CN110353650B - PPG signal-based characteristic waveform extraction system - Google Patents
PPG signal-based characteristic waveform extraction system Download PDFInfo
- Publication number
- CN110353650B CN110353650B CN201910650212.7A CN201910650212A CN110353650B CN 110353650 B CN110353650 B CN 110353650B CN 201910650212 A CN201910650212 A CN 201910650212A CN 110353650 B CN110353650 B CN 110353650B
- Authority
- CN
- China
- Prior art keywords
- point
- sample
- ppg signal
- wave
- characteristic
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/02028—Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
- A61B5/0295—Measuring blood flow using plethysmography, i.e. measuring the variations in the volume of a body part as modified by the circulation of blood therethrough, e.g. impedance plethysmography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
Abstract
According to the characteristic waveform extraction system based on the PPG signal, an input unit obtains the PPG signal acquired by finger tip photoplethysmography pulse wave detection equipment; the preprocessing unit preprocesses the PPG signal to obtain a correct wave band in the PPG signal; the analysis unit respectively calculates the characteristic quantity of each correct waveband; and the clustering unit extracts the characteristic waveform of the PPG signal according to the characteristic quantity by utilizing clustering operation. The system collects the finger tip photoplethysmography pulse wave detection equipment and extracts the characteristic waveform from the preprocessed PPG signal. From the test result, the confidence coefficient of the extracted characteristic waveform is basically over 90 percent, and the accuracy of characteristic waveform extraction is improved. The characteristic waveform can help medical staff to estimate the disease severity of the tested person or infer other physical conditions; and the method can also help medical researchers to more accurately explore various properties of the pulse wave. Greatly improving the working efficiency of medical staff.
Description
Technical Field
The invention belongs to the technical field of signal processing, and particularly relates to a PPG signal-based characteristic waveform extraction system.
Background
Cardiovascular and cerebrovascular diseases have the characteristics of high morbidity, high mortality, multiple complications and the like, are the most deadly of various diseases in China, and the morbidity of cardiovascular diseases in China will have a well-spraying type sharp increase situation in the next 20 years.
The research finds that the structural and functional change of the arterial blood vessel is the root cause of the diseases, so that the early detection of the structural and functional abnormality of the blood vessel has important significance for detecting early cardiovascular diseases and intervening the change process. Photoplethysmography (PPG) is an electro-optical measurement technique for measuring the volume change of blood in human tissue, which signals interpret information about the cardiovascular system, especially the arterial vasculature. Due to the demand for prevention and treatment of cardiovascular diseases, noninvasive and accurate assessment of vascular characteristics by using PPG detection technology is a hot spot of current PPG application research. Among them, PPG morphological analysis is favored by people because of its convenient detection and clear physiological significance.
At present, no complete mechanism exists for selecting the PPG signal characteristic waveform, and the PPG signal characteristic waveform can be determined only by subjective identification. However, to ensure data accuracy and avoid accidents and errors, hardware devices usually acquire a large number of PPG signals, which may be of varying quality, and medical staff and medical researchers need to select the most representative waveforms empirically, which is too simple and lacks uniform standards and bases. Individual waveforms of a particular modality may be distracting to medical personnel and medical researchers, and they are most likely to be caused by errors, and it is not practical to analyze them. The representative waveform is selected from a plurality of correct and similar waveforms, which is time-consuming and labor-consuming, and greatly reduces the working efficiency of the hospital.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the PPG signal-based characteristic waveform extraction system, which improves the accuracy of characteristic waveform extraction and greatly improves the working efficiency of medical staff.
A PPG signal based signature extraction system, comprising:
an input unit: the device is used for obtaining a PPG signal acquired by finger tip photoplethysmography detection equipment;
a pretreatment unit: for pre-processing the PPG signal to obtain a correct band in the PPG signal;
an analysis unit: the characteristic quantities are used for respectively calculating the correct wave bands;
a clustering unit: and the characteristic waveform of the PPG signal is extracted according to the characteristic quantity by utilizing clustering operation.
Preferably, the preprocessing unit is specifically configured to:
and screening the wave bands in the PPG signal, and removing the wave bands with nonzero error codes to obtain the correct wave bands in the PPG signal.
Preferably, the feature amounts include a first feature amount K1, a second feature amount K2, and a third feature amount K;
wherein the content of the first and second substances,
in the formula, SABCThe area enclosed by the point A, the point B and the point C and a horizontal axis in the wave curve of the wave band; sAHGIThe area of a rectangle enclosed by a point A, a point H, a point G and a point I in the wave curve of the wave band; sCDEThe area enclosed by the point C, the point D and the point E and a transverse axis in the wave curve of the wave band; sIGFEThe area of a rectangle enclosed by a point I, a point G, a point F and a point E in the wave-shaped curve of the wave band;
the point A, the point B, the point C, the point D and the point E are respectively a starting point, a main wave peak, a descending isthmus, a dicrotic wave peak and an ending point in the volume pulse blood flow curve; the abscissa of the point H is 0, and the ordinate is the ordinate of the point B; the abscissa of the point I is the abscissa of the point E, and the ordinate is 0; the abscissa of the point G is the abscissa of the point C, and the ordinate is the ordinate of the point B; the abscissa of the point F is the abscissa of the point E, and the ordinate is the ordinate of the point B;
k is K1+ K2 or
In the formula (I), the compound is shown in the specification,
is the wave curve of the wave band, T is the time, T is the ending point time, QmaxIs the maximum value of said band, QminIs the minimum value of the band; sABCDEThe area enclosed by the points A, B, C, D and E and a horizontal axis in the wave curve of the wave band; sAHFEThe area of a rectangle enclosed by the points A, H, F and E in the wave curve of the wave band.
Preferably, the clustering unit is specifically configured to:
screening out a first representative parameter set S1, a second representative parameter set S2 and a third representative parameter set S corresponding to the first characteristic quantity K1, the second characteristic quantity K2 and the third characteristic quantity K in all the wave bands by using the characteristic quantities and clustering operation;
respectively recording the number sets of the wave bands corresponding to the samples in the first representative parameter set S1, the second representative parameter set S2 and the third representative parameter set S as a first number set, a second number set and a third number set;
calculating the sample center of the intersection of the first number set, the second number set and the third number set;
and extracting the characteristic waveform of the PPG signal by using the sample center of the intersection.
Preferably, the clustering unit is specifically configured to:
defining a set of the same characteristic quantity in all wave bands as a sample set, wherein each characteristic quantity is a sample;
calculating the sample center Kmid, the average value Kmed and the initial threshold sigma of each sample set; wherein sigma is 0.1 × (Kmed-Kmid);
and (3) circulating step: calculating the distance D between the sample in each sample set and the center Kmid of the sample in the sample set;
defining a set of all samples with sigma being larger than or equal to D in each sample set as a first subset corresponding to the sample set;
defining a set of all samples with sigma < D and K value of a wave band corresponding to the samples less than Kmid in each sample set as a second subset corresponding to the sample set;
defining a set of all samples with sigma < D and K value of a wave band corresponding to the samples larger than Kmid in each sample set as a third subset corresponding to the sample set;
calculating the intermediate values of all the subsets, calculating the mean value of all the intermediate values, and updating the mean value to the sample center Kmid of the sample set;
repeating the loop step until the number of samples of a subset in each sample set is more than one half of the total number of samples of the sample set, and outputting intermediate values of the subset and the subset;
obtaining a subset of sample set output corresponding to each characteristic value;
subsets of the first, second, and third feature quantities K1, K2, and K outputs are defined as a first set S1, a second set S2, and a third set S of representative parameters, respectively.
Preferably, the clustering unit is specifically configured to:
calculating the intersection of the first number set, the second number set and the third number set;
calculating a third characteristic quantity K of the intersection; defining a third characteristic quantity K of the intersection as the sample center;
calculating the sample center Kmid, the average value Kmed and the initial threshold sigma of the sample set;
re-executing the loop step to obtain a first representative parameter set S1, a second representative parameter set S2 and a third representative parameter set S of the intersection;
defining the sample centers of the first, second and third representative parameter sets S1, S2, S as the sample center of the intersection, as a first ideal value, a second ideal value and a third ideal value, respectively.
Preferably, the clustering unit is specifically configured to:
and calculating the intersection of the first number set, the second number set and the third number set, and updating the intersection into the third number set if the intersection is empty.
Preferably, the clustering unit is specifically configured to:
extracting a sample with the minimum difference value with the sample center of the third generation table parameter set from the intersected third generation table parameter set;
and defining the wave band corresponding to the sample as the characteristic waveform.
Preferably, the system further comprises:
a confidence calculation unit: for calculating the confidence C of the signature according to:
C＝0.3×V1+0.3×V2+0.4×V；
wherein, V1Is the similarity of the first eigenvalue K1 of the signature waveform to a first ideal value, V2Is the similarity of the second characteristic quantity K2 of the characteristic waveform to the second ideal value, and V is the similarity of the third characteristic quantity K of the characteristic waveform to the third ideal value.
According to the technical scheme, the characteristic waveform extraction system based on the PPG signals provided by the invention extracts the characteristic waveform of the PPG signals which are acquired by finger-end photoplethysmography detection equipment and are preprocessed. From the test result, the confidence coefficient of the extracted characteristic waveform is basically over 90 percent, and the accuracy of characteristic waveform extraction is improved. The characteristic waveform can help medical staff to estimate the disease severity of the tested person or infer other physical conditions; and the method can also help medical researchers to more accurately explore various properties of the pulse wave. Greatly improving the working efficiency of medical staff.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a block diagram of a characteristic waveform extraction system according to this embodiment.
Fig. 2 is a flowchart of a method executed by the system for extracting a characteristic waveform according to this embodiment.
Fig. 3 is a flowchart of a method executed by the clustering unit according to this embodiment.
Fig. 4 is a single waveform diagram.
Fig. 5 is the raw PPG signal without extraction.
Fig. 6 shows a characteristic waveform extracted by the system.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby. It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
Example (b):
a PPG signal-based feature waveform extraction system, see fig. 1, and fig. 2 is a flow chart of a method performed by the PPG signal-based feature waveform extraction system, including:
an input unit: the device is used for obtaining a PPG signal acquired by finger tip photoplethysmography detection equipment;
a pretreatment unit: for pre-processing the PPG signal to obtain a correct band in the PPG signal;
specifically, the finger-end photoplethysmography detection device is a conventional device for acquiring a PPG signal, where the PPG signal includes multiple bands, each band corresponds to an error code, and the error code of the correct band is 0. The system can register the correct band in the PPG signal as the set dcor. Namely, the preprocessing unit is specifically configured to: and screening the wave bands in the PPG signal, and removing the wave bands with nonzero error codes to obtain the correct wave bands in the PPG signal.
An analysis unit: the characteristic quantities are used for respectively calculating the correct wave bands;
preferably, the feature amounts include a first feature amount K1, a second feature amount K2, and a third feature amount K;
wherein the content of the first and second substances,
see FIG. 4, where SABCThe area enclosed by the point A, the point B and the point C and a horizontal axis in the wave curve of the wave band; sAHGIThe area of a rectangle enclosed by a point A, a point H, a point G and a point I in the wave curve of the wave band; sCDEThe area enclosed by the point C, the point D and the point E and a transverse axis in the wave curve of the wave band; sIGFEThe area of a rectangle enclosed by a point I, a point G, a point F and a point E in the wave-shaped curve of the wave band;
the point A, the point B, the point C, the point D and the point E are respectively a starting point, a main wave peak, a descending isthmus, a dicrotic wave peak and an ending point in the volume pulse blood flow curve; the abscissa of the point H is 0, and the ordinate is the ordinate of the point B; the abscissa of the point I is the abscissa of the point E, and the ordinate is 0; the abscissa of the point G is the abscissa of the point C, and the ordinate is the ordinate of the point B; the abscissa of the point F is the abscissa of the point E, and the ordinate is the ordinate of the point B;
k is K1+ K2 or
In the formula (I), the compound is shown in the specification,
q (T) is the wave curve of the wave band, T is time, T is the ending point time, QmaxIs the maximum value of said band, QminIs the minimum value of the band; sABCDEThe area enclosed by the points A, B, C, D and E and a horizontal axis in the wave curve of the wave band; sAHFEThe area of a rectangle enclosed by the points A, H, F and E in the wave curve of the wave band.
Specifically, the characteristic quantity K can macroscopically describe the characteristics of the volume pulse wave waveform, and can reflect the microcirculation state and the elasticity of the blood vessel wall to a certain extent. For young people with better cardiovascular function, the K value is generally smaller. K1 represents the area characteristic quantity of the systole, which reflects the changes of peripheral resistance of blood vessels, blood viscosity and the like; k2 represents a diastolic area characteristic quantity reflecting changes in peripheral resistance of blood vessels, blood viscosity, and the like.
A clustering unit: and the characteristic waveform of the PPG signal is extracted according to the characteristic quantity by utilizing clustering operation.
Referring to fig. 3, the clustering unit is specifically configured to:
s1: by utilizing the characteristic quantities, a first representative parameter set S1, a second representative parameter set S2 and a third representative parameter set S corresponding to the first characteristic quantity K1, the second characteristic quantity K2 and the third characteristic quantity K in all the wave bands are screened out by using clustering operation, and the method specifically comprises the following steps:
s11: defining a set of the same characteristic quantity in all wave bands as a sample set, wherein each characteristic quantity is a sample; that is, the first feature quantities K1 of all the bands are defined as a first sample set, the second feature quantities K2 of all the bands are defined as a second sample set, and the third feature quantities K of all the bands are defined as a third sample set.
S12: calculating the sample center Kmid, the average value Kmed and the initial threshold sigma of each sample set; wherein sigma is 0.1 × (Kmed-Kmid);
s13: and (3) circulating step: calculating the distance D between the sample in each sample set and the center Kmid of the sample in the sample set; specifically, the distance D is the absolute value of the difference between the sample and Kmid.
Defining a set of all samples with sigma being larger than or equal to D in each sample set as a first subset miu1 corresponding to the sample set;
defining a set of all samples in each sample set, wherein sigma is less than D, and the K value of the wave band corresponding to the sample is less than Kmid, as a second subset miu2 corresponding to the sample set;
defining a set of all samples in each sample set with sigma < D and K value greater than Kmid for the corresponding band of samples as a third subset miu3 corresponding to the sample set;
calculating the intermediate values of all the subsets, calculating the mean value of all the intermediate values, and updating the mean value to the sample center Kmid of the sample set;
s14: repeating the loop step S13 until there is a subset in each sample set, the number of samples in the subset is greater than one half of the total number of samples in the sample set, and the intermediate values between the subset and the subset are output;
obtaining a subset of sample set output corresponding to each characteristic value;
subsets of the first, second, and third feature quantities K1, K2, and K outputs are defined as a first set S1, a second set S2, and a third set S of representative parameters, respectively.
S2: respectively recording the number sets of the wave bands corresponding to the samples in the first representative parameter set S1, the second representative parameter set S2 and the third representative parameter set S as a first number set mark11, a second number set mark12 and a third number set mark 1;
s3: calculating the sample center of the intersection intSecMark1 of the first number set mark11, the second number set mark12 and the third number set mark 1; the method is specifically used for:
s31: calculating the intersection intSecMark1 of the first number set mark11, the second number set mark12 and the third number set mark 1; specifically, if the intersection intSecMark1 is empty, the intersection intSecMark1 is updated to the third number set.
That is, if intSecMark1 is empty, which indicates that the above extracted sets do not have an intersection, intSecMark1 is made equal to mark1 because the partial features of the waveform are stored in mark11 and mark12, and mark1 is the complete feature of the waveform, so it is reasonable to select the complete feature when there is no intersection.
S32: calculating a third characteristic quantity K of the intersection; defining a third characteristic quantity K of the intersection as the sample center;
s33: calculating the sample center Kmid, the average value Kmed and the initial threshold sigma of the sample set;
s34: the loop step S13 is re-executed: obtaining a first representative parameter set S1, a second representative parameter set S2 and a third representative parameter set S of the intersection;
s35: the sample centers of the first, second and third representative parameter sets S1, S2, S are defined as the sample center of the intersection, and are respectively defined as a first ideal value Sint1, a second ideal value Sint2 and a third ideal value Sint.
S4: and extracting the characteristic waveform of the PPG signal by using the sample center of the intersection. Specifically, in the intersected third generation table parameter set, a sample with the smallest difference with the sample center of the third generation table parameter set is extracted;
and defining the wave band corresponding to the sample as the characteristic waveform.
Specifically, the center of the obtained sample is the theoretically most representative value of K under the light intensity.
Preferably, the system further comprises:
a confidence calculation unit: for calculating the confidence C of the signature according to:
C＝0.3×V1+0.3×V2+0.4×V；
wherein, V1Is the first characteristic value K1 and the second characteristic value of the characteristic waveformSimilarity of an ideal value, V2Is the similarity of the second characteristic quantity K2 of the characteristic waveform to the second ideal value, and V is the similarity of the third characteristic quantity K of the characteristic waveform to the third ideal value.
Specifically, the system can also be provided with a confidence coefficient calculation unit for calculating the confidence coefficient of the extracted characteristic waveform. Since the first feature quantity K1, the second feature quantity K2, and the third feature quantity K are all important criteria for determining the characteristic waveform, and K represents the overall characteristics of the waveform more than K1 and K2, V1, V2, and V may be weighted by 30%, and 40%, respectively.
The system is based on a data mining technology and a K-MEANS clustering algorithm, firstly uses the systolic area characteristic quantity, the diastolic area characteristic quantity and the sum of the systolic area characteristic quantity and the diastolic area characteristic quantity of an initial signal waveform collected by hardware equipment as characteristic parameters, then carries out 2-layer clustering operation to select a representative waveform, and finally achieves the effect that the confidence coefficient of the characteristic waveform is more than 90% on average.
For example, the raw PPG signal without extraction is shown in fig. 5, 43 correct bands are collected, which are very similar in shape, and it is difficult to see their fine difference by naked eyes. The characteristic waveform extracted by the system is shown in fig. 6, and the confidence coefficient is up to 95.57%.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (4)
1. A PPG signal-based feature waveform extraction system, comprising:
an input unit: the device is used for obtaining a PPG signal acquired by finger tip photoplethysmography detection equipment;
a pretreatment unit: for pre-processing the PPG signal to obtain a correct band in the PPG signal;
an analysis unit: the characteristic quantities are used for respectively calculating the correct wave bands;
a clustering unit: the PPG signal processing device is used for extracting a characteristic waveform of the PPG signal according to the characteristic quantity by utilizing clustering operation;
a confidence calculation unit: a confidence C for calculating the characteristic waveform;
the clustering unit comprises a first clustering unit, a second clustering unit and a third clustering unit;
the first clustering unit is used for:
defining a set of the same characteristic quantity in all wave bands as a sample set, wherein each characteristic quantity is a sample;
calculating the sample center Kmid, the average value Kmed and the initial threshold sigma of each sample set; wherein sigma is 0.1 × (Kmed-Kmid);
and (3) circulating step: calculating the distance D between the sample in each sample set and the center Kmid of the sample in the sample set;
defining a set of all samples with sigma being larger than or equal to D in each sample set as a first subset corresponding to the sample set;
defining a set of all samples with sigma < D and K value of a wave band corresponding to the samples less than Kmid in each sample set as a second subset corresponding to the sample set;
defining a set of all samples with sigma < D and K value of a wave band corresponding to the samples greater than Kmid in each sample set as a third subset corresponding to the sample set;
calculating the intermediate values of all the subsets, calculating the mean value of all the intermediate values, and updating the mean value to the sample center Kmid of the sample set;
repeating the loop step until the number of samples of a subset in each sample set is more than one half of the total number of samples of the sample set, and outputting intermediate values of the subset and the subset;
obtaining a subset of sample set output corresponding to each characteristic value;
defining subsets of the first characteristic quantity K1, the second characteristic quantity K2 and the third characteristic quantity K output as a first representative parameter set S1, a second representative parameter set S2 and a third representative parameter set S, respectively;
the second type of unit is specifically used for:
respectively recording the number sets of the wave bands corresponding to the samples in the first representative parameter set S1, the second representative parameter set S2 and the third representative parameter set S as a first number set, a second number set and a third number set;
calculating the intersection of the first number set, the second number set and the third number set; calculating the intersection of the first number set, the second number set and the third number set, and if the intersection is empty, updating the intersection into the third number set;
calculating a third characteristic quantity K of the intersection; defining a third characteristic quantity K of the intersection as a sample center;
calculating the sample center Kmid, the average value Kmed and the initial threshold sigma of the intersection;
re-executing the loop step to obtain a first representative parameter set S1, a second representative parameter set S2 and a third representative parameter set S of the intersection;
defining the sample centers of the first representative parameter set S1, the second representative parameter set S2 and the third representative parameter set S as the sample center of the intersection, and respectively defining the sample centers as a first ideal value, a second ideal value and a third ideal value;
the third hierarchical unit is used for:
extracting a characteristic waveform of the PPG signal by using the sample center of the intersection;
wherein the confidence coefficient calculating unit calculates the confidence coefficient of the characteristic waveform by a formula:
C＝0.3×V1+0.3×V2+0.4×V；
in the formula, V1Is the similarity of the first eigenvalue K1 of the signature waveform to a first ideal value, V2Is the similarity of the second characteristic quantity K2 of the characteristic waveform to the second ideal value, and V is the similarity of the third characteristic quantity K of the characteristic waveform to the third ideal value.
2. The PPG signal-based feature waveform extraction system according to claim 1,
the preprocessing unit is specifically configured to:
and screening the wave bands in the PPG signal, and removing the wave bands with nonzero error codes to obtain the correct wave bands in the PPG signal.
3. The PPG signal-based feature waveform extraction system according to claim 1,
the feature amounts include a first feature amount K1, a second feature amount K2, and a third feature amount K;
wherein the content of the first and second substances,
in the formula, SABCThe area enclosed by the point A, the point B and the point C and a horizontal axis in the wave curve of the wave band; sAHGIThe area of a rectangle enclosed by a point A, a point H, a point G and a point I in the wave curve of the wave band; sCDEThe area enclosed by the point C, the point D and the point E and a transverse axis in the wave curve of the wave band; sIGFEThe area of a rectangle enclosed by a point I, a point G, a point F and a point E in the wave-shaped curve of the wave band;
the point A, the point B, the point C, the point D and the point E are respectively a starting point, a main wave peak, a descending isthmus, a dicrotic wave peak and an ending point in the volume pulse blood flow curve; the abscissa of the point H is 0, and the ordinate is the ordinate of the point B; the abscissa of the point I is the abscissa of the point E, and the ordinate is 0; the abscissa of the point G is the abscissa of the point C, and the ordinate is the ordinate of the point B; the abscissa of the point F is the abscissa of the point E, and the ordinate is the ordinate of the point B;
k is K1+ K2 or
In the formula (I), the compound is shown in the specification,
q (T) is the wave curve of the wave band, T is time, T is the ending point time, QmaxIs the maximum value of said band, QminIs the minimum value of the band; sABCDEThe area enclosed by the points A, B, C, D and E and a horizontal axis in the wave curve of the wave band; sAHFEThe area of a rectangle enclosed by the points A, H, F and E in the wave curve of the wave band.
4. The PPG signal-based feature waveform extraction system according to claim 1,
the third clustering unit is specifically used for:
extracting a sample with the minimum difference value with the sample center of the third generation table parameter set from the intersected third generation table parameter set;
and defining the wave band corresponding to the sample as the characteristic waveform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910650212.7A CN110353650B (en) | 2019-07-18 | 2019-07-18 | PPG signal-based characteristic waveform extraction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910650212.7A CN110353650B (en) | 2019-07-18 | 2019-07-18 | PPG signal-based characteristic waveform extraction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110353650A CN110353650A (en) | 2019-10-22 |
| CN110353650B true CN110353650B (en) | 2022-05-03 |
Family
ID=68221025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910650212.7A Active CN110353650B (en) | 2019-07-18 | 2019-07-18 | PPG signal-based characteristic waveform extraction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110353650B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9298739B2 (en) * | 2010-11-23 | 2016-03-29 | Nec Corporation | Position information providing apparatus, position information providing system, position information providing method, program, and recording medium |
| CN108577883A (en) * | 2018-04-03 | 2018-09-28 | 上海交通大学 | A kind of Screening for coronary artery disease device, screening system and signal characteristic extracting methods |
| CN108601527A (en) * | 2016-10-21 | 2018-09-28 | 华为技术有限公司 | The calibration method and blood pressure measurement device of blood pressure measurement device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1860993B1 (en) * | 2005-03-01 | 2019-01-23 | Masimo Laboratories, Inc. | Noninvasive multi-parameter patient monitor |
-
2019
- 2019-07-18 CN CN201910650212.7A patent/CN110353650B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9298739B2 (en) * | 2010-11-23 | 2016-03-29 | Nec Corporation | Position information providing apparatus, position information providing system, position information providing method, program, and recording medium |
| CN108601527A (en) * | 2016-10-21 | 2018-09-28 | 华为技术有限公司 | The calibration method and blood pressure measurement device of blood pressure measurement device |
| CN108577883A (en) * | 2018-04-03 | 2018-09-28 | 上海交通大学 | A kind of Screening for coronary artery disease device, screening system and signal characteristic extracting methods |
Non-Patent Citations (2)
| Title |
|---|
| 原亚欣.基于单导脉搏波的多生理参数测量研究与实现.《中国优秀硕士学位论文全文数据库信息科技辑》.2018,(第4期), * |
| 基于单导脉搏波的多生理参数测量研究与实现;原亚欣;《中国优秀硕士学位论文全文数据库信息科技辑》;20180415(第4期);第2章第14页、第3章第18-33页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110353650A (en) | 2019-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11529101B2 (en) | Method to quantify photoplethysmogram (PPG) signal quality | |
| Costa et al. | Multiscale entropy analysis of complex physiologic time series | |
| Thuraisingham et al. | On multiscale entropy analysis for physiological data | |
| CN110623658B (en) | Signal processing method, signal processing apparatus, medical device, and storage medium | |
| CN101061950B (en) | Atrial fibrilation detection by SP02 | |
| Moreno et al. | Type 2 diabetes screening test by means of a pulse oximeter | |
| CN110367969A (en) | A kind of improved electrocardiosignal K-Means Cluster | |
| CN110558960A (en) | continuous blood pressure non-invasive monitoring method based on PTT and MIV-GA-SVR | |
| Reddy et al. | PerDMCS: Weighted fusion of PPG signal features for robust and efficient diabetes mellitus classification | |
| Jaafar et al. | Acceleration plethysmogram based biometric identification | |
| CN109106345A (en) | Pulse signal characteristic detection method and device | |
| Jarvis et al. | Apnea patients characterized by 0.02 Hz peak in the multitaper spectrogram of electrocardiogram signals | |
| CN109171678B (en) | Pulse wave analysis method and device | |
| CN110353650B (en) | PPG signal-based characteristic waveform extraction system | |
| US20150182140A1 (en) | Arterial pulse analysis method and system thereof | |
| Nath et al. | Towards photoplethysmogram based non-invasive blood pressure classification | |
| CN114145725B (en) | PPG sampling rate estimation method based on noninvasive continuous blood pressure measurement | |
| CN115770028A (en) | Blood pressure detection method, system, device and storage medium | |
| EP3547904A1 (en) | Aortic stenosis classification | |
| CN114176532A (en) | Clinical verification method for determining cfPWV parameters and application system thereof | |
| Liu et al. | Signal quality index-based two-step method for heart rate estimation by combining electrocardiogram and arterial blood pressure signals | |
| Fan et al. | Application research of pulse signal physiology and pathology feature mining in the field of disease diagnosis | |
| CN114145722B (en) | Pulse pathological feature mining method for pancreatitis patients | |
| CN111685754B (en) | Heart rate calculation method and system for wearable ECG acquisition equipment | |
| CN115736850B (en) | Pulse data classification system and classification method |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20191022 Assignee: Zhicheng spacetime Technology (Zhejiang) Co.,Ltd. Assignor: Beijing Hezhong Sizhuang Space-time Material Union Technology Co.,Ltd. Contract record no.: X2023980032183 Denomination of invention: Characteristic waveform extraction system based on PPG signal Granted publication date: 20220503 License type: Common License Record date: 20230215 |
|
| EE01 | Entry into force of recordation of patent licensing contract |