WO2022068589A1 - 动态心率预测方法、装置、设备及可读存储介质 - Google Patents

动态心率预测方法、装置、设备及可读存储介质 Download PDF

Info

Publication number
WO2022068589A1
WO2022068589A1 PCT/CN2021/118488 CN2021118488W WO2022068589A1 WO 2022068589 A1 WO2022068589 A1 WO 2022068589A1 CN 2021118488 W CN2021118488 W CN 2021118488W WO 2022068589 A1 WO2022068589 A1 WO 2022068589A1
Authority
WO
WIPO (PCT)
Prior art keywords
heart rate
value
predicted
current moment
rate prediction
Prior art date
Application number
PCT/CN2021/118488
Other languages
English (en)
French (fr)
Inventor
王德信
Original Assignee
青岛歌尔智能传感器有限公司
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 青岛歌尔智能传感器有限公司 filed Critical 青岛歌尔智能传感器有限公司
Publication of WO2022068589A1 publication Critical patent/WO2022068589A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, 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
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A61B5/681—Wristwatch-type devices
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters

Definitions

  • the present application relates to the field of physiological signal monitoring, and in particular, to a dynamic heart rate prediction method, apparatus, device, and readable storage medium.
  • the present application provides a dynamic heart rate prediction method, device, device, and readable storage medium, aiming to improve the accuracy of heart rate acquisition.
  • a dynamic heart rate prediction method comprising:
  • Kalman filtering is performed based on the predicted value and the observed value of the measurement parameter at the current moment to obtain a dynamic heart rate prediction result at the current moment.
  • the determining a reference value and a measurement value from the ECG signal to be predicted based on the signal quality index includes:
  • the signal quality index is greater than or equal to the preset value, and the main wave heart rate value calculated based on the peak or trough feature points in the ECG signal to be predicted is used as the measurement value, and the heart rate value based on the ECG signal to be predicted is used as the measurement value.
  • the main wave heart rate value calculated from the maximum slope point of the main wave or the zero-crossing point of the pulse wave is used as the reference value;
  • the signal quality index is less than the preset value, and the main wave heart rate value calculated based on the maximum slope point of the main wave or the zero-crossing point of the pulse wave in the ECG signal to be predicted is used as the measurement value, and the ECG signal to be predicted is based on the ECG signal to be predicted.
  • the main wave heart rate value calculated from the peak or trough characteristic point is used as the reference value.
  • the obtaining the predicted value at the current moment based on the reference value of the reference parameter at the previous moment includes:
  • the reference value of the reference parameter at the previous moment is substituted into the state equation of the discrete control system to obtain the predicted value at the current moment.
  • the Kalman filtering is performed based on the predicted value and the measurement parameter at the current moment, and the dynamic heart rate prediction result at the current moment is obtained, which also includes before:
  • the Kalman gain is determined based on the covariance of the current moment, the covariance of the previous moment, and the observation matrix.
  • the Kalman filter is performed based on the predicted value and the measurement parameter at the current moment to obtain the dynamic heart rate prediction result at the current moment, including:
  • the predicted value, the measurement parameter at the current moment and the Kalman gain are input into the correction equation to obtain the dynamic heart rate prediction result at the current moment.
  • the Kalman gain is determined based on the covariance of the current moment, the covariance of the previous moment, and the observation matrix, and further includes:
  • the determining the reference parameter and the measurement parameter of the ECG signal to be predicted based on the signal quality index further includes:
  • the ECG signal to be predicted is input into a signal quality evaluation system, and the quality evaluation system outputs a signal quality index.
  • the present application also provides a dynamic heart rate prediction device, the device comprising:
  • a determination module used for determining the reference parameters and measurement parameters of the ECG signal to be predicted based on the signal quality index
  • an obtaining module for obtaining the predicted value at the current moment based on the reference value of the reference parameter at the previous moment
  • a filtering module configured to perform Kalman filtering based on the predicted value and the observed value of the measurement parameter at the current moment to obtain a dynamic heart rate prediction result at the current moment.
  • the present application also provides a dynamic heart rate prediction device, the dynamic heart rate prediction device includes a processor, a memory and a dynamic heart rate prediction program stored in the memory, the dynamic heart rate prediction program is When the processor is running, the steps of the dynamic heart rate prediction method described above are implemented.
  • the present application also provides a computer-readable storage medium, where a dynamic heart rate prediction program is stored on the computer-readable storage medium, and the dynamic heart rate prediction program is executed by a processor to realize the dynamic heart rate as described above. The steps of the heart rate prediction method.
  • the present application discloses a dynamic heart rate prediction method, device, device and readable storage medium.
  • the method includes: determining reference parameters and measurement parameters of an ECG signal to be predicted based on a signal quality index;
  • the reference value of the reference parameter at one moment obtains the predicted value at the current moment;
  • Kalman filtering is performed based on the predicted value and the observed value of the measurement parameter at the current moment to obtain the dynamic heart rate prediction result at the current moment. Therefore, the reference parameters and measurement parameters are determined according to the signal quality index, and then the dynamic heart rate prediction result is obtained through Kalman filtering, which improves the accuracy of heart rate acquisition.
  • FIG. 1 is a schematic diagram of a hardware structure of a dynamic heart rate prediction device involved in various embodiments of the present application
  • FIG. 2 is a schematic flowchart of the first embodiment of the dynamic heart rate prediction method of the present application
  • FIG. 3 is a schematic diagram of functional modules of the first embodiment of the dynamic heart rate prediction apparatus of the present application.
  • the dynamic heart rate prediction device mainly involved in the embodiments of the present application refers to a network connection device capable of realizing network connection, and the dynamic heart rate prediction device may be a wearable device such as a sports bracelet, a phone watch, or the like.
  • FIG. 1 is a schematic diagram of a hardware structure of a dynamic heart rate prediction device involved in various embodiments of the present application.
  • the dynamic heart rate prediction device may include a processor 1001 (for example, a central processing unit Central Processing Unit, CPU), communication bus 1002 , input port 1003 , output port 1004 , memory 1005 .
  • the communication bus 1002 is used to realize the connection communication between these components; the input port 1003 is used for data input; the output port 1004 is used for data output, and the memory 1005 can be a high-speed RAM memory or a stable memory (non-volatile memory).
  • the memory 1005 may also be a storage device independent of the aforementioned processor 1001 in one embodiment.
  • the hardware structure shown in FIG. 1 does not constitute a limitation to the present application, and may include more or less components than the one shown, or combine some components, or arrange different components.
  • FIG. 2 is a schematic flowchart of the first embodiment of the dynamic heart rate prediction method of the present application.
  • the dynamic heart rate prediction method includes:
  • Step S101 Determine the reference parameters and measurement parameters of the ECG signal to be predicted based on the signal quality index
  • the ECG signal to be predicted is input into a signal quality evaluation system, and the quality evaluation system outputs a signal quality index.
  • the signal quality evaluation system of ECG signal integrates several analysis algorithms, and through the synthesis of several algorithms, the comprehensive quality index of the evaluation signal is a value between 0 and 1. The larger the value is, the better the signal quality is. .
  • the several algorithms may at least include: quality evaluation based on the stability of ECG signal characteristic parameters, quality evaluation based on signal kurtosis analysis, and quality evaluation based on signal power spectrum distribution.
  • Kalman filtering can provide the best estimate of random signals and is suitable for the estimation of cardiovascular signals such as heart rate and blood pressure.
  • the tested heart rate signal is first transmitted to the signal quality detection device, and the signal quality detection device can measure the signal quality index, and the signal quality index can characterize the quality of the ECG signal in real time, so as to adjust the residual of the Kalman filter. basis.
  • the determining a reference value and a measurement value from the ECG signal to be predicted based on the signal quality index includes:
  • the signal quality index is compared with a preset value; wherein, the preset value can be set according to experience, for example, set to 0.5, 0.6, 0.7 and so on.
  • the signal quality index is greater than or equal to the preset value, and the main wave heart rate value calculated based on the peak or trough feature points in the ECG signal to be predicted is used as the measurement value, and the heart rate value based on the ECG signal to be predicted is used as the measurement value.
  • the main wave heart rate value calculated from the maximum slope point of the main wave or the zero-crossing point of the pulse wave is used as the reference value;
  • the signal quality index is less than the preset value, and the main wave heart rate value calculated based on the maximum slope point of the main wave or the zero-crossing point of the pulse wave in the ECG signal to be predicted is used as the measurement value, and the ECG signal to be predicted is based on the ECG signal to be predicted.
  • the main wave heart rate value calculated from the peak or trough characteristic point is used as the reference value.
  • one of the various heart rate detection methods may be arbitrarily selected as the measurement signal, the heart rate values obtained by other methods may be used as the reference signal and input to the Kalman filter, and the alternate selection may be adjusted in real time according to the residual value. Accurate estimation of heart rate.
  • Step S102 obtaining a predicted value at the current moment based on the reference value of the reference parameter at the previous moment;
  • the Kalman filter is an optimized autoregressive data processing algorithm.
  • the core idea is to fuse the two inputs of the predicted value and the measured value to estimate the current state of the object in an optimal way under the linear unbiased minimum variance estimation criterion. Karl filtering can estimate past and current states of a signal, and even predict future states.
  • Step S103 Perform Kalman filtering based on the predicted value and the observed value of the measurement parameter at the current moment to obtain a dynamic heart rate prediction result at the current moment.
  • the Kalman filter cleverly uses the product of the independent Gaussian distribution to fuse the measured value and the estimated value, and the Kalman gain Kg is the proportion of the predicted value variance to the total variance. For a linear time-varying system, the Kalman gain is usually used to correct the state estimate.
  • the specific derivation process is as follows:
  • X(k) is the n-dimensional state vector of the discrete control system at time k
  • u(k) is the control input vector of the discrete control system at time k
  • A(k) is the state of the discrete control system Transfer matrix
  • B(k) is the input control matrix of the discrete control system
  • w(k) is the process noise
  • Y(k) is the observation vector of the discrete control system at time k
  • C(k) is the observation matrix of the discrete control system
  • D(k) is the external input
  • v(k) is the observation noise
  • the current time is represented as K time
  • the previous time of the current time is represented as K-1 time.
  • the discrete control system transfers from the previous time k-1 to k
  • the state at time can be predicted by time k-1:
  • k-1) A(k)*X'(k-1) + B(k)*u(k-1) + w(k-1) 3)
  • Equation 3 X'(k
  • the Kalman filter is described based on the predicted value and the measurement parameter at the current moment, and the dynamic heart rate prediction result at the current moment is obtained, which also includes before:
  • the Kalman gain is determined based on the covariance of the current moment, the covariance of the previous moment, and the observation matrix.
  • k-1) A(k)*P'(k-1)*AT(k) + Q(k-1) 4)
  • k-1) is the covariance corresponding to X'(k
  • P'(k-1) is the covariance corresponding to X'(k-1)
  • formulas 3) and 4) are the state prediction and covariance update of the discrete control system by the Kalman filter.
  • k-1) of the discrete control system state at time k is corrected by the Kalman gain, and the correction equation is as follows:
  • X'(k) X'(k
  • the predicted value, the measurement parameter at the current moment and the Kalman gain are input into the correction equation to obtain the dynamic heart rate prediction result at the current moment.
  • the Kalman gain Kg can be expressed as:
  • Kg P'(k
  • k-1) at time k can be output.
  • the covariance is updated if the Kalman gain converges on the observed value.
  • the reference parameters and measurement parameters of the ECG signal to be predicted are determined based on the signal quality index; the prediction value at the current moment is obtained based on the reference value of the reference parameter at the previous moment; Kalman filtering is performed on the observed values of the measurement parameters at the moment to obtain the dynamic heart rate prediction result at the current moment. Therefore, the reference parameters and measurement parameters are determined according to the signal quality index, and then the dynamic heart rate prediction result is obtained through Kalman filtering, which improves the accuracy of heart rate acquisition.
  • FIG. 3 is a schematic diagram of functional modules of the first embodiment of the behavioral dynamic heart rate prediction device of the present application.
  • the device is a virtual device, including:
  • a determination module 10 configured to determine reference parameters and measurement parameters of the ECG signal to be predicted based on the signal quality index
  • Obtaining module 20 for obtaining the predicted value of the current moment based on the reference value of the reference parameter of the previous moment;
  • the filtering module 30 is configured to perform Kalman filtering based on the predicted value and the observed value of the measurement parameter at the current moment to obtain a dynamic heart rate prediction result at the current moment.
  • the determining module is further configured to:
  • the signal quality index is greater than or equal to the preset value, and the main wave heart rate value calculated based on the peak or trough feature points in the ECG signal to be predicted is used as the measurement value, and the heart rate value based on the ECG signal to be predicted is used as the measurement value.
  • the main wave heart rate value calculated from the maximum slope point of the main wave or the zero-crossing point of the pulse wave is used as the reference value;
  • the signal quality index is less than the preset value, and the main wave heart rate value calculated based on the maximum slope point of the main wave or the zero-crossing point of the pulse wave in the ECG signal to be predicted is used as the measurement value, and the ECG signal to be predicted is based on the ECG signal to be predicted.
  • the main wave heart rate value calculated from the peak or trough characteristic point is used as the reference value.
  • the obtaining module is further used for:
  • the reference value of the reference parameter at the previous moment is substituted into the state equation of the discrete control system to obtain the predicted value at the current moment.
  • the prediction module is further used to:
  • the Kalman gain is determined based on the covariance of the current moment, the covariance of the previous moment, and the observation matrix.
  • the prediction module is further used to:
  • the predicted value, the measurement parameter at the current moment and the Kalman gain are input into the correction equation to obtain the dynamic heart rate prediction result at the current moment.
  • the prediction module is further used to:
  • the determining module is further configured to:
  • the ECG signal to be predicted is input into a signal quality evaluation system, and the quality evaluation system outputs a signal quality index.
  • an embodiment of the present application further provides a computer-readable storage medium, where a dynamic heart rate prediction program is stored on the computer-readable storage medium, and when the dynamic heart rate prediction program is run by a processor, the dynamic heart rate prediction method as described above is implemented A step of.
  • a dynamic heart rate prediction method, device, device and readable storage medium proposed in the present application include: determining reference parameters and measurement parameters of an ECG signal to be predicted based on a signal quality index; The reference value of the reference parameter at one moment obtains the predicted value at the current moment; Kalman filtering is performed based on the predicted value and the observed value of the measurement parameter at the current moment to obtain the dynamic heart rate prediction result at the current moment. Therefore, the reference parameters and measurement parameters are determined according to the signal quality index, and then the dynamic heart rate prediction result is obtained through Kalman filtering, which improves the accuracy of heart rate acquisition.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Physiology (AREA)
  • Cardiology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Psychiatry (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

一种动态心率预测方法、装置、设备及可读存储介质。方法包括：基于信号质量指数确定待预测心电信号的参考参数和测量参数（S101）；基于上一时刻的参考参数的参考值获得当前时刻的预测值（S102）；基于预测值和当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果（S103）。

Description

动态心率预测方法、装置、设备及可读存储介质
本申请要求于2020年9月30日提交中国专利局、申请号为202011070826.7、申请名称为“动态心率预测方法、装置、设备及可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及生理信号监测领域，尤其涉及一种动态心率预测方法、装置、设备及可读存储介质。
 背景技术
当前，有各种各样的可穿戴设备可以监测心率，但是当前的可穿戴设备信号强度弱、抗干扰性差、信号不稳定，而脉搏波传感器通常灵敏度很高。这使得在方便采集脉搏信号的同时也极易引入干扰噪声，因此难以根据获取到的脉搏信号获得佩戴者的准确心率。
 技术问题
本申请提供一种动态心率预测方法、装置、设备及可读存储介质，旨在提高心率获取的准确性。
 技术解决方案
一种动态心率预测方法，该方法包括：
基于信号质量指数确定待预测心电信号的参考参数和测量参数；
基于上一时刻的参考参数的参考值获得当前时刻的预测值；
基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。
在一实施例中，所述基于所述信号质量指数从所述待预测心电信号中确定参考值和测量值，包括：
将所述信号质量指数与预设值进行比较；
所述信号质量指数大于或等于所述预设值，将基于所述待预测心电信号中的波峰或波谷特征点计算的主波心率值作为测量值，将基于所述待预测心电信号中主波最大斜率点或脉搏波过零点计算的主波心率值作为参考值；
所述信号质量指数小于所述预设值，将基于所述待预测心电信号中主波最大斜率点或脉搏波过零点计算的主波心率值作为测量值，基于所述待预测心电信号中波峰或波谷特征点计算的主波心率值作为参考值。
在一实施例中，所述基于上一时刻的参考参数的参考值获得当前时刻的预测值，包括：
将所述上一时刻的参考参数的参考值代入离散控制系统的状态方程中，获得当前时刻的预测值。
在一实施例中，所述基于所述预测值和当前时刻的测量参数进行卡尔曼滤波，获得当前时刻的动态心率预测结果，之前还包括:
根据系统转移理论确定协方差计算公式，基于所述协方差计算公式确定当前时刻的协方差和前一时刻的协方差；
基于所述当前时刻的协方差、所述前一时刻的协方差、观测矩阵确定卡尔曼增益。
在一实施例中，所述基于所述预测值和当前时刻的测量参数进行卡尔曼滤波，获得当前时刻的动态心率预测结果，包括：
将所述预测值、所述当前时刻的测量参数以及所述卡尔曼增益输入修正方程，获得当前时刻的动态心率预测结果。
在一实施例中，所述基于所述当前时刻的协方差、所述前一时刻的协方差、观测矩阵确定卡尔曼增益，之后还包括：
若所述卡尔曼增益收敛于所述观测值，则更新所述协方差。
在一实施例中，所述基于信号质量指数确定待预测心电信号的参考参数和测量参数，之前还包括：
将待预测心电信号输入信号质量评估系统，由所述质量评估系统输出信号质量指数。
此外，为实现上述目的，本申请还提供一种动态心率预测装置，所述装置包括：
确定模块，用于基于信号质量指数确定待预测心电信号的参考参数和测量参数；
获得模块，用于基于上一时刻的参考参数的参考值获得当前时刻的预测值；
滤波模块，用于基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。
此外，为实现上述目的，本申请还提供一种动态心率预测设备，所述动态心率预测设备包括处理器，存储器以及存储在所述存储器中的动态心率预测程序，所述动态心率预测程序被所述处理器运行时，实现如上所述的动态心率预测方法的步骤。
此外，为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有动态心率预测程序，所述动态心率预测程序被处理器运行时实现如上所述动态心率预测方法的步骤。
 有益效果
相比现有技术，本申请公开了一种动态心率预测方法、装置、设备及可读存储介质，所述方法包括：基于信号质量指数确定待预测心电信号的参考参数和测量参数；基于上一时刻的参考参数的参考值获得当前时刻的预测值；基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。由此，根据信号质量指数确定参考参数和测量参数，然后通过卡尔曼滤波获得动态心率预测结果，提高了心率获取的准确性。
 附图说明
图1是本申请各实施例涉及的动态心率预测设备的硬件结构示意图；
图2是本申请动态心率预测方法第一实施例的流程示意图；
图3是本申请动态心率预测装置第一实施例的功能模块示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
 本发明的实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请实施例主要涉及的动态心率预测设备是指能够实现网络连接的网络连接设备，所述动态心率预测设备可以是运动手环、电话手表等可穿戴设备。
参照图1，图1是本申请各实施例涉及的动态心率预测设备的硬件结构示意图。本申请实施例中，动态心率预测设备可以包括处理器1001（例如中央处理器Central Processing Unit、CPU），通信总线1002，输入端口1003，输出端口1004，存储器1005。其中，通信总线1002用于实现这些组件之间的连接通信；输入端口1003用于数据输入；输出端口1004用于数据输出，存储器1005可以是高速RAM存储器，也可以是稳定的存储器（non-volatile memory），例如磁盘存储器，存储器1005在一实施例中还可以是独立于前述处理器1001的存储装置。本领域技术人员可以理解，图1中示出的硬件结构并不构成对本申请的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
参照图2，图2是本申请动态心率预测方法第一实施例的流程示意图。如图2所示，所述动态心率预测方法，包括：
步骤S101：基于信号质量指数确定待预测心电信号的参考参数和测量参数；
本实施例中，将待预测心电信号输入信号质量评估系统，由所述质量评估系统输出信号质量指数。心电信号的信号质量评估系统综合了若干个分析算法，通过对若干个算法的综合得出了评价信号的综合质量指数是一个介于0和1的数值，取值越大表明信号质量越好。其中，所述若干个算法至少可以包括：基于心电信号特征参数稳定性的质量评估、基于信号峰度分析的质量评估和基于信号功率谱分布的质量评估。
卡尔曼滤波可以提供对随机信号的最佳估计，适用于对心率、血压等心血管信号的估计。本实施例中，先将测试的心率信号传递给信号质量检测装置，信号质量检测装置可以测量信号质量指数，信号质量指数可以实时地表征心电信号的质量，从而作为卡尔曼滤波器残差调节的依据。
具体地，所述基于所述信号质量指数从所述待预测心电信号中确定参考值和测量值，包括：
将所述信号质量指数与预设值进行比较；其中，所述预设值可以根据经验设置，例如设置为0.5、0.6、0.7等。
所述信号质量指数大于或等于所述预设值，将基于所述待预测心电信号中的波峰或波谷特征点计算的主波心率值作为测量值，将基于所述待预测心电信号中主波最大斜率点或脉搏波过零点计算的主波心率值作为参考值；
所述信号质量指数小于所述预设值，将基于所述待预测心电信号中主波最大斜率点或脉搏波过零点计算的主波心率值作为测量值，基于所述待预测心电信号中波峰或波谷特征点计算的主波心率值作为参考值。
在其他实施例中，还可以在各种心率检测方法中任意选择其中一种信号作为测量信号，其他方法得出的心率值作为参考信号输入卡尔曼滤波器，根据残差值实时调整交替选择以实现心率的精准估计。
步骤S102：基于上一时刻的参考参数的参考值获得当前时刻的预测值；
卡尔曼滤波是最优化自回归数据处理算法，核心思想就是融合预测值和测量值两种输入在线性无偏差最小方差估计准则下以最优的方式来估计物体当前的状态。卡尔滤波可以估计信号的过去和当前状态，甚至能预测将来的状态。
步骤S103：基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。
卡尔曼滤波器巧妙地用独立高斯分布的乘积降测量值和估计值进行融合，卡尔曼增益Kg为预测值方差占总方差的比重。对于线性时变系统，通常采用卡尔曼增益来修正状态估计值，具体推导过程如下：
首先，引入一个离散控制系统，将所述离散控制系统的状态方程为：
X(k+1) = A(k)*X(k) + B(k)*u(k) + w(k)            1)
式1)中，X(k)为所述离散控制系统处于k时刻的n维状态向量，u(k)作为离散控制系统在k时刻的控制输入向量，A(k)为离散控制系统的状态转移矩阵，B(k)为离散控制系统的输入控制矩阵，w(k)为过程噪声；
Y(k) = C(k)*X(k) + D(k) + v(k)              2)
式2)中，Y(k)为离散控制系统在k时刻的观察向量，C(k)为所述离散控制系统的观测矩阵，D(k)为外部输入，v(k)为观测噪声；如此，将所述上一时刻的参考参数的参考值代入所述离散控制系统的状态方程中，即可获得当前时刻的预测值。
本实施例中，将当前时刻表示为K时刻，将当前时刻的上一时刻表示为K-1时刻，根据离散控制系统的状态空间表达式，离散控制系统从上一时刻k-1转移到k时刻的状态可由k-1时刻预测：
X'(k|k-1) = A(k)*X'(k-1) + B(k)*u(k-1) + w(k-1)        3)
式3)中，X'(k|k-1)是离散控制系统处于上一时刻状态预测的估计值，X'(k-1)是k-1时刻离散控制系统的状态值，u(k-1)为k-1时刻离散控制系统的输入量，w(k-1)是过程噪声。
所述基于所述预测值和当前时刻的测量参数进行卡尔曼滤波，获得当前时刻的动态心率预测结果，之前还包括:
根据系统转移理论确定协方差计算公式，基于所述协方差计算公式确定当前时刻的协方差和前一时刻的协方差；
基于所述当前时刻的协方差、所述前一时刻的协方差、观测矩阵确定卡尔曼增益。
如果用P’(k|k-1) 表示X'(k-1)的协方差，依据系统理论可以将更新后的协方差计算公式表示为：
P'(k|k-1) = A(k)*P'(k-1)*AT(k) + Q(k-1)           4)
式4)中，P'(k|k-1)是X'(k|k-1)对应的协方差，P'(k-1)是与X'(k-1)对应的协方差，是k-1时刻离散控制系统过程的协方差，公式3)和4)即为卡尔曼滤波器对离散控制系统的状态预测和协方差更新。
利用卡尔曼增益对k时刻离散控制系统状态的估计值X'(k|k-1)进行修正，修正方程如下：
X'(k) = X'(k|k-1) + Kg*(Y(k) - C(k)*X'(k|k-1))         5)
将所述预测值、所述当前时刻的测量参数以及所述卡尔曼增益输入修正方程，获得当前时刻的动态心率预测结果。
其中，卡尔曼增益Kg可以表示为：
Kg = P'(k|k-1)*CT(k)*(C(k)* P'(k|k-1)*CT(k) + R(k))-1    6)
经过以上推导，便可输出k时刻最优估计值X'(k|k-1)。
此外，若所述卡尔曼增益收敛于所述观测值，则更新所述协方差。
为了使算法不断地循环和迭代下去，收敛于观测值则需要对k时刻时所述离散控制系统的协方差也进行更新：
P(k) = (I- Kg*C(k))* P'(k|k-1)                 7)
其中I为单位矩阵，当离散控制系统由k-1时刻转移到k时刻，P即为公式4)中的P'(k|k-1)；基于此转移算法过程，卡尔曼滤波器就可以从最初状态到最后时刻状态自回归地进行下去。
本实施例通过上述方案，基于信号质量指数确定待预测心电信号的参考参数和测量参数；基于上一时刻的参考参数的参考值获得当前时刻的预测值；基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。由此，根据信号质量指数确定参考参数和测量参数，然后通过卡尔曼滤波获得动态心率预测结果，提高了心率获取的准确性。
此外，本申请实施例还提供一种动态心率预测装置，具体地，参照图3，图3是本申请行为动态心率预测装置第一实施例的功能模块示意图，所述装置为虚拟装置，包括：
确定模块10，用于基于信号质量指数确定待预测心电信号的参考参数和测量参数；
获得模块20，用于基于上一时刻的参考参数的参考值获得当前时刻的预测值；
滤波模块30，用于基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。
在一实施例中，所述确定模块还用于：
将所述信号质量指数与预设值进行比较；
所述信号质量指数大于或等于所述预设值，将基于所述待预测心电信号中的波峰或波谷特征点计算的主波心率值作为测量值，将基于所述待预测心电信号中主波最大斜率点或脉搏波过零点计算的主波心率值作为参考值；
所述信号质量指数小于所述预设值，将基于所述待预测心电信号中主波最大斜率点或脉搏波过零点计算的主波心率值作为测量值，基于所述待预测心电信号中波峰或波谷特征点计算的主波心率值作为参考值。
在一实施例中，所述获得模块还用于：
将所述上一时刻的参考参数的参考值代入离散控制系统的状态方程中，获得当前时刻的预测值。
在一实施例中，所述预测模块还用于：
根据系统转移理论确定协方差计算公式，基于所述协方差计算公式确定当前时刻的协方差和前一时刻的协方差；
基于所述当前时刻的协方差、所述前一时刻的协方差、观测矩阵确定卡尔曼增益。
在一实施例中，所述预测模块还用于：
将所述预测值、所述当前时刻的测量参数以及所述卡尔曼增益输入修正方程，获得当前时刻的动态心率预测结果。
在一实施例中，所述预测模块还用于：
若所述卡尔曼增益收敛于所述观测值，则更新所述协方差。
在一实施例中，所述确定模块还用于：
将待预测心电信号输入信号质量评估系统，由所述质量评估系统输出信号质量指数。
此外，本申请实施例还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有动态心率预测程序，所述动态心率预测程序被处理器运行时实现如上所述动态心率预测方法的步骤。
相比现有技术，本申请提出的一种动态心率预测方法、装置、设备及可读存储介质，所述方法包括：基于信号质量指数确定待预测心电信号的参考参数和测量参数；基于上一时刻的参考参数的参考值获得当前时刻的预测值；基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。由此，根据信号质量指数确定参考参数和测量参数，然后通过卡尔曼滤波获得动态心率预测结果，提高了心率获取的准确性。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者离散控制系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者离散控制系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者离散控制系统中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个可读存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备执行本申请各个实施例所述的方法。
以上所述仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或流程变换，或直接或间接运用在其它相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (10)

  1. 一种动态心率预测方法，其中，该方法包括：
    基于信号质量指数确定待预测心电信号的参考参数和测量参数；
    基于上一时刻的参考参数的参考值获得当前时刻的预测值；
    基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。
  2. 根据权利要求1所述的方法，其中，所述基于所述信号质量指数从所述待预测心电信号中确定参考值和测量值，包括：
    将所述信号质量指数与预设值进行比较；
    所述信号质量指数大于或等于所述预设值，将基于所述待预测心电信号中的波峰或波谷特征点计算的主波心率值作为测量值，将基于所述待预测心电信号中主波最大斜率点或脉搏波过零点计算的主波心率值作为参考值；
    所述信号质量指数小于所述预设值，将基于所述待预测心电信号中主波最大斜率点或脉搏波过零点计算的主波心率值作为测量值，基于所述待预测心电信号中波峰或波谷特征点计算的主波心率值作为参考值。
  3. 根据权利要求1所述的方法，其中，所述基于上一时刻的参考参数的参考值获得当前时刻的预测值，包括：
    将所述上一时刻的参考参数的参考值代入离散控制系统的状态方程中，获得当前时刻的预测值。
  4. 根据权利要求1所述的方法，其中，所述基于所述预测值和当前时刻的测量参数进行卡尔曼滤波，获得当前时刻的动态心率预测结果，之前还包括:
    根据系统转移理论确定协方差计算公式，基于所述协方差计算公式确定当前时刻的协方差和前一时刻的协方差；
    基于所述当前时刻的协方差、所述前一时刻的协方差、观测矩阵确定卡尔曼增益。
  5. 根据权利要求4所述的方法，其中，所述基于所述预测值和当前时刻的测量参数进行卡尔曼滤波，获得当前时刻的动态心率预测结果，包括：
    将所述预测值、所述当前时刻的测量参数以及所述卡尔曼增益输入修正方程，获得当前时刻的动态心率预测结果。
  6. 根据权利要求4所述的方法，其中，所述基于所述当前时刻的协方差、所述前一时刻的协方差、观测矩阵确定卡尔曼增益，之后还包括：
    若所述卡尔曼增益收敛于所述观测值，则更新所述协方差。
  7. 根据权利要求1所述的方法，其中，所述基于信号质量指数确定待预测心电信号的参考参数和测量参数，之前还包括：
    将待预测心电信号输入信号质量评估系统，由所述质量评估系统输出信号质量指数。
  8. 一种动态心率预测装置，其中，所述装置包括：
    确定模块，用于基于信号质量指数确定待预测心电信号的参考参数和测量参数；
    获得模块，用于基于上一时刻的参考参数的参考值获得当前时刻的预测值；
    滤波模块，用于基于所述预测值和所述当前时刻的测量参数的观测值进行卡尔曼滤波，获得当前时刻的动态心率预测结果。
  9. 一种动态心率预测设备，其中，所述动态心率预测设备包括处理器，存储器以及存储在所述存储器中的动态心率预测程序，所述动态心率预测程序被所述处理器运行时，实现如权利要求1-7中任一项所述的动态心率预测方法的步骤。
  10. 一种计算机可读存储介质，其中，所述计算机可读存储介质上存储有动态心率预测程序，所述动态心率预测程序被处理器运行时实现如权利要求1-7中任一项所述动态心率预测方法的步骤。
PCT/CN2021/118488 2020-09-30 2021-09-15 动态心率预测方法、装置、设备及可读存储介质 WO2022068589A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011070826.7A CN112043258A (zh) 2020-09-30 2020-09-30 动态心率预测方法、装置、设备及可读存储介质
CN202011070826.7 2020-09-30

Publications (1)

Publication Number Publication Date
WO2022068589A1 true WO2022068589A1 (zh) 2022-04-07

Family

ID=73605508

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/118488 WO2022068589A1 (zh) 2020-09-30 2021-09-15 动态心率预测方法、装置、设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN112043258A (zh)
WO (1) WO2022068589A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115460047A (zh) * 2022-08-02 2022-12-09 北京睿信丰科技有限公司 复杂信道下快速跟踪频偏和距离的方法、装置及电子设备
CN116148678A (zh) * 2023-04-19 2023-05-23 河南创达电子科技有限公司 基于大数据估算电池soc值的方法和装置
CN115460047B (zh) * 2022-08-02 2024-06-11 北京睿信丰科技有限公司 复杂信道下快速跟踪频偏和距离的方法、装置及电子设备

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112043258A (zh) * 2020-09-30 2020-12-08 青岛歌尔智能传感器有限公司 动态心率预测方法、装置、设备及可读存储介质
CN112716506B (zh) * 2021-01-15 2023-03-07 京东科技信息技术有限公司 一种信号处理方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107693000A (zh) * 2017-10-23 2018-02-16 山东大学 基于心电和脉搏信号融合的心率估计方法、装置和系统
CN109700450A (zh) * 2018-12-28 2019-05-03 联想(北京)有限公司 一种心率检测方法及电子设备
US20200000360A1 (en) * 2018-06-29 2020-01-02 Tata Consultancy Services Limited Heart rate driven unsupervised techniques for continuous monitoring of arousal trend of users
CN111265204A (zh) * 2019-04-30 2020-06-12 索思（苏州）医疗科技有限公司 一种由母亲腹部混合ecg信号提取胎儿心率的算法
CN112043258A (zh) * 2020-09-30 2020-12-08 青岛歌尔智能传感器有限公司 动态心率预测方法、装置、设备及可读存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2016894A1 (en) * 2007-07-20 2009-01-21 Stichting Voor De Technische Wetenschappen ECG signal processing
CN103020472B (zh) * 2012-12-27 2015-12-09 中国科学院深圳先进技术研究院 基于约束估计的生理信号质量评估方法和系统
CN104688219A (zh) * 2013-12-04 2015-06-10 乐普（北京）医疗器械股份有限公司 一种心电信号预测方法与系统
CN111474481B (zh) * 2020-04-13 2022-08-09 深圳埃瑞斯瓦特新能源有限公司 基于扩展卡尔曼滤波算法的电池soc估算方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107693000A (zh) * 2017-10-23 2018-02-16 山东大学 基于心电和脉搏信号融合的心率估计方法、装置和系统
US20200000360A1 (en) * 2018-06-29 2020-01-02 Tata Consultancy Services Limited Heart rate driven unsupervised techniques for continuous monitoring of arousal trend of users
CN109700450A (zh) * 2018-12-28 2019-05-03 联想(北京)有限公司 一种心率检测方法及电子设备
CN111265204A (zh) * 2019-04-30 2020-06-12 索思（苏州）医疗科技有限公司 一种由母亲腹部混合ecg信号提取胎儿心率的算法
CN112043258A (zh) * 2020-09-30 2020-12-08 青岛歌尔智能传感器有限公司 动态心率预测方法、装置、设备及可读存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115460047A (zh) * 2022-08-02 2022-12-09 北京睿信丰科技有限公司 复杂信道下快速跟踪频偏和距离的方法、装置及电子设备
CN115460047B (zh) * 2022-08-02 2024-06-11 北京睿信丰科技有限公司 复杂信道下快速跟踪频偏和距离的方法、装置及电子设备
CN116148678A (zh) * 2023-04-19 2023-05-23 河南创达电子科技有限公司 基于大数据估算电池soc值的方法和装置

Also Published As

Publication number Publication date
CN112043258A (zh) 2020-12-08

Similar Documents

Publication Publication Date Title
WO2022068589A1 (zh) 动态心率预测方法、装置、设备及可读存储介质
Suppappola et al. Nonlinear transforms of ECG signals for digital QRS detection: a quantitative analysis
US5521851A (en) Noise reduction method and apparatus
JP2001517128A (ja) 血液成分値の最良な評価を得るために調停し，高調波を除去するための方法および装置
CN111652135B (zh) 心电图数据生成方法、装置及电子设备
CN114788918B (zh) 一种反应力训练方案制定方法、装置、设备及存储介质
EP3342332A1 (en) Adaptive bio-signal feature combining apparatus and method
Bourdillon et al. RMSSD is more sensitive to artifacts than frequency-domain parameters: implication in athletes’ monitoring
CN111387936A (zh) 一种睡眠阶段识别方法、装置及设备
WO2020147149A1 (zh) 纠偏心率的方法、装置及存储介质
WO2014190254A1 (en) A system and method for assessing the clinical stability of critically ill patients under intensive care
CN113576423A (zh) 一种核心体温的确定方法、装置、设备及存储介质
EP3954289A1 (en) Monitoring device and physiological parameter processing method therefor
CN112806961A (zh) 体征数据评估方法及装置
Forouzanfar et al. Adaptive neuro-fuzzy inference system for oscillometric blood pressure estimation
US11406309B2 (en) Heartbeat rate calculation device and method
CN108670231B (zh) 血压测量方法、终端和计算机可读存储介质
US20130079652A1 (en) Assessment of cardiac health based on heart rate variability
CN114246563A (zh) 基于毫米波雷达的心肺功能智能监测设备
Lee et al. Ensemble methodology for confidence interval in oscillometric blood pressure measurements
US20240050043A1 (en) Method And Apparatus For Heart-level Blood Pressure Estimation Based On Ensemble Learning
CN111805545B (zh) 灵巧手控制方法、装置及终端设备
CN113647917B (zh) 一种核心体温的确定方法、装置、移动终端及存储介质
Eleftheriadis et al. Fast and accurate power spectral analysis of heart rate variability using fast Gaussian gridding
RU2766409C2 (ru) Система и способ для оценивания объема крови в мозге, и/или кровотока в мозге, и/или глубины анестезии пациента

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: 21874250

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: 21874250

Country of ref document: EP

Kind code of ref document: A1