CN111988097A - Method and device for detecting signal quality of PPG signal and computer readable storage medium - Google Patents
Method and device for detecting signal quality of PPG signal and computer readable storage medium Download PDFInfo
- Publication number
- CN111988097A CN111988097A CN202010867486.4A CN202010867486A CN111988097A CN 111988097 A CN111988097 A CN 111988097A CN 202010867486 A CN202010867486 A CN 202010867486A CN 111988097 A CN111988097 A CN 111988097A
- Authority
- CN
- China
- Prior art keywords
- signal
- ppg
- ppg signal
- signal quality
- value
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
Abstract
The invention discloses a PPG signal quality detection method, which comprises the following steps: acquiring a PPG signal and a plurality of first reference values of the PPG signal, wherein the first reference values are a first mean value of differences between adjacent peaks in the PPG signal, a second mean value of differences between adjacent valleys in the PPG signal, a third mean value of lengths between adjacent valleys and peaks in the PPG signal or a first average amplitude of the PPG signal; determining a signal quality of the PPG signal from each of the first reference values. The invention also discloses a signal quality detection device and a computer readable storage medium of the PPG signal. The PPG signal of the invention has higher signal quality detection accuracy.
Description
Technical Field
The present invention relates to the field of heart rate detection technologies, and in particular, to a method and an apparatus for detecting signal quality of a PPG signal, and a computer-readable storage medium.
Background
Most of intelligent watches and bracelets in the market at present have heart rate and blood oxygen monitoring functions, namely, the heart rate, blood oxygen, blood pressure and other human health parameters are monitored by a PPG (PhotoPlethysmoGraphy) heart rate sensor.
At present, when the signal quality of the PPG signal is analyzed, an alternating current component and a noise component of the PPG signal are acquired, a signal-to-noise ratio is calculated, and the acquired signal is classified and evaluated according to the magnitude of the signal-to-noise ratio. However, because the heart rate sensor collects signals under different working conditions, the detected alternating current component and noise component of the signals are inaccurate, so that the accuracy of judging the signal quality of the PPG signals is low.
Disclosure of Invention
The invention mainly aims to provide a method and a device for detecting the signal quality of a PPG signal and a computer readable storage medium, aiming at solving the problem of low accuracy in judging the signal quality of the PPG signal.
In order to achieve the above object, the present invention provides a method for detecting signal quality of a PPG signal, which includes the following steps:
acquiring a PPG signal and a plurality of first reference values of the PPG signal, wherein the first reference values are a first mean value of differences between adjacent peaks in the PPG signal, a second mean value of differences between adjacent valleys in the PPG signal, a third mean value of lengths between adjacent valleys and peaks in the PPG signal or a first average amplitude of the PPG signal;
determining a signal quality of the PPG signal from each of the first reference values.
In an embodiment, the step of determining a first quality score of the PPG signal from the respective first reference value comprises:
determining a weight corresponding to each first reference value;
according to the weight corresponding to each first reference value, weighting and calculating each first reference value to obtain a quality score;
determining a signal quality of the PPG signal according to the quality score.
In an embodiment, the weight of the third average value is greater than the weight corresponding to the second average value, the weight corresponding to the second average value is greater than the weight corresponding to the first average value, and the weight of the first average value is greater than the weight of the first average amplitude value.
In an embodiment, the step of determining a first quality score of the PPG signal from the respective first reference value comprises:
inputting each of the first reference values to a signal quality assessment model;
and acquiring the signal quality of the PPG signal output by the quality evaluation model.
In an embodiment, before the step of inputting each of the first reference values to the signal quality estimation model, the method further includes:
obtaining each training signal sample and a plurality of second reference values corresponding to each training signal sample, where the second reference values are the first average value, the second average value, the third average value, or the first average amplitude value;
training a preset model according to each second reference value corresponding to each training sample;
and when the convergence value of the preset model is smaller than a preset threshold value, stopping training the preset model, and storing the preset model which is stopped training as a signal quality evaluation model.
In an embodiment, after the step of acquiring the PPG signal, the method further includes:
determining a length of the PPG signal;
when the length is less than or equal to a preset length, performing the step of acquiring a plurality of first reference values of the PPG signal.
In an embodiment, after the step of determining the length of the PPG signal, the method further includes:
when the length is larger than a preset length, the PPG signal is divided into a plurality of PPG sub-signals, and the length of each PPG sub-signal is smaller than or equal to the preset length;
obtaining a plurality of third reference values for each PPG sub-signal, the third reference values being a fourth mean of differences between adjacent peaks within the PPG sub-signal, a fifth mean of differences between adjacent valleys within the PPG sub-signal, a sixth mean of lengths between adjacent valleys and peaks within the PPG sub-signal, or a second average magnitude of the PPG signal;
and determining the signal quality of each PPG sub-signal according to each third reference value corresponding to each PPG confidence.
In an embodiment, after the step of acquiring the PPG signal, the method further includes:
sequentially carrying out high-pass filtering and low-pass filtering on the PPG signal to obtain a processed PPG signal;
acquiring a plurality of reference values of the processed PPG signal as a plurality of first reference values of the PPG signal.
In order to achieve the above object, the present invention further provides a signal quality detection apparatus for a PPG signal, which is characterized in that the signal quality detection apparatus for a PPG signal comprises a memory, a processor, and a signal quality detection program stored in the memory and executable on the processor, and the signal quality detection program, when executed by the processor, implements the steps of the signal quality detection method for a PPG signal as described above.
In order to achieve the above object, the present invention also provides a computer-readable storage medium storing a signal quality detection program which, when executed by a processor, implements the steps of the signal quality detection method for PPG signals as described above.
According to the PPG signal quality detection method and device and the computer readable storage medium, the device obtains a PGG signal and a plurality of reference values in a first mean value of differences between adjacent peak values in the PPG signal, a second mean value of differences between adjacent valley values in the PPG signal, a third mean value of lengths between adjacent valley values and peak values in the PPG signal and an average amplitude value of the PPG signal, and accordingly the signal quality of the PPG signal is determined according to the reference values. The device comprehensively considers the signal quality of the PPG signal through the time domain characteristics of the first mean value, the second mean value and the third mean value in the PPG signal and the average amplitude serving as the frequency domain characteristics, so that the accuracy of judging the signal quality of the PPG signal is improved.
Drawings
Fig. 1 is a schematic diagram of a hardware structure of a signal quality detection apparatus for a PPG signal according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a signal quality detection method for a PPG signal according to a first embodiment of the present invention;
fig. 3 is a schematic flowchart of a signal quality detection method for PPG signals according to a second embodiment of the present invention;
fig. 4 is a schematic flow chart of a method for detecting signal quality of a PPG signal according to a third embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The main solution of the embodiment of the invention is as follows: acquiring a PPG signal and a plurality of first reference values of the PPG signal, wherein the first reference values are a first mean value of differences between adjacent peaks in the PPG signal, a second mean value of differences between adjacent valleys in the PPG signal, a third mean value of lengths between adjacent valleys and peaks in the PPG signal or a first average amplitude of the PPG signal; determining a signal quality of the PPG signal from each of the first reference values.
The device comprehensively considers the signal quality of the PPG signal through the time domain characteristics of the first mean value, the second mean value and the third mean value in the PPG signal and the average amplitude serving as the frequency domain characteristics, so that the accuracy of judging the signal quality of the PPG signal is improved.
As an implementation, the signal quality detection device of the PPG signal may be as shown in fig. 1.
The embodiment of the invention relates to a signal quality detection device for a PPG signal, which comprises a memory 101, a processor 102, for example a CPU, and a communication bus 103. Wherein a communication bus 103 is used for enabling the connection communication between these components.
The memory 101 may be a high-speed RAM storage device or a non-volatile storage device (e.g., a magnetic disk storage device). As shown in fig. 1, a playback program may be included in the memory 101; and the processor 102 may be configured to call the signal quality detection program stored in the memory 101 and perform the following operations:
acquiring a PPG signal and a plurality of first reference values of the PPG signal, wherein the first reference values are a first mean value of differences between adjacent peaks in the PPG signal, a second mean value of differences between adjacent valleys in the PPG signal, a third mean value of lengths between adjacent valleys and peaks in the PPG signal or a first average amplitude of the PPG signal;
determining a signal quality of the PPG signal from each of the first reference values.
In one embodiment, the processor 102 may be configured to call a signal quality detection program stored in the memory 101 and perform the following operations:
determining a weight corresponding to each first reference value;
according to the weight corresponding to each first reference value, weighting and calculating each first reference value to obtain a quality score;
determining a signal quality of the PPG signal according to the quality score.
In one embodiment, the processor 102 may be configured to call a signal quality detection program stored in the memory 101 and perform the following operations:
the weight of the third average value is greater than the weight corresponding to the second average value, the weight corresponding to the second average value is greater than the weight corresponding to the first average value, and the weight of the first average value is greater than the weight of the first average amplitude value.
In one embodiment, the processor 102 may be configured to call a signal quality detection program stored in the memory 101 and perform the following operations:
inputting each of the first reference values to a signal quality assessment model;
and acquiring the signal quality of the PPG signal output by the quality evaluation model.
In one embodiment, the processor 102 may be configured to call a signal quality detection program stored in the memory 101 and perform the following operations:
obtaining each training signal sample and a plurality of second reference values corresponding to each training signal sample, where the second reference values are the first average value, the second average value, the third average value, or the first average amplitude value;
training a preset model according to each second reference value corresponding to each training sample;
and when the convergence value of the preset model is smaller than a preset threshold value, stopping training the preset model, and storing the preset model which is stopped training as a signal quality evaluation model.
In one embodiment, the processor 102 may be configured to call a signal quality detection program stored in the memory 101 and perform the following operations:
determining a length of the PPG signal;
when the length is less than or equal to a preset length, performing the step of acquiring a plurality of first reference values of the PPG signal.
In one embodiment, the processor 102 may be configured to call a signal quality detection program stored in the memory 101 and perform the following operations:
when the length is larger than a preset length, the PPG signal is divided into a plurality of PPG sub-signals, and the length of each PPG sub-signal is smaller than or equal to the preset length;
obtaining a plurality of third reference values for each PPG sub-signal, the third reference values being a fourth mean of differences between adjacent peaks within the PPG sub-signal, a fifth mean of differences between adjacent valleys within the PPG sub-signal, a sixth mean of lengths between adjacent valleys and peaks within the PPG sub-signal, or a second average magnitude of the PPG signal;
and determining the signal quality of each PPG sub-signal according to each third reference value corresponding to each PPG confidence.
In one embodiment, the processor 102 may be configured to call a signal quality detection program stored in the memory 101 and perform the following operations:
sequentially carrying out high-pass filtering and low-pass filtering on the PPG signal to obtain a processed PPG signal;
acquiring a plurality of reference values of the processed PPG signal as a plurality of first reference values of the PPG signal.
According to the scheme, the device acquires a plurality of reference values in the PGG signal, a first mean value of difference values between adjacent peak values in the PPG signal, a second mean value of difference values between adjacent valley values in the PPG signal, a third mean value of lengths between adjacent valley values and peak values in the PPG signal and an average amplitude value of the PPG signal, so that the signal quality of the PPG signal is determined according to the reference values. The device comprehensively considers the signal quality of the PPG signal through the time domain characteristics of the first mean value, the second mean value and the third mean value in the PPG signal and the average amplitude serving as the frequency domain characteristics, so that the accuracy of judging the signal quality of the PPG signal is improved.
Based on the hardware architecture of the signal quality detection device of the PPG signal, an embodiment of the signal quality detection method of the PPG signal of the invention is provided.
Referring to fig. 2, fig. 2 is a first embodiment of the signal quality detection method for a PPG signal according to the present invention, which includes the following steps:
step S10, obtaining a PPG signal and a plurality of first reference values of the PPG signal, wherein the first reference values are a first mean value of differences between adjacent peaks in the PPG signal, a second mean value of differences between adjacent valleys in the PPG signal, a third mean value of lengths between adjacent valleys and peaks in the PPG signal or a first average amplitude of the PPG signal;
in the present embodiment, a signal quality detection apparatus for the subject being the PPG signal is implemented, and for convenience of description, the apparatus is hereinafter referred to as the signal quality detection apparatus for the PPG signal. The wearable device may send the PPG signal to the apparatus after the heart rate sensor of the wearable device has acquired the PPG signal. The device may be considered a backend server.
After the device acquires the PPG signal, the time domain feature and the frequency domain feature in the PPG signal are extracted. The time domain feature includes a first mean of differences between adjacent peaks within the PPG signal, a second mean of differences between adjacent valleys within the PPG signal, and a third mean of lengths between adjacent valleys and peaks within the PPG signal.
Specifically, the device acquires peak values of all peaks and valley values of all troughs in the PPG signal, then sequentially selects the peaks adjacent in time to calculate first difference values of the peaks and the valleys, and then calculates the average value of the first difference values to obtain a first average value; the device sequentially selects the valleys adjacent in time to calculate second difference values of the valleys and then calculates the average value of the second difference values to obtain a first average value; and finally, the device sequentially selects the peak value and the valley value which are adjacent in time, calculates the length between the peak value and the valley value, and then calculates the average value of all the lengths to obtain a third average value. The device converts time data in the PPG signal into a frequency domain through discrete Fourier transform, and then calculates the average amplitude of each point amplitude of the frequency domain as a first average amplitude.
After the device obtains the PPG signal, the high-pass filtering and the low-pass filtering may be sequentially performed on the PPG signal to obtain a processed PPG signal, and a plurality of reference values of the processed PPG signal are obtained to be used as first reference values corresponding to the PPG signal. The device can more accurately acquire the first reference value by carrying out high-pass filtering and low-pass filtering on the PPG signal.
Step S20, determining the signal quality of the PPG signal according to each of the first reference values.
After the device obtains each first reference value, the signal quality of the PPG signal can be determined according to each first reference value. The signal quality includes two cases, one is that the signal quality is good, and the other is that the signal quality is poor. The apparatus may determine the range within which each first reference value lies, thereby determining the signal quality of the PPG signal from the range. Specifically, if the first average value is within a first preset range (the first preset range may be 20 to 60), it indicates that the peak variation of the PPG signal is small, so as to represent that the peak variation of the PPG signal is small; if the second mean value is in a second preset range (the second preset range can be 20-60), the variation of the trough of the PPG signal is small, so as to represent that the variation of the trough of the PPG signal is small; if the third mean value is in a third preset range (the third preset range is greater than 100), it can be shown that the length between the peak and the trough of the PPG signal is normal; and the first average amplitude is in a fourth preset range (the fourth preset range can be 5 Hz-100 Hz), namely the frequency of the PPG signal is normal. If the first reference values obtained by the device are all in the corresponding ranges, the signal quality of the PPG signal can be determined to be good. If at least one of the first reference values obtained by the device is not in the corresponding range, the poor quality of the PPG signal can be determined.
It should be noted that, the quality of the PPG signal is mainly determined whether the third average value is within the first preset range, and then determined whether the second average value is within the second preset range, and then determined whether the first average value is within the third preset range, and finally determined whether the first average amplitude is within the fourth preset range. If the first average value, the second average value and the third average value are all in the corresponding preset ranges, the quality of the PPG signal can be judged to be good even if the first average amplitude is not in the fourth preset range.
In the technical solution provided in this embodiment, the apparatus obtains a plurality of reference values in a first mean value of differences between adjacent peaks in the PGG signal and the PPG signal, a second mean value of differences between adjacent valleys in the PPG signal, a third mean value of lengths between adjacent valleys and peaks in the PPG signal, and an average amplitude of the PPG signal, thereby determining the signal quality of the PPG signal according to each reference value. The device comprehensively considers the signal quality of the PPG signal through the time domain characteristics of the first mean value, the second mean value and the third mean value in the PPG signal and the average amplitude serving as the frequency domain characteristics, so that the accuracy of judging the signal quality of the PPG signal is improved.
Referring to fig. 3, fig. 3 is a second embodiment of the method for detecting signal quality of a PPG signal according to the present invention, where, based on the first embodiment, the step S20 includes:
step S21, determining a weight corresponding to each of the first reference values;
step S22, according to the weight corresponding to each first reference value, weighting and calculating each first reference value to obtain a quality score;
and step S23, determining the signal quality of the PPG signal according to the quality score.
In the present embodiment, the apparatus gives a weight to each of the acquired first reference values. Considering that the influence degrees of the third mean value, the second mean value, the first mean value and the fourth mean value on the signal quality of the PPG signal are sequentially reduced, the weight of the third mean value is greater than the weight corresponding to the second mean value, the weight corresponding to the second mean value is greater than the weight corresponding to the first mean value, and the weight of the first mean value is greater than the weight of the first average amplitude value.
The device sets the weight of each first reference value, and carries out weighted calculation on each first reference value to obtain the quality score. The mass score Q is P1 × W1+ P2 × W2+ P3 × W3+ P1 × W4, where P1 is a first average value, W1 is a weight corresponding to the first average value, P1 is the first average value, W1 is a weight corresponding to the first average value, P2 is a second average value, W2 is a weight corresponding to the second average value, P3 is a third average value, W3 is a weight corresponding to the third average value, P4 is a first amplitude average value, and W4 is a weight corresponding to the first amplitude average value. W3 may be 0.3-0.4, W2 may be 0.2-0.3, W1 may be 0.1-0.2, and W4 may be 0-0.1.
After the device determines the quality score, judging whether the quality score is larger than a preset score, if so, determining that the signal quality of the PPG signal is good; and if the quality score is smaller than or equal to the preset score, determining that the signal quality of the PPG signal is poor.
In the technical scheme provided by this embodiment, the device determines the weight corresponding to each first reference value, so as to perform weighting calculation on each first reference value according to the weight corresponding to each first reference value to obtain a quality score, thereby accurately determining the signal quality of the PPG signal according to the quality score.
Referring to fig. 4, fig. 4 is a third embodiment of the method for detecting signal quality of a PPG signal according to the present invention, where, based on the first embodiment, the step S20 includes:
step S24, inputting each of the first reference values into a signal quality evaluation model;
and step S25, acquiring the signal quality of the PPG signal output by the quality evaluation model.
In this embodiment, a signal quality evaluation model is provided in the apparatus. After the device obtains each first reference value, each first reference value is input into a signal quality evaluation model, a weight corresponding to each first reference value is arranged in the signal quality evaluation model, the signal quality evaluation model performs weighting calculation on each first reference value according to each weight to obtain a quality score, so that the signal quality of the PPG signal is determined according to the quality score, and then the signal quality is output, namely the result of the signal quality is output.
In addition, the signal quality evaluation model comprises a weak classifier, the weak classifier is provided with a corresponding error value, and the signal quality evaluation model corrects the calculated quality score according to the error value so as to output a correct signal quality result.
It will be appreciated that the apparatus needs to train a signal quality assessment model. That is, before each first reference value is input into the signal quality evaluation model, the device obtains each training signal sample and a plurality of second reference values corresponding to each training signal sample, wherein the second reference values are a first average value, a second average value, a third average value or a first average amplitude value; the device trains the preset model according to each second reference value corresponding to each training sample; and when the convergence value of the preset model is smaller than a preset threshold value, stopping training the preset model, and storing the preset model which is stopped training as a signal quality evaluation model. In addition, when the device trains the signal quality evaluation model, the label of the training signal sample needs to be input into the preset model, and the label is the signal quality of the training signal sample. For example, a label of 1 indicates that the signal quality of the training signal sample is good, and a label of 0 indicates that the signal quality of the training signal sample is poor. The training signal samples are artificially labeled PPG signals.
In addition, the device needs to obtain a weak classifier in the signal quality evaluation model. Specifically, the device first initializes a weight distribution D of training signal samples (W ═ D1，W2，…，Wi) Wi is 1/N, i is 1, 2, 3. For m 1, 2.. times.m, D with a weight distribution is usedmTraining and learning the data set to obtain a weak classifier Gm(x) In that respect The device is calculating the classification error emAnd specific gravity am. The method comprises the following specific steps:
the device renews the weight distribution:
finally, a classifier is obtained
In the technical solution provided in this embodiment, the apparatus inputs each of the first reference values to a signal quality evaluation model, so as to accurately determine the signal quality of the PPG signal according to the quality evaluation model.
In an embodiment, in order to ensure the accuracy of the signal quality of the PPG signal, there is a certain limit to the length of the PPG signal, that is, the device detects the signal quality of the PPG signal below a preset length. For this, the device determines the length of the PPG signal after it has been obtained. If the length is smaller than or equal to the preset length, the step of obtaining a plurality of first reference values of the PPG signal is performed, and then step S20 is performed. And if the length is greater than the preset length, segmenting the PPG signal to obtain a plurality of PPG sub-signals, wherein the length of each PPG sub-signal is less than or equal to the preset length. The device acquires a plurality of third reference values of each PPG signal in turn, wherein the third reference values are a fourth mean value of differences between adjacent peaks in the PPG sub-signals, a fifth mean value of differences between adjacent valleys in the PPG sub-signals, a sixth mean value of lengths between adjacent valleys and peaks in the PPG sub-signals or a second average amplitude of the PPG signal. The process of obtaining the third reference value refers to the process of obtaining the first reference value, and is not repeated again. The device determines the signal quality of each PPG signal from the respective third reference value of each PPG sub-signal. It should be noted that, before the PPG sub-signals are split, high-pass filtering and low-pass filtering may be performed on the PPG sub-signals to improve the accuracy of determining the signal quality of the PPG signals.
When the signal quality detection device is provided with the signal quality evaluation model, the process of determining the signal quality of the PPG signal by the signal quality detection device is as follows:
1. collecting a PPG signal;
2. carrying out high-pass filtering and low-pass filtering on the PPG signal to obtain a PPG signal to be processed;
3. segmenting the PPG signal to be processed to obtain a plurality of PPG sub-signals, wherein the length of each PPG sub-signal is smaller than a preset length;
4. taking each PPG sub-signal as a training signal sample, and initializing the weight distribution of the training samples;
5. learning by using the weight distributed data set to obtain a weak classifier;
6. acquiring time domain characteristics and frequency domain characteristics of training signal samples, and labeling signal quality of each training signal sample to obtain a label of each training signal sample;
7. inputting the time domain characteristics, the frequency domain characteristics and the labels of training signal samples into a model with a weak classifier for training to obtain a signal quality evaluation model;
8. acquiring a PPG signal to be evaluated;
9. carrying out high-pass filtering and low-pass filtering on the PPG signal to be evaluated, and then carrying out segmentation to obtain each PPG sub-signal to be evaluated;
10. and sequentially inputting the time domain characteristics and the frequency domain characteristics of each PPG sub-signal to be evaluated into the quality evaluation model to obtain the signal quality of each PPG sub-signal to be evaluated, which is output by the quality evaluation model.
When the signal quality detection device is not provided with a signal quality evaluation model, the process of determining the signal quality of the PPG signal by the signal quality detection device is as follows:
1. collecting a PPG signal;
2. carrying out high-pass filtering and low-pass filtering on the PPG signal, and then carrying out segmentation to obtain each PPG sub-signal;
3. giving corresponding weight to the time domain characteristics and the frequency domain characteristics of the PPG sub-signals, and performing weighted calculation on the time domain characteristics and the frequency domain characteristics of the PPG sub-signals according to the weight to obtain the quality score of each PPG sub-signal;
4. determining the signal quality of each PPG sub-signal according to the interval in which the quality score of each PPG sub-signal is located.
The present invention also provides a signal quality detection apparatus for a PPG signal, which includes a memory, a processor, and a signal quality detection program stored in the memory and executable on the processor, and when the signal quality detection program is executed by the processor, the steps of the signal quality detection method for a PPG signal according to the above embodiments are implemented.
The present invention also provides a computer-readable storage medium storing a signal quality detection program, which when executed by a processor implements the steps of the signal quality detection method for PPG signals as described in the above embodiments.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A signal quality detection method for a PPG signal is characterized by comprising the following steps:
acquiring a PPG signal and a plurality of first reference values of the PPG signal, wherein the first reference values are a first mean value of differences between adjacent peaks in the PPG signal, a second mean value of differences between adjacent valleys in the PPG signal, a third mean value of lengths between adjacent valleys and peaks in the PPG signal or a first average amplitude of the PPG signal;
determining a signal quality of the PPG signal from each of the first reference values.
2. The method for signal quality detection of a PPG signal according to claim 1, wherein the step of determining a first quality score of the PPG signal from the respective first reference value comprises:
determining a weight corresponding to each first reference value;
according to the weight corresponding to each first reference value, weighting and calculating each first reference value to obtain a quality score;
determining a signal quality of the PPG signal according to the quality score.
3. The method for signal quality detection of a PPG signal according to claim 2, wherein the weight of the third mean value is greater than the weight corresponding to the second mean value, the weight corresponding to the second mean value is greater than the weight corresponding to the first mean value, and the weight of the first mean value is greater than the weight of the first average amplitude value.
4. The method for signal quality detection of a PPG signal according to claim 1, wherein the step of determining a first quality score of the PPG signal from the respective first reference value comprises:
inputting each of the first reference values to a signal quality assessment model;
and acquiring the signal quality of the PPG signal output by the quality evaluation model.
5. The method for signal quality detection of a PPG signal according to claim 4, wherein the step of inputting each of the first reference values into a signal quality assessment model is preceded by the step of:
obtaining each training signal sample and a plurality of second reference values corresponding to each training signal sample, where the second reference values are the first average value, the second average value, the third average value, or the first average amplitude value;
training a preset model according to each second reference value corresponding to each training sample;
and when the convergence value of the preset model is smaller than a preset threshold value, stopping training the preset model, and storing the preset model which is stopped training as a signal quality evaluation model.
6. The method for signal quality detection of a PPG signal according to any of claims 1-5, wherein the step of acquiring the PPG signal is followed by further comprising:
determining a length of the PPG signal;
when the length is less than or equal to a preset length, performing the step of acquiring a plurality of first reference values of the PPG signal.
7. The method for signal quality detection of a PPG signal according to claim 6, wherein the step of determining the length of the PPG signal is followed by further comprising:
when the length is larger than a preset length, the PPG signal is divided into a plurality of PPG sub-signals, and the length of each PPG sub-signal is smaller than or equal to the preset length;
obtaining a plurality of third reference values for each PPG sub-signal, the third reference values being a fourth mean of differences between adjacent peaks within the PPG sub-signal, a fifth mean of differences between adjacent valleys within the PPG sub-signal, a sixth mean of lengths between adjacent valleys and peaks within the PPG sub-signal, or a second average magnitude of the PPG signal;
and determining the signal quality of each PPG sub-signal according to each third reference value corresponding to each PPG confidence.
8. The method for signal quality detection of a PPG signal according to any of claims 1-5, wherein the step of acquiring the PPG signal is followed by further comprising:
sequentially carrying out high-pass filtering and low-pass filtering on the PPG signal to obtain a processed PPG signal;
acquiring a plurality of reference values of the processed PPG signal as a plurality of first reference values of the PPG signal.
9. A signal quality detection apparatus for a PPG signal, characterized in that the signal quality detection apparatus for a PPG signal comprises a memory, a processor, and a signal quality detection program stored in the memory and executable on the processor, which when executed by the processor implements the steps of the signal quality detection method for a PPG signal according to any of claims 1-8.
10. A computer-readable storage medium, characterized in that it stores a signal quality detection program which, when executed by a processor, implements the steps of the signal quality detection method of PPG signals according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010867486.4A CN111988097B (en) | 2020-08-25 | 2020-08-25 | Method and device for detecting signal quality of PPG signal and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010867486.4A CN111988097B (en) | 2020-08-25 | 2020-08-25 | Method and device for detecting signal quality of PPG signal and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111988097A true CN111988097A (en) | 2020-11-24 |
| CN111988097B CN111988097B (en) | 2022-05-13 |
Family
ID=73444142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010867486.4A Active CN111988097B (en) | 2020-08-25 | 2020-08-25 | Method and device for detecting signal quality of PPG signal and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111988097B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115670397A (en) * | 2022-11-17 | 2023-02-03 | 北京中科心研科技有限公司 | PPG artifact identification method and device, storage medium and electronic equipment |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070239220A1 (en) * | 2006-03-29 | 2007-10-11 | Greenhut Saul E | Implantable medical device system and method with signal quality monitoring and response |
| CN102512158A (en) * | 2011-12-31 | 2012-06-27 | 济南汇医融工科技有限公司 | Electrocardiosignal quality evaluation method and device based on high-dimensional fuzzy recognition |
| CN103888992A (en) * | 2014-04-08 | 2014-06-25 | 苏州信美通信技术有限公司 | Signal quality estimation method of hidden sound transmission technology |
| CN105138823A (en) * | 2015-07-28 | 2015-12-09 | 中国科学院电子学研究所 | Method for detecting quality of physiological signal based on self-correlation function |
| CN105595990A (en) * | 2016-01-27 | 2016-05-25 | 浙江铭众科技有限公司 | Intelligent terminal device for evaluating and distinguishing quality of electrocardiosignal |
| CN105769122A (en) * | 2016-03-16 | 2016-07-20 | 中国科学院电子学研究所 | Method for measuring sleep apnea hyponea index |
| CN105816163A (en) * | 2016-05-09 | 2016-08-03 | 安徽华米信息科技有限公司 | Method, device and wearable equipment for detecting heart rate |
| CN106569840A (en) * | 2015-10-08 | 2017-04-19 | 上海智瞳通科技有限公司 | Method for machine vision driving assistance system to automatically obtain sample to improve recognition accuracy |
| CN106994010A (en) * | 2016-01-26 | 2017-08-01 | 深圳市新元素健康管理有限公司 | A kind of heart rate detection method and system based on PPG signals |
| CN108042141A (en) * | 2017-11-17 | 2018-05-18 | 深圳和而泰智能控制股份有限公司 | A kind of signal processing method and device |
| CN108289615A (en) * | 2015-11-24 | 2018-07-17 | 皇家飞利浦有限公司 | For quantifying photoplethysmo graph（PPG）The method of signal quality |
| CN108523877A (en) * | 2018-03-23 | 2018-09-14 | 南京中医药大学 | A kind of electrocardiosignal quality discrimination method and its ecg analysis method |
| CN108670242A (en) * | 2018-02-13 | 2018-10-19 | 安徽奇智科技有限公司 | A kind of method and system of smartwatch detection health data |
| CN108670245A (en) * | 2018-05-31 | 2018-10-19 | 哈尔滨工业大学深圳研究生院 | A kind of electrocardiograph signal detection method and system |
| US20180360390A1 (en) * | 2017-06-15 | 2018-12-20 | The University Of Massachusetts | Methods and systems for diagnosing or monitoring progress of a pathology using laser induced breakdown spectroscopy and biological fluids |
| CN109699171A (en) * | 2017-08-22 | 2019-04-30 | 深圳市汇顶科技股份有限公司 | Heart rate detection method and device, electric terminal |
| KR20200050530A (en) * | 2018-11-02 | 2020-05-12 | 주식회사 에이치엘메디텍 | System for measuring blood vessel health and method thereof |
-
2020
- 2020-08-25 CN CN202010867486.4A patent/CN111988097B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070239220A1 (en) * | 2006-03-29 | 2007-10-11 | Greenhut Saul E | Implantable medical device system and method with signal quality monitoring and response |
| CN102512158A (en) * | 2011-12-31 | 2012-06-27 | 济南汇医融工科技有限公司 | Electrocardiosignal quality evaluation method and device based on high-dimensional fuzzy recognition |
| CN103888992A (en) * | 2014-04-08 | 2014-06-25 | 苏州信美通信技术有限公司 | Signal quality estimation method of hidden sound transmission technology |
| CN105138823A (en) * | 2015-07-28 | 2015-12-09 | 中国科学院电子学研究所 | Method for detecting quality of physiological signal based on self-correlation function |
| CN106569840A (en) * | 2015-10-08 | 2017-04-19 | 上海智瞳通科技有限公司 | Method for machine vision driving assistance system to automatically obtain sample to improve recognition accuracy |
| CN108289615A (en) * | 2015-11-24 | 2018-07-17 | 皇家飞利浦有限公司 | For quantifying photoplethysmo graph（PPG）The method of signal quality |
| CN106994010A (en) * | 2016-01-26 | 2017-08-01 | 深圳市新元素健康管理有限公司 | A kind of heart rate detection method and system based on PPG signals |
| CN105595990A (en) * | 2016-01-27 | 2016-05-25 | 浙江铭众科技有限公司 | Intelligent terminal device for evaluating and distinguishing quality of electrocardiosignal |
| CN105769122A (en) * | 2016-03-16 | 2016-07-20 | 中国科学院电子学研究所 | Method for measuring sleep apnea hyponea index |
| CN105816163A (en) * | 2016-05-09 | 2016-08-03 | 安徽华米信息科技有限公司 | Method, device and wearable equipment for detecting heart rate |
| US20180360390A1 (en) * | 2017-06-15 | 2018-12-20 | The University Of Massachusetts | Methods and systems for diagnosing or monitoring progress of a pathology using laser induced breakdown spectroscopy and biological fluids |
| CN109699171A (en) * | 2017-08-22 | 2019-04-30 | 深圳市汇顶科技股份有限公司 | Heart rate detection method and device, electric terminal |
| CN108042141A (en) * | 2017-11-17 | 2018-05-18 | 深圳和而泰智能控制股份有限公司 | A kind of signal processing method and device |
| CN108670242A (en) * | 2018-02-13 | 2018-10-19 | 安徽奇智科技有限公司 | A kind of method and system of smartwatch detection health data |
| CN108523877A (en) * | 2018-03-23 | 2018-09-14 | 南京中医药大学 | A kind of electrocardiosignal quality discrimination method and its ecg analysis method |
| CN108670245A (en) * | 2018-05-31 | 2018-10-19 | 哈尔滨工业大学深圳研究生院 | A kind of electrocardiograph signal detection method and system |
| KR20200050530A (en) * | 2018-11-02 | 2020-05-12 | 주식회사 에이치엘메디텍 | System for measuring blood vessel health and method thereof |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115670397A (en) * | 2022-11-17 | 2023-02-03 | 北京中科心研科技有限公司 | PPG artifact identification method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111988097B (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3703052B1 (en) | Echo cancellation method and apparatus based on time delay estimation | |
| US6173074B1 (en) | Acoustic signature recognition and identification | |
| CN105872156A (en) | Echo time delay tracking method and device | |
| JP2018173285A (en) | Activity recognition system and activity recognition method | |
| US20160334437A1 (en) | Mobile terminal, computer-readable recording medium, and activity recognition device | |
| CN111988097B (en) | Method and device for detecting signal quality of PPG signal and computer readable storage medium | |
| US11232810B2 (en) | Voice evaluation method, voice evaluation apparatus, and recording medium for evaluating an impression correlated to pitch | |
| US20170296081A1 (en) | Frame based spike detection module | |
| CN114048773A (en) | Behavior identification method and system based on transfer learning and WiFi | |
| CN113259031A (en) | Bottom noise fitting and eliminating method for satellite spectrum situation generation | |
| US20110246185A1 (en) | Voice activity detector, voice activity detection program, and parameter adjusting method | |
| CN111341333A (en) | Noise detection method, noise detection device, medium, and electronic apparatus | |
| US8551007B2 (en) | Pulse rate measuring apparatus | |
| CN111929489B (en) | Fault arc current detection method and system | |
| CN102006252A (en) | Single-tone signal identification method | |
| US20130211273A1 (en) | Method and apparatus for heart rate measurement | |
| CN111259926A (en) | Meat freshness detection method and device, computing equipment and storage medium | |
| US10636438B2 (en) | Method, information processing apparatus for processing speech, and non-transitory computer-readable storage medium | |
| CN115310574A (en) | Motion counting method and device, electronic equipment and computer readable medium | |
| US11004463B2 (en) | Speech processing method, apparatus, and non-transitory computer-readable storage medium for storing a computer program for pitch frequency detection based upon a learned value | |
| EP1489597A2 (en) | Voice detection device | |
| CN101853262A (en) | Voice frequency fingerprint rapid searching method based on cross entropy | |
| CN116594057B (en) | Earthquake early warning method and device based on deep learning and edge calculation | |
| CN115063402B (en) | Cable foreign matter detection method, system, terminal and medium based on sliding analysis | |
| KR101294405B1 (en) | Method for voice activity detection using phase shifted noise signal and apparatus for thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |