CN114052677B - Pulse wave beat quality evaluation method, device, computer equipment and storage medium - Google Patents
Pulse wave beat quality evaluation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114052677B CN114052677B CN202111375476.XA CN202111375476A CN114052677B CN 114052677 B CN114052677 B CN 114052677B CN 202111375476 A CN202111375476 A CN 202111375476A CN 114052677 B CN114052677 B CN 114052677B
- Authority
- CN
- China
- Prior art keywords
- pulse wave
- beat
- evaluated
- wave beat
- beats
- 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.)
- Active
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Cardiology (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The application relates to a pulse wave beat quality assessment method, a pulse wave beat quality assessment device, computer equipment and a storage medium. The method comprises the following steps: acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window, and determining the number of the correlation coefficients larger than a first threshold value; determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold; generating a target pulse wave beat according to the candidate beat; and evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated. By adopting the method, the accuracy of the obtained evaluation result of the pulse wave beat to be evaluated can be improved.
Description
Technical Field
The present disclosure relates to the field of wearable devices, and in particular, to a pulse wave beat quality evaluation method, apparatus, computer device, and storage medium.
Background
Along with the rapid development of mobile internet technology, wearable devices are increasingly different day by day, so as to meet the increasing demands of modern people on health, various wearable devices are successively provided with health tracking functions capable of collecting pulse wave beats of users, and accordingly vital sign data (such as heart rate, blood oxygen saturation and the like) of the users are analyzed by utilizing the pulse wave beats. However, the wavelength light source commonly used in the wearable device at present has weak anti-interference capability and is easily affected by interference signals introduced by bad wearing, motion artifacts and the like, so that the quality of the acquired pulse beat signal is poor, and therefore, in order to better analyze vital sign data of a user, pulse wave beats with good signal quality need to be screened for analysis.
In the traditional technology, the signal quality of the pulse wave beat is judged and screened mainly based on predefined template matching and waveform parameters, so that the pulse wave beat with better signal quality is determined. However, the current signal quality judging method for pulse wave beat has the problem of lower judging accuracy.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a pulse wave beat quality evaluation method, apparatus, computer device, and storage medium capable of improving the accuracy of signal quality judgment of pulse wave beats.
A pulse wave beat quality assessment method, the method comprising:
acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window, and determining the number of the correlation coefficients larger than a first threshold value;
determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold;
generating a target pulse wave beat according to the candidate beat;
and evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated.
In one embodiment, the preset number threshold includes a first number threshold and a second number threshold; the first number threshold is greater than the second number threshold; the determining the candidate beat from the initial pulse wave beats according to the number and the preset number threshold value comprises the following steps:
If the number is greater than the first number threshold, determining the initial pulse wave beats corresponding to the correlation coefficients greater than the first threshold as the candidate beats;
if the number is greater than the second number threshold, acquiring the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient greater than the first threshold, and determining the candidate beat from the initial pulse wave beats according to the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient greater than the first threshold.
In one embodiment, the determining the candidate beat from the initial pulse wave beats according to the feature value of the initial pulse wave beat in which each correlation coefficient is greater than the first threshold value includes:
acquiring variation coefficients of the characteristic values according to the characteristic values of the initial pulse wave beats corresponding to the correlation coefficients larger than a first threshold;
and if the variation coefficient of each characteristic value is smaller than a second threshold value, determining the initial pulse wave beat corresponding to each correlation coefficient larger than a first threshold value as the candidate beat.
In one embodiment, the estimating the quality of the pulse wave beat to be estimated according to the target pulse wave beat, to obtain the estimation result of the pulse wave beat to be estimated includes:
Comparing the similarity between the pulse wave beat to be evaluated and the target pulse wave beat to obtain the similarity between the pulse wave beat to be evaluated and the target pulse wave beat;
and obtaining an evaluation result of the pulse wave beat to be evaluated according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat.
In one embodiment, the obtaining the evaluation result of the pulse wave beat to be evaluated according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat includes:
and if the similarity between the pulse wave beat to be evaluated and the target pulse wave beat is greater than a third threshold value, determining that the evaluation result of the pulse wave beat to be evaluated is passing.
If the similarity between the pulse wave beat to be evaluated and the target pulse wave beat is larger than a fourth threshold value, calculating a variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat, and obtaining an evaluation result of the pulse wave beat to be evaluated according to the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat; wherein the third threshold is greater than the fourth threshold.
In one embodiment, the obtaining the evaluation result of the pulse wave beat to be evaluated according to the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat includes:
and if the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat is smaller than a fifth threshold value, determining that the evaluation result of the pulse wave beat to be evaluated is passing.
In one embodiment, the method further comprises:
if the evaluation result of the pulse wave beat to be evaluated is passing, calculating vital sign parameters of the user corresponding to the pulse wave beat to be evaluated by using the pulse wave beat to be evaluated.
A pulse beat quality assessment device, the device comprising:
the acquisition module is used for acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window and determining the quantity of each correlation coefficient larger than a first threshold value;
the determining module is used for determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold;
the generation module is used for generating a target pulse wave beat according to the candidate beat;
the evaluation module is used for evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window, and determining the number of the correlation coefficients larger than a first threshold value;
determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold;
generating a target pulse wave beat according to the candidate beat;
and evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window, and determining the number of the correlation coefficients larger than a first threshold value;
determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold;
generating a target pulse wave beat according to the candidate beat;
And evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated.
According to the pulse wave beat quality evaluation method, the device, the computer equipment and the storage medium, the number of initial pulse wave beats with each correlation coefficient larger than the first threshold can be determined by acquiring the correlation coefficient between at least two adjacent initial pulse wave beats in the preset time window, so that candidate beats can be determined from the initial pulse wave beats according to the number of the initial pulse wave beats with each correlation coefficient larger than the first threshold and the preset number threshold, pulse wave beats with high or low signal quality can be respectively identified, the pulse wave beats with serious interference are removed, the candidate beats with high signal quality are obtained, then a target pulse wave beat with high signal quality can be generated according to the candidate beats, and further the quality of the pulse wave beat to be evaluated can be accurately evaluated according to the target pulse wave beat, so that the accuracy of the evaluation result of the obtained pulse wave beat to be evaluated is improved.
Drawings
FIG. 1 is a diagram of an application environment of a pulse wave beat quality assessment method in one embodiment;
FIG. 1a is a schematic diagram of pulse wave beat morphology of high signal quality acquired in one embodiment;
FIG. 1b is a schematic diagram of pulse wave beat morphology with noise disturbance acquired in one embodiment;
FIG. 2 is a flowchart of a pulse wave beat quality evaluation method according to an embodiment;
FIG. 2a is a schematic diagram of a predetermined time window according to one embodiment;
FIG. 2b is a schematic diagram of candidate beats in an embodiment;
FIG. 2c is a schematic diagram of a target pulse wave beat in one embodiment;
FIG. 3 is a flowchart of a pulse wave beat quality evaluation method according to another embodiment;
FIG. 4 is a flowchart of a pulse wave beat quality evaluation method according to another embodiment;
FIG. 5 is a flowchart of a pulse wave beat quality evaluation method according to another embodiment;
FIG. 6 is a flowchart of a pulse wave beat quality evaluation method according to another embodiment;
FIG. 7 is a flowchart of a pulse wave beat quality evaluation method according to another embodiment;
FIG. 8 is a diagram illustrating variation differences in pulse node beat waveforms for people of different ages according to an embodiment;
FIG. 9 is a schematic diagram of the construction of a pulse wave beat characteristic parameter data set according to one embodiment;
Fig. 10 is a block diagram of a pulse wave beat quality evaluation device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The pulse wave beat quality evaluation method provided by the application can be applied to computer equipment shown in fig. 1. The computer device comprises a processor, a memory, and a computer program stored in the memory, wherein the processor is connected through a system bus, and when executing the computer program, the processor can execute the steps of the method embodiments described below. Optionally, the computer device may further comprise a network interface, a display screen and an input means. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, which stores an operating system and a computer program, an internal memory. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. Optionally, the computer device may be a server, may be a personal computer, may also be a personal digital assistant, may also be other terminal devices, such as a tablet computer, a mobile phone, etc., and may also be a cloud or remote server.
First, before the technical solution of the embodiments of the present application is specifically described, a description is first given of a technical background or a technical evolution context on which the embodiments of the present application are based. With the rapid development of mobile internet technology, the attention and the demand of wearable devices are continuously improved, and in order to meet the increasing demands of modern people on health, various wearable devices sequentially push out health tracking functions capable of detecting vital sign data (such as heart rate, blood oxygen saturation and the like) of users. At present, a reflection type photoelectric sensor is mostly adopted in a measuring method of the vital sign data of the user by the wearable equipment, for example, the wearable equipment has a blood oxygen saturation measuring function, generally, red light with the wavelength of 660nm and near infrared light with the wavelength of 940nm are used as incident light sources, and the blood oxygen saturation is calculated by measuring the light transmission intensity of tissues of a part; for example, the wearable device has heart rate measurement function, and usually uses 550nm green light as an incident light source to calculate heart rate. However, the wavelength light source commonly used in the wearable device has weak anti-interference capability, is easily affected by interference signals introduced by bad wearing, motion artifacts and the like, so that the quality of the acquired pulse node beat signals is poor, and accurate heart rate, blood oxygen saturation and the like are not easy to detect. In addition, because the factors such as skin colors, blood vessels and environments of different people are different, the pulse wave beat amplitude and the morphology of the pulse wave collected by the wearable device are also different, and in general, the pulse wave beat with high signal quality collected by the wearable device is basically as shown in fig. 1 a; while the signals subject to noise interference are of different morphologies, as shown in fig. 1 b.
The technical solutions related to the embodiments of the present application are described below in conjunction with the scenarios applied by the embodiments of the present application.
In one embodiment, as shown in fig. 2, a pulse wave beat quality evaluation method is provided, and the method is applied to the computer device in fig. 1 for illustration, and includes the following steps:
s201, obtaining correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window, and determining the number of the correlation coefficients larger than a first threshold value.
The preset time window may be an area as shown in fig. 2a, and at least two adjacent initial pulse wave beats in the preset time window may be beats formed by three adjacent nodes as shown in fig. 2 a. Optionally, in this embodiment, the computer device may use a pearson correlation coefficient calculation method to obtain a correlation coefficient between at least two adjacent initial pulse wave beats in the preset time window, or use another correlation coefficient calculation method to obtain a correlation coefficient between at least two adjacent initial pulse wave beats in the preset time window, which is not limited herein. Alternatively, in this embodiment, the first threshold may be 0.9, or may be another value, where the value of the first threshold is not limited in this embodiment. For example, the number of adjacent initial pulse wave beats in the preset time window is 5 beats, and the correlation coefficients among the 5 adjacent beats acquired by the computer device are 1.0, 0.8, 1.2 and 0.6, and then the number of the correlation coefficients among the five adjacent beats is 2, wherein the number is greater than the first threshold value 0.9. Alternatively, when determining that the number of correlation coefficients is greater than the first threshold, the computer device may first order the correlation coefficients in order from greater to lesser or from lesser to greater, and determine, using the ordered correlation coefficients, the number of correlation coefficients greater than the first threshold.
S202, determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold.
Specifically, in this embodiment, the computer device compares the number of the determined correlation coefficients greater than the first threshold with a preset number threshold, and determines the candidate beat from the initial pulse wave beats according to the comparison result. For example, if the number of the correlation coefficients is greater than the first threshold value and greater than a preset number threshold value, the computer device determines the initial pulse wave beats as candidate beats, or extracts an initial pulse wave beat having a specific characteristic from the initial pulse wave beats as the candidate beats.
S203, generating a target pulse wave beat according to the candidate beat.
Alternatively, the computer device may perform normalized weighted average processing on the candidate beats, and generate a target pulse wave beat. Here, the normalization weighted average processing performed on the candidate beats refers to performing normalization processing on the candidate beats to obtain normalized candidate beats, and then performing weighted average processing on the normalized candidate beats to generate the target pulse wave beats. For example, as shown in fig. 2b, the target pulse wave beat generated by performing the normalized weighted average processing on the determined candidate beat may be shown in fig. 2c, where the vertical axis in fig. 2b and the vertical axis in fig. 2c both represent the amplitude of the pulse wave beat.
S204, evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated.
Specifically, the computer device may evaluate the quality of the pulse wave beat to be evaluated with the target pulse wave beat as a standard, to obtain an evaluation result of the pulse wave beat to be evaluated. Optionally, the computer device may obtain a similarity between the target pulse wave beat and the pulse wave beat to be evaluated, and evaluate the quality of the pulse wave beat to be evaluated according to the similarity; alternatively, the computer device may acquire a difference between the target pulse wave beat and the pulse wave beat to be evaluated, and evaluate the quality of the pulse wave beat to be evaluated according to the difference.
According to the pulse wave beat quality evaluation method, the number of initial pulse wave beats with each correlation coefficient larger than the first threshold can be determined by acquiring the correlation coefficient between adjacent initial pulse wave beats in the preset time window, so that candidate beats can be determined from the initial pulse wave beats according to the number of the initial pulse wave beats with each correlation coefficient larger than the first threshold and the preset number threshold, pulse wave beats with high or low signal quality can be respectively identified, the pulse wave beats with serious interference are removed, the candidate beats with high signal quality are obtained, normalization processing and/or weighted average processing are carried out on the candidate beats, the target pulse wave beats (target templates) with high signal quality can be generated, and further the quality of the pulse wave beats to be evaluated can be accurately evaluated according to the target pulse wave beats, so that the accuracy of the evaluation result of the obtained pulse wave beats to be evaluated is improved.
Further, the preset number threshold includes a first number threshold and a second number threshold, where the first number threshold is greater than the second number threshold, and in one embodiment, as shown in fig. 3, the step S202 includes:
and S301, if the number value is larger than the first number threshold, determining the initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold as a candidate beat.
Specifically, if the number of correlation coefficients between adjacent initial pulse wave beats within the preset time window is greater than the first threshold value and is greater than the first number threshold value, the computer device determines an initial pulse wave beat corresponding to the correlation coefficient between adjacent initial pulse wave beats within the preset time window being greater than the first threshold value as a candidate beat. For example, the first number threshold may be 3 x (N-1)/4, where N is the length of the sequence of adjacent initial pulse wave beats in the preset time window, that is, if the number of correlation coefficients between adjacent initial pulse beats in the preset time window is greater than 3 x (N-1)/4, the computer device determines, as the candidate beats, the initial pulse wave beats corresponding to the correlation coefficients between adjacent initial pulse wave beats in the preset time window being greater than the first threshold.
S302, if the number is larger than the second number threshold, obtaining the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold, and determining the candidate beat from the initial pulse wave beat according to the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold.
Specifically, if the number of correlation coefficients between adjacent initial pulse wave beats in the preset time window is greater than the first threshold and is greater than the second threshold, the computer device obtains the characteristic value of the initial pulse wave beat corresponding to the correlation coefficient between the adjacent initial pulse wave beats in the preset time window which is greater than the first threshold, and determines a candidate beat from the initial pulse wave beats according to the characteristic values of the initial pulse wave beats corresponding to the correlation coefficients which are greater than the first threshold. For example, the second number of thresholds may be 2 x (N-1)/4, where N is the length of the adjacent initial pulse wave beat sequence in the preset time window, that is, if the number of correlation coefficients between adjacent initial pulse wave beats in the preset time window is greater than 2 x (N-1)/4, the computer device obtains a characteristic value of the initial pulse wave beat corresponding to the correlation coefficient between adjacent initial pulse wave beats in the preset time window greater than the first threshold, and determines a candidate beat from the initial pulse wave beats according to the characteristic value. Optionally, the computer device may obtain the variation coefficient of each feature value according to the feature value of the initial pulse wave beat corresponding to the correlation coefficient between adjacent initial pulse wave beats in the preset time window being greater than the first threshold, and if the variation coefficient of each feature value is smaller than the second threshold, the computer device determines the initial pulse wave beat corresponding to the correlation coefficient between adjacent initial pulse wave beats in the preset time window being greater than the first threshold as the candidate beat. For example, the computer device may obtain the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient greater than the first threshold according to the following formula:
X in the above formulas (1) - (4) max Representing the maximum amplitude value, x, of each initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold value min Representing the minimum amplitude of each initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold value, x i Indicating the amplitude of each initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold,representing the average value of the beat amplitudes of the initial pulse waves corresponding to the correlation coefficients being greater than the first threshold value, sigma represents the variance of the beat amplitudes of the initial pulse waves corresponding to the correlation coefficients being greater than the first threshold value, N represents the number of the beats of the initial pulse waves corresponding to the correlation coefficients being greater than the first threshold value, and sigma represents the variance of the beat amplitudes of the initial pulse waves corresponding to the correlation coefficients being greater than the first threshold value>And taking norms from the average value of the amplitude of each initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold value. Alternatively, the computer device may obtain the coefficient of variation of each characteristic value according to the following formula: cv= |x i -x m |/x m Wherein CV represents the coefficient of variation of each characteristic value, x i Representing the deviation, x, of each initial pulse wave beat corresponding to each correlation coefficient greater than a first threshold m And the average value of the skewness of each initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold value is shown.
In this embodiment, if the number of correlation coefficients between adjacent initial pulse wave beats in the preset time window is greater than the first threshold, the computer device determines the initial pulse wave beat corresponding to the correlation coefficient between adjacent initial pulse wave beats in the preset time window being greater than the first threshold as a candidate beat, and if the number of correlation coefficients between adjacent initial pulse wave beats in the preset time window being greater than the first threshold is greater than the second threshold, the computer device obtains a characteristic value of the initial pulse wave beat corresponding to the correlation coefficient between adjacent initial pulse wave beats in the preset time window being greater than the first threshold, and determines the candidate beat from the initial pulse wave beats corresponding to the correlation coefficient between adjacent initial pulse wave beats in the preset time window being greater than the first threshold according to the characteristic value of the initial pulse wave beat corresponding to the correlation coefficient between adjacent initial pulse wave beats in the preset time window being greater than the first threshold.
In the scenario where the quality of the pulse wave beat to be evaluated is evaluated according to the target pulse wave beat to obtain the evaluation result of the pulse wave beat to be evaluated, as shown in fig. 4, S204 includes:
S401, comparing the similarity between the pulse wave beat to be evaluated and the target pulse wave beat to obtain the similarity between the pulse wave beat to be evaluated and the target pulse wave beat.
Specifically, the computer equipment compares the similarity between the pulse wave beat to be evaluated and the target pulse wave beat to obtain a correlation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat, and obtains the similarity between the pulse wave beat to be evaluated and the target pulse wave beat according to the correlation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat. Optionally, the computer device may calculate any one of a Jaccard correlation coefficient, a cosine similarity, a pearson correlation coefficient, and a euclidean distance between the pulse wave beat to be evaluated and the target pulse wave beat, to obtain a similarity between the pulse wave beat to be evaluated and the target pulse wave beat.
S402, according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat, an evaluation result of the pulse wave beat to be evaluated is obtained.
Specifically, the computer device evaluates the quality of the pulse wave beat to be evaluated according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat, and obtains an evaluation result of the pulse wave beat to be evaluated. Alternatively, if to be evaluated If the similarity between the pulse wave beat and the target pulse wave beat is larger than a third threshold value, the computer equipment determines that the evaluation result of the pulse wave beat to be evaluated is passing; if the similarity between the pulse wave beat to be evaluated and the target pulse wave beat is larger than a fourth threshold value, the computer equipment calculates a variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat, and an evaluation result of the pulse wave beat to be evaluated is obtained according to the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat, wherein the third threshold value is larger than the fourth threshold value. Further, the process of obtaining the evaluation result of the pulse wave beat to be evaluated by the computer device according to the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat may include: if the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat is smaller than the fifth threshold value, determining that the evaluation result of the pulse wave beat to be evaluated is passing. Optionally, if the similarity between the pulse wave beat to be evaluated and the target pulse wave beat is greater than a third threshold, the computer device may further update the target pulse wave beat according to a preset rule, where the preset rule may be a formula: templite obj ＝0.9×Template obj +0.1×PPG seg In the formula, PPG seg Representing the pulse wave beat of the target sample obj Representing the updated target pulse wave beat.
In this embodiment, the computer device compares the similarity between the pulse wave beat to be evaluated and the target pulse wave beat, so that the similarity between the pulse wave beat to be evaluated and the target pulse wave beat can be accurately obtained, and further, according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat, the evaluation result of the pulse wave beat to be evaluated can be accurately obtained, and the accuracy of obtaining the evaluation result of the pulse wave beat to be evaluated is improved.
Further, on the basis of the foregoing embodiment, in one embodiment, the foregoing method further includes: if the evaluation result of the pulse wave beat to be evaluated is passing, calculating vital sign parameters of the user corresponding to the pulse wave beat to be evaluated by using the pulse wave beat to be evaluated.
Specifically, if the computer device determines that the evaluation result of the pulse wave beat to be evaluated is passing, the computer device calculates vital sign parameters of the user corresponding to the pulse beat to be evaluated by using the pulse beat to be evaluated. Optionally, the vital sign parameters of the user may include parameters such as blood oxygen saturation, pulse rate, heart Rate Variability (HRV), etc. It can be understood that the pulse node beat waveform coefficient can reflect the change of physiological parameters such as the peripheral resistance of the blood vessel of the human body and the elasticity of the blood vessel wall, and the change of the physiological parameters such as the peripheral resistance of the blood vessel of the human body and the elasticity of the blood vessel wall can be obtained through the waveform coefficient of the pulse wave beat to be evaluated.
In this embodiment, if the evaluation result of the pulse wave beat to be evaluated is passing, the computer device may rapidly calculate the vital sign parameter of the user corresponding to the pulse node beat to be evaluated by using the pulse wave beat to be evaluated, and the calculation process is relatively simple, so that the efficiency of obtaining the vital sign parameter of the user corresponding to the pulse node beat to be evaluated is improved.
It should be noted that, in the foregoing embodiments, a signal with a slightly stronger anti-interference in a multi-wavelength light source of a wearable device is generally adopted as a reference signal, and a complete flow of the pulse wave beat quality evaluation method provided in the embodiments of the present application may be described with reference to fig. 5 to 6, where, as shown in fig. 5, in one embodiment, the generation process of the target template may include:
s1, forming a pulse wave signal of a target area;
s2, counting the pulse node beats in the target area;
s3, if the number of pulse node beats in the target area is larger than N, calculating correlation coefficients [ coeff (1), … …, coeff (N-1) ] of adjacent beats;
s4, sequentially comparing whether the correlation coefficient of the adjacent beats is larger than a first set threshold value, and if the correlation coefficient of the adjacent beats is larger than the first set threshold value, determining whether the number M of beats with the correlation coefficient of the adjacent beats larger than the first set threshold value is larger than 3 (N-1)/4;
S5, if the number M of beats with the correlation coefficient of adjacent beats being larger than the first set threshold is larger than 3 (N-1)/4, taking all pulse wave beats (number M) larger than the first set threshold as candidate beats of the template to be formed, and carrying out normalization weighted average processing to generate a target template;
and S6, if the number M of beats with the correlation coefficient larger than the first set threshold is smaller than 3 (N-1)/4, determining whether the number M of beats with the correlation coefficient larger than the first set threshold is larger than 2 (N-1)/4, if so, taking all pulse wave beats (number M) larger than the first set threshold as candidate beats of the template to be formed, calculating characteristic values of all the candidate beats, counting various dimension result variation coefficient sequences [ CV (1), … … CV (K) ], sequentially comparing whether various dimension result variation coefficient sequences are smaller than a second set threshold, if so, comparing the number of the various dimension result variation coefficient sequences smaller than the second set threshold with K, if so, determining the initial pulse wave beats corresponding to the various dimension result variation coefficient sequences smaller than the second set threshold as candidate beats, and carrying out normalized weighted average processing to generate a target template.
As shown in fig. 6, in one embodiment, the process of the vital sign parameter calculation update method may include:
s1, if the target template does not exist, generating the target template;
s2, calculating a target template characteristic value sequence [ Fea (1), … …, fea (n) ], comparing the similarity of a single pulse wave beat with a target template, judging whether the similarity of the single pulse wave beat and the target template is larger than a third set threshold, calculating vital sign parameters by using the beat and updating the target template if the similarity of the single pulse wave beat and the target template is larger than the third set threshold, determining whether the similarity of the single pulse wave beat and the target template is larger than a fourth set threshold if the similarity of the single pulse wave beat and the target template is smaller than the third set threshold, calculating a result variation coefficient sequence [ CV (1), … … CV (K) ] between the characteristic value of the beat and the characteristic value of the target template if the similarity of the single pulse wave beat and the target template is larger than the third set threshold, and sequentially comparing whether the result variation coefficient between the characteristic value of the beat and the characteristic value of the target template is smaller than the fifth set threshold if the result variation coefficient between the characteristic value of the beat and the characteristic value of the target template is smaller than the fifth set threshold and K, and if the result variation coefficient between the characteristic value of the beat and the characteristic value of the target template is not equal to the fifth set threshold, and the vital sign is not equal to each other, and if the result variation coefficient is not equal to the characteristic is not equal to the calculated.
It should be noted that, the descriptions of fig. 5 to 6 may be referred to the descriptions related to the above embodiments, and the effects thereof are similar, which is not repeated here.
Optionally, as an implementation manner, the pulse wave beat quality evaluation method provided in the embodiment of the present application may also apply a two-way wavelength signal. If the target templates of the single-path wavelength signals are respectively generated aiming at infrared light and red light; then calculating the correlation coefficient between the single beat of the infrared light pulse wave and the target template and the correlation coefficient between the single beat of the red light pulse wave and the target template; when the correlation coefficients are both greater than the set threshold (the thresholds of the two-path wavelength signals can be set respectively), the vital sign parameters are calculated and updated by using the pulse wave node beat, if not, the beat is discarded, and the specific implementation flow of the pulse wave beat quality evaluation method of the two-path wavelength signals is described in fig. 7. As shown in fig. 7, there is provided a signal processing method of a wearable device, the method applying processing of a two-way wavelength signal, the two-way wavelength signal including an infrared light signal and a red light signal, the processing process may include:
s1, aiming at infrared light, judging whether a target template exists, if the target template does not exist, generating the target template, comparing the similarity between the single infrared light pulse wave beat and the target template, judging whether the similarity between the single infrared light pulse wave beat and the target template is larger than a set threshold, if so, calculating vital sign parameters by using the infrared light pulse wave beat two-way wavelength signal and updating the template, and if not, discarding the beat and not incorporating calculation update.
S1, aiming at red light, judging whether a target template exists, if the target template does not exist, generating the target template, comparing the similarity between the single red light pulse wave beat and the target template, judging whether the similarity between the single red light pulse wave beat and the target template is larger than a set threshold, if so, calculating vital sign parameters by using the red light pulse wave beat two-way wavelength signal and updating the template, and if not, discarding the beat and not incorporating calculation update.
It should be noted that, for the description of fig. 7, reference may be made to the description related to the above embodiment, and the effects are similar, which is not repeated here.
In addition, as an implementation manner, the generated target pulse wave beats may be transmitted to a remote server to establish a personal pulse beat template library, as shown in fig. 8, which shows variation differences of pulse beat waveforms of people of different age groups, and pulse beat waveform coefficients may reflect variation of physiological parameters such as peripheral resistance of blood vessels and elasticity of blood vessel walls of human bodies, so that further deep blood vessel variation analysis may be further completed based on the pulse wave beat waveform coefficients K a See formula (i): Wherein P is m Mean value of pulse wave beat waveform, P d Trough value, P representing pulse wave beat waveform s Representing the peak value of the pulse wave beat waveform.
Further, as shown in fig. 9, by establishing a pulse wave beat template library, the pulse wave beat characteristic parameter data set can be constructed, if an App or a web page end data input interface is used, the vital sign parameter data set can also be constructed by acquiring personal health index values measured by other professional medical equipment, such as blood pressure, blood sugar and the like; the implementation application of the comprehensive evaluation algorithm for personal health management at the server side is further mined by combining the construction of the two data sets. Meanwhile, a related template display module can be built on the basis of the pulse wave beat template library of the remote server, and the related template display module comprises template display, template analysis result display and the like.
It should be understood that, although the steps in the flowcharts of fig. 2-9 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps of fig. 2-9 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 10, there is provided a pulse wave beat quality assessment device comprising: the device comprises an acquisition module, a determination module, a generation module and an evaluation module, wherein:
the acquisition module is used for acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window and determining the number of the correlation coefficients larger than a first threshold value.
And the determining module is used for determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold.
And the generating module is used for generating the target pulse wave beat according to the candidate beat.
The evaluation module is used for evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated.
The pulse wave beat quality evaluation device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the preset number threshold includes a first number threshold and a second number threshold; the first number threshold is greater than the second number threshold; the determining module includes: a first determination unit and a second determination unit, wherein:
And the first determining unit is used for determining the initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold value as a candidate beat if the number is larger than the first number threshold value.
And the second determining unit is used for acquiring the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold value if the number is larger than the second number threshold value, and determining the candidate beat from the initial pulse wave beat according to the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold value.
The pulse wave beat quality evaluation device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the second determining unit is configured to obtain a variation coefficient of each feature value according to a feature value of an initial pulse wave beat corresponding to each correlation coefficient being greater than a first threshold; if the variation coefficient of each characteristic value is smaller than the second threshold value, determining the initial pulse wave beat corresponding to each correlation coefficient larger than the first threshold value as a candidate beat.
The pulse wave beat quality evaluation device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the above evaluation module includes: a comparison unit and an evaluation unit, wherein:
and the comparison unit is used for comparing the similarity between the pulse wave beat to be evaluated and the target pulse wave beat to obtain the similarity between the pulse wave beat to be evaluated and the target pulse wave beat.
The evaluation unit is used for obtaining an evaluation result of the pulse wave beat to be evaluated according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat.
The pulse wave beat quality evaluation device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the evaluation unit is configured to determine that an evaluation result of the pulse wave beat to be evaluated is passing if a similarity between the pulse wave beat to be evaluated and the target pulse wave beat is greater than a third threshold; if the similarity between the pulse wave beat to be evaluated and the target pulse wave beat is larger than a fourth threshold value, calculating a variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat, and obtaining an evaluation result of the pulse wave beat to be evaluated according to the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat; wherein the third threshold is greater than the fourth threshold.
The pulse wave beat quality evaluation device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the foregoing embodiment, optionally, the evaluation unit is configured to determine that the evaluation result of the pulse wave beat to be evaluated is passing if a variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat is smaller than a fifth threshold.
The pulse wave beat quality evaluation device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the above apparatus further includes: a computing module, wherein:
the calculation module is used for calculating vital sign parameters of the user corresponding to the pulse beat to be evaluated by using the pulse beat to be evaluated if the evaluation result of the pulse beat to be evaluated is passing.
The pulse wave beat quality evaluation device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
For specific limitations on the pulse wave beat quality assessment device, reference may be made to the above limitations on the pulse beat quality assessment method, and no further description is given here. The respective modules in the above-described pulse wave beat quality evaluation device may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window, and determining the number of the correlation coefficients larger than a first threshold value;
determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold;
generating a target pulse wave beat according to the candidate beat;
and evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated.
The computer device provided in the foregoing embodiments has similar implementation principles and technical effects to those of the foregoing method embodiments, and will not be described herein in detail.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window, and determining the number of the correlation coefficients larger than a first threshold value;
determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold;
Generating a target pulse wave beat according to the candidate beat;
and evaluating the quality of the pulse wave beat to be evaluated according to the target pulse wave beat to obtain an evaluation result of the pulse wave beat to be evaluated.
The computer readable storage medium provided in the above embodiment has similar principle and technical effects to those of the above method embodiment, and will not be described herein.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (9)
1. A pulse wave beat quality assessment method, the method comprising:
acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window, and determining the number of the correlation coefficients larger than a first threshold value;
determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold;
Generating a target pulse wave beat according to the candidate beat;
comparing the similarity between the pulse wave beat to be evaluated and the target pulse wave beat to obtain the similarity between the pulse wave beat to be evaluated and the target pulse wave beat;
and obtaining an evaluation result of the pulse wave beat to be evaluated according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat.
2. The method of claim 1, wherein the preset quantity threshold comprises a first quantity threshold and a second quantity threshold; the first number threshold is greater than the second number threshold; the determining the candidate beat from the initial pulse wave beats according to the number and the preset number threshold value comprises the following steps:
if the number is greater than the first number threshold, determining the initial pulse wave beats corresponding to the correlation coefficients greater than the first threshold as the candidate beats;
if the number is greater than the second number threshold, acquiring the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient greater than the first threshold, and determining the candidate beat from the initial pulse wave beats according to the characteristic value of the initial pulse wave beat corresponding to each correlation coefficient greater than the first threshold.
3. The method according to claim 2, wherein the determining the candidate beats from the initial pulse wave beats based on the feature values of the initial pulse wave beats for which each of the correlation coefficients is greater than a first threshold value includes:
acquiring variation coefficients of the characteristic values according to the characteristic values of the initial pulse wave beats corresponding to the correlation coefficients larger than a first threshold;
and if the variation coefficient of each characteristic value is smaller than a second threshold value, determining the initial pulse wave beat corresponding to each correlation coefficient larger than a first threshold value as the candidate beat.
4. The method according to claim 1, wherein the obtaining the evaluation result of the pulse wave beat to be evaluated according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat includes:
if the similarity between the pulse wave beat to be evaluated and the target pulse wave beat is greater than a third threshold value, determining that the evaluation result of the pulse wave beat to be evaluated is passing;
if the similarity between the pulse wave beat to be evaluated and the target pulse wave beat is larger than a fourth threshold value, calculating a variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat, and obtaining an evaluation result of the pulse wave beat to be evaluated according to the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat; wherein the third threshold is greater than the fourth threshold.
5. The method according to claim 4, wherein the obtaining the evaluation result of the pulse wave beat to be evaluated according to the coefficient of variation between the pulse wave beat to be evaluated and the target pulse wave beat includes:
and if the variation coefficient between the pulse wave beat to be evaluated and the target pulse wave beat is smaller than a fifth threshold value, determining that the evaluation result of the pulse wave beat to be evaluated is passing.
6. The method according to any one of claims 4-5, further comprising:
if the evaluation result of the pulse wave beat to be evaluated is passing, calculating vital sign parameters of the user corresponding to the pulse wave beat to be evaluated by using the pulse wave beat to be evaluated.
7. A pulse beat quality assessment device, the device comprising:
the acquisition module is used for acquiring correlation coefficients between at least two adjacent initial pulse wave beats in a preset time window and determining the quantity of each correlation coefficient larger than a first threshold value;
the determining module is used for determining candidate beats from the initial pulse wave beats according to the number and a preset number threshold;
The generation module is used for generating a target pulse wave beat according to the candidate beat;
the evaluation module is used for comparing the similarity between the pulse wave beat to be evaluated and the target pulse wave beat to obtain the similarity between the pulse wave beat to be evaluated and the target pulse wave beat; and obtaining an evaluation result of the pulse wave beat to be evaluated according to the similarity between the pulse wave beat to be evaluated and the target pulse wave beat.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111375476.XA CN114052677B (en) | 2021-11-19 | 2021-11-19 | Pulse wave beat quality evaluation method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111375476.XA CN114052677B (en) | 2021-11-19 | 2021-11-19 | Pulse wave beat quality evaluation method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114052677A CN114052677A (en) | 2022-02-18 |
| CN114052677B true CN114052677B (en) | 2023-07-21 |
Family
ID=80278517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111375476.XA Active CN114052677B (en) | 2021-11-19 | 2021-11-19 | Pulse wave beat quality evaluation method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114052677B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019006631A1 (en) * | 2017-07-03 | 2019-01-10 | 深圳市汇顶科技股份有限公司 | Quality evaluation method and apparatus, model establishment method and module, and wearable device |
| CN109288515A (en) * | 2018-11-14 | 2019-02-01 | 东南大学 | Periodical monitoring method and device based on premature beat signal in wearable ECG signal |
| JP2020025732A (en) * | 2018-08-10 | 2020-02-20 | 株式会社東芝 | Pulse wave evaluation apparatus and pulse wave evaluation method |
| CN113558584A (en) * | 2021-06-22 | 2021-10-29 | 深圳市大数据研究院 | Pulse wave preprocessing method based on signal quality evaluation |
-
2021
- 2021-11-19 CN CN202111375476.XA patent/CN114052677B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019006631A1 (en) * | 2017-07-03 | 2019-01-10 | 深圳市汇顶科技股份有限公司 | Quality evaluation method and apparatus, model establishment method and module, and wearable device |
| JP2020025732A (en) * | 2018-08-10 | 2020-02-20 | 株式会社東芝 | Pulse wave evaluation apparatus and pulse wave evaluation method |
| CN109288515A (en) * | 2018-11-14 | 2019-02-01 | 东南大学 | Periodical monitoring method and device based on premature beat signal in wearable ECG signal |
| CN113558584A (en) * | 2021-06-22 | 2021-10-29 | 深圳市大数据研究院 | Pulse wave preprocessing method based on signal quality evaluation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114052677A (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dey et al. | InstaBP: cuff-less blood pressure monitoring on smartphone using single PPG sensor | |
| Fan et al. | Robust blood pressure estimation using an RGB camera | |
| US11357410B2 (en) | Measuring blood pressure | |
| Costa et al. | Multiscale entropy analysis of complex physiologic time series | |
| CN112200162B (en) | Non-contact heart rate measuring method, system and device based on end-to-end network | |
| Yang et al. | Estimation and validation of arterial blood pressure using photoplethysmogram morphology features in conjunction with pulse arrival time in large open databases | |
| Chen et al. | Machine learning method for continuous noninvasive blood pressure detection based on random forest | |
| US20230255503A1 (en) | Apparatus and method for estimating bio-information | |
| Schlesinger et al. | Estimation and tracking of blood pressure using routinely acquired photoplethysmographic signals and deep neural networks | |
| CN112836546A (en) | Method and device for detecting quality of physiological signal and electronic equipment | |
| Tabei et al. | A novel diversity method for smartphone camera-based heart rhythm signals in the presence of motion and noise artifacts | |
| CN112788200A (en) | Method and device for determining frequency spectrum information, storage medium and electronic device | |
| US20220192607A1 (en) | Apparatus and method for estimating blood pressure | |
| Roy et al. | BePCon: a photoplethysmography-based quality-aware continuous beat-to-beat blood pressure measurement technique using deep learning | |
| CN114052677B (en) | Pulse wave beat quality evaluation method, device, computer equipment and storage medium | |
| JP6715397B1 (en) | Data processing device, data processing method and program | |
| US20210085259A1 (en) | Apparatus and method for estimating bio-information | |
| CN112957018A (en) | Heart state detection method and device based on artificial intelligence | |
| Schmith et al. | Photoplethysmography signal quality assessment using attractor reconstruction analysis | |
| US11950891B2 (en) | Apparatus and method for estimating bio-information | |
| EP3753484A1 (en) | Apparatus and method for calibrating bio-information estimation model, and apparatus for estimating bio-information | |
| CN114557691A (en) | Non-invasive blood lipid detection method and system based on multi-wavelength PPG (photoplethysmography) signals | |
| Bizzego et al. | DBD-RCO: Derivative Based Detection and Reverse Combinatorial Optimization to improve heart beat detection for wearable devices | |
| JP2020089729A (en) | Autonomous full spectrum biometric monitoring | |
| CN112244865B (en) | Dynamic electrocardiogram analysis method, device, computer equipment and storage medium |
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 |