CN115444377A - Method for extracting pulse wave three-dimensional parameters - Google Patents
Method for extracting pulse wave three-dimensional parameters Download PDFInfo
- Publication number
- CN115444377A CN115444377A CN202211279788.5A CN202211279788A CN115444377A CN 115444377 A CN115444377 A CN 115444377A CN 202211279788 A CN202211279788 A CN 202211279788A CN 115444377 A CN115444377 A CN 115444377A
- Authority
- CN
- China
- Prior art keywords
- wave
- dimensional
- waves
- pulse wave
- pulse
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims abstract description 24
- 238000004215 lattice model Methods 0.000 claims abstract description 18
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 3
- 208000024172 Cardiovascular disease Diseases 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000010606 normalization Methods 0.000 description 5
- 230000000877 morphologic effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008719 thickening Effects 0.000 description 2
- 210000005249 arterial vasculature Anatomy 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 210000000467 autonomic pathway Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000000748 cardiovascular system Anatomy 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000005037 parasympathetic nerve Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000001020 rhythmical effect Effects 0.000 description 1
- 230000002889 sympathetic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Cardiology (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
A method for extracting three-dimensional parameters of pulse waves belongs to the technical field of signal processing. The method comprises the steps of collecting pulse wave signals with a certain duration, and intercepting the signals with fixed duration; identifying the starting point of the pulse wave to carry out single wave decomposition; sequentially removing baseline drift by using single waves and carrying out standardization treatment; converting the single-wave data into a two-dimensional matrix to obtain a space lattice model in a three-dimensional space; and after the spatial lattice model is subjected to interpolation, the volume of the three-dimensional spatial pulse wave is obtained. The invention has the advantages that the novel pulse wave parameters are provided, the pulse wave period variability and form variability information can be synthesized, and guidance can be provided for monitoring cardiovascular diseases.
Description
Technical Field
The invention belongs to the technical field of signal processing, and particularly relates to a method for extracting three-dimensional parameters of pulse waves.
Background
The pulse wave originates from the rhythmic contraction and relaxation of the heart, propagates in the arterial vasculature, and is constantly reflected in branches at different locations. The reflected wave is superposed with the original pulse wave from the heart, so that the pulse wave contains rich physiological and pathological characteristics of the cardiovascular system, and the variability of the pulse wave is closely related to the cardiovascular diseases.
The pulse wave variability can be embodied in terms of period and morphology. The variation of the pulse wave in the period is the variation of the pulse rate. The pulse rate variability can quantify the activity of autonomic nerves and reflect the balance state between sympathetic nerves and parasympathetic nerves; the morphological variation of the pulse wave can reflect the ability of the heart to shoot blood and the state of the artery and blood vessels. But there is currently no information that features can integrate period and morphological variations.
Disclosure of Invention
In view of the above analysis, the present invention provides a method for extracting three-dimensional parameters of pulse waves, so as to solve the problem that the existing pulse parameters cannot simultaneously synthesize the period variation and morphological variation of pulse waves. In order to achieve the purpose, the invention is realized by the following technical scheme:
a method for extracting three-dimensional parameters of pulse waves comprises the following steps:
step A1: collecting a section of radial pulse wave signal O, and intercepting a preset length O 1 ；
Step A2: for radial pulse wave signal O 1 Identifying the starting point of the single wave, and comparing O 1 Obtaining a signal set U containing N single waves after decomposition;
step A3: respectively preprocessing the single waves in the signal set U to obtain a preprocessed signal set U 1 ；
Step A4: converting the single-wave data in the signal set U1 into a matrix M after unifying the length, and obtaining a space lattice model S by taking the abscissa of the element in the matrix M as the X coordinate in a three-dimensional coordinate system, taking the ordinate as the Y coordinate in the three-dimensional coordinate system and taking the value of the element as the Z coordinate in the three-dimensional coordinate system;
step A5: performing three-dimensional interpolation on the space lattice model S to obtain three-dimensional space pulse wave S 1 Calculating S 1 Volume V under the curved surface of (a).
As a further technical solution of the present invention, the algorithm in step A2 includes the following steps:
step B1: by usingPulse wave signal O by five-point differential threshold method 1 Identifying a single wave starting point;
and step B2: and forming a signal set U by the decomposed N single waves P.
As a further technical solution of the present invention, the algorithm in step A3 includes the following steps:
step C1: and for one single wave in the N single waves in the signal set U, calculating the slope between each data point in the single wave and the starting point of the single wave and the slope between the starting point and the end point of the single wave, and subtracting the product of the two slopes from the amplitude of each data point in the single wave to remove the baseline drift.
And C2: and D, sequentially performing the baseline drift removal on each single wave in the signal set U through the step C1.
And C3: carrying out standardization processing on the signal set U with the baseline drift removed to obtain the signal set U 1 。
As a further technical solution of the present invention, the algorithm in step A4 includes the following steps:
step D1: by signal set U 1 The length of the medium-length and longest-length single waves is a unified standard, and the length of the medium-length and longest-length single waves is a unified standard for U 1 The other single waves except the longest single wave are not long enough to perform zero filling treatment, so that U is ensured 1 The lengths of the single waves of N contained in the data are consistent;
step D2: will U 1 Converting into a matrix M; taking the sequence of N single waves decomposed in the step A2 as a corresponding sequence, taking the sequence as the ordinate of the matrix M, taking the sampling points corresponding to the single waves in the U1 as the abscissa of the matrix M (the starting point of each single wave corresponding to the abscissa is an orderly marked starting point), and taking the amplitude corresponding to the single wave sampling point in the U1 as the data point of the element in the matrix M.
And D3: and establishing a space lattice model through the matrix M. Taking the abscissa of the element in the matrix M as the X coordinate in a three-dimensional coordinate system, the ordinate of the element as the Y coordinate in the three-dimensional coordinate system, and the value of the element as the Z coordinate in the three-dimensional coordinate system to obtain a space lattice model S;
as a further technical solution of the present invention, the algorithm in step A5 includes the following steps:
step E1: performing three-dimensional interpolation on the space lattice model S to obtain three-dimensional space pulse wave S 1 ；
Step E2: calculating three-dimensional space pulse wave S 1 And XOY. Calculating three-dimensional space pulse wave S 1 The area and height of each grid curved surface are multiplied, and then the volume under all the grid curved surfaces is accumulated, and finally the three-dimensional space pulse wave S is obtained 1 The volume V of (a).
The invention is not used for diagnosis and treatment of diseases.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method for extracting three-dimensional parameters of pulse waves, which realizes the acquisition of the volume of the pulse waves in a three-dimensional space and the visual display of the period and the morphological variation of the pulse waves and provides theoretical guidance for monitoring cardiovascular diseases by the pulse waves.
Drawings
Fig. 1 is a flowchart of an embodiment of a pulse wave spatial feature acquisition algorithm according to the present invention.
FIG. 2 is a schematic diagram of single wave start point identification according to the present invention.
FIG. 3 is a schematic diagram of the single wave removal baseline drift of the present invention.
FIG. 4 is a schematic diagram of a space lattice model S of the present invention
FIG. 5 shows a three-dimensional pulse wave S according to the present invention 1 Schematic representation.
Detailed Description
The present invention will be further described with reference to the following examples, but the present invention is not limited to the following examples.
Example 1
According to heart rate variability research, pulse wave signals required by ultra-short time heart rate variability at least comprise 30 heartbeats. The following result detailed description and the accompanying drawings describe the present invention in detail, but the embodiments of the present invention are not limited thereto.
Step A1: collecting a section of radial pulse wave signal O, and intercepting a preset length O 1 ；
Step A2: for radial pulse wave signal O 1 Identifying the starting point of the single wave, and comparing O 1 Obtaining a signal set U containing N single waves after decomposition;
step A3: respectively preprocessing the single waves in the signal set U to obtain a preprocessed signal set U 1 ；
Step A4: converting the single-wave data in the signal set U1 into a matrix M after unifying the length, and obtaining a space lattice model S by taking the abscissa of the element in the matrix M as the X coordinate in a three-dimensional coordinate system, the ordinate as the Y coordinate in the three-dimensional coordinate system and the value of the element as the Z coordinate in the three-dimensional coordinate system;
step A5: performing three-dimensional interpolation on the space lattice model S to obtain a three-dimensional space pulse wave S 1 Calculating S 1 Volume V under the curved surface of (a).
As a further technical scheme of the invention, the pulse wave length is intercepted in the step A1, and the intercepted O is 1 The length is 30 seconds.
As a further technical solution of the present invention, the algorithm in step A2 includes the following steps:
step B1: as shown in FIG. 2, the pulse wave signal O is subjected to a differential threshold method 1 Identifying the starting point of the single wave, wherein the star mark points are the starting points of the identified pulse wave single wave;
and step B2: and (5) forming a signal set U by the decomposed N single waves P, wherein N is 30.
As a further technical solution of the present invention, the algorithm in step A3 includes the following steps:
step C1: and for one single wave in the N single waves in the signal set U, calculating the slope between each data point in the single wave and the starting point of the single wave and the slope between the starting point and the end point of the single wave, and subtracting the product of the two slopes from the amplitude of each data point in the single wave to remove the baseline drift. As shown in fig. 3, the solid line without thickening is the waveform of the single wave before the baseline drift is removed, the solid line with thickening is the waveform of the single wave after the baseline drift is removed, and the dotted line is the connecting line between the starting point and the end point of the single wave after the baseline drift is removed. The baseline drift removal is calculated as in equation (1):
y in the formula after (x) Is the amplitude of the pulse wave at x after baseline removal, y before (x) The amplitude of the pulse wave at x before baseline removal, y start Is the amplitude at the origin of the pulse wave, y end Is the amplitude at the end of the pulse wave, x start Is the abscissa, x, of the origin of the pulse wave end The abscissa of the pulse wave endpoint.
And C2: sequentially performing the step C1 on each single wave in the signal set U to remove the baseline drift;
and C3: standardizing all the single waves in the signal set U after the baseline drift is removed to obtain the signal set U 1 . The normalization calculation is as in equation (2):
wherein Y (x) is the pulse wave amplitude at x after normalization, Y (x) is the pulse wave amplitude at x before normalization, Y min Is the minimum value of the amplitude of the pulse wave before normalization, y max Is the maximum value of the pulse wave amplitude before normalization.
As a further technical solution of the present invention, the algorithm in step A4 includes the following steps:
step D1: by signal set U 1 The length of the longest single wave is a unified standard, and the length is U 1 Other single waves except the longest single wave are subjected to zero filling treatment, so that U is formed 1 The lengths of the single waves of N contained in (1) are consistent;
step D2: step D2: will U 1 Converting into a matrix M; taking the sequence of N single waves decomposed in the step A2 as a corresponding sequence, taking the sequence as the ordinate of the matrix M, taking the sampling point of the corresponding single wave in the U1 as the abscissa of the matrix M, and taking the sampling point of the corresponding single wave in the U1 as the axisThe corresponding amplitude values of the single-wave sampling points are the data points of the elements in the matrix M.
And D3: and establishing a space lattice model of the three-dimensional space. Taking the abscissa of the element in the matrix M as the X coordinate in the three-dimensional coordinate system, the ordinate of the element as the Y coordinate in the three-dimensional coordinate system, and the value of the element as the Z coordinate in the three-dimensional coordinate system, and obtaining a space lattice model S as shown in FIG. 4;
as a further technical solution of the present invention, the algorithm in step A5 includes the following steps:
step E1: performing three-dimensional interpolation on the space lattice model S to obtain three-dimensional space pulse wave S 1 ；
And E2: calculating the three-dimensional space pulse wave S 1 And XOY. Calculating three-dimensional space pulse wave S 1 Multiplying the area and height of the curved surface of each grid to obtain the volume under the curved surface of the grid, accumulating the volume under the curved surface of all the grids to finally obtain the three-dimensional space pulse wave S 1 The volume V of (a).
Claims (4)
1. A method for extracting three-dimensional parameters of pulse waves is used for extracting the volume of the pulse waves in a three-dimensional space, and comprises the following steps:
step A1: collecting a radial pulse wave signal O, and intercepting a preset length O 1 ；
Step A2: for radial pulse wave signal O 1 Identifying the starting point of the single wave, and comparing O 1 Obtaining a signal set U containing N single waves after decomposition;
step A3: respectively preprocessing the single waves in the signal set U to obtain a preprocessed signal set U 1 ；
Step A4: converting the single-wave data in the signal set U1 into a matrix M after unifying the length, and obtaining a space lattice model S by taking the abscissa of the element in the matrix M as the X coordinate in a three-dimensional coordinate system, taking the ordinate as the Y coordinate in the three-dimensional coordinate system and taking the value of the element as the Z coordinate in the three-dimensional coordinate system;
step A5: performing three-dimensional interpolation on the space lattice model S to obtain three-dimensional space pulse wave S 1 Calculating S 1 Volume V under the curved surface of (1).
2. The method for extracting three-dimensional parameters of pulse waves according to claim 1, wherein the algorithm in step A3 comprises the following steps:
step C1: and for one single wave in the N single waves in the signal set U, calculating the slope between each data point in the single wave and the starting point of the single wave and the slope between the starting point and the end point of the single wave, and subtracting the product of the two slopes from the amplitude of each data point in the single wave to remove the baseline drift.
And C2: and D, sequentially performing the baseline drift removal on each single wave in the signal set U through the step C1.
And C3: carrying out standardization processing on the signal set U after baseline drift is removed to obtain the signal set U 1 。
3. The method for extracting three-dimensional parameters of pulse waves according to claim 1, wherein the algorithm in step A4 comprises the following steps:
step D1: by signal set U 1 The length of the medium-length and longest single waves is a unified standard, and the longest single wave is used as the unified standard for U 1 The zero filling processing is carried out on the single waves except the longest single wave in the U wave, so that the U wave is not long enough 1 The lengths of the single waves of N contained in (1) are consistent;
step D2: will U 1 Converting into a matrix M; taking the sequence of N single waves decomposed in the step A2 as a corresponding sequence, taking the sequence as the ordinate of the matrix M, taking the sampling points corresponding to the single waves in the U1 as the abscissa of the matrix M (the starting point of each single wave corresponding to the abscissa is an orderly marked starting point), and taking the amplitude corresponding to the single wave sampling point in the U1 as the data point of the element in the matrix M.
And D3: and establishing a space lattice model through the matrix M. And taking the abscissa of the element in the matrix M as the X coordinate in the three-dimensional coordinate system, the ordinate of the element as the Y coordinate in the three-dimensional coordinate system, and the value of the element as the Z coordinate in the three-dimensional coordinate system to obtain a space lattice model S.
4. The method for extracting three-dimensional parameters of pulse waves according to claim 1, wherein the algorithm in step A5 comprises the following steps:
step E1: performing three-dimensional interpolation on the space lattice model S to obtain three-dimensional space pulse wave S 1 ；
And E2: calculating three-dimensional space pulse wave S 1 And XOY. Calculating the three-dimensional space pulse wave S 1 The area and height of each grid curved surface are multiplied, the volume under all the grid curved surfaces is accumulated, and finally the three-dimensional space pulse wave S is obtained 1 Volume V of (c).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211279788.5A CN115444377A (en) | 2022-10-19 | 2022-10-19 | Method for extracting pulse wave three-dimensional parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211279788.5A CN115444377A (en) | 2022-10-19 | 2022-10-19 | Method for extracting pulse wave three-dimensional parameters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115444377A true CN115444377A (en) | 2022-12-09 |
Family
ID=84311676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211279788.5A Pending CN115444377A (en) | 2022-10-19 | 2022-10-19 | Method for extracting pulse wave three-dimensional parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115444377A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102469984A (en) * | 2009-06-30 | 2012-05-23 | 皇家飞利浦电子股份有限公司 | Three dimensional fetal heart imaging by non-ecg physiological gated acquisition |
| US20120310100A1 (en) * | 2011-05-31 | 2012-12-06 | Nellcor Puritan Bennett Ireland | Systems And Methods For Detecting And Monitoring Arrhythmias Using the PPG |
| US20130080489A1 (en) * | 2011-09-23 | 2013-03-28 | Nellcor Puritan Bennett Ireland | Systems and methods for determining respiration information from a photoplethysmograph |
| CN105873503A (en) * | 2013-12-25 | 2016-08-17 | 旭化成株式会社 | Cardiac pulse waveform measurement device, portable device, medical device system, and vital sign information communication system |
| CN111248880A (en) * | 2020-02-21 | 2020-06-09 | 乐普（北京）医疗器械股份有限公司 | Blood pressure prediction method and device based on photoplethysmography signals |
| US20200211713A1 (en) * | 2018-12-26 | 2020-07-02 | Analytics For Life Inc. | Method and system to characterize disease using parametric features of a volumetric object and machine learning |
| CN112274118A (en) * | 2020-08-18 | 2021-01-29 | 北京工业大学 | Method for automatically identifying stable sequence in radial artery pulse wave signal |
-
2022
- 2022-10-19 CN CN202211279788.5A patent/CN115444377A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102469984A (en) * | 2009-06-30 | 2012-05-23 | 皇家飞利浦电子股份有限公司 | Three dimensional fetal heart imaging by non-ecg physiological gated acquisition |
| US20120310100A1 (en) * | 2011-05-31 | 2012-12-06 | Nellcor Puritan Bennett Ireland | Systems And Methods For Detecting And Monitoring Arrhythmias Using the PPG |
| US20130080489A1 (en) * | 2011-09-23 | 2013-03-28 | Nellcor Puritan Bennett Ireland | Systems and methods for determining respiration information from a photoplethysmograph |
| CN105873503A (en) * | 2013-12-25 | 2016-08-17 | 旭化成株式会社 | Cardiac pulse waveform measurement device, portable device, medical device system, and vital sign information communication system |
| US20200211713A1 (en) * | 2018-12-26 | 2020-07-02 | Analytics For Life Inc. | Method and system to characterize disease using parametric features of a volumetric object and machine learning |
| CN111248880A (en) * | 2020-02-21 | 2020-06-09 | 乐普（北京）医疗器械股份有限公司 | Blood pressure prediction method and device based on photoplethysmography signals |
| CN112274118A (en) * | 2020-08-18 | 2021-01-29 | 北京工业大学 | Method for automatically identifying stable sequence in radial artery pulse wave signal |
Non-Patent Citations (3)
| Title |
|---|
| 丑永新 等: "基于时空解析建模的脉搏信号量化分析方法研究", 生物医学工程学杂志, vol. 37, no. 1, 28 February 2020 (2020-02-28), pages 61 - 79 * |
| 张爱华;刘宗福;林冬梅;杨力铭: "基于有限元分析的脉搏形态三维重构", 中国医学物理学杂志, no. 004, 31 December 2015 (2015-12-31) * |
| 林冬梅;张爱华;杨富龙;陈晓雷;: "基于图像熵的脉搏波提取算法", 中南大学学报(自然科学版), no. 09, 26 September 2013 (2013-09-26) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Karpagachelvi et al. | ECG feature extraction techniques-a survey approach | |
| US7509159B2 (en) | Method and apparatus for detecting cardiac repolarization abnormality | |
| CN109381181B (en) | End point detection method for electrocardiosignal characteristic waveform | |
| Kantz et al. | Human ECG: nonlinear deterministic versus stochastic aspects | |
| Campolo et al. | ECG-derived respiratory signal using empirical mode decomposition | |
| CN104161509A (en) | Heart rate variability analyzing method based on amplitude spectrum and instruments | |
| CN106073783B (en) | Method for extracting respiration rate from photoplethysmography wave | |
| CN102955889B (en) | A kind of pulse wave reconstruction method for extracting temporal signatures point | |
| CN110367936B (en) | Electrocardiosignal detection method and device | |
| Vijaya et al. | Arrhythmia detection through ECG feature extraction using wavelet analysis | |
| CN106137185A (en) | A kind of epileptic chracter wave detecting method based on structure of transvers plate small echo | |
| CN114052744A (en) | Electrocardiosignal classification method based on pulse neural network | |
| CN102334986B (en) | Method for identifying dicrotic notch point in arterial tension signal | |
| CN109009088B (en) | TWA multichannel fusion estimation method based on tensor decomposition | |
| Rapalis et al. | Estimation of blood pressure variability during orthostatic test using instantaneous photoplethysmogram frequency and pulse arrival time | |
| CN115444377A (en) | Method for extracting pulse wave three-dimensional parameters | |
| CN110179456B (en) | Electrocardio noise recognition model training and electrocardio noise detection method and device | |
| Karvounis et al. | A non-invasive methodology for fetal monitoring during pregnancy | |
| Kumari et al. | Electrocardiographic signal analysis using wavelet transforms | |
| CN110141244A (en) | Electrocardiogram personal identification method | |
| Turajlic | A novel algorithm for ECG parametrization and synthesis | |
| CN113576438B (en) | Non-invasive blood pressure extraction method and system | |
| Li et al. | J peak extraction from non-standard ballistocardiography data: A preliminary study | |
| Shahid et al. | Classification of Fetal Cardiac Arrhythmia Using Heart Rate Variability and Machine Learning | |
| Afzal et al. | Noisy ECG Signal Data Transformation to Augment Classification Accuracy. |
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 |