WO2022222472A1 - 呼吸率测量方法及装置、电子设备、可读介质 - Google Patents

呼吸率测量方法及装置、电子设备、可读介质 Download PDF

Info

Publication number
WO2022222472A1
WO2022222472A1 PCT/CN2021/133436 CN2021133436W WO2022222472A1 WO 2022222472 A1 WO2022222472 A1 WO 2022222472A1 CN 2021133436 W CN2021133436 W CN 2021133436W WO 2022222472 A1 WO2022222472 A1 WO 2022222472A1
Authority
WO
WIPO (PCT)
Prior art keywords
ppg
fuzzy
interval
change value
interval data
Prior art date
Application number
PCT/CN2021/133436
Other languages
English (en)
French (fr)
Inventor
马传龙
陈峭岩
Original Assignee
北京超思电子技术有限责任公司
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 北京超思电子技术有限责任公司 filed Critical 北京超思电子技术有限责任公司
Priority to US18/275,410 priority Critical patent/US20240122496A1/en
Priority to EP21937694.4A priority patent/EP4327737A1/en
Publication of WO2022222472A1 publication Critical patent/WO2022222472A1/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
    • A61B5/08—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
    • A61B5/01—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
    • A61B5/68—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
    • A61B5/6825—Hand
    • A61B5/6826—Finger
    • 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
    • A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
    • 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
    • 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
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • 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
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7278—Artificial waveform generation or derivation, e.g. synthesising signals from measured signals
    • 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 invention relates to the technical field of respiratory rate monitoring, in particular to a respiratory rate measurement method and device, electronic equipment, and readable medium.
  • Respiration rate is an important physiological parameter that can assist in judging physical conditions.
  • Photoplethysmography (PPG) tracing is a common method for measuring respiration rate.
  • the PPG signal is easily interfered by the ambient light/dark light current signal, power frequency signal, electromagnetic signal, etc., resulting in inaccurate analysis results of the PPG signal, thereby affecting the accuracy of the respiration rate measurement.
  • the present disclosure provides a method and device for measuring respiratory rate, electronic equipment, and readable medium, so as to improve the accuracy of measuring respiratory rate.
  • a respiratory rate measurement method comprising:
  • the PPG interval change value refers to the difference between two adjacent PPG intervals in the PPG interval data
  • the PPG interval data is corrected, and the respiration rate is calculated based on the corrected PPG interval data.
  • the preprocessing of the PPG signal includes:
  • the PPG signal is filtered to remove baseline drift and myoelectric noise.
  • a Butterworth filter is used to filter the PPG signal.
  • the correction of the PPG interval data includes:
  • a fuzzy algorithm is used to correct the abnormal PPG interval change value in the PPG interval data to obtain the corrected PPG interval data.
  • the fuzzy algorithm is used to correct the abnormal PPG interval change value in the PPG interval data, and the corrected PPG interval data is obtained, including:
  • Fuzzy processing is performed on the input to obtain an input fuzzy set and an input membership function; the output is fuzzified to obtain an output fuzzy set and an output membership function;
  • De-blurring is performed on the blurred value of the output to obtain the corrected PPG interval data.
  • the input amount is the abnormal PPG interval change value ⁇ PNT md in the PPG interval data, adjacent to the abnormal PPG interval change value and located in the abnormal PPG interval change value
  • the output is the corrected abnormal PPG interval change value ⁇ PNT' md .
  • the fuzzy rule is that if the first fuzzy subset, the second fuzzy subset and the third fuzzy subset are true, there is a fourth fuzzy subset; wherein, the first fuzzy subset is the abnormal The fuzzy subset of the PPG interval change value ⁇ PNT md , the second fuzzy subset is the fuzzy subset of the preceding PPG interval change value ⁇ PNT fr , and the third fuzzy subset is the latter The fuzzy subset of the PPG interval change value ⁇ PNT hd , and the fourth fuzzy subset is the fuzzy subset of the corrected abnormal PPG interval change value ⁇ PNT' md .
  • the fuzzy set operation is performed based on the fuzzy rules to obtain a fuzzy relationship set, including:
  • the corresponding elements in the first fuzzy subset, the second fuzzy subset, the third fuzzy subset and the fourth fuzzy subset are respectively operated to determine a fuzzy relationship subset
  • the fuzzy value of the output quantity is de-fuzzy calculated by using the coefficient weighted average method.
  • the input fuzzy sets include negative large fuzzy sets, negative small fuzzy sets, zero fuzzy sets, positive small fuzzy sets and positive large fuzzy sets; the output fuzzy sets include significantly increased fuzzy sets, approximate zero fuzzy sets and significantly reduce the blur set.
  • calculating the respiratory rate based on the PPG interval data/corrected PPG interval data includes:
  • the respiration rate is obtained based on the number of adjacent peak points and the time difference.
  • a respiration rate measurement device comprising:
  • the first acquisition module is used to acquire the PPG signal
  • a preprocessing module for preprocessing the PPG signal
  • a second acquisition module configured to acquire PPG interval data based on the preprocessed PPG signal
  • the judgment module is used to judge whether there is an abnormal PPG interval change value in the PPG interval data; wherein, the PPG interval change value refers to the difference between two adjacent PPG intervals in the PPG interval data. difference between;
  • a calculation module configured to calculate a respiratory rate based on the PPG interval data under the condition that the PPG interval change value is not abnormal
  • a correction module configured to correct the PPG interval data when the PPG interval change value is abnormal
  • the calculation module is further configured to calculate the respiratory rate based on the corrected PPG interval data.
  • an electronic device comprising:
  • the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the respiration rate measurement method of any one of method.
  • a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of the respiratory rate measurement methods.
  • the respiration rate measurement method firstly processes the PPG signal, then obtains PPG interval data based on the processed PPG signal, and determines whether there is an abnormal PPG interval change value in the PPG interval data.
  • the respiratory rate is obtained based on the PPG interval data;
  • the PPG interval change value is abnormal, the PPG interval data is corrected, and the respiration rate is calculated based on the corrected PPG interval data, which can improve The accuracy of PPG interval change detection, thereby reducing the measurement error of respiration rate.
  • FIG. 1 is a flowchart of a method for measuring respiratory rate according to an embodiment of the present disclosure
  • PPG interval curve diagram obtained from filtered PPG interval data in an embodiment of the present disclosure, and a CO 2 concentration change curve diagram
  • FIG. 3 is a flow chart of calculating respiratory rate through PPG interval data in an embodiment of the present disclosure
  • Fig. 5 is the PPG interval curve graph obtained after correcting the abnormal PPG interval data
  • Fig. 6 is the flow chart of calculating respiratory rate by the PPG interval data after correction
  • FIG. 7 is a block diagram of a respiratory rate measurement device provided by an embodiment of the present disclosure.
  • FIG. 8 is a block diagram of an electronic device used to implement the breathing rate measurement method according to an embodiment of the present disclosure.
  • 700-respiratory rate measurement device 701-first acquisition module; 702-preprocessing module; 703-second acquisition module; 704-judgment module; 705-calculation module; 706-correction module; 800-equipment; 801-calculation unit 802-ROM; 803-RAM; 804-bus; 805-I/O interface; 806-input unit; 807-output unit; 808-storage unit; 809-communication unit.
  • Breathing affects changes in heart rate, which increases during inspiration, resulting in a decrease in the RR interval (the time between the R waves in two QRS complexes) and the PPG interval, and an increase in the PPG interval during expiration. big.
  • the embodiment of the present disclosure utilizes the variation law of the PPG interval with the respiratory cycle to detect the respiratory rate.
  • FIG. 1 is a flowchart of a method for measuring a respiratory rate according to an embodiment of the present disclosure.
  • respiration rate measurement methods include:
  • Step S101 acquiring a PPG signal.
  • the PPG signal may be obtained through an acquisition module, and the acquisition module may be a thermal imaging sensor or other module, which is not limited in the present disclosure.
  • Step S102 preprocessing the PPG signal.
  • the PPG signal is preprocessed to remove baseline drift and EMG noise to improve the accuracy of respiratory rate monitoring.
  • the PPG signal is filtered to remove baseline drift and electromyographic noise in the PPG signal.
  • a Butterworth filter is used to preprocess the PPG signal, and the principle of the Butterworth filter is as shown in formula (1).
  • a m and b m are the filter coefficients calculated by matlab, x is the preprocessed input signal, and y is the preprocessed output signal.
  • Step S103 obtaining PPG interval data based on the preprocessed PPG signal.
  • PPG data features are extracted from the preprocessed PPG signal to obtain PPG interval data.
  • the PPG interval curve and the PPG interval change value can be obtained.
  • the PPG interval curve is used to present the PPG interval data, and the user can intuitively understand the trend of the PPG interval data through the PPG interval curve.
  • the CO 2 concentration is obtained by using a test device, and then the CO 2 concentration change curve and the PPG interval curve are placed in the same coordinate system to facilitate the comparison of the PPG interval.
  • Figure 2 is a PPG interval curve graph obtained from filtered PPG interval data, and a graph of CO 2 concentration changes.
  • the abscissa represents the number of sampling points
  • the ordinate represents the CO 2 concentration and the PPG interval, respectively.
  • an increase in CO2 concentration represents an exhalation process
  • a decrease in CO2 concentration represents an inspiratory process.
  • the CO 2 concentration detection equipment detects that the change of CO 2 concentration is not completely synchronized with the respiration process, there is also a lag between the PPG interval and the RR interval. However, the PPG interval change can still reflect the PPG interval caused by respiration. changing laws.
  • Step S104 it is determined whether there is an abnormal PPG interval change value in the PPG interval data.
  • the PPG interval change value refers to the difference between two adjacent PPG intervals in the PPG interval data.
  • the PPG interval change value is obtained from the PPG interval data. If there is no abnormal PPG interval change value in the PPG interval data, the respiration rate is directly calculated using the PPG interval data. If there is an abnormal PPG interval change value in the PPG interval data, the PPG interval data needs to be corrected first, and then the respiration rate is calculated based on the corrected PPG interval data.
  • whether there is an abnormal PPG interval change value in the PPG interval data is visually determined through the PPG interval curve. As shown in Figure 2, the PPG interval change value in the box is abnormal, the PPG interval in the middle has a small increase, while the adjacent PPG interval before and after it decreases greatly.
  • the determination of whether there is an abnormal PPG interval change value in the PPG interval change value is not limited to using the PPG interval curve, but can also be obtained by analyzing the PPG interval data.
  • the present application does not limit the manner of judging whether there is an abnormal PPG interval change value in the PPG interval change value.
  • Step S105 in the case that there is no abnormality in the PPG interval change value, calculate the respiration rate based on the PPG interval data.
  • Step S106 in the case that the PPG interval change value is abnormal, correct the PPG interval data.
  • Step S107 calculating the respiration rate based on the corrected PPG interval data.
  • the respiration rate is directly calculated from the PPG interval data.
  • the steps of calculating the respiratory rate from the PPG interval data include:
  • Step S301 extracting the peak point and the trough point in the PPG interval data.
  • the crest point and the trough point respectively correspond to the crest and the trough in the PPG interval curve.
  • the peak point is the maximum value (peak) of all PPG interval changes in the PPG interval curve
  • the trough point is the minimum value (the lowest point) of all PPG interval changes in the PPG interval curve
  • the PPG interval to the left of the peak point The interval change value has been increasing, indicating the expiratory process; the PPG interval change value on the right side of the peak point has been decreasing, indicating the inhalation process.
  • Step S302 between adjacent peak points and trough points, the PPG interval variation value whose sum of the absolute value of the PPG interval variation value is less than a preset threshold is deleted.
  • the PPG interval change is too small, it is caused by measurement error or not breathing in the strict sense. Therefore, the sum of the absolute values of the PPG interval change values between adjacent peak points and trough points is calculated. If the sum of the absolute values If the sum is less than the preset threshold, the PPG interval change value is deleted.
  • the preset threshold is set according to the specific situation in the field, which is not limited in the present disclosure.
  • Step S303 extracting multiple adjacent peak points from the PPG interval data.
  • n adjacent peak points are extracted from the PPG interval data, where n is a positive integer greater than 2. It should be noted that the PPG interval data in step S303 refers to deleting the PPG interval after the absolute value of the PPG interval change value between adjacent peak points and trough points is less than the PPG interval change value of the preset threshold. period data.
  • Step S304 acquiring the time difference between the first peak point and the last peak point among the multiple adjacent peak points.
  • the sampling time can be obtained by the time difference between the peak points. After acquiring the first peak point and the last peak point among the multiple adjacent peak points, the time difference can be determined by sampling times corresponding to the first peak point and the last peak point.
  • Step S305 calculating the respiration rate based on the number of adjacent peak points and the time difference.
  • the breathing rate is the number of breaths in the set time. Such as the number of breaths in 60s.
  • respiration rate (n-1) ⁇ (60s/t).
  • the PPG interval data is corrected first, and then the respiration rate is calculated based on the corrected PPG interval data.
  • Correcting the PPG interval data includes: using a fuzzy algorithm to correct abnormal PPG interval change values in the PPG interval data to obtain corrected PPG interval data.
  • FIG. 4 is a flowchart of correcting PPG interval data in an embodiment of the present disclosure. As shown in Figure 4, the abnormal PPG interval change value in the PPG interval data is corrected by the fuzzy algorithm, and the corrected PPG interval data is obtained, including:
  • Step S401 select the input amount and the output amount based on the PPG interval data.
  • the input and output of the fuzzy algorithm are selected from the PPG interval data.
  • the abnormal PPG interval change value ⁇ PNT md in the PPG interval data, the preceding PPG interval change value adjacent to and preceding the abnormal PPG interval change value The value ⁇ PNT fr , and the subsequent PPG interval change value ⁇ PNT hd adjacent to and following the abnormal PPG interval change value are used as input quantities.
  • the corrected abnormal PPG interval change value ⁇ PNT' md was used as the output.
  • step S402 fuzzy processing is performed on the input quantity to obtain the input quantity fuzzy set and the input quantity membership function; and the output quantity is fuzzified to obtain the output quantity fuzzy set and the output quantity membership function.
  • the input volume fuzzy set can be divided into five input volume fuzzy sets as required, and the output volume fuzzy set can be divided into three input volume fuzzy sets as required.
  • the input-quantity fuzzy sets include negative large fuzzy sets, negative small fuzzy sets, zero fuzzy sets, positive small fuzzy sets, and positive large fuzzy sets.
  • the large negative fuzzy set means that the first difference between each input quantity in the fuzzy set and the preset first intermediate value is large, and the first difference is a negative value, that is, the input quantity is smaller than the first intermediate value.
  • Negative small fuzzy set means that the second difference between each input quantity in the fuzzy set and the preset first intermediate value is small, and the second difference is a negative value, that is, the input quantity is smaller than the first intermediate value, and the second difference is smaller than the first intermediate value.
  • the absolute value of the value is greater than the absolute value of the first difference.
  • the zero fuzzy set means that the difference between each input quantity in the fuzzy set and the preset first intermediate value is 0.
  • a positive small fuzzy set means that the third difference between each input quantity in the fuzzy set and the preset first intermediate value is small, and the third difference is a positive value, that is, the input quantity is greater than the first intermediate value.
  • a positive fuzzy set means that the fourth difference between each input quantity in the fuzzy set and the preset first intermediate value is large, and the fourth difference is a positive value, that is, the input quantity is greater than the first intermediate value, and the fourth The absolute value of the difference is greater than the absolute value of the third difference.
  • the output fuzzy sets include significantly increased fuzzy sets, approximately zero fuzzy sets and significantly reduced fuzzy sets.
  • significantly increasing the fuzzy set means that each output amount in the fuzzy set is greater than the preset second intermediate value, and, moreover, the absolute value of the fifth difference between the output amount and the preset second intermediate value is greater than the preset second intermediate value the threshold value.
  • the approximate zero fuzzy set means that the sixth difference between each output quantity in the fuzzy set and the preset second intermediate value is small, and the absolute value of the sixth difference is smaller than the set threshold.
  • Significantly reducing the fuzzy set means that each output amount in the fuzzy set is smaller than the preset second intermediate value, and the absolute value of the seventh difference between the output amount and the preset second intermediate value is greater than the preset threshold value.
  • the input quantity membership function is a triangular function
  • the output quantity membership function is a gradient function
  • Step S403 obtaining a fuzzy rule between the input quantity and the output quantity.
  • Fuzzy rules are determined based on input quantities and output quantities. For example, the fuzzy rule is that if the first fuzzy subset A, the second fuzzy subset B and the third fuzzy subset C are true, then there is a fourth fuzzy subset D.
  • the fuzzy rule can be expressed as: if A and B and C then D.
  • the first fuzzy subset A is the fuzzy subset of the abnormal PPG interval change value ⁇ PNT md
  • the second fuzzy subset B is the fuzzy subset of the previous PPG interval change value ⁇ PNT fr
  • the set C is a fuzzy subset of the later PPG interval change value ⁇ PNT hd
  • the fourth fuzzy subset D is the fuzzy subset of the corrected abnormal PPG interval change value ⁇ PNT' md .
  • the experience of the detection personnel is integrated into the fuzzy rules, that is, the fuzzy rules are obtained according to experience, and the experience of the detection personnel is integrated into the judgment of the PPG interval change, so as to improve the accuracy of the judgment of the PPG interval change.
  • Step S404 perform fuzzy set operation based on fuzzy rules to obtain a fuzzy relation set.
  • the fuzzy relation set includes at least one fuzzy relation subset. Perform corresponding operations according to fuzzy rules to obtain fuzzy relation subsets, and obtain fuzzy relation sets after union processing of multiple fuzzy relation subsets.
  • corresponding elements in the first fuzzy subset, the second fuzzy subset, the third fuzzy subset and the fourth fuzzy subset are respectively operated according to fuzzy rules to determine the fuzzy relation subset;
  • the set is processed by union to obtain the fuzzy relation set.
  • Step S405 obtaining the fuzzy value of the output based on the fuzzy relation set.
  • step S405 the fuzzy value of the output is calculated based on the fuzzy relationship set, that is, the fuzzy value u of the output is equal to the previous PPG interval change value ⁇ PNT fr , the abnormal PPG interval change value ⁇ PNT md and the subsequent PPG
  • the interval variation value ⁇ PNT hd is obtained from the fuzzy relation set R.
  • Step S406 perform anti-blur calculation on the fuzzy value of the output to obtain corrected PPG interval data.
  • step S406 de-blurring is performed on the fuzzy value of the output by using the coefficient weighted average method to obtain corrected PPG interval data.
  • the anti-blur calculation is performed by the anti-blur calculation formula provided by formula (3).
  • ⁇ PNT′ md ⁇ k i ⁇ PNT i / ⁇ k i (3)
  • ⁇ PNT′ md represents the corrected PPG interval change value
  • ki represents the ith weighting coefficient
  • ⁇ PNT i represents the ith PPG interval change value
  • the abnormal PPG interval data is processed by the fuzzy algorithm. If it is judged that the reduction of the PPG interval change value at the box position in Figure 4 is caused by interference, the abnormal PPG interval change value is deleted, and the corrected PPG interval is obtained. Interval data. In order to intuitively understand the corrected PPG interval data, the corrected PPG interval data is presented in the form of a PPG interval graph in FIG. 5 .
  • Figure 5 is a PPG interval curve obtained after correcting abnormal PPG interval data. By comparing the positions of the boxes in Figure 4 and Figure 5, it can be seen that after the abnormal PPG interval change value is deleted, the abnormal PPG interval change value in the PPG interval curve is eliminated.
  • the embodiment of the present disclosure utilizes the preceding PPG interval change value ⁇ PNT fr , which is adjacent to the abnormal PPG interval change value and is located before the abnormal PPG interval change value, and the abnormal PPG interval change value according to the fuzzy algorithm.
  • the subsequent PPG interval change value ⁇ PNT hd which is adjacent to the abnormal PPG interval change value ⁇ PNT hd corrects the abnormal PPG interval change value ⁇ PNT md .
  • the detection can be The experience of personnel is integrated into the judgment of PPG interval change, which reduces the influence of other factors on PPG interval change and improves the accuracy of PPG interval change judgment.
  • the respiration rate is calculated based on the corrected PPG interval data.
  • the difference between calculating the respiratory rate based on the uncorrected raw PPG interval data and calculating the respiratory rate based on the corrected PPG interval data is that the basis for calculating the respiratory rate is different, that is, the PPG interval data used are different, but the calculation steps and principles are the same .
  • the steps for calculating the respiration rate from the corrected PPG interval data are described below.
  • the steps of calculating the respiratory rate from the corrected PPG interval data include:
  • Step S601 extracting the peak point and the trough point in the corrected PPG interval data.
  • the peak and trough points are extracted from the corrected PPG interval data, wherein the peak and trough points correspond to the peak and trough points in the corrected PPG interval curve, respectively.
  • the peak point is the maximum value (peak) of all PPG interval changes in the corrected PPG interval curve
  • the trough point is the minimum value (the lowest point) of all PPG interval changes in the corrected PPG interval curve.
  • the PPG interval change value on the left side of the point has been increasing, indicating the expiratory process; the PPG interval change value on the right side of the peak point has been decreasing, indicating the inhalation process.
  • Step S602 between adjacent peak points and trough points, the PPG interval variation value whose sum of the absolute value of the PPG interval variation value is less than a preset threshold is deleted.
  • the PPG interval change is too small, it is caused by measurement error or not breathing in the strict sense. Therefore, the sum of the absolute values of the PPG interval change values between adjacent peak points and trough points is calculated. If the sum of the absolute values If the sum is less than the preset threshold, the PPG interval change value is deleted.
  • the preset threshold is set according to the specific situation in the field, which is not limited in the present disclosure.
  • Step S603 extracting multiple adjacent peak points from the corrected PPG interval data.
  • n adjacent peak points are extracted from the corrected PPG interval data, where n is a positive integer greater than 2.
  • Step S604 acquiring the time difference between the first peak point and the last peak point among the multiple adjacent peak points.
  • the sampling time can be obtained by the time difference between the peak points. After acquiring the first and last peak points among multiple adjacent peak points, the time difference can be determined by the sampling times corresponding to the first and last peak points.
  • Step S605 Calculate the respiration rate based on the number of adjacent peak points and the time difference.
  • the breathing rate is the number of breaths in the set time. Such as the number of breaths in 60s.
  • respiration rate (n-1) ⁇ (60s/t).
  • the PPG interval data and the PPG interval change value are obtained based on the processed PPG signal, and when the PPG interval change value is not abnormal, based on The PPG interval data is used to calculate the respiration rate; when the PPG interval change value is abnormal, the abnormal PPG interval change value is corrected, and the respiration rate is calculated based on the corrected PPG interval data, which can improve the detection of the PPG interval change. accuracy, thereby reducing the measurement error of respiration rate.
  • FIG. 7 is a block diagram of a respiratory rate measurement apparatus provided by an embodiment of the present disclosure. As shown in FIG. 7, the respiratory rate measurement device 700 includes:
  • the first acquisition module 701 is used to acquire the PPG signal.
  • the first acquisition module 701 may be an acquisition module, such as a thermal imaging sensor, and the thermal imaging sensor may be of a clip-on type to facilitate wearing.
  • the present disclosure does not limit the acquisition module.
  • the preprocessing module 702 is used for preprocessing the PPG signal.
  • the PPG signal is preprocessed to remove baseline drift and EMG noise to improve the accuracy of respiratory rate monitoring.
  • the second obtaining module 703 is configured to obtain PPG interval data based on the preprocessed PPG signal.
  • PPG data features are extracted from the preprocessed PPG signal to obtain PPG interval data.
  • the PPG interval curve and the PPG interval change value can be obtained.
  • the PPG interval curve is used to present the PPG interval data, and the user can intuitively understand the trend of the PPG interval data through the PPG interval curve.
  • the determination module 704 determines whether there is an abnormal PPG interval change value in the PPG interval data.
  • the PPG interval change value refers to the difference between two adjacent PPG intervals in the PPG interval data.
  • the PPG interval change value is obtained from the PPG interval data. If there is no abnormal PPG interval change value in the PPG interval data, the respiration rate is directly calculated using the PPG interval data. If there is an abnormal PPG interval change value in the PPG interval data, the PPG interval data needs to be corrected first, and then the respiration rate is calculated based on the corrected PPG interval data.
  • the calculation module 705 is configured to calculate the respiration rate based on the PPG interval data under the condition that there is no abnormality in the PPG interval change value.
  • the steps of calculating the respiration rate by the calculation module 705 through the PPG interval data mainly include: extracting the peak point and the trough point in the PPG interval data, and dividing the absolute value of the PPG interval change value between the adjacent peak points and trough points. and delete the PPG interval change value less than the preset threshold, extract multiple adjacent peak points from the PPG interval data, and obtain the time difference between the first peak point and the last peak point in the multiple adjacent peak points, The respiration rate is calculated based on the number of adjacent peak points and the time difference.
  • the correction module 706 is configured to correct the PPG interval data when the PPG interval variation value is abnormal.
  • the correction module 706 is configured to perform the following steps: select the input quantity and the output quantity based on the PPG interval data, perform fuzzification processing on the input quantity, obtain the input quantity fuzzy set and the input quantity membership function; perform fuzzification processing on the output quantity , obtain the fuzzy set of the output quantity and the membership function of the output quantity, obtain the fuzzy rules between the input quantity and the output quantity, perform the fuzzy set operation based on the fuzzy rules, and obtain the fuzzy relation set, and obtain the fuzzy value of the output quantity based on the fuzzy relation set.
  • the fuzzy value of the output is subjected to anti-blur calculation to obtain the corrected PPG interval data.
  • the calculation module 705 is further configured to be based on the corrected PPG interval data.
  • the calculation module 705 is further configured to perform the following steps: extracting the peak points and trough points in the corrected PPG interval data, and calculating the sum of the absolute values of the PPG interval variation values between the adjacent peak points and trough points to be less than a predetermined value.
  • the PPG interval change value of the threshold is deleted, and multiple adjacent peak points are extracted from the corrected PPG interval data, and the time difference between the first peak point and the last peak point among the multiple adjacent peak points is obtained,
  • the respiration rate is calculated based on the number of adjacent peak points and the time difference.
  • the respiratory rate measurement device further includes a display module for displaying the respiratory rate.
  • a PPG signal is acquired by a first acquisition module, the PPG signal is processed by a preprocessing module, and the PPG interval data and the PPG interval change are acquired by the second acquisition module based on the processed PPG signal.
  • the calculation module calculates the respiratory rate based on the PPG interval data; if the PPG interval change value is abnormal, the correction module corrects the PPG interval data and calculates The module calculates the respiration rate based on the corrected PPG interval data, which can improve the accuracy of the PPG interval change detection, thereby reducing the measurement error of the respiration rate.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • FIG. 8 shows a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure.
  • Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 800 includes a computing unit 801 that can be executed according to a computer program stored in a read only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803 Various appropriate actions and handling. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored.
  • the computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804.
  • An input/output (I/O) interface 805 is also connected to bus 804 .
  • Various components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc. ; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 809 allows the device 800 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.
  • Computing unit 801 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of computing units 801 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the computing unit 801 performs the various methods and processes described above, such as the breathing rate measurement method.
  • the respiratory rate measurement method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 808 .
  • part or all of the computer program may be loaded and/or installed on device 800 via ROM 802 and/or communication unit 809.
  • ROM 802 and/or communication unit 809 When a computer program is loaded into RAM 803 and executed by computing unit 801, one or more steps of the respiratory rate measurement method described above may be performed.
  • the computing unit 801 may be configured to perform the respiration rate measurement method by any other suitable means (eg, by means of firmware).
  • Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC systems on chips system
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that
  • the processor which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.
  • Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer.
  • a display device eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.
  • the systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
  • a computer system can include clients and servers.
  • Clients and servers are generally remote from each other and usually interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the present disclosure also provides a computer program product, including a computer program, which, when executed by a processor, implements any one of the above respiratory rate measurement methods.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Surgery (AREA)
  • Public Health (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Physiology (AREA)
  • Pulmonology (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Power Engineering (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种呼吸率测量呼吸率测量方法及装置、电子设备、可读介质，属于呼吸率监测技术领域。呼吸率测量方法包括：获取PPG信号；对PPG信号进行预处理；基于预处理后的PPG信号获得PPG间期数据和PPG间期变化值；其中，PPG间期变化值是指PPG间期数据中相邻的两个PPG间期之间的差值；在PPG间期变化值不存在异常的情况下，基于PPG间期数据计算呼吸率；以及，在PPG间期变化值存在异常的情况下，对PPG间期数据进行矫正，基于矫正后的PPG间期数据计算呼吸率，可以提高PPG间期变化检测的准确性，从而减小呼吸率的测量误差。

Description

呼吸率测量方法及装置、电子设备、可读介质 技术领域
本发明涉及呼吸率监测技术领域，具体涉及一种呼吸率测量方法及装置、电子设备、可读介质。
背景技术
呼吸率是一种重要的生理参数，可辅助判断身体状况。光电容积脉搏波(Photoplethysmography，PPG)描记法是常见的测量呼吸率的方法，其原理是利用血液对光线的吸收和反射引起的皮肤表层光亮度变化，获得PPG信号，再分析PPG信号获得呼吸率。然而，PPG信号容易受环境光/暗光的电流信号、工频信号、电磁信号等干扰，导致PPG信号的分析结果不准确，从而影响呼吸率测量的准确性。
发明内容
本公开提供一种呼吸率测量方法及装置、电子设备、可读介质，用以提高测量呼吸率的准确性。
根据本公开的第一方面，提供了一种呼吸率测量方法，所述方法包括：
获取PPG信号；
对所述PPG信号进行预处理；
基于预处理后的所述PPG信号获得PPG间期数据；
判断所述PPG间期数据中是否存在异常的PPG间期变化值；其中，所述PPG间期变化值是指所述PPG间期数据中相邻的两个PPG间期之间的差值；
在所述PPG间期变化值不存在异常的情况下，基于所述PPG间期数据 计算呼吸率；以及，
在所述PPG间期变化值存在异常的情况下，对所述PPG间期数据进行矫正，基于矫正后的PPG间期数据计算呼吸率。
其中，所述对所述PPG信号进行预处理，包括：
对所述PPG信号进行滤波处理，以去除基线漂移和肌电噪声。
其中，采用Butterworth滤波器对所述PPG信号进行滤波处理。
其中，所述对所述PPG间期数据进行矫正，包括：
采用模糊算法对所述PPG间期数据中所述异常的PPG间期变化值进行矫正，获得矫正后的所述PPG间期数据。
其中，所述采用模糊算法对所述PPG间期数据中所述异常的PPG间期变化值进行矫正，获得矫正后的所述PPG间期数据，包括：
基于所述PPG间期数据选择输入量和输出量；
对所述输入量进行模糊化处理，获得输入量模糊集和输入量隶属度函数；对所述输出量进行模糊化处理，获得输出量模糊集和输出量隶属度函数；
获取所述输入量和所述输出量之间的模糊规则；
基于所述模糊规则进行模糊集合运算，得到模糊关系集合；
基于所述模糊关系集合获得所述输出量的模糊值；
对所述输出量的模糊值进行反模糊计算，获得矫正后的所述PPG间期数据。
其中，所述输入量为所述PPG间期数据中所述异常的PPG间期变化值△PNT md、与所述异常的PPG间期变化值相邻且位于所述异常的PPG间期变化值之前的在前PPG间期变化值△PNT fr、以及与所述异常的PPG间期变化值相邻且位于所述异常的PPG间期变化值之后的在后PPG间期变化值△PNT hd；
所述输出量为矫正后的异常PPG间期变化值△PNT' md。
其中，所述模糊规则为如果第一模糊子集、第二模糊子集和第三模糊子集为真，则有第四模糊子集；其中，所述第一模糊子集为所述异常的PPG间期变化值△PNT md的模糊子集，所述第二模糊子集为所述在前PPG间期变化值△PNT fr的模糊子集，所述第三模糊子集为所述在后PPG间期变化值△PNT hd的模糊子集，所述第四模糊子集为所述矫正后的异常PPG间期变化值△PNT' md的模糊子集。
其中，所述基于所述模糊规则进行模糊集合运算，得到模糊关系集合，包括：
根据所述模糊规则对所述第一模糊子集、所述第二模糊子集、所述第三模糊子集和所述第四模糊子集中的对应元素分别进行运算，确定模糊关系子集；
对所述模糊关系子集作并集处理，获得所述模糊关系集合。
其中，利用系数加权平均法对所述输出量的模糊值进行反模糊计算。
其中，所述输入量模糊集包括负大模糊集、负小模糊集、零模糊集、正小模糊集和正大模糊集；所述输出量模糊集包括明显增大模糊集、近似为零模糊集和明显减小模糊集。
其中，所述基于所述PPG间期数据/矫正后的PPG间期数据计算呼吸率，包括：
提取所述PPG间期数据/矫正后的PPG间期数据中的波峰点和波谷点；
将相邻的所述波峰点和所述波谷点之间，PPG间期变化值的绝对值之和小于预设阈值的PPG间期变化值删除；
从所述PPG间期数据/矫正后的PPG间期数据中提取多个相邻的所述波峰点；
获取所述多个相邻的波峰点中第一个波峰点与最后一个波峰点的时间差；
基于所述相邻的波峰点的数量和所述时间差获得所述呼吸率。
根据本公开的第二方面，提供了一种呼吸率测量装置，所述装置包括：
第一获取模块，用于获取PPG信号；
预处理模块，用于对所述PPG信号进行预处理；
第二获取模块，用于基于预处理后的所述PPG信号获得PPG间期数据；
判断模块，用于判断所述PPG间期数据中是否存在异常的PPG间期变化值；其中，所述PPG间期变化值是指所述PPG间期数据中相邻的两个PPG间期之间的差值；
计算模块，用于在所述PPG间期变化值不存在异常的情况下，基于所述PPG间期数据计算呼吸率；
矫正模块，用于在所述PPG间期变化值存在异常的情况下，对所述PPG间期数据进行矫正；
所述计算模块，还用于基于矫正后的PPG间期数据计算呼吸率。
根据本公开的第三方面，提供了一种电子设备，其包括：
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行呼吸率测量方法中任一项所述的方法。
根据本公开的第四方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，所述计算机指令用于使所述计算机执行呼吸率测量方法中任一项所述的方法。
本公开提供的呼吸率测量方法，先对PPG信号进行处理，再基于处理后的PPG信号获得PPG间期数据，判断PPG间期数据中是否存在PPG间期变化值异常，在PPG间期变化值不存在异常的情况下，基于PPG间期数据获 得呼吸率；在PPG间期变化值存在异常的情况下，对PPG间期数据进行矫正，基于矫正后的PPG间期数据计算呼吸率，可以提高PPG间期变化检测的准确性，从而减小呼吸率的测量误差。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
附图用来提供对本公开的进一步理解，并且构成说明书的一部分，与本公开的实施例一起用于解释本公开，并不构成对本公开的限制。通过参考附图对详细示例实施例进行描述，以上和其他特征和优点对本领域技术人员将变得更加显而易见。
图1为本公开实施例提供的一种呼吸率测量方法的流程图；
图2为本公开实施例中经滤波处理后的PPG间期数据获得的PPG间期曲线图，以及CO 2浓度变化曲线图；
图3为本公开实施例中通过PPG间期数据计算呼吸率的流程图；
图4为本公开实施例中矫正PPG间期数据的流程图；
图5为对存在异常的PPG间期数据矫正后获得的PPG间期曲线图；
图6为通过矫正后的PPG间期数据计算呼吸率的流程图；
图7为本公开实施例提供的一种呼吸率测量装置的框图；
图8为用来实现本公开实施例的呼吸率测量方法的电子设备的框图。
在附图中：
700-呼吸率测量装置；701-第一获取模块；702-预处理模块；703-第二获取模块；704-判断模块；705-计算模块；706-矫正模块；800-设备；801-计算单元；802-ROM；803-RAM；804-总线；805-I/O接口；806-输入单元；807-输出单元；808-存储单元；809-通信单元。
具体实施方式
为使本领域的技术人员更好地理解本公开的技术方案，以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
在不冲突的情况下，本公开各实施例及实施例中的各特征可相互组合。
如本文所使用的，术语“和/或”包括一个或多个相关列举条目的任何和所有组合。
本文所使用的术语仅用于描述特定实施例，且不意欲限制本公开。如本文所使用的，单数形式“一个”和“该”也意欲包括复数形式，除非上下文另外清楚指出。还将理解的是，当本说明书中使用术语“包括”和/或“由……制成”时，指定存在特征、整体、步骤、操作、元件和/或组件，但不排除存在或添加一个或多个其它特征、整体、步骤、操作、元件、组件和/或其群组。“连接”或者“相连”等类似的词语并非限定于物理的或者机械的连接，而是可以包括电性的连接，不管是直接的还是间接的。
除非另外限定，否则本文所用的所有术语(包括技术和科学术语)的含义与本领域普通技术人员通常理解的含义相同。还将理解，诸如那些在常用字典中限定的那些术语应当被解释为具有与其在相关技术以及本公开的背景下的含义一致的含义，且将不解释为具有理想化或过度形式上的含义，除非本文明确如此限定。
呼吸影响心率的变化，在吸气过程中，心率会加快，导致RR间期(两个QRS波中R波之间的时间)和PPG间期减小，在呼气过程中，PPG间期 增大。本公开实施例即利用PPG间期随呼吸周期变化的规律来检测呼吸率。
图1为本公开实施例提供的一种呼吸率测量方法的流程图。如图1所示，呼吸率测量方法包括：
步骤S101，获取PPG信号。
其中，PPG信号可以通过采集模块获得，采集模块可以是热成像传感器等模块，本公开对采集模块不作限定。
步骤S102，对PPG信号进行预处理。
其中，对PPG信号进行预处理是为了去除基线漂移和肌电噪声，以提高呼吸率监测的准确性。
在一些实施例中，对PPG信号进行滤波处理，通过滤波处理去除PPG信号中基线漂移和肌电噪声。
例如，采用Butterworth滤波器对PPG信号进行预处理，Butterworth滤波器的原理如公式(1)。
Figure PCTCN2021133436-appb-000001
在公式(1)中，a m和b m为采用matlab计算的滤波器系数，x为预处理的输入信号，y为预处理的输出信号。
步骤S103，基于预处理后的PPG信号获得PPG间期数据。
在对PPG信号进行预处理后，从预处理后的PPG信号提取PPG数据特征，获取PPG间期数据。基于PPG间期数据可以获得PPG间期曲线和PPG间期变化值。其中，PPG间期曲线用于呈现PPG间期数据，用户可以通过PPG间期曲线直观地了解PPG间期数据的走势。
在一些实施例中，在获取PPG信号的同时，利用测试设备获得CO 2浓度，然后将CO 2浓度变化曲线与PPG间期曲线放在同一坐标系中，便于对PPG间期进行比较。
图2为经滤波处理后的PPG间期数据获得的PPG间期曲线图，以及CO 2 浓度变化曲线图。其中，横坐标表示采样点的个数，纵坐标分别表示CO 2浓度大小和PPG间期的大小。
在图2中，CO 2浓度增大表示呼气过程，CO 2浓度减小表示吸气过程。由于CO 2浓度检测设备检测到CO 2浓度的变化与呼吸过程并不完全同步，PPG间期与RR间期也存在滞后的情况，但是，PPG间期变化仍可反映出呼吸引起的PPG间期变化规律。
步骤S104，判断PPG间期数据中是否存在异常的PPG间期变化值。
其中，PPG间期变化值是指PPG间期数据中相邻的两个PPG间期之间的差值。
由于PPG间期受生理、外部干扰或者信号处理等因素的影响而发生改变，导致影响最终呼吸率的计算。为了提高检测的准确性和稳定性，从PPG间期数据中获取PPG间期变化值，若PPG间期数据中没有异常的PPG间期变化值，则直接利用该PPG间期数据计算呼吸率。若PPG间期数据中有异常的PPG间期变化值，则需要先对PPG间期数据进行矫正处理，再基于矫正处理后的PPG间期数据计算呼吸率。
在一些实施例中，通过PPG间期曲线直观地判断PPG间期数据是否存在异常的PPG间期变化值。如图2所示，方框中的PPG间期变化值出现异常，中间的PPG间期有较小幅度的增加，而其前后相邻的PPG间期减小的幅度较大。
需要说明的是，判断PPG间期变化值中是否存在异常的PPG间期变化值，并不局限于借助PPG间期曲线，也可以通过分析PPG间期数据获得。本申请对判断PPG间期变化值中是否存在异常的PPG间期变化值的方式不作限定。
步骤S105，在PPG间期变化值不存在异常的情况下，基于PPG间期数据计算呼吸率。
步骤S106，在PPG间期变化值存在异常的情况下，对PPG间期数据进行矫正。
步骤S107，基于矫正后的PPG间期数据计算呼吸率。
在判断PPG间期变化值没有异常的情况下，直接通过PPG间期数据计算呼吸率。
如图3所示，通过PPG间期数据计算呼吸率的步骤包括：
步骤S301，提取PPG间期数据中的波峰点和波谷点。
通过分析PPG间期数据，并从PPG间期数据中提取波峰点和波谷点，其中，波峰点和波谷点分别对应PPG间期曲线中的波峰和波谷。波峰点是PPG间期曲线中所有PPG间期变化值的最大值(顶点)，波谷点是PPG间期曲线中所有PPG间期变化值的最小值(最低点)，波峰点左侧的PPG间期变化值一直在增大，表示呼气过程；波峰点右侧的PPG间期变化值一直在减小，表示吸气过程。
需要说明的是，在PPG间期变化值为零时，则只提取其中的一个PPG间期变化值。
步骤S302，将相邻的波峰点和波谷点之间，PPG间期变化值的绝对值之和小于预设阈值的PPG间期变化值删除。
因为PPG间期变化过小是由测量误差或者不是严格意义上的呼吸造成的，因此，计算相邻的波峰点和波谷点之间PPG间期变化值的绝对值之和，若该绝对值之和小于预设阈值，则将该PPG间期变化值删除。其中，预设阈值是根据本领域的具体情况设定的，本公开对此不作限定。
步骤S303，从PPG间期数据中提取多个相邻的波峰点。
在一些实施例中，从PPG间期数据中提取n个相邻的波峰点，其中，n为大于2的正整数。需要说明的是，步骤S303中的PPG间期数据是指删除相邻的波峰点和波谷点之间PPG间期变化值的绝对值之和小于预设阈值的 PPG间期变化值之后的PPG间期数据。
步骤S304，获取多个相邻的波峰点中第一个波峰点与最后一个波峰点的时间差。
由于波峰点是按照测量时间序列排列，通过波峰点之间的时间差可以获得采样时间。当获取多个相邻的波峰点中的第一个波峰点与最后一个波峰点后，可以通过第一个波峰点和最后一个波峰点对应的采样时间确定时间差。
步骤S305，基于相邻的波峰点的数量和时间差计算呼吸率。
其中，呼吸率为设定时间内呼吸的次数。如60s内呼吸的次数。
例如，呼吸率＝(n-1)×(60s/t)。
在一些实施例中，在判断PPG间期变化值存在异常的情况下，先对PPG间期数据进行矫正，再基于矫正后的PPG间期数据计算呼吸率。
对所述PPG间期数据进行矫正，包括：采用模糊算法对PPG间期数据中异常的PPG间期变化值进行矫正，获得矫正后的PPG间期数据。
图4为本公开实施例中矫正PPG间期数据的流程图。如图4所示，采用模糊算法对PPG间期数据中异常的PPG间期变化值进行矫正，获得矫正后的PPG间期数据，包括：
步骤S401，基于PPG间期数据选择输入量和输出量。
从PPG间期数据中选择模糊算法的输入量和输出量。在一些实施例中，将PPG间期数据中异常的PPG间期变化值△PNT md、与异常的PPG间期变化值相邻且位于异常的PPG间期变化值之前的在前PPG间期变化值△PNT fr、以及与异常的PPG间期变化值相邻且位于异常的PPG间期变化值之后的在后PPG间期变化值△PNT hd作为输入量。将矫正后的异常PPG间期变化值△PNT' md作为输出量。
步骤S402，对输入量进行模糊化处理，获得输入量模糊集和输入量隶属度函数；以及对输出量进行模糊化处理，获得输出量模糊集和输出量隶属度 函数。
在一些实施例中，输入量模糊集可以根据需要被划分为五个输入量模糊集，输出量模糊集可以根据需要被划分为三个输入量模糊集。
例如，输入量模糊集包括负大模糊集、负小模糊集、零模糊集、正小模糊集和正大模糊集。其中，负大模糊集是指模糊集中各个输入量与预设的第一中间值之间的第一差值较大，而且第一差值为负值，即输入量小于第一中间值。负小模糊集是指模糊集中各个输入量与预设的第一中间值之间的第二差值较小，而且第二差值为负值，即输入量小于第一中间值，第二差值的绝对值大于第一差值的绝对值。零模糊集是指模糊集中各个输入量与预设的第一中间值之间的差值为0。正小模糊集是指模糊集中各个输入量与预设的第一中间值之间的第三差值较小，而且第三差值为正值，即输入量大于第一中间值。正大模糊集是指模糊集中各个输入量与预设的第一中间值之间的第四差值较大，而且第四差值为正值，即输入量大于第一中间值，而且，第四差值的绝对值大于第三差值的绝对值。
输出量模糊集包括明显增大模糊集、近似为零模糊集和明显减小模糊集。其中，明显增大模糊集是指模糊集中各个输出量大于预设的第二中间值，而且，而且，输出量与预设的第二中间值之间的第五差值的绝对值大于设定的阈值。近似为零模糊集是指模糊集中各个输出量与预设的第二中间值之间的第六差值较小，而且第六差值的绝对值小于设定的阈值。明显减小模糊集是指模糊集中各个输出量小于预设的第二中间值，而且，输出量与预设的第二中间值之间的第七差值的绝对值大于设定的阈值。
在一些实施例中，输入量隶属度函数为三角形函数，输出量隶属度函数为梯度函数。
步骤S403，获取输入量和输出量之间的模糊规则。
模糊规则基于输入量和输出量来确定。例如，模糊规则为如果第一模糊 子集A、第二模糊子集B和第三模糊子集C为真，则有第四模糊子集D。
该模糊规则可以表述为：if A and B and C then D。
其中，第一模糊子集A为异常的PPG间期变化值△PNT md的模糊子集，第二模糊子集B为在前PPG间期变化值△PNT fr的模糊子集，第三模糊子集C为在后PPG间期变化值△PNT hd的模糊子集，第四模糊子集D为矫正后的异常PPG间期变化值△PNT' md的模糊子集。
在一些实施例中，将检测人员的经验融入模糊规则，即模糊规则根据经验得出，并将检测人员的经验融入到PPG间期变化大小的判断，提高PPG间期变化判断的准确性。
步骤S404，基于模糊规则进行模糊集合运算，得到模糊关系集合。
其中，模糊关系集合包括至少一个模糊关系子集。根据模糊规则进行相应的运算得到模糊关系子集，将多个模糊关系子集并集处理后获得模糊关系集合。
在一些实施例中，根据模糊规则对第一模糊子集、第二模糊子集、第三模糊子集和第四模糊子集中的对应元素分别进行运算，确定模糊关系子集；对模糊关系子集作并集处理，获得模糊关系集合。
例如，根据模糊规则对第一模糊子集A、第二模糊子集B、第三模糊子集C和第四模糊子集D中的元素进行模糊集合运算，确定模糊关系子集R i＝A×B×C×D，然后对模糊关系子集求并集，得到模糊关系集合R，其中，R＝∪R i。
步骤S405，基于模糊关系集合获得输出量的模糊值。
在步骤S405中，基于模糊关系集合计算得到输出量的模糊值，即输出量的模糊值u等于在前PPG间期变化值△PNT fr、异常的PPG间期变化值△PNT md和在后PPG间期变化值△PNT hd与模糊关系集合R得到。
具体地，u＝[△PNT fr，△PNT md，△PNT hd]·R
步骤S406，对输出量的模糊值进行反模糊计算，获得矫正后的PPG间期数据。
在步骤S406中，利用系数加权平均法对输出量的模糊值进行反模糊计算，获得矫正后的PPG间期数据。
例如，通过公式(3)提供的反模糊计算公式进行反模糊计算。
ΔPNT′ md＝∑k i·ΔPNT i/∑k i  (3)
在公式(3)中，ΔPNT′ md表示矫正后的PPG间期变化值，k i表示第i个加权系数，ΔPNT i表示第i个PPG间期变化值。
通过模糊算法对异常的PPG间期数据进行处理，若判断图4中方框位置的PPG间期变化值的减少是因干扰造成，则将该异常的PPG间期变化值删除，获得矫正后的PPG间期数据。为了直观地了解矫正后的PPG间期数据，在图5中以PPG间期曲线图的形式呈现矫正后的PPG间期数据。
图5为对存在异常的PPG间期数据矫正后获得的PPG间期曲线图。通过比较图4和图5中方框位置可知，将异常的PPG间期变化值删除后，PPG间期曲线中存在异常的PPG间期变化值被消除。
本公开实施例根据模糊算法，利用与异常的PPG间期变化值相邻且位于异常的PPG间期变化值之前的在前PPG间期变化值△PNT fr、以及与异常的PPG间期变化值相邻且位于异常的PPG间期变化值之后的在后PPG间期变化值△PNT hd矫正异常的PPG间期变化值△PNT md，利用模糊规则判断PPG间期变化值的大小，可以将检测人员的经验融入到PPG间期变化大小的判断，减小了其它因素对PPG间期变化的影响，提高了PPG间期变化判断的准确性。
在矫正存在异常的PPG间期数据之后，基于矫正后的PPG间期数据计算呼吸率。基于未矫正的原始PPG间期数据计算呼吸率与基于矫正后的PPG间期数据计算呼吸率不同之处在于计算呼吸率的基础不同，即采用的PPG间 期数据不同，但计算步骤和原理相同。为了更好地理解本公开，下面介绍以矫正后的PPG间期数据计算呼吸率的步骤。
如图6所示，通过矫正后的PPG间期数据计算呼吸率的步骤包括：
步骤S601，提取矫正后的PPG间期数据中的波峰点和波谷点。
通过分析矫正后的PPG间期数据，从矫正后的PPG间期数据中提取波峰点和波谷点，其中，波峰点和波谷点分别对应矫正后的PPG间期曲线中的波峰点和波谷点。波峰点是矫正后的PPG间期曲线中所有PPG间期变化值的最大值(顶点)，波谷点是矫正后的PPG间期曲线中所有PPG间期变化值的最小值(最低点)，波峰点左侧的PPG间期变化值一直在增大，表示呼气过程；波峰点右侧的PPG间期变化值一直在减小，表示吸气过程。
需要说明的是，在PPG间期变化值为零时，则只提取其中的一个PPG间期变化值。
步骤S602，将相邻的波峰点和波谷点之间，PPG间期变化值的绝对值之和小于预设阈值的PPG间期变化值删除。
因为PPG间期变化过小是由测量误差或者不是严格意义上的呼吸造成的，因此，计算相邻的波峰点和波谷点之间PPG间期变化值的绝对值之和，若该绝对值之和小于预设阈值，则将该PPG间期变化值删除。其中，预设阈值是根据本领域的具体情况设定的，本公开对此不作限定。
步骤S603，从矫正后的PPG间期数据中提取多个相邻的波峰点。
在一些实施例中，从矫正后的PPG间期数据中提取n个相邻的波峰点，其中，n为大于2的正整数。
步骤S604，获取多个相邻的波峰点中第一个波峰点与最后一个波峰点的时间差。
由于波峰点是按照测量时间序列排列，通过波峰点之间的时间差可以获得采样时间。当获取多个相邻的波峰点中的第一个波峰点与最后一个波峰点 后，可以通过第一个波峰点和最后一个波峰点对应的采样时间确定时间差。
步骤S605，基于相邻的波峰点的数量和时间差计算呼吸率。
其中，呼吸率为设定时间内呼吸的次数。如60s内呼吸的次数。例如，呼吸率＝(n-1)×(60s/t)。
本公开实施例提供的呼吸率测量方法，对PPG信号处理后，基于处理后的PPG信号获得PPG间期数据和PPG间期变化值，并在PPG间期变化值不存在异常的情况下，基于PPG间期数据计算呼吸率；在PPG间期变化值存在异常的情况下，对异常的PPG间期变化值进行矫正，基于矫正后的PPG间期数据计算呼吸率，可以提高PPG间期变化检测的准确性，从而减小呼吸率的测量误差。
图7为本公开实施例提供的一种呼吸率测量装置的框图。如图7所示，呼吸率测量装置700包括：
第一获取模块701，用于获取PPG信号。
第一获取模块701可以是采集模块，如热成像传感器，而且热成像传感器可以是指夹式，以方便佩戴。本公开对采集模块不作限定。
预处理模块702，用于对PPG信号进行预处理。
其中，对PPG信号进行预处理是为了去除基线漂移和肌电噪声，以提高呼吸率监测的准确性。
第二获取模块703，用于基于预处理后的PPG信号获得PPG间期数据。
在对PPG信号进行预处理后，从预处理后的PPG信号提取PPG数据特征，获取PPG间期数据。基于PPG间期数据可以获得PPG间期曲线和PPG间期变化值。其中，PPG间期曲线用于呈现PPG间期数据，用户可以通过PPG间期曲线直观地了解PPG间期数据的走势。
判断模块704，判断PPG间期数据中是否存在异常的PPG间期变化值。
其中，PPG间期变化值是指PPG间期数据中相邻的两个PPG间期之间 的差值。
由于PPG间期受生理、外部干扰或者信号处理等因素的影响而发生改变，导致影响最终呼吸率的计算。为了提高检测的准确性和稳定性，从PPG间期数据中获取PPG间期变化值，若PPG间期数据中没有异常的PPG间期变化值，则直接利用该PPG间期数据计算呼吸率。若PPG间期数据中有异常的PPG间期变化值，则需要先对PPG间期数据进行矫正处理，再基于矫正处理后的PPG间期数据计算呼吸率。
计算模块705，用于在PPG间期变化值不存在异常的情况下，基于PPG间期数据计算呼吸率。
计算模块705通过PPG间期数据计算呼吸率的步骤主要包括：提取PPG间期数据中的波峰点和波谷点，将相邻的波峰点和波谷点之间，PPG间期变化值的绝对值之和小于预设阈值的PPG间期变化值删除，从PPG间期数据中提取多个相邻的波峰点，获取多个相邻的波峰点中第一个波峰点与最后一个波峰点的时间差，基于相邻的波峰点的数量和时间差计算呼吸率。
矫正模块706，用于在PPG间期变化值存在异常的情况下，对PPG间期数据进行矫正。
矫正模块706被配置为可执行以下步骤：基于PPG间期数据选择输入量和输出量，对输入量进行模糊化处理，获得输入量模糊集和输入量隶属度函数；对输出量进行模糊化处理，获得输出量模糊集和输出量隶属度函数，获取输入量和输出量之间的模糊规则，基于模糊规则进行模糊集合运算，得到模糊关系集合，基于模糊关系集合获得输出量的模糊值，对输出量的模糊值进行反模糊计算，获得矫正后的PPG间期数据。
计算模块705，还用于基于矫正后的PPG间期数据。
计算模块705还配置为执行以下步骤：提取矫正后的PPG间期数据中的波峰点和波谷点，将相邻的波峰点和波谷点之间，PPG间期变化值的绝对值 之和小于预设阈值的PPG间期变化值删除，从矫正后的PPG间期数据中提取多个相邻的波峰点，获取多个相邻的波峰点中第一个波峰点与最后一个波峰点的时间差，基于相邻的波峰点的数量和时间差计算呼吸率。
在一些实施例中，呼吸率测量装置还包括显示模块，用于显示呼吸率。
本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文呼吸率测量方法，其具体实现和技术效果可参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例提供的呼吸率测量装置，通过第一获取模块获取PPG信号，利用预处理模块对PPG信号处理，由第二获取模块基于处理后的PPG信号获得PPG间期数据和PPG间期变化值，计算模块在PPG间期变化值不存在异常的情况下，基于PPG间期数据计算呼吸率；在PPG间期变化值存在异常的情况下，由矫正模块对PPG间期数据进行矫正，计算模块基于矫正后的PPG间期数据计算呼吸率，可以提高PPG间期变化检测的准确性，从而减小呼吸率的测量误差。
本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
图8示出了可以用来实施本公开的实施例的示例电子设备800的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图8所示，设备800包括计算单元801，其可以根据存储在只读存储器(ROM)802中的计算机程序或者从存储单元808加载到随机访问存储器 (RAM)803中的计算机程序，来执行各种适当的动作和处理。在RAM 803中，还可存储设备800操作所需的各种程序和数据。计算单元801、ROM 802以及RAM 803通过总线804彼此相连。输入/输出(I/O)接口805也连接至总线804。
设备800中的多个部件连接至I/O接口805，包括：输入单元806，例如键盘、鼠标等；输出单元807，例如各种类型的显示器、扬声器等；存储单元808，例如磁盘、光盘等；以及通信单元809，例如网卡、调制解调器、无线通信收发机等。通信单元809允许设备800通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
计算单元801可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元801的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元801执行上文所描述的各个方法和处理，例如呼吸率测量方法。例如，在一些实施例中，呼吸率测量方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元808。在一些实施例中，计算机程序的部分或者全部可以经由ROM 802和/或通信单元809而被载入和/或安装到设备800上。当计算机程序加载到RAM 803并由计算单元801执行时，可以执行上文描述的呼吸率测量方法的一个或多个步骤。备选地，在其他实施例中，计算单元801可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行呼吸率测量方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实 施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任 何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。
根据本公开的实施例，本公开还提供了一种计算机程序产品，包括计算机程序，计算机程序在被处理器执行时实现上述呼吸率测量方法中任一项方法。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。

Claims (14)

  1. 一种呼吸率测量方法，其特征在于，所述方法包括：
    获取PPG信号；
    对所述PPG信号进行预处理；
    基于预处理后的所述PPG信号获得PPG间期数据；
    判断所述PPG间期数据中是否存在异常的PPG间期变化值；其中，所述PPG间期变化值是指所述PPG间期数据中相邻的两个PPG间期之间的差值；
    在所述PPG间期变化值不存在异常的情况下，基于所述PPG间期数据计算呼吸率；以及，
    在所述PPG间期变化值存在异常的情况下，对所述PPG间期数据进行矫正，基于矫正后的PPG间期数据计算呼吸率。
  2. 根据权利要求1所述的呼吸率测量方法，其特征在于，所述对所述PPG信号进行预处理，包括：
    对所述PPG信号进行滤波处理，以去除基线漂移和肌电噪声。
  3. 根据权利要求2所述的呼吸率测量方法，其特征在于，采用Butterworth滤波器对所述PPG信号进行滤波处理。
  4. 根据权利要求1所述的呼吸率测量方法，其特征在于，所述对所述PPG间期数据进行矫正，包括：
    采用模糊算法对所述PPG间期数据中所述异常的PPG间期变化值进行矫正，获得矫正后的所述PPG间期数据。
  5. 根据权利要求4所述的呼吸率测量方法，其特征在于，所述采用模 糊算法对所述PPG间期数据中所述异常的PPG间期变化值进行矫正，获得矫正后的所述PPG间期数据，包括：
    基于所述PPG间期数据选择输入量和输出量；
    对所述输入量进行模糊化处理，获得输入量模糊集和输入量隶属度函数；对所述输出量进行模糊化处理，获得输出量模糊集和输出量隶属度函数；
    获取所述输入量和所述输出量之间的模糊规则；
    基于所述模糊规则进行模糊集合运算，得到模糊关系集合；
    基于所述模糊关系集合获得所述输出量的模糊值；
    对所述输出量的模糊值进行反模糊计算，获得矫正后的所述PPG间期数据。
  6. 根据权利要求5所述的呼吸率测量方法，其特征在于，所述输入量为所述PPG间期数据中所述异常的PPG间期变化值△PNT md、与所述异常的PPG间期变化值相邻且位于所述异常的PPG间期变化值之前的在前PPG间期变化值△PNT fr、以及与所述异常的PPG间期变化值相邻且位于所述异常的PPG间期变化值之后的在后PPG间期变化值△PNT hd；
    所述输出量为矫正后的异常PPG间期变化值△PNT' md。
  7. 根据权利要求5所述的呼吸率测量方法，其特征在于，所述模糊规则为如果第一模糊子集、第二模糊子集和第三模糊子集为真，则有第四模糊子集；其中，所述第一模糊子集为所述异常的PPG间期变化值△PNT md的模糊子集，所述第二模糊子集为所述在前PPG间期变化值△PNT fr的模糊子集，所述第三模糊子集为所述在后PPG间期变化值△PNT hd的模糊子集，所述第四模糊子集为所述矫正后的异常PPG间期变化值△PNT' md的模糊子集。
  8. 根据权利要求7所述的呼吸率测量方法，其特征在于，所述基于所述模糊规则进行模糊集合运算，得到模糊关系集合，包括：
    根据所述模糊规则对所述第一模糊子集、所述第二模糊子集、所述第三模糊子集和所述第四模糊子集中的对应元素分别进行运算，确定模糊关系子集；
    对所述模糊关系子集作并集处理，获得所述模糊关系集合。
  9. 根据权利要求5所述的呼吸率测量方法，其特征在于，利用系数加权平均法对所述输出量的模糊值进行反模糊计算。
  10. 根据权利要求5-9任意一项所述的呼吸率测量方法，其特征在于，所述输入量模糊集包括负大模糊集、负小模糊集、零模糊集、正小模糊集和正大模糊集；所述输出量模糊集包括明显增大模糊集、近似为零模糊集和明显减小模糊集。
  11. 根据权利要求1-9任意一项所述的呼吸率测量方法，其特征在于，所述基于所述PPG间期数据/矫正后的PPG间期数据计算呼吸率，包括：
    提取所述PPG间期数据/矫正后的PPG间期数据中的波峰点和波谷点；
    将相邻的所述波峰点和所述波谷点之间，PPG间期变化值的绝对值之和小于预设阈值的PPG间期变化值删除；
    从所述PPG间期数据/矫正后的PPG间期数据中提取多个相邻的所述波峰点；
    获取所述多个相邻的波峰点中第一个波峰点与最后一个波峰点的时间差；
    基于所述相邻的波峰点的数量和所述时间差获得所述呼吸率。
  12. 一种呼吸率测量装置，其特征在于，所述装置包括：
    第一获取模块，用于获取PPG信号；
    预处理模块，用于对所述PPG信号进行预处理；
    第二获取模块，用于基于预处理后的所述PPG信号获得PPG间期数据；
    判断模块，用于判断所述PPG间期数据中是否存在异常的PPG间期变化值；其中，所述PPG间期变化值是指所述PPG间期数据中相邻的两个PPG间期之间的差值；
    计算模块，用于在所述PPG间期变化值不存在异常的情况下，基于所述PPG间期数据计算呼吸率；
    矫正模块，用于在所述PPG间期变化值存在异常的情况下，对所述PPG间期数据进行矫正；
    所述计算模块，还用于基于矫正后的PPG间期数据计算呼吸率。
  13. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-11中任一项所述的方法。
  14. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行权利要求1-11中任一项所述的方法。
PCT/CN2021/133436 2021-04-19 2021-11-26 呼吸率测量方法及装置、电子设备、可读介质 WO2022222472A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US18/275,410 US20240122496A1 (en) 2021-04-19 2021-11-26 Method and Device for Measuring a respiratory rate, Electronic device, and Readable Medium
EP21937694.4A EP4327737A1 (en) 2021-04-19 2021-11-26 Respiratory rate measurement method and apparatus, and electronic device and readable medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110419179.4A CN114027822B (zh) 2021-04-19 2021-04-19 一种基于ppg信号的呼吸率测量方法及装置
CN202110419179.4 2021-04-19

Publications (1)

Publication Number Publication Date
WO2022222472A1 true WO2022222472A1 (zh) 2022-10-27

Family

ID=80134159

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/133436 WO2022222472A1 (zh) 2021-04-19 2021-11-26 呼吸率测量方法及装置、电子设备、可读介质

Country Status (4)

Country Link
US (1) US20240122496A1 (zh)
EP (1) EP4327737A1 (zh)
CN (1) CN114027822B (zh)
WO (1) WO2022222472A1 (zh)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000021438A1 (en) * 1998-10-15 2000-04-20 University Of Florida Research Foundation Device for determining respiratory rate from optoplethysmogram
CN101732050A (zh) * 2009-12-04 2010-06-16 西安交通大学 一种基于光电容积波的呼吸率监测方法
CN105662345A (zh) * 2016-01-05 2016-06-15 深圳和而泰智能控制股份有限公司 心跳信号处理方法、装置和系统
CN106539586A (zh) * 2016-11-07 2017-03-29 广州视源电子科技股份有限公司 一种呼吸率计算方法及装置
CN106777884A (zh) * 2016-11-22 2017-05-31 北京心量科技有限公司 一种hrv测量方法以及装置
KR101922221B1 (ko) * 2017-06-26 2018-11-26 부산대학교 산학협력단 Ppg 신호를 사용한 호흡 검출 장치 및 방법
US20190117097A1 (en) * 2017-10-19 2019-04-25 Hill-Rom Services Pte. Ltd. Respiration rate estimation from a photoplethysmography signal
US20190133537A1 (en) * 2017-11-03 2019-05-09 Tata Consultancy Services Limited System and method for breathing pattern extraction from ppg signals
CN112494031A (zh) * 2020-11-26 2021-03-16 咸宁职业技术学院 一种呼吸率计算方法及装置
CN112494008A (zh) * 2020-10-29 2021-03-16 深圳市奋达智能技术有限公司 基于ppg信号的呼吸率测量方法及装置

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100462182B1 (ko) * 2002-04-15 2004-12-16 삼성전자주식회사 Ｐｐｇ 기반의 심박 검출 장치 및 방법
US10188295B2 (en) * 2009-06-01 2019-01-29 The Curators Of The University Of Missouri Integrated sensor network methods and systems
US9179876B2 (en) * 2012-04-30 2015-11-10 Nellcor Puritan Bennett Ireland Systems and methods for identifying portions of a physiological signal usable for determining physiological information
CN102813998B (zh) * 2012-08-01 2015-01-14 上海交通大学 中枢神经损伤患者用多功能复合康复系统
US20150190060A1 (en) * 2014-01-06 2015-07-09 Oridion Medical 1987 Ltd. Method, device and system for calculating integrated capnograph-oximetry values
US9848820B2 (en) * 2014-01-07 2017-12-26 Covidien Lp Apnea analysis system and method
US20160206247A1 (en) * 2015-01-21 2016-07-21 Covidien Lp Adaptive motion correction in photoplethysmography using reference signals
CN106175742A (zh) * 2016-07-19 2016-12-07 北京心量科技有限公司 一种心脏体征获取方法以及装置
CN106725385A (zh) * 2016-12-29 2017-05-31 深圳汇通智能化科技有限公司 一种用于监测睡眠状态的健康分析系统
DE102017203767A1 (de) * 2016-12-29 2018-07-05 Robert Bosch Gmbh Verfahren zur Erfassung der Herzfrequenz und Vorrichtung
IT201700081018A1 (it) * 2017-07-18 2019-01-18 St Microelectronics Srl Trattamento di segnali elettrofisiologici
CN108209904A (zh) * 2017-12-26 2018-06-29 山东农业大学 一种获得成年中华田园犬心电图标准参数范围的方法
US11445927B2 (en) * 2019-02-13 2022-09-20 Viavi Solutions Inc. Baseline correction and extraction of heartbeat profiles
FR3100705B1 (fr) * 2019-09-13 2024-04-05 Sensoria Analytics Procédé de détermination du taux respiratoire
CN111862558A (zh) * 2020-01-07 2020-10-30 武汉烽火富华电气有限责任公司 一种火灾探测信号的智能处理方法
CN111796185B (zh) * 2020-06-16 2022-11-08 合肥力高动力科技有限公司 基于t-s型模糊算法的磷酸铁锂电池soc-ocv校准方法

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000021438A1 (en) * 1998-10-15 2000-04-20 University Of Florida Research Foundation Device for determining respiratory rate from optoplethysmogram
CN101732050A (zh) * 2009-12-04 2010-06-16 西安交通大学 一种基于光电容积波的呼吸率监测方法
CN105662345A (zh) * 2016-01-05 2016-06-15 深圳和而泰智能控制股份有限公司 心跳信号处理方法、装置和系统
CN106539586A (zh) * 2016-11-07 2017-03-29 广州视源电子科技股份有限公司 一种呼吸率计算方法及装置
CN106777884A (zh) * 2016-11-22 2017-05-31 北京心量科技有限公司 一种hrv测量方法以及装置
KR101922221B1 (ko) * 2017-06-26 2018-11-26 부산대학교 산학협력단 Ppg 신호를 사용한 호흡 검출 장치 및 방법
US20190117097A1 (en) * 2017-10-19 2019-04-25 Hill-Rom Services Pte. Ltd. Respiration rate estimation from a photoplethysmography signal
US20190133537A1 (en) * 2017-11-03 2019-05-09 Tata Consultancy Services Limited System and method for breathing pattern extraction from ppg signals
CN112494008A (zh) * 2020-10-29 2021-03-16 深圳市奋达智能技术有限公司 基于ppg信号的呼吸率测量方法及装置
CN112494031A (zh) * 2020-11-26 2021-03-16 咸宁职业技术学院 一种呼吸率计算方法及装置

Also Published As

Publication number Publication date
CN114027822B (zh) 2022-11-25
EP4327737A1 (en) 2024-02-28
US20240122496A1 (en) 2024-04-18
CN114027822A (zh) 2022-02-11

Similar Documents

Publication Publication Date Title
CN110664390B (zh) 基于腕带式ppg和深度学习的心率监测系统及方法
US10813583B2 (en) Sleep state prediction device
US20130338519A1 (en) Apparatus and Method for Measuring Physiological Signal Quality
WO2012114080A1 (en) Respiration monitoring method and system
Papini et al. Photoplethysmography beat detection and pulse morphology quality assessment for signal reliability estimation
CN105578960A (zh) 用于处理生理信号的处理装置、处理方法和系统
US10973423B2 (en) Determining health markers using portable devices
EP3453321A1 (en) Non-invasive method and system for estimating blood pressure from photoplethysmogram using statistical post-processing
CN116138745B (zh) 融合毫米波雷达和血氧数据的睡眠呼吸监测方法及设备
Loo et al. A machine learning approach to assess magnitude of asynchrony breathing
US20210000384A1 (en) Method and apparatus for monitoring a human or animal subject
JP2012505456A (ja) マルチパラメーターモニタリングにおける改善又はマルチパラメーターモニタリングに関する改善
US20190021633A1 (en) Detecting respiratory rates in audio using an adaptive low-pass filter
CN111128327A (zh) 一种低血糖预警方法和装置
WO2022222472A1 (zh) 呼吸率测量方法及装置、电子设备、可读介质
CN114098721B (zh) 心冲击图信号的提取方法、装置以及设备
CN105982664A (zh) 基于单导联ecg的心肺耦合分析方法
CN115758122A (zh) 基于多尺度卷积神经网络的睡眠呼吸事件定位方法及装置
CN111383764B (zh) 一种机械通气驱动压与呼吸机相关事件的相关性检测系统
US20230029547A1 (en) Assistance in the detection of pulmonary diseases
CN111466877B (zh) 一种基于lstm网络的氧减状态预测方法
KR20200042076A (ko) 피부영상을 이용한 디지털 호흡 청진 방법
CN117831744B (zh) 一种呼吸重症患者远程监控方法及系统
CN117338253B (zh) 基于生理信号的睡眠呼吸暂停检测方法以及装置
FI128598B (en) Apparatus and procedure for QT correction

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: 21937694

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18275410

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 2021937694

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021937694

Country of ref document: EP

Effective date: 20231120