判定室内人体运动速度模型
CN106936526A (zh) * 2017-03-30 2017-07-07 西北工业大学 一种基于信道状态信息的非接触式睡眠分期装置及方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105232022A (zh) * 2015-09-17 2016-01-13 太原理工大学 基于WiFi中CSI信号强度的非侵入式呼吸心跳检测实现方法
WO2017156492A1 (en) * 2016-03-11 2017-09-14 Origin Wireless, Inc. Methods, apparatus, servers, and systems for vital signs detection and monitoring
CN106108904A (zh) * 2016-06-23 2016-11-16 华中科技大学 一种非接触式的人体呼吸参数实时测量方法及系统
CN106618497A (zh) * 2016-12-13 2017-05-10 北京理工大学 复杂环境下基于信道状态信息监测睡眠的方法
CN106725488A (zh) * 2016-12-27 2017-05-31 深圳大学 一种无线场强呼吸检测方法、装置及呼吸检测仪
CN107822617A (zh) * 2017-10-23 2018-03-23 上海百芝龙网络科技有限公司 一种基于WiFi信号的心率异常检测方法

Also Published As

Publication number Publication date
CN107822617A (zh) 2018-03-23
CN107822617B (zh) 2020-10-16

Similar Documents

Publication Publication Date Title
WO2019080728A1 (zh) 一种基于WiFi信号的心率异常检测方法
CN111481184B (zh) 基于毫米波雷达技术的多目标呼吸心率监测方法与系统
CN106937808B (zh) 一种智能床垫的数据采集系统
CN109480787B (zh) 一种基于超宽带雷达的非接触式睡眠监测设备及睡眠分期方法
CN108577834B (zh) 一种用于癫痫间期棘波自动检测的方法
CN106108904B (zh) 一种非接触式的人体呼吸参数实时测量方法及系统
CN108652615B (zh) 一种心电数据病理特征量化分析方法及装置
CN109907752A (zh) 一种去除运动伪影干扰与心电特征检测的心电诊断与监护方法及系统
CN112998701A (zh) 基于毫米波雷达的生命体征检测与身份识别系统和方法
CN110236536A (zh) 一种基于卷积神经网络的脑电高频振荡信号检测系统
CN106264499B (zh) 一种量化心肺系统交互作用的分析方法
CN110037668B (zh) 脉搏信号时空域结合模型判断年龄、健康状态及恶性心律失常识别的系统
CN107822645B (zh) 一种基于WiFi信号的情绪识别方法
CN108056770A (zh) 一种基于人工智能的心率检测方法
US11406304B2 (en) Systems and methods for physiological sign analysis
US20220110590A1 (en) System and Method for Assessing Physiological Signal Quality
Han et al. UWB radar for non-contact heart rate variability monitoring and mental state classification
CN110751131B (zh) 一种心律失常检测装置
CN114886388B (zh) 一种麻醉深度监测过程中脑电信号质量的评估方法及装置
CN107847146B (zh) 在ecg数据上自动标记活动的方法和系统
CN112057087B (zh) 精神分裂症高风险人群自主神经功能数据处理方法及装置
CN110974196A (zh) 一种运动状态下非接触式的呼吸和心率检测方法
KR101510522B1 (ko) 심전도 신호 분류 시스템
Bobrova et al. Mathematical methods of fetal activity signal processing
Zhuang et al. SleepSense: Non-invasive sleep event recognition using an electromagnetic probe

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18869841

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18869841

Country of ref document: EP

Kind code of ref document: A1