CN104706349A - Electrocardiosignal construction method based on pulse wave signals - Google Patents
Electrocardiosignal construction method based on pulse wave signals Download PDFInfo
- Publication number
- CN104706349A CN104706349A CN201510173090.9A CN201510173090A CN104706349A CN 104706349 A CN104706349 A CN 104706349A CN 201510173090 A CN201510173090 A CN 201510173090A CN 104706349 A CN104706349 A CN 104706349A
- Authority
- CN
- China
- Prior art keywords
- electrocardiosignal
- pulse wave
- signal
- peak
- control point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims abstract description 6
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 12
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 238000003780 insertion Methods 0.000 claims description 7
- 230000037431 insertion Effects 0.000 claims description 7
- 101710097688 Probable sphingosine-1-phosphate lyase Proteins 0.000 claims description 6
- 101710105985 Sphingosine-1-phosphate lyase Proteins 0.000 claims description 6
- 101710122496 Sphingosine-1-phosphate lyase 1 Proteins 0.000 claims description 6
- 239000000470 constituent Substances 0.000 claims description 6
- 230000007935 neutral effect Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000001537 neural effect Effects 0.000 claims description 4
- 230000001360 synchronised effect Effects 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 2
- 238000000263 scanning probe lithography Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000013528 artificial neural network Methods 0.000 abstract 1
- 238000002474 experimental method Methods 0.000 abstract 1
- 230000002349 favourable effect Effects 0.000 abstract 1
- 238000010606 normalization Methods 0.000 abstract 1
- 238000012847 principal component analysis method Methods 0.000 abstract 1
- 230000001131 transforming effect Effects 0.000 abstract 1
- 238000000513 principal component analysis Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000000737 periodic effect Effects 0.000 description 3
- 235000007926 Craterellus fallax Nutrition 0.000 description 2
- 240000007175 Datura inoxia Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000000747 cardiac effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000000718 qrs complex Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- 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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Abstract
The invention provides an electrocardiosignal construction method based on pulse wave signals. The method comprises the following steps: performing normalization processing of pulse wave signals and electrocardiosignals, which are segmented periodically, by means of scale transformation, fitting the pulse wave signals and the electrocardiosignals by adopting a cubic b-spline curve, and extracting characteristic parameters, transforming the characteristic parameters by a principal component analysis method to obtain the principal components of the signals; performing sample training of the principal components of the pulse wave signals and the electrocardiosignals by adopting a BP neural network to obtain model parameters, and constructing a forecasting model; and constructing electrocardiosignal parameters through the model by utilizing the pulse wave signals and the network model parameters. Experiments show that the method provided by the invention has favorable algorithm performance and constructed electrocardiosignals have small distortion. According to the method, the electrocardiosignals are constructed according to pulse waves through a portable waist type pulse detector, the use of chest leads are avoided, and the improvement in portability of an electrocardiograph is facilitated.
Description
Technical field
The present invention relates to medical science and bio-signal acquisition and analysis technical field, relate to the construction method of electrocardiosignal, be related specifically to the method utilizing the pulse wave signal of synchronous acquisition to build electrocardiosignal.
Background technology
Electrocardiosignal many employings chest leads obtains, very not convenient, have impact on the portability of electrocardioscanner.If pulse wave can be utilized to recover electrocardiosignal, then significantly can improve the comfort level of ECG signal sampling.At present, in the research about relation between pulse wave and electrocardiosignal, the method adopting the characteristic vector extracting pulse wave signal and electrocardiosignal, utilizes significance test to analyze the internal association between pulse wave signal and electrocardiosignal more.But these methods only illustrate the dependency of pulse wave cycle and cardiac electrical cycle, cannot recover with pulse wave signal or build electrocardiosignal.The people such as Mart í n propose random association model, for rebuilding the pulse wave signal of loss, also can be used for utilizing pulse wave signal and electrocardiosignal to rebuild the electrocardiosignal of loss.But the method is only applicable to rebuild that part of losing in electrocardiosignal sequence, can not be used for building electrocardiosignal by pulse wave signal, also cannot accomplish real-time process.In addition, the method is comparatively strong for the dependency of electrocardiosignal, requires that the leading portion of institute's loss part and back segment all have complete electrocardiosignal and only lose a small amount of electrocardiosignal, helps little for the portability improving EGC detecting Instrument.
Summary of the invention
The problem that what main purpose of the present invention was is in order to solve prior art, provides a kind of method utilizing pulse wave signal to build electrocardiosignal.
Based on the electrocardiosignal construction method of pulse wave signal, comprise the following steps:
A. the pulse wave signal obtained synchronous acquisition and electrocardiosignal carry out pretreatment
A1. utilize the mode of medium filtering to remove baseline drift interference to pulse wave and electrocardiosignal, utilize average filter to remove the noise such as Hz noise and myoelectricity interference to pulse wave and electrocardiosignal.
A2. utilize the method for difference threshold algorithm and local transform domain to complete and work is divided to the cycle of pulse wave and electrocardiosignal.
A3. divide gained signal to A2 to be normalized.Temporal change of scale is adopted to signal, is normalized.Change of scale formula used is:
Wherein, t
peakwith t
endbe respectively the peak point of signal and the time corresponding to terminating point, T
1for the average time of the peak point of signal, T
2for peak point is to the average time of terminating point.Record original cycle of pulse wave and electrocardiosignal simultaneously.
B. to the pulse wave after pretreatment and electrocardiosignal, adopt three b SPLs to carry out waveform fitting, extract the characteristic parameter vector of signal.
B1. adopt the mode of three b spline curve fittings to carry out signal waveform matching to pulse wave signal, solve control point, as characteristic parameter.
B2. the matching of electrocardiosignal is also adopted to the mode of three b spline curve fittings, but to choose mode be non-homogeneous insertion at control point.Non-homogeneous insertion is the electrocardiosignal to each cycle, before P ripple, inserts 2 to 4 control point; To information such as middle QRS wave groups compared with the place of horn of plenty, insert 10 to 12 control point; To rear end T ripple part, insert 4 to 6 control point, make control point add up to 20 simultaneously.
C. build model by the signal based on neutral net, utilize pulse wave signal to build electrocardiosignal.
C1. adopt PCA to convert pulse wave and electrocardiosignal characteristic parameter, obtain the main constituent that it reduces dimension.
C2. to the main constituent of pulse wave and electrocardiosignal, first carry out sample training, obtain model parameter, set up forecast model.And utilize the parameter of this model prediction electrocardiosignal.
C21. utilize 3 layers of BP neutral net, the electrocardiosignal choosing each 100 groups of pulse wave signals and correspondence respectively, as training set, carries out neural metwork training.
C22. the network parameter utilizing C21 to obtain sets up forecast model.After model is set up, 50 groups of pulse wave signal test sets and gained network parameter is utilized to carry out the structure prediction of electrocardiosignal parameter.
C3. the electrocardiosignal parameter of gained is converted to the control point of b SPL through principal component analysis PCA (Principal Component Analysis) inverse transformation, again via cubic B-spline equation, and through time scale inverse transformation, obtain the electrocardiosignal built.
The present invention, by the pulse wave of synchronous acquisition and the basis of ECG signal processing, carries out waveform fitting, obtains its corresponding characteristic parameter.Then, utilize the signal based on neural net method provided by the invention to build model, the electro-cardiologic signal waveforms corresponding with it can be constructed by pulse wave signal.
This method can realize building electrocardiosignal by pulse wave signal, obtains some important informations of electrocardiosignal.By portable wrist-pulse detecting device, electrocardiosignal can be constructed.Avoid the use of chest leads, thus contribute to the portability improving electrocardioscanner.
Accompanying drawing explanation
Fig. 1 is the system block diagram building electrocardiosignal based on pulse wave signal of the present invention.
Fig. 2 A is the electro-cardiologic signal waveforms fitted figure (number of control points is 20 points) evenly inserting control point method.
Fig. 2 B is the electrocardiosignal segmented waveform fitted figure (number of control points is 20 points) of non-homogeneous insertion control point of the present invention method.
Fig. 3 is that signal of the present invention builds model system block diagram.
Fig. 4 is the comparison diagram of the electrocardiosignal that builds of the present invention and original electrocardiosignal.
Fig. 5 is the root-mean-square percentage error curve chart of test sample book of the present invention.
Detailed description of the invention
For making object of the invention process, technical scheme and advantage more clear, be described in further detail below in conjunction with technical scheme of the present invention and accompanying drawing:
Utilize pulse wave signal to build the method for electrocardiosignal, its overall system block diagram as shown in Figure 1.The method can be divided into three links, is respectively: Signal Pretreatment, waveform fitting and signal build model.Wherein, Signal Pretreatment part is used for removing noise jamming and by periodic segment, waveform fitting part is for obtaining the characteristic parameter of signal, and the ECG signal corresponding with PPG is constructed in the effect that signal builds model to detecting the PPG signal that obtains.Concrete steps are as follows:
Steps A. pretreatment is carried out to the pulse wave signal in each 150 cycles that synchronous acquisition obtains and electrocardiosignal.Mainly comprise the steps:
A1. the window length first first arranging median filter is 100, by electrocardiosignal by this wave filter, obtains the trend term of electrocardiosignal.From original electrocardiosignal, deduct this trend term, acquired results is the electrocardiosignal after removing baseline drift.Be the average filter of 8 again by window length by gained electrocardiosignal, to remove Hz noise and myoelectricity interference.
A2. carry out same pretreatment to the pulse wave signal collected, the window length first arranging median filter is 100, by pulse wave signal by this wave filter, obtains the trend term of pulse wave signal.From original pulse wave signal, deduct this trend term, acquired results is the pulse wave signal after removing baseline drift.Be the average filter of 8 again by window length by gained pulse wave signal, Hz noise and myoelectricity interference can be removed.
A3. adopt difference threshold algorithm to extract the main ripple of pulse wave and the R ripple of electrocardiosignal, utilize the method in partial transformation territory to detect the starting point of pulse wave signal and the starting point of electrocardiosignal.Complete to pulse wave signal and electrocardiosignal by periodic segment.
A4. gained signal is normalized.Due to do not appear at synchronization by the pulse wave signal of periodic segment and the maximum in electrocardiosignal each cycle and the cycle different in size, thus need to adopt temporal change of scale to signal, be normalized.Change of scale formula used is:
Wherein, t
peakwith t
endbe respectively the peak point of signal and the time corresponding to terminating point, T
1for the average time of the peak point of signal, T
2for peak point is to the average time of terminating point.Recording original cycle of pulse wave and electrocardiosignal simultaneously, waveform inverse transformation can be returned when carrying out signal post-processing so that follow-up.
Step B. for gained in steps A pretreatment after pulse wave and electrocardiosignal, carry out waveform fitting, extract characteristic parameter vector.
Described step B specifically comprises the steps:
B1. adopt the mode of three b spline curve fittings to carry out signal waveform matching to pulse wave signal, solve control point, as characteristic parameter.Three times b SPL equation is:
p(t
i)＝B
0P
0+B
1P
1+B
2P
2+B
3P
3
Wherein, p (t
i) be corresponding point t
iinterpolation, P
0, P
1, P
2and P
3four control point.B
0, B
1, B
2and B
3for the basic function of b SPL.To pulse wave signal, control point sum is set to 30, and mode is chosen for evenly to choose method in control point.The control point set of gained is the parameter vector of required pulse wave signal.
B2. the matching of electrocardiosignal is also adopted to the mode of three b spline curve fittings, but to choose mode be the non-homogeneous insertion that the present invention proposes at control point.For the electrocardiosignal in each cycle, before P ripple, because waveform is comparatively smooth, therefore only insert 2 to 4 control point; For information such as middle QRS wave groups compared with the place of horn of plenty, insert 10 to 12 control point; To rear end T ripple part, insert 4 to 6 control point, make control point add up to 20 simultaneously.Accompanying drawing 2A be evenly insert control point method electro-cardiologic signal waveforms fitted figure as shown in fig. 2.The electrocardiosignal segmented waveform fitted figure of non-homogeneous insertion control point of the present invention method as shown in figure 2b.
Step C. can obtain the characteristic parameter vector W of pulse wave and electrocardiosignal by step B
pPGwith W
eCG, the two is made up of 30 and 20 control point respectively.For how to build electrocardiosignal by pulse wave signal, the signal that the present invention proposes based on neutral net builds model.Model system block diagram as shown in Figure 3.
Step C specifically comprises:
C1. adopt principal component analysis (PCA) method to W
pPG[n] and W
eCG[n] converts, and can obtain its main constituent Y
pPG[n] and Y
eCG[n], wherein " n " represents the periodicity of signal.
C2. to the main constituent of pulse wave and electrocardiosignal, first carry out sample training, obtain model parameter, set up forecast model.And utilize the parameter of this model prediction electrocardiosignal.
Described step C2 specifically comprises following two steps:
C21. be first the process of parameter training, the present invention selects 3 layers of BP neutral net.The electrocardiosignal choosing each 100 groups of pulse wave signals and correspondence respectively as training set, with Y
pPG[n] conduct input, Y
eCG[n] is as exporting.Transfer function used is tansig, and training function adopts traingdx, and e-learning function is learngdm, carries out neural metwork training.
C22. the network parameter utilizing C21 to obtain sets up forecast model.After model is set up, 50 groups of pulse wave signal test sets and gained network parameter is utilized to carry out the structure prediction of electrocardiosignal parameter.
C3. the electrocardiosignal parameter of C2 gained is converted to the control point of b SPL through PCA inverse transformation, then via cubic B-spline equation, and through time scale inverse transformation, obtain the electrocardiosignal built.So far the work being built ECG signal by PPG signal is completed.
Fig. 4 gives original electro-cardiologic signals waveform and the present invention the waveform utilizing the constructed corresponding cycle ECG signal of one-period PPG signal.By the contrast with original ECG signal waveform, can find that the information of the main waveform such as the P ripple of structure ECG signal, QRS ripple and T ripple is all better recovered, the overall condition building waveform is good.Root-mean-square percentage (PRD) error is the standard for evaluating electrocardio compression quality, the PRD curve of error of Fig. 5 ECG signal and original ECG signal constructed by 50 cycles of test set used herein.If build the PRD value of electrocardiosignal between 0 to 9, then quality judging is " very good " or " good ".As can be seen from the figure, recover signal PRD all fluctuate near 7, and be all less than 10.Through there being experience clinician to evaluate, constructed electrocardiosignal contains the information of original electro-cardiologic signals substantially.In actual applications, the evaluation of medical signals recovery effects also depends on and is resumed signal quality inspection clinically and the acceptance level of subjective vision.The present invention has carried out relative analysis to building the QRS complex wave of electrocardiosignal and T ripple and original electro-cardiologic signals characteristic of correspondence waveform, and give the error of range error and corresponding time, it is as shown in the table.
As can be seen from the table, the amplitude error of electrocardiosignal signature waveform is less, and its time error fluctuates between 0 to 4 sampled point, and because sample rate is 200Hz, thus temporal error is 0 to 20ms.Above-mentioned error is all within tolerance interval.
The above; be only the present invention's preferably detailed description of the invention; but protection scope of the present invention is not limited thereto; anyly be familiar with those skilled in the art in the technical scope that the present invention discloses; be equal to according to technical scheme of the present invention and inventive concept thereof and replace or change, all should be encompassed within protection scope of the present invention.
Claims (1)
1., based on an electrocardiosignal construction method for pulse wave signal, it is characterized in that, step is as follows:
A. the pulse wave signal obtained synchronous acquisition and electrocardiosignal carry out pretreatment
A1. utilize the mode of medium filtering to remove baseline drift interference to pulse wave and electrocardiosignal, utilize average filter to remove Hz noise and myoelectricity interference to pulse wave and electrocardiosignal;
A2. utilize the method for difference threshold algorithm and local transform domain to complete to divide the cycle of pulse wave and electrocardiosignal;
A3. divide gained signal to A2 to be normalized: adopt temporal change of scale to signal, be normalized, change of scale formula used is:
Wherein, t
peakwith t
endbe respectively the peak point of signal and the time corresponding to terminating point, T
1for the average time of the peak point of signal, T
2for peak point is to the average time of terminating point, record original cycle of pulse wave and electrocardiosignal simultaneously;
B. to the pulse wave after pretreatment and electrocardiosignal, adopt three b SPLs to carry out waveform fitting, extract the characteristic parameter vector of signal;
B1. adopt the mode of three b spline curve fittings to carry out signal waveform matching to pulse wave signal, solve control point, as characteristic parameter;
B2. the matching of electrocardiosignal is also adopted to the mode of three b spline curve fittings, it is non-homogeneous insertion that mode is chosen at control point; Non-homogeneous insertion is the electrocardiosignal to each cycle, before P ripple, insert 2 to 4 control point; Middle QRS wave group inserts 10 to 12 control point; Insert 4 to 6 control point to rear end T ripple, control point adds up to 20;
C. build model by the signal based on neutral net, utilize pulse wave signal to build electrocardiosignal
C1. adopt PCA to convert pulse wave and electrocardiosignal characteristic parameter, obtain the main constituent that it reduces dimension;
C2. to the main constituent of pulse wave and electrocardiosignal, first carry out sample training, obtain model parameter, set up forecast model, and utilize the parameter of this model prediction electrocardiosignal;
C21. utilize 3 layers of BP neutral net, the electrocardiosignal choosing each 100 groups of pulse wave signals and correspondence respectively, as training set, carries out neural metwork training;
C22. the network parameter utilizing C21 to obtain sets up forecast model, after model is set up, utilizes 50 groups of pulse wave signal test sets and gained network parameter to carry out the structure prediction of electrocardiosignal parameter;
C3. the electrocardiosignal parameter of gained is converted to the control point of b SPL through PCA inverse transformation, then via cubic B-spline equation, and through time scale inverse transformation, obtain the electrocardiosignal built.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510173090.9A CN104706349B (en) | 2015-04-13 | 2015-04-13 | Electrocardiosignal construction method based on pulse wave signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510173090.9A CN104706349B (en) | 2015-04-13 | 2015-04-13 | Electrocardiosignal construction method based on pulse wave signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104706349A true CN104706349A (en) | 2015-06-17 |
| CN104706349B CN104706349B (en) | 2017-03-22 |
Family
ID=53406431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510173090.9A Expired - Fee Related CN104706349B (en) | 2015-04-13 | 2015-04-13 | Electrocardiosignal construction method based on pulse wave signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104706349B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106725376A (en) * | 2016-11-30 | 2017-05-31 | 高军峰 | Sign detection method and device |
| CN108236461A (en) * | 2017-12-22 | 2018-07-03 | 天津天堰科技股份有限公司 | It is a kind of can be into the processing method of the electrocardiosignal of edlin |
| CN108701219A (en) * | 2017-03-14 | 2018-10-23 | 华为技术有限公司 | The method and device of waveform signal processing |
| CN109157202A (en) * | 2018-09-18 | 2019-01-08 | 东北大学 | A kind of cardiovascular disease early warning system based on more physiological signal depth integrations |
| CN109805921A (en) * | 2018-12-18 | 2019-05-28 | 深圳小辣椒科技有限责任公司 | The cross-platform method of sampling of electrocardiogram (ECG) data and cardioelectric monitor system |
| CN109833034A (en) * | 2017-11-24 | 2019-06-04 | 深圳市岩尚科技有限公司 | The method and device of blood pressure data is extracted in a kind of pulse wave signal |
| CN110025296A (en) * | 2019-03-01 | 2019-07-19 | 西安理工大学 | A kind of acquisition method of the characteristic parameter of photoplethysmographic |
| CN110327031A (en) * | 2018-11-29 | 2019-10-15 | 武汉中旗生物医疗电子有限公司 | A method of removal electrocardiosignal motion artifacts |
| CN110678816A (en) * | 2017-04-04 | 2020-01-10 | 西门子股份公司 | Method and control device for controlling a technical system |
| CN110840436A (en) * | 2018-11-15 | 2020-02-28 | 深圳市松恩电子科技有限公司 | Method, device and terminal for acquiring electrocardiosignals and computer readable storage medium |
| CN111000538A (en) * | 2019-12-30 | 2020-04-14 | 北京丰顺科技发展有限公司 | Pulse condition acquisition and pulse diagnosis device and method capable of exceeding human touch spatial resolution |
| WO2020198522A1 (en) * | 2019-03-26 | 2020-10-01 | University Of Maryland, College Park | Electrocardiogram waveform reconstruction from photoplethysmogram |
| CN111914655A (en) * | 2020-07-06 | 2020-11-10 | 电子科技大学 | Pulse condition classification method based on significant signal subsection extraction |
| CN110179456B (en) * | 2019-05-23 | 2021-11-02 | 中国航天员科研训练中心 | Electrocardio noise recognition model training and electrocardio noise detection method and device |
| CN114010167A (en) * | 2021-11-25 | 2022-02-08 | 中山大学 | Pulse wave fitting method based on Weibull function |
| CN114081502A (en) * | 2021-11-11 | 2022-02-25 | 中国科学院深圳先进技术研究院 | Non-invasive heart disease diagnosis method and device based on machine learning |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100249623A1 (en) * | 2009-03-25 | 2010-09-30 | Sorin Crm S.A.S. | Non-linear filtering for the reconstruction of a surface Electrocardiogram from an endocardial electrogram |
| US20110077538A1 (en) * | 2009-09-11 | 2011-03-31 | Agency For Science, Technology And Research | Electrocardiogram signal processing system |
| CN102812644A (en) * | 2010-03-15 | 2012-12-05 | 高通股份有限公司 | Method and apparatus for processing and reconstructing data |
| US20130289426A1 (en) * | 2012-04-30 | 2013-10-31 | Choudur K. Lakshminarayan | Classification of a signal in a time domain |
| CN103908243A (en) * | 2014-04-01 | 2014-07-09 | 南京普澳医疗设备有限公司 | Lifting wavelet and median filter combined algorithm |
| WO2014120719A1 (en) * | 2013-01-29 | 2014-08-07 | Covidien Lp | Low power monitoring systems and methods |
| CN104145262A (en) * | 2011-12-14 | 2014-11-12 | 高通股份有限公司 | System and method for analysis and reconstruction of variable pulse-width signals with finite-rates-of-innovation |
| CN104173030A (en) * | 2014-09-09 | 2014-12-03 | 北京航空航天大学 | Pulse wave starting point real-time detection method resisting waveform change interference and application thereof |
-
2015
- 2015-04-13 CN CN201510173090.9A patent/CN104706349B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100249623A1 (en) * | 2009-03-25 | 2010-09-30 | Sorin Crm S.A.S. | Non-linear filtering for the reconstruction of a surface Electrocardiogram from an endocardial electrogram |
| US20110077538A1 (en) * | 2009-09-11 | 2011-03-31 | Agency For Science, Technology And Research | Electrocardiogram signal processing system |
| CN102812644A (en) * | 2010-03-15 | 2012-12-05 | 高通股份有限公司 | Method and apparatus for processing and reconstructing data |
| CN104145262A (en) * | 2011-12-14 | 2014-11-12 | 高通股份有限公司 | System and method for analysis and reconstruction of variable pulse-width signals with finite-rates-of-innovation |
| US20130289426A1 (en) * | 2012-04-30 | 2013-10-31 | Choudur K. Lakshminarayan | Classification of a signal in a time domain |
| WO2014120719A1 (en) * | 2013-01-29 | 2014-08-07 | Covidien Lp | Low power monitoring systems and methods |
| CN103908243A (en) * | 2014-04-01 | 2014-07-09 | 南京普澳医疗设备有限公司 | Lifting wavelet and median filter combined algorithm |
| CN104173030A (en) * | 2014-09-09 | 2014-12-03 | 北京航空航天大学 | Pulse wave starting point real-time detection method resisting waveform change interference and application thereof |
Non-Patent Citations (2)
| Title |
|---|
| EMIR TURAJLIC: "A Novel Algorithm for ECG Parametrization and Synthesis", 《2012 IEEE EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING AND SCIENCES》 * |
| 张爱华等: "基于脉搏信号的心电特征研究", 《电子测量技术》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106725376B (en) * | 2016-11-30 | 2017-12-19 | 中南民族大学 | Sign detection method and device |
| CN106725376A (en) * | 2016-11-30 | 2017-05-31 | 高军峰 | Sign detection method and device |
| CN108701219A (en) * | 2017-03-14 | 2018-10-23 | 华为技术有限公司 | The method and device of waveform signal processing |
| US11321561B2 (en) | 2017-03-14 | 2022-05-03 | Huawei Technologies Co., Ltd. | Electrocardiogram waveform signal processing method and apparatus |
| CN110678816B (en) * | 2017-04-04 | 2021-02-19 | 西门子股份公司 | Method and control device for controlling a technical system |
| US10983485B2 (en) | 2017-04-04 | 2021-04-20 | Siemens Aktiengesellschaft | Method and control device for controlling a technical system |
| CN110678816A (en) * | 2017-04-04 | 2020-01-10 | 西门子股份公司 | Method and control device for controlling a technical system |
| CN109833034A (en) * | 2017-11-24 | 2019-06-04 | 深圳市岩尚科技有限公司 | The method and device of blood pressure data is extracted in a kind of pulse wave signal |
| CN108236461A (en) * | 2017-12-22 | 2018-07-03 | 天津天堰科技股份有限公司 | It is a kind of can be into the processing method of the electrocardiosignal of edlin |
| CN108236461B (en) * | 2017-12-22 | 2021-02-19 | 天津天堰科技股份有限公司 | Processing method of electrocardiosignal capable of being edited |
| CN109157202A (en) * | 2018-09-18 | 2019-01-08 | 东北大学 | A kind of cardiovascular disease early warning system based on more physiological signal depth integrations |
| CN110840436A (en) * | 2018-11-15 | 2020-02-28 | 深圳市松恩电子科技有限公司 | Method, device and terminal for acquiring electrocardiosignals and computer readable storage medium |
| CN110327031A (en) * | 2018-11-29 | 2019-10-15 | 武汉中旗生物医疗电子有限公司 | A method of removal electrocardiosignal motion artifacts |
| CN109805921A (en) * | 2018-12-18 | 2019-05-28 | 深圳小辣椒科技有限责任公司 | The cross-platform method of sampling of electrocardiogram (ECG) data and cardioelectric monitor system |
| CN110025296A (en) * | 2019-03-01 | 2019-07-19 | 西安理工大学 | A kind of acquisition method of the characteristic parameter of photoplethysmographic |
| WO2020198522A1 (en) * | 2019-03-26 | 2020-10-01 | University Of Maryland, College Park | Electrocardiogram waveform reconstruction from photoplethysmogram |
| CN110179456B (en) * | 2019-05-23 | 2021-11-02 | 中国航天员科研训练中心 | Electrocardio noise recognition model training and electrocardio noise detection method and device |
| CN111000538A (en) * | 2019-12-30 | 2020-04-14 | 北京丰顺科技发展有限公司 | Pulse condition acquisition and pulse diagnosis device and method capable of exceeding human touch spatial resolution |
| CN111914655A (en) * | 2020-07-06 | 2020-11-10 | 电子科技大学 | Pulse condition classification method based on significant signal subsection extraction |
| CN114081502A (en) * | 2021-11-11 | 2022-02-25 | 中国科学院深圳先进技术研究院 | Non-invasive heart disease diagnosis method and device based on machine learning |
| CN114081502B (en) * | 2021-11-11 | 2022-09-27 | 中国科学院深圳先进技术研究院 | Non-invasive heart disease diagnosis method and device based on machine learning |
| CN114010167A (en) * | 2021-11-25 | 2022-02-08 | 中山大学 | Pulse wave fitting method based on Weibull function |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104706349B (en) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104706349B (en) | Electrocardiosignal construction method based on pulse wave signals | |
| CN108714026B (en) | Fine-grained electrocardiosignal classification method based on deep convolutional neural network and online decision fusion | |
| CN102697493B (en) | Method for rapidly and automatically identifying and removing ocular artifacts in electroencephalogram signal | |
| CN103156599B (en) | Detection method of electrocardiosignal R characteristic waves | |
| Seena et al. | A review on feature extraction and denoising of ECG signal using wavelet transform | |
| CN104688220B (en) | Method for removing ocular artifacts in EEG signals | |
| CN103845079B (en) | A kind of detection method of the Doppler's fetal heart sound instantaneous heart rate based on blind separation | |
| CN103325381B (en) | A kind of speech separating method based on fuzzy membership functions | |
| CN110680308B (en) | Electrocardiosignal denoising method based on fusion of improved EMD and threshold method | |
| CN104473631B (en) | A kind of based on non-negative blind separation Fetal ECG instantaneous heart rate recognition methods and system | |
| CN103405227A (en) | Double-layer morphological filter based electrocardiosignal preprocessing method | |
| CN103610461A (en) | EEG noise elimination method based on dual-density wavelet neighborhood related threshold processing | |
| CN102499670A (en) | Electrocardiogram baseline drifting correction method based on robust estimation and intrinsic mode function | |
| CN103761424A (en) | Electromyography signal noise reducing and aliasing removing method based on second-generation wavelets and ICA (independent component analysis) | |
| CN100586367C (en) | Apparatus for testing gastric electricity of body surface | |
| CN105147252A (en) | Heart disease recognition and assessment method | |
| CN101554325A (en) | Method for extracting fetal electrocardiograms (FECG) by separation | |
| Rezk et al. | An algebraic derivative-based method for R wave detection | |
| CN104905786A (en) | Electrocardiographic artifact on-line removal algorithm | |
| CN107886078A (en) | A kind of Threshold Denoising method based on layered self-adapting threshold function table | |
| CN111504640B (en) | Weighted sliding window second-order synchronous compression S transformation bearing fault diagnosis method | |
| Liu et al. | Systematic methods for fetal electrocardiographic analysis: Determining the fetal heart rate, RR interval and QT interval | |
| CN110313903B (en) | Pulse wave frequency domain characteristic parameter extraction method and device | |
| CN112998690A (en) | Pulse wave multi-feature fusion-based respiration rate extraction method | |
| CN105138823B (en) | A kind of physiological signal quality determining method based on auto-correlation function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170322 |