WO2020042711A1 - 一种提高睡眠监测准确性的可穿戴设备 - Google Patents

一种提高睡眠监测准确性的可穿戴设备 Download PDF

Info

Publication number
WO2020042711A1
WO2020042711A1 PCT/CN2019/090537 CN2019090537W WO2020042711A1 WO 2020042711 A1 WO2020042711 A1 WO 2020042711A1 CN 2019090537 W CN2019090537 W CN 2019090537W WO 2020042711 A1 WO2020042711 A1 WO 2020042711A1
Authority
WO
WIPO (PCT)
Prior art keywords
signals
signal
module
sleep
ecg
Prior art date
Application number
PCT/CN2019/090537
Other languages
English (en)
French (fr)
Inventor
张新静
王晓东
胡继松
杨豪放
Original Assignee
江苏盖睿健康科技有限公司
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 江苏盖睿健康科技有限公司 filed Critical 江苏盖睿健康科技有限公司
Priority to US16/606,532 priority Critical patent/US20210212630A1/en
Publication of WO2020042711A1 publication Critical patent/WO2020042711A1/zh

Links

Images

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
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
    • 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
    • A61B5/02405—Determining heart rate variability
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
    • A61B5/0816—Measuring devices for examining respiratory frequency
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
    • A61B5/28—Bioelectric electrodes therefor specially adapted for particular uses for electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
    • A61B5/28—Bioelectric electrodes therefor specially adapted for particular uses for electrocardiography [ECG]
    • A61B5/282—Holders for multiple electrodes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/389—Electromyography [EMG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/389—Electromyography [EMG]
    • A61B5/397—Analysis of electromyograms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4812—Detecting sleep stages or cycles
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4815—Sleep quality
    • 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
    • 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
    • A61B5/6813—Specially adapted to be attached to a specific body part
    • A61B5/6823—Trunk, e.g., chest, back, abdomen, hip
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0271—Thermal or temperature sensors
    • 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
    • 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
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems

Definitions

  • the invention relates to the technical field of sleep monitoring, in particular to a wearable device for improving the accuracy of sleep monitoring.
  • PSG polysomnography
  • Existing polysomnography monitors require multiple parameters to be monitored during hospitalization. Because they use separate modules for breathing and EMG acquisition, the subject's head, face, and body require multiple electrode leads and sensors. The operation is complicated, and because Monitoring environmental changes can have psychological and physiological effects on subjects, easily interfere with sleep, and even cause inaccurate measurements.
  • the module used for breathing information collection usually uses a thermistor to monitor changes in airflow during breathing during sleep, wears a foreign body sensation, and is susceptible to environmental temperature interference, and the data accuracy is poor; in addition to monitoring the trunk and limbs For the movement situation, a separate EMG acquisition module is often used, which increases the complexity of monitoring equipment and data.
  • the technical problems to be solved by the present invention are: the existing sleep monitoring equipment has complex equipment, easily interferes with the sleep quality of the testee, tedious data processing, and poor data accuracy.
  • a wearable device for improving the accuracy of sleep monitoring includes: a signal acquisition module, a signal conditioning module, a parameter extraction module, a decision module, and a sleep quality evaluation module; the signal acquisition module collects physiological signals through a sensor, and the signal conditioning module receives the above Physiological signals and various data signals are obtained through signal conditioning.
  • the parameter extraction module receives the data signals to extract the characteristic parameter signals.
  • the decision module is used to fuse the multiple characteristic parameter signals.
  • the sleep quality assessment module is used to perform the fusion based on the multiple characteristic parameter signals. Sleep quality assessment; After receiving the ECG electrode signals, the signal adjustment module extracts three physiological signals: ECG signals, respiratory signals, and myoelectric signals through different band-pass filtering methods.
  • the wearable device further includes a wireless communication module, a display module, a local storage module, a power module, and a USB interface.
  • the signal acquisition module includes an electrocardiogram electrode, a posture change sensor, and a temperature sensor.
  • the attitude change sensor is a three-axis magnetic flux door sensor, a tilt-compensated three-dimensional electronic compass, and / or a three-axis accelerometer.
  • the electrocardiogram electrode includes two or more electrocardiogram electrodes, and through detection of the electrocardiogram electrodes, it is possible to collect a high-precision electrocardiogram signal of the wearer.
  • the signal conditioning module includes a filter circuit, and the filter circuit includes a low-pass filter section, a linear section and a resonance section.
  • the method includes:
  • a physiological signal collection step wherein the physiological signals include an electrocardiogram electrode signal, a body temperature signal, and a posture movement signal;
  • step S3 Obtain ECG signals, respiratory signals, EMG signals, standard body temperature, and exercise data according to step S2, and further extract corresponding feature values through a parameter extraction module;
  • a multi-parameter fusion method is used to establish a specific sleep staging process
  • S5. Use the sleep quality assessment module to perform sleep quality assessment.
  • the S2 further includes:
  • the signals obtained by the ECG electrodes are signal-conditioned by the signal conditioning module, and the ECG signals, respiratory signals, and myoelectric signals in the ECG electrode signals are extracted by filtering in different frequency bands.
  • step S3 further includes:
  • the step S4 specifically includes: adjusting the initial threshold of each feature in different sleep stages according to the body temperature and the age and sex of the wearer, including the upper threshold TH and the lower threshold TL; wearing it for several days, saving and updating the template, and extracting the corresponding
  • the characteristics of each period of data corresponding to the sleep state, the above-mentioned characteristics are cross-validated, or the maximum correlation minimum redundancy criterion is used to select the characteristics and input to the classifier.
  • the preferred support vector machine is used for classification and discrimination to establish specificity. Sleep staging process.
  • the wearable device provided by the present invention for improving the accuracy of sleep monitoring has the following beneficial effects: 1) obtaining ECG electrode signals from two or more electrodes, and extracting ECG signals, breathing signals and Three physiological signals of EMG signals reduce the complexity of the device; 2) Multi-parameter fusion is adopted to improve the reliability of sleep staging detection.
  • FIG. 1 is a schematic diagram of the overall structure of a wearable device for improving the accuracy of sleep monitoring provided by the present invention.
  • Figure 2 is a filter circuit diagram in a signal conditioning module.
  • FIG. 3 is a flowchart of a sleep monitoring method for a wearable device based on the present invention to improve the accuracy of sleep monitoring.
  • the device includes a signal acquisition module, a signal conditioning module, a parameter extraction module, a decision module, a wireless communication module, and a local storage module.
  • a USB interface in order to achieve the communication and power requirements of the wearable device, a power supply module and a display module are also provided in the device.
  • the signal acquisition module includes an ECG electrode, an attitude change sensor, and a temperature sensor.
  • the electrocardiogram electrode is disposed on a heart rate band
  • the attitude change sensor and the temperature sensor are disposed on a main body portion of the wearable device.
  • the body part of the wearable device may be an existing wearable device that is in contact with the head and / or limbs of the subject.
  • the wearable device may be in the form of a watch, a headband, a neckband, etc. But it is not limited to the above.
  • the heart rate band and the main body of the wearable device are connected by wireless communication.
  • the specific connection method can be local area network, Bluetooth or Zigbee.
  • the electrocardiogram electrode may include two or more electrocardiogram electrodes, and through detection of the electrocardiogram electrodes, it is possible to collect a high-precision electrocardiogram signal of the wearer.
  • the ECG electrode may be installed in the heart rate belt, and the wearer only needs to fix the heart rate belt to the chest before falling asleep, so that the ECG electrode in the heart rate belt contacts the detection position.
  • the heart rate band may be an elastic textile, and the electrocardiogram electrodes and related circuits and wireless communication equipment are arranged at corresponding positions.
  • the data information collected by the heart rate band is sent to the main body of the wearable device through the wireless communication device, and is preferably sent to a local memory for storage.
  • the attitude change sensor uses a single-axis, dual-axis or three-axis acceleration sensor and / or a gyroscope and / or a magnetometer to monitor the attitude change of the subject.
  • the posture change of the subject can be collected through the above sensors or a combination of sensors, and the motion data of the subject during sleep can be obtained through long-term data accumulation.
  • the attitude change sensor is a three-axis magnetic flux door sensor, an inclination-compensated three-dimensional electronic compass, or a three-axis accelerometer.
  • the above-mentioned integrated high-precision MCU control can achieve an accurate measurement of the detected person's attitude and movement.
  • the temperature sensor is exposed on the surface of the wearable device and is in contact with the skin of the test subject, and is used to detect the temperature change of the test subject.
  • the temperature sensor can be installed on the heart rate belt together with the heart electrode, so as to obtain the body temperature signal of the person's chest more accurately.
  • the body temperature signal in front of the chest can more accurately reflect the physical state of the person being detected.
  • the data collected by the sensors in the above signal acquisition module are stored in a local memory through a data transmission circuit and / or a wireless network, and are stored as raw data.
  • the signal conditioning module is used for conditioning the signals collected by the signal acquisition module to obtain ECG signals, respiratory signals, myoelectric signals, standard body temperature and motion data (including acceleration, angular acceleration, etc.).
  • the signal conditioning module includes a filter circuit, as shown in Figure 2.
  • the signal conditioning module includes a low-pass filtering section, a linear section and a resonance section.
  • the low-pass filtering part adopts a first-order low-pass filtering method, and the signal is low-pass filtered through an amplifier. Because the amplifier is used instead of inductive filtering, better attenuation performance can be obtained.
  • the signal of the low-pass filtering part is further filtered by the linear part and the resonance part.
  • the structure is used to implement the filter, so that the filter has strict linear phase characteristics.
  • the filter coefficients are all integer powers, so simple shift operations can be used instead of traditional floating-point multiplication, and the operation efficiency is very high. high.
  • the low-pass filter can be easily extended to simple integer coefficient filters of the high-pass, band-pass, and band-stop types.
  • band-pass filtering in different frequency bands is used to extract the signals.
  • the breathing signal is lower than 0.5Hz
  • the first bandpass filter is used to extract the breathing signal
  • the QRS main wave frequency in the ECG signal is about 5-15Hz
  • the second bandpass filter is used to extract the ECG signal
  • EMG The energy of the signal is mainly concentrated at 20-150Hz, so the third band-stop filter is used to filter out 50Hz power frequency interference, and the fourth band-pass filter is used to extract the EMG signal.
  • the above-mentioned first, second and fourth band-pass frequencies correspond to corresponding signal frequencies
  • the third band-stop frequency is 50 Hz.
  • the signal may be down-sampled.
  • the parameter extraction module is used to perform heart rate variability analysis on the above-mentioned ECG signals, and extract time-domain and frequency-domain parameters within a certain time window.
  • the frequency-domain parameters LF / HF can be used to evaluate the sympathetic and parasympathetic nerve balance.
  • the time domain within the time window is preferably 5 min.
  • the normalized value can be within a certain range. To a certain extent, it reduces individual differences and highlights their variability.
  • the time window is preferably 30s.
  • the breathing signal can also be extracted from the low frequency components of the heart rate variability index.
  • the normalization value can reduce individual differences to a certain extent, and highlight their variability.
  • the single-axis, any two-axis, and three-axis vector sum of the motion sensor and integrate or average the data within a certain time window, or calculate its spectrum and its kurtosis and skewness.
  • the decision module is used to adjust the initial threshold of each feature in different sleep stages according to the body temperature and the age and sex of the wearer, including the upper threshold TH and the lower threshold TL;
  • the classification is performed in a preferred support vector machine to establish a specific sleep staging process, such as awake, light sleep and deep sleep corresponding to three levels of 1, 2, and 3, respectively.
  • the output result of the classifier is analyzed retrospectively, which is based on the change rule of the sleep stage.
  • the sleep quality calculation module is used to perform statistical analysis on sleep all night, time statistics of each sleep phase, and calculate the index of deep sleep as the total sleep time.
  • the index related to deep sleep is a direct assessment index of sleep quality.
  • Low-pass filtering or difference processing is performed on the sleep stage to convert the jagged sleep phase into a slightly smooth curve, and power spectrum analysis is performed to observe the regularity of the change, which is used as another sleep quality assessment index.
  • the wireless communication module is used to send the analysis result of the sleep phase to the smart terminal through the wireless communication method to reduce the power consumption of data transmission. And send the instructions of the smart terminal to the wearable device.
  • the local storage module is used to continuously store the collected raw data or signal-conditioned data and status parameters.
  • the sleep analysis is drawn using different colored line segments, and the quality of sleep statistics is displayed.
  • the above structure is visually displayed on a straight line.
  • the USB interface is used for data derivative and charging.
  • a sleep monitoring method based on the wearable device that improves the accuracy of sleep monitoring is described below with reference to FIG. 3.
  • the above sleep monitoring method includes:
  • the ECG electrodes, posture change sensors and temperature sensors in the signal acquisition module collect the ECG signals, posture movement data and body temperature data of the subject, respectively.
  • S2 Process the above detection data through a signal conditioning module to obtain ECG signals, respiratory signals, myoelectric signals, standard body temperature and motion data (including acceleration, angular acceleration, etc.).
  • the above S2 further includes:
  • the signals obtained by the ECG electrodes are signal-conditioned by the signal conditioning module, and the ECG signals, respiratory signals, and myoelectric signals in the ECG electrode signals are extracted by filtering in different frequency bands.
  • the signal conditioning module uses bandpass filtering of different frequency bands to extract signals according to the frequency band characteristics of different signals.
  • the respiratory signal is lower than 0.5Hz, and the QRS main wave frequency in the ECG signal is about 5-15Hz.
  • the energy of the EMG signal is mainly concentrated at 20-150Hz.
  • the ECG signal is extracted, and the third band stop filter is used to filter out 50Hz power frequency interference.
  • the fourth band pass filter is used to extract the myoelectric signal.
  • the signal may be down-sampled.
  • a coefficient relationship between the corresponding position and the standard body temperature is obtained, and the above-mentioned coefficient relationship may be stored in a local memory.
  • the person being tested wears a wearable device, they can select the position where the temperature sensor is set on the display, read the coefficient relationship in the local memory according to the position signal conditioning module, and use the coefficient relationship to convert the body temperature signal (such as the chest Body temperature signal) to obtain standard body temperature (such as underarm body temperature).
  • the body temperature signal such as the chest Body temperature signal
  • standard body temperature such as underarm body temperature
  • the signal conditioning module first removes the initial error of the above-mentioned attitude motion data to obtain a preliminary correction value; then, the data of various sensors are fused by a fusion algorithm, and the specific fusion algorithm may be a Kalman filter known in the art. Method and other extended forms of Kalman filtering method to obtain motion data, acceleration or angular acceleration data.
  • step S2 the ECG signal, respiratory signal, myoelectric signal, standard body temperature, and exercise data are obtained, and the corresponding feature values are further extracted through the parameter extraction module.
  • step S3 further includes:
  • a multi-parameter fusion method is used to establish a specific sleep staging process.
  • the initial threshold of each feature in different sleep stages is adjusted according to the body temperature and the age and sex of the wearer, including the upper threshold TH and the lower threshold TL;
  • the classification is performed in a preferred support vector machine to establish a specific sleep staging process, such as awake, light sleep and deep sleep corresponding to three levels of 1, 2, and 3, respectively.
  • the output result of the classifier is analyzed retrospectively, which is based on the change rule of the sleep stage.
  • S5. Use the sleep quality assessment module to perform sleep quality assessment.
  • the whole night's sleep is statistically analyzed, and the time statistics of each sleep phase are used to calculate the index of deep sleep as the total sleep time.
  • the index related to deep sleep is a direct assessment index of sleep quality.
  • Low-pass filtering or difference processing is performed on the sleep stage to convert the jagged sleep phase into a slightly smooth curve, and power spectrum analysis is performed to observe the regularity of the change, which is used as another sleep quality assessment index.
  • the wearable device provided by the present invention for improving the accuracy of sleep monitoring has the following beneficial effects: 1) obtaining ECG electrode signals from two or more electrodes, and extracting ECG signals, breathing signals and Three physiological signals of EMG signals reduce the complexity of the device; 2) Multi-parameter fusion is adopted to improve the reliability of sleep staging detection.
  • this application may be provided as a method, an apparatus, or a computer program product. Therefore, this application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.

Abstract

一种提高睡眠监测准确性的可穿戴设备，包括：信号采集模块、信号调理模块、参数提取模块、决策模块、睡眠质量评估模块；信号采集模块通过传感器采集生理信号，信号调理模块接收生理信号并通过信号调理获得多种数据信号，参数提取模块接收数据信号提取特征参数信号，决策模块用于融合多种特征参数信号，睡眠质量评估模块用于根据融合后的多种特征参数信号进行睡眠质量评估；信号调理模块接收心电电极信号后，通过不同带通滤波的方式提取心电信号、呼吸信号和肌电信号三种生理信号。实现了提供连续、准确、舒适、低复杂度的睡眠监测的技术效果。

Description

一种提高睡眠监测准确性的可穿戴设备 技术领域
本发明涉及睡眠监测技术领域，特别涉及一种提高睡眠监测准确性的可穿戴设备。
背景技术
睡眠质量直接影响人们的生活和工作质量，睡眠质量差或紊乱会导致身体出现亚健康状态，甚至诱发疾病。随着生活节奏的加快，压力也越来越大，睡眠质量易出现问题，且难以预测。因此，对于睡眠质量进行检测的设备逐渐受到厂商和消费者的关注。目前，市场上睡眠质量监测装置的主流产品为多导睡眠监测仪(Polysomnography，PSG)。
现有的多导睡眠监测仪需要住院监测多个参数，由于其采用单独的模块分别进行呼吸和肌电采集，被试者头面部和身体需要安放多个电极导线和传感器，操作复杂，且由于监测环境变化，对被试者产生心理和生理影响，易干扰睡眠，甚至导致测量不准确。并且，用于呼吸信息采集的模块，在睡眠中的呼吸通常采用热敏电阻来监测气流变化，佩戴有异物感，且容易受到环境温度的干扰，数据准确性差；再加上为监测躯干和四肢的运动情况，常采用单独的肌电采集模块，增加了监测的设备和数据复杂度。
因此，针对现有产品的缺陷，需要提供一种可以提供连续、准确、舒适、低复杂度的睡眠监测的睡眠监测设备。
发明内容
本发明所要解决的技术问题是：现有睡眠监测设备的设备复杂、容易干扰被测试者睡眠质量、数据处理过程繁琐、数据准确性差等问题。
本发明解决其技术问题所采取的技术方案是：
一种提高睡眠监测准确性的可穿戴设备，该设备包括：信号采集模块、信号调理模块、参数提取模块、决策模块、睡眠质量评估模块；信号采集模块通过传感器采集生理信号，信号调理模块接收上述生理信号并通过信 号调理获得多种数据信号，参数提取模块接收数据信号提取特征参数信号，决策模块用于融合多种特征参数信号，睡眠质量评估模块用于根据融合后的多种特征参数信号进行睡眠质量评估；信号调整模块接收心电电极信号后，通过不同带通滤波的方式提取心电信号、呼吸信号和肌电信号三种生理信号。
进一步地，该穿戴设备进一步还包括无线通讯模块、显示模块、本地存储模块、电源模块和USB接口。
进一步地，信号采集模块包括心电电极、姿态变化传感器和温度传感器。
进一步地，姿态变化传感器为三轴磁通门传感器、倾角补偿式三维电子罗盘和/或三轴加速度计。
进一步地，心电电极包括两个或者两个以上的心电电极，通过该心电电极的检测，能够采集佩戴者高精度的心电信号。
进一步地，信号调理模块包括滤波电路，滤波电路包括低通滤波部分，线性部分和谐振部分。
基于所述的提高睡眠监测准确性的可穿戴设备的睡眠监测方法，该方法包括：
S1.生理信号采集步骤，上述生理信号包括心电电极信号、体温信号和姿态运动信号；
S2.将上述检测数据通过信号调理模块进行处理，分别得到心电信号、呼吸信号、肌电信号、标准体温和运动数据；
S3.根据S2步骤中获得心电信号、呼吸信号、肌电信号、标准体温和运动数据，通过参数提取模块进一步提取相应地特征值；
S4.通过决策模块，采用多参数融合方法，建立具有特异性的睡眠分期过程；
S5.通过睡眠质量评估模块，进行睡眠质量的评估。
进一步地，所述S2进一步包括：
S21.通过信号调理模块将心电电极获得的信号进行信号调理，通过不同频带滤波，提取心电电极信号中的心电信号、呼吸信号和肌电信号。
S22.对体温信号进行温度补偿，得到标准体温信号。
S23.对姿态运动信号进行处理，获得运动数据、加速度或者角加速度数据。
进一步地，所述步骤S3进一步包括：
S31.从心电信号中提取心率变异性特征值；
S32.从呼吸信号中提取呼吸频次的最大值、最小值特征值；
S33.从肌电信号中提取中位频率和平均频率特征值；
S34.从标准体温信号中提取体温的最大值、最小值、均值和标准差特征值；
S35.从运动数据中提取运动数据矢量和的积分、均值、峰度特征值。
进一步地，所述S4步骤，具体包括：根据体温和佩戴者年龄性别调整不同睡眠阶段的各特征的初始阈值，包括阈值上限TH和阈值下限TL；连续佩戴若干天，保存并更新模板，提取相应睡眠状态对应的各时段数据特征，将上述各特征通过交叉验证，或最大相关最小冗余准则，进行特征筛选，并输入到分类器，优选的支持向量机中进行分类判别，从而建立具有特异性的睡眠分期过程。
本发明提供的提高睡眠监测准确性的可穿戴设备，具有以下有益效果：1)从两个或这两个以上的电极获得心电电极信号，通过信号调理的方式提取心电信号、呼吸信号和肌电信号三种生理信号，降低了设备的复杂度；2)采用多参数融合，提高了睡眠分期检测的可靠性。
附图说明
图1为本发明提供的提高睡眠监测准确性的可穿戴设备的整体结构示意图。
图2为信号调理模块中的滤波电路图。
图3为基于本发明提供的提高睡眠监测准确性的可穿戴设备的睡眠监测方法的流程图。
具体实施方式
下面将参照附图对本发明进行更详细的描述，其中表示了本发明的优选实施例，应该理解本领域技术人员可以修改在此描述的本发明而仍然实 现本发明的有益效果。因此，下列描述应当被理解为对于本领域技术人员的广泛知道，而并不作为对本发明的限制。
为了清楚，不描述实际实施例的全部特征。在下列描述中，不详细描述公知的功能和结构，因为它们会使本发明由于不必要的细节而混乱。应当认为在任何实际实施例的开发中，必须作出大量实施细节以实现开发者的特定目标。
为使本发明的目的、特征更明显易懂，下面结合附图对本发明的具体实施方式作进一步的说明。需要说明的是，附图均采用非常简化的形式且均使用非精准的比率，仅用一方便、清晰地辅助说明本发明实施例的目的。
本实施例提供了一种提高睡眠监测准确性的可穿戴设备，如图1所示，该设备包括：信号采集模块、信号调理模块、参数提取模块、决策模块、无线通信模块、本地存储模块。此外，为了实现该可穿戴设备的通讯和电能需求，在该设备中还设置了USB接口、电源供电模块和显示模块。
下面对本申请提供的提高睡眠监测准确性的可穿戴设备的主要模块进行介绍：
信号采集模块
其中，信号采集模块包括心电电极、姿态变化传感器和温度传感器。其中，心电电极设置在一心率带上，而姿态变化传感器和温度传感器设置在可穿戴设备的主体部分上。该可穿戴设备的主体部分可以为现有的与被检测者头部和/或四肢相接触的可穿戴设备，作为举例性的说明，可穿戴设备可以为手表、头箍、颈圈等形式，但不限于上述方式。心率带和可穿戴设备主体部分之间通过无线通讯连接，具体的连接方式可以为局域网，蓝牙或者Zigbee。
心电电极可以包括两个或者两个以上的心电电极，通过该心电电极的检测，能够采集佩戴者高精度的心电信号。在具体实施例中，该心电电极可以安装于心率带中，佩戴者仅需要在入睡前将心率带固定佩戴与胸部，使得心率带中的心电电极接触检测位置即可。优选地，心率带可以弹性纺织物，并在相应位置上配置了心电电极及其相关电路和无线通信设备。上述心率带采集的数据信息，通过无线通信设备发送到可穿戴设备的主体部分，优选发送到本地存储器存储。
姿态变化传感器采用单轴、双轴或三轴的加速度传感器和/或陀螺仪和/或磁力计监测被试的姿态变化。通过上述传感器或者传感器的组合可 以采集被检测者的姿态变化情况，并且通过长时间的数据累计可以获得被检测者在睡眠中的运动数据。优选地，该姿态变化传感器为三轴磁通门传感器、倾角补偿式三维电子罗盘或三轴加速度计，上述集成高精度的MCU控制，能够实现对于被检测者姿态和动作最大化的精度测量。
温度传感器暴露在可穿戴设备表面，并且与被测试者的皮肤接触，其用来检测被检测者的体温变化。优选地，该温度传感器可以和心电极一起安装在心率带上，从而更加准确地获得该被检测人员胸前的体温信号。该胸前的体温信号能够更准确地反映被检测人员的身体状态。
上述信号采集模块中的传感器采集的数据通过数据传输电路和/或无线网络被储存到本地存储器中，作为原始数据被保存。
信号调理模块
信号调理模块用于将信号采集模块采集的信号进行调理处理，分别得到心电信号、呼吸信号、肌电信号、标准体温和运动数据(包括加速度、角加速度等)。
信号调理模块包括滤波电路，如图2所示。该信号调理模块包括低通滤波部分，线性部分和谐振部分。其中，低通滤波部分采用一阶低通滤波方式，信号经由放大器进行低通滤波。由于采用了放大器，而不是电感滤波，能够获得较好的衰减性能。经低通滤波部分的信号，进一步通过线性部分和谐振部分处理实现滤波。
采用结构来实现滤波器，使滤波器具有严格的线性相位特性；另一方面，滤波器系数都采用的整次幂，故可以用简单的移位运算来代替传统的浮点乘法，运算效率非常高。而且，该低通滤波器可以很容易扩展成高通、带通和带阻型的简单整系数滤波器。
在信号滤波处理时，由于不同信号的特点，采用了不同频段的带通滤波来提取信号。具体地，由于呼吸信号低于0.5Hz，因此采用第一带通滤波提取呼吸信号；心电信号中的QRS主波频率约5-15Hz，因此采用第二带通滤波提取心电信号；肌电信号的能量主要集中在20-150Hz，因此采用第三带阻滤波滤除50Hz工频干扰，采用第四带通滤波提取肌电信号。上述第一、二、四带通频率与相应的信号频率相对应，第三带阻频率为50Hz。
优选地，为降低存储空间，可考虑对信号进行降采样处理。
参数提取模块
参数提取模块用于对上述心电信号进行心率变异性分析，提取某个时间窗内的时域和频域参数，其中频域参数LF/HF可用于评估交感神经和副交感神经的平衡性。其中，上述时间窗内的时域优选为5min。
对上述呼吸信号，提取某个时间窗内呼吸频次最大值、最小值、均值及标准差，并利用z-Score方法，计算连续5min的各参数的归一化值，归一化值能在一定程度上降低个体差异性，而突出其变化性。上述时间窗优选为30s。呼吸信号亦可通过心率变异性指标的低频成分提取。
对上述体温信号，提取某个时间窗内(优选的30s)体温信号的最大值、最小值、均值及标准差，并利用z-Score方法，计算连续5min的各参数的归一化值，归一化值能在一定程度上降低个体差异性，而突出其变化性。
运动传感器的各单轴、任两轴及三轴矢量和，并对某一时间窗长内数据进行积分或求均值，或计算其频谱及其峰度和偏度。
对肌电信号进行功率谱分析，提取其中位频率和平均频率。
决策模块
决策模块用于根据体温和佩戴者年龄性别调整不同睡眠阶段的各特征的初始阈值，包括阈值上限TH和阈值下限TL；
连续佩戴若干天，如一周，保存并更新模板，提取相应睡眠状态对应的各时段数据特征，将上述各特征通过交叉验证，或最大相关最小冗余准则，进行特征筛选，并输入到分类器，优选的支持向量机中进行分类判别，从而建立具有特异性的睡眠分期过程，如清醒，浅睡眠和深睡眠分别对应着1，2，3三个等级。
进一步地，分类器输出结果进行回溯分析，其依据是睡眠阶段的变化规律。
计算睡眠质量模块
计算睡眠质量模块用于将整晚睡眠进行统计分析，各睡眠时相的时间统计，计算深度睡眠占总睡眠时间的指数，与深度睡眠相关的指数是睡眠质量的直接评估指标。
对睡眠分期进行低通滤波或差值处理，将锯齿状变化的睡眠时相转换为稍平滑的曲线，并进行功率谱分析，观察其变化的规律性，以此作为另一睡眠质量评估指标。
无线通信模块
无线通信模块用于将睡眠时相的分析结果，通过无线通信方式，发送到智能终端，以降低数据传送的功耗。并将智能终端的指令发送到可穿戴设备。
本地存储模块
本地存储模块用于在本地连续存储采集到的原始数据，或经过信号调理的数据，及状态参数等。
显示模块
将睡眠分析使用不同颜色的线段进行描绘，并显示睡眠统计质量结果，将上述结构直观地显示在一条直线上。
USB接口
USB接口用于将数据导数及充电用。
电源供电模块：
为可穿戴设备供电，以满足设备独立工作的需求。
下面结合附图3说明基于上述提高睡眠监测准确性的可穿戴设备的一种睡眠监测方法。
如图3所示，上述睡眠监测方法包括：
S1.生理信号采集步骤；
其中，通过信号采集模块中的心电电极、姿态变化传感器和温度传感器，分别采集被检测者的心电信号、姿态运动数据和人体体温数据。
S2.将上述检测数据通过信号调理模块进行处理，分别得到心电信号、呼吸信号、肌电信号、标准体温和运动数据(包括加速度、角加速度等)。
其中，上述S2进一步包括：
S21.通过信号调理模块将心电电极获得的信号进行信号调理，通过不同频带滤波，提取心电电极信号中的心电信号、呼吸信号和肌电信号。
具体地，通过信号调理模块根据不同信号的频带特点，采用了不同频段的带通滤波来提取信号。呼吸信号低于0.5Hz，心电信号中的QRS主波频率约5-15Hz，肌电信号的能量主要集中在20-150Hz，因此采用第一低通 滤波提取呼吸信号，采用第二带通滤波提取心电信号，采用第三带阻滤波滤除50Hz工频干扰，采用第四带通滤波提取肌电信号。优选地，为降低存储空间，可考虑对信号进行降采样处理。
S22.对体温信号进行温度补偿，得到标准体温(例如腋下体温)。
具体地，根据温度传感器设置的不同位置，获取相应位置与标准体温之间的系数关系，上述系数关系可以存储于本地存储器中。当被检测人佩戴可穿戴设备后，可以在显示器上选择输入温度传感器设置的位置，根据上述位置信号调理模块读取本地存储器中的系数关系，并通过上述系数关系，将体温信号(例如胸前的体温信号)进行补偿获得标准体温(例如腋下体温)。
S23.对姿态运动信号进行处理，获得运动数据、加速度或者角加速度数据。
具体地，信号调理模块首先将上述姿态运动数据进行初始误差的去除，获得初步校正值；随后将通过融合算法将多种传感器的数据进行融合，具体的融合算法可以为本领域公知的卡尔曼滤波法和卡尔曼滤波法的其他扩展形式，从而获得运动数据、加速度或者角加速度数据。
S3.根据S2步骤中获得心电信号、呼吸信号、肌电信号、标准体温和运动数据，通过参数提取模块进一步提取相应地特征值。
具体地，上述步骤S3进一步包括：
S31.从心电信号中提取心率变异性特征值，例如：LF/HF，RMSSD等；
S32.从呼吸信号中提取呼吸频次的最大值、最小值等特征值；
S33.从肌电信号中提取中位频率和平均频率等特征值；
S34.从标准体温信号中提取体温的最大值、最小值、均值和标准差等特征值；
S35.从运动数据中提取运动数据矢量和的积分、均值、峰度等特征值。
S4.通过决策模块，采用多参数融合方法，建立具有特异性的睡眠分期过程。
具体地，根据体温和佩戴者年龄性别调整不同睡眠阶段的各特征的初始阈值，包括阈值上限TH和阈值下限TL；
连续佩戴若干天，如一周，保存并更新模板，提取相应睡眠状态对应的各时段数据特征，将上述各特征通过交叉验证，或最大相关最小冗余准则，进行特征筛选，并输入到分类器，优选的支持向量机中进行分类判别，从而建立具有特异性的睡眠分期过程，如清醒，浅睡眠和深睡眠分别对应着1，2，3三个等级。
进一步地，分类器输出结果进行回溯分析，其依据是睡眠阶段的变化规律。
S5.通过睡眠质量评估模块，进行睡眠质量的评估。
具体地，将整晚睡眠进行统计分析，各睡眠时相的时间统计，计算深度睡眠占总睡眠时间的指数，与深度睡眠相关的指数是睡眠质量的直接评估指标。
对睡眠分期进行低通滤波或差值处理，将锯齿状变化的睡眠时相转换为稍平滑的曲线，并进行功率谱分析，观察其变化的规律性，以此作为另一睡眠质量评估指标。
本发明提供的提高睡眠监测准确性的可穿戴设备，具有以下有益效果：1)从两个或这两个以上的电极获得心电电极信号，通过信号调理的方式提取心电信号、呼吸信号和肌电信号三种生理信号，降低了设备的复杂度；2)采用多参数融合，提高了睡眠分期检测的可靠性。
本领域内的技术人员应明白，本申请的实施例可提供为方法、装置、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上显示和描述了本发明的基本原理、主要特征和优点。本行业的技术人员应该了解，本发明不受上述实施例的限制，上述实施例和说明书中描述的只是说明本发明的原理，在不脱离本发明精神和范围的前提下，本发明还会有各种变化和改进，这些变化和改进都落入要求保护的本发明范围内。本发明要求保护范围由所附的权利要求书及其等效物界定。

Claims (10)

  1. 一种提高睡眠监测准确性的可穿戴设备，其特征在于，该设备包括：信号采集模块、信号调理模块、参数提取模块、决策模块、睡眠质量评估模块；信号采集模块通过传感器采集生理信号，信号调理模块接收上述生理信号并通过信号调理获得多种数据信号，参数提取模块接收数据信号提取特征参数信号，决策模块用于融合多种特征参数信号，睡眠质量评估模块用于根据融合后的多种特征参数信号进行睡眠质量评估；信号调整模块接收心电电极信号后，通过不同带通滤波的方式提取心电信号、呼吸信号和肌电信号三种生理信号。
  2. 根据权利要求1所述的提高睡眠监测准确性的可穿戴设备，其特征在于：该穿戴设备进一步还包括无线通讯模块、显示模块、本地存储模块、电源模块和USB接口。
  3. 根据权利要求2所述的提高睡眠监测准确性的可穿戴设备，其特征在于：信号采集模块包括心电电极、姿态变化传感器和温度传感器。
  4. 根据权利要求3所述的提高睡眠监测准确性的可穿戴设备，其特征在于：姿态变化传感器为三轴磁通门传感器、倾角补偿式三维电子罗盘和/或三轴加速度计。
  5. 根据权利要求3所述的提高睡眠监测准确性的可穿戴设备，其特征在于：心电电极包括两个或者两个以上的心电电极，通过该心电电极的检测，能够采集佩戴者高精度的心电信号。
  6. 根据权利要求1所述的提高睡眠监测准确性的可穿戴设备，其特征在于：信号调理模块包括滤波电路，滤波电路包括低通滤波部分，线性部分和谐振部分。
  7. 基于权利要求1-6所述的提高睡眠监测准确性的可穿戴设备的睡眠监测方法，其特征在于，该方法包括：
    S1.生理信号采集步骤，上述生理信号包括心电电极信号、体温信号和姿态运动信号；
    S2.将上述检测数据通过信号调理模块进行处理，分别得到心电信号、呼吸信号、肌电信号、标准体温和运动数据；
    S3.根据S2步骤中获得心电信号、呼吸信号、肌电信号、标准体温和运动数据，通过参数提取模块进一步提取相应地特征值；
    S4.通过决策模块，采用多参数融合方法，建立具有特异性的睡眠分期过程；
    S5.通过睡眠质量评估模块，进行睡眠质量的评估。
  8. 根据权利要求7所述的睡眠监测方法，其特征在于：所述S2进一步包括：
    S21.通过信号调理模块将心电电极获得的信号进行信号调理，通过不同频带滤波，提取心电电极信号中的心电信号、呼吸信号和肌电信号。
    S22.对体温信号进行温度补偿，得到标准体温信号。
    S23.对姿态运动信号进行处理，获得运动数据、加速度或者角加速度数据。
  9. 根据权利要求7所述的睡眠监测方法，其特征在于：所述步骤S3进一步包括：
    S31.从心电信号中提取心率变异性特征值；
    S32.从呼吸信号中提取呼吸频次的最大值、最小值特征值；
    S33.从肌电信号中提取中位频率和平均频率特征值；
    S34.从标准体温信号中提取体温的最大值、最小值、均值和标准差特征值；
    S35.从运动数据中提取运动数据矢量和的积分、均值、峰度特征值。
  10. 根据权利要求7所述的睡眠监测方法，其特征在于：所述S4步骤，具体包括：根据体温和佩戴者年龄性别调整不同睡眠阶段的各特征的初始阈值，包括阈值上限TH和阈值下限TL；连续佩戴若干天，保存并更新模板，提取相应睡眠状态对应的各时段数据特征，将上述各特征通过交叉验证，或最大相关最小冗余准则，进行特征筛选，并输入到分类器，优选的支持向量机中进行分类判别，从而建立具有特异性的睡眠分期过程。
PCT/CN2019/090537 2018-08-27 2019-06-10 一种提高睡眠监测准确性的可穿戴设备 WO2020042711A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/606,532 US20210212630A1 (en) 2018-08-27 2019-06-10 Wearable device with improved sleep monitoring accuracy

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810981164.5A CN109091125B (zh) 2018-08-27 2018-08-27 一种提高睡眠监测准确性的可穿戴设备
CN201810981164.5 2018-08-27

Publications (1)

Publication Number Publication Date
WO2020042711A1 true WO2020042711A1 (zh) 2020-03-05

Family

ID=64851287

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/090537 WO2020042711A1 (zh) 2018-08-27 2019-06-10 一种提高睡眠监测准确性的可穿戴设备

Country Status (3)

Country Link
US (1) US20210212630A1 (zh)
CN (1) CN109091125B (zh)
WO (1) WO2020042711A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116013470A (zh) * 2023-03-30 2023-04-25 安徽星辰智跃科技有限责任公司 一种睡眠行为活跃水平动态调节的方法、系统和装置
CN116509338A (zh) * 2023-06-29 2023-08-01 安徽星辰智跃科技有限责任公司 基于模态分析的睡眠周期性检测及调节方法、系统和装置

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109091125B (zh) * 2018-08-27 2020-06-30 江苏盖睿健康科技有限公司 一种提高睡眠监测准确性的可穿戴设备
WO2020133536A1 (zh) * 2018-12-29 2020-07-02 深圳迈瑞生物医疗电子股份有限公司 一种睡眠状态判断的方法及装置
KR102631160B1 (ko) * 2019-07-11 2024-01-30 엘지전자 주식회사 차량 탑승자 상태 감지방법 및 차량 탑승자 상태 감지장치
CN110825232B (zh) * 2019-11-07 2022-10-21 中国航天员科研训练中心 基于航天医监医保信号的手势识别人机交互装置
CN111248922B (zh) * 2020-02-11 2022-05-17 中国科学院半导体研究所 基于加速度计和陀螺仪的人体呼吸情况采集贴及制备方法
CN111317446B (zh) * 2020-02-27 2020-09-08 中国人民解放军空军特色医学中心 基于人体肌肉表面电信号的睡眠结构自动分析方法
CN112545851A (zh) * 2020-11-03 2021-03-26 未来穿戴技术有限公司 按摩方法及装置、电子设备、计算机可读存储介质
CN112656398B (zh) * 2020-12-13 2022-10-28 贵州省通信产业服务有限公司 一种用于无人看护的睡眠质量分析方法
CN112914589B (zh) * 2021-03-02 2023-04-18 钦州市第二人民医院 一种多导睡眠监测无线网帽装置及监测方法
CN113080897B (zh) * 2021-04-02 2023-07-28 北京正气和健康科技有限公司 一种基于生理和环境数据分析的入睡时刻评估系统及方法
CN113273967A (zh) * 2021-05-20 2021-08-20 贵州优品睡眠健康产业有限公司 一种睡眠体征监测系统
CN114403835B (zh) * 2021-12-31 2023-11-07 北京津发科技股份有限公司 一种可穿戴的多指标融合生理智能传感器系统及生理指标监测方法
CN116035536B (zh) * 2023-03-14 2023-06-30 安徽星辰智跃科技有限责任公司 一种睡眠行为活跃水平检测量化的方法、系统和装置
CN116386120B (zh) * 2023-05-24 2023-08-18 杭州企智互联科技有限公司 一种用于智慧校园宿舍的无感监控管理系统

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080009685A1 (en) * 2006-06-20 2008-01-10 Samsung Electronics Co., Ltd. Apparatus and method of sensing sleeping condition of user
CN101536904A (zh) * 2008-03-18 2009-09-23 中国计量学院 基于心电的睡眠呼吸暂停检测装置
US8292819B2 (en) * 2008-11-17 2012-10-23 National Yang-Ming University Sleep analysis system and method for analyzing sleep thereof
CN103908241A (zh) * 2012-12-31 2014-07-09 中国移动通信集团公司 睡眠及呼吸检测方法、装置
CN104224132A (zh) * 2014-09-26 2014-12-24 天彩电子（深圳）有限公司 睡眠监测装置及其监测方法
CN104224147A (zh) * 2014-09-15 2014-12-24 中国科学院苏州生物医学工程技术研究所 无线便携式人体健康与睡眠质量监护仪
CN104523262A (zh) * 2014-11-18 2015-04-22 南京丰生永康软件科技有限责任公司 基于心电信号的睡眠质量检测方法
CN104545844A (zh) * 2014-12-25 2015-04-29 中国科学院苏州生物医学工程技术研究所 一种基于4g移动通讯技术的多参数睡眠监测与智能诊断系统及其使用方法
US20150374279A1 (en) * 2014-06-25 2015-12-31 Kabushiki Kaisha Toshiba Sleep state estimation device, method and storage medium
CN105877745A (zh) * 2016-03-29 2016-08-24 东北大学 基于表面肌电信号的直流电机速度控制系统及方法
CN107007278A (zh) * 2017-04-25 2017-08-04 中国科学院苏州生物医学工程技术研究所 基于多参数特征融合的自动睡眠分期方法
CN107184183A (zh) * 2017-06-14 2017-09-22 杭州千成科技有限公司 一种穿戴式睡眠检测仪
CN109091125A (zh) * 2018-08-27 2018-12-28 江苏盖睿健康科技有限公司 一种提高睡眠监测准确性的可穿戴设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070073266A1 (en) * 2005-09-28 2007-03-29 Zin Technologies Compact wireless biometric monitoring and real time processing system
WO2016061381A1 (en) * 2014-10-15 2016-04-21 Atlasense Biomed Ltd. Remote physiological monitor

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080009685A1 (en) * 2006-06-20 2008-01-10 Samsung Electronics Co., Ltd. Apparatus and method of sensing sleeping condition of user
CN101536904A (zh) * 2008-03-18 2009-09-23 中国计量学院 基于心电的睡眠呼吸暂停检测装置
US8292819B2 (en) * 2008-11-17 2012-10-23 National Yang-Ming University Sleep analysis system and method for analyzing sleep thereof
CN103908241A (zh) * 2012-12-31 2014-07-09 中国移动通信集团公司 睡眠及呼吸检测方法、装置
US20150374279A1 (en) * 2014-06-25 2015-12-31 Kabushiki Kaisha Toshiba Sleep state estimation device, method and storage medium
CN104224147A (zh) * 2014-09-15 2014-12-24 中国科学院苏州生物医学工程技术研究所 无线便携式人体健康与睡眠质量监护仪
CN104224132A (zh) * 2014-09-26 2014-12-24 天彩电子（深圳）有限公司 睡眠监测装置及其监测方法
CN104523262A (zh) * 2014-11-18 2015-04-22 南京丰生永康软件科技有限责任公司 基于心电信号的睡眠质量检测方法
CN104545844A (zh) * 2014-12-25 2015-04-29 中国科学院苏州生物医学工程技术研究所 一种基于4g移动通讯技术的多参数睡眠监测与智能诊断系统及其使用方法
CN105877745A (zh) * 2016-03-29 2016-08-24 东北大学 基于表面肌电信号的直流电机速度控制系统及方法
CN107007278A (zh) * 2017-04-25 2017-08-04 中国科学院苏州生物医学工程技术研究所 基于多参数特征融合的自动睡眠分期方法
CN107184183A (zh) * 2017-06-14 2017-09-22 杭州千成科技有限公司 一种穿戴式睡眠检测仪
CN109091125A (zh) * 2018-08-27 2018-12-28 江苏盖睿健康科技有限公司 一种提高睡眠监测准确性的可穿戴设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116013470A (zh) * 2023-03-30 2023-04-25 安徽星辰智跃科技有限责任公司 一种睡眠行为活跃水平动态调节的方法、系统和装置
CN116509338A (zh) * 2023-06-29 2023-08-01 安徽星辰智跃科技有限责任公司 基于模态分析的睡眠周期性检测及调节方法、系统和装置
CN116509338B (zh) * 2023-06-29 2024-04-30 安徽星辰智跃科技有限责任公司 基于模态分析的睡眠周期性检测及调节方法、系统和装置

Also Published As

Publication number Publication date
CN109091125B (zh) 2020-06-30
CN109091125A (zh) 2018-12-28
US20210212630A1 (en) 2021-07-15

Similar Documents

Publication Publication Date Title
WO2020042711A1 (zh) 一种提高睡眠监测准确性的可穿戴设备
Sun et al. Sleepmonitor: Monitoring respiratory rate and body position during sleep using smartwatch
US11350835B2 (en) Wearable device for reflecting fatigue level of human body
WO2020119245A1 (zh) 一种基于可穿戴手环的情绪识别系统及方法
CN107106085B (zh) 用于睡眠监测的设备和方法
KR102090968B1 (ko) 개인의 수면 및 수면 단계들을 결정하기 위한 시스템 및 방법
CN109222961B (zh) 一种便携式睡眠监测系统及相关睡眠监测方法
CN102988051B (zh) 用于计算机操作者健康的监测装置
WO2013016007A2 (en) Apparatus and methods for estimating time-state physiological parameters
CN104083160A (zh) 一种基于机器视觉的睡眠状态监测方法及装置
US20220375590A1 (en) Sleep staging algorithm
US20230414149A1 (en) Method and System for Measuring and Displaying Biosignal Data to a Wearer of a Wearable Article
US11291406B2 (en) System for determining a set of at least one cardio-respiratory descriptor of an individual during sleep
CN107184208A (zh) 一种具有综合功能的智能睡眠监测眼罩
JP6702559B2 (ja) 電子機器、方法及びプログラム
CN108392176A (zh) 一种基于心冲击信号采集的睡眠结构检测方法
CN209966365U (zh) 一种便携式睡眠监测系统
CN106308771A (zh) 一种心电监测系统
CN113057600A (zh) 一种筛选睡眠障碍和睡眠呼吸暂停的装置及方法
Degtyarenko et al. Low-power continuous heart and respiration rates monitoring on wearable devices
Tsukahara et al. A 15-μA metabolic equivalents monitoring system using adaptive acceleration sampling and normally off computing
US20220375591A1 (en) Automatic sleep staging classification with circadian rhythm adjustment
US20230210385A1 (en) Techniques for determining relationships between skin temperature and surrounding temperature
Li et al. Research progress on wearable devices for daily human health management
Chuan et al. An effective way to improve actigraphic algorithm by using tri-axial accelerometer in sleep detection

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: 19855988

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: 19855988

Country of ref document: EP

Kind code of ref document: A1