CN108922619A - A kind of RdR scatter plot recognition methods based on sparse core leading role - Google Patents
A kind of RdR scatter plot recognition methods based on sparse core leading role Download PDFInfo
- Publication number
- CN108922619A CN108922619A CN201810756125.5A CN201810756125A CN108922619A CN 108922619 A CN108922619 A CN 108922619A CN 201810756125 A CN201810756125 A CN 201810756125A CN 108922619 A CN108922619 A CN 108922619A
- Authority
- CN
- China
- Prior art keywords
- leading role
- sample
- scatter plot
- rdr
- core leading
- 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
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention discloses a kind of RdR scatter plot recognition methods based on sparse core leading role, and step 1) obtains electrocardiosignal, and filtering and noise reduction extracts R crest value position;Step 2) draws RdR scatter plot using heartbeat interval;Step 3) zooms in and out RdR scatter plot;The scatter plot sample of acquisition is marked in step 4);Step 5) is respectively to every class specimen sample;Step 6) selects different parameters, solves approximate base to every class sample respectively;Each test sample is calculated core leading role with approximate base respectively by step 7), its value the maximum is set as the prediction classification of test sample, compared with concrete class, assesses the performance of classifier, the step 8) if meeting performance indicator, otherwise return step 6) Reparametrization;Step 8) obtains disaggregated model, and algorithm terminates;The present invention carries out the Classification and Identification of heart rate variability using sparse core leading role, has satisfactory classifying quality.
Description
Technical field
The present invention relates to a kind of RdR scatter plot recognition methods based on sparse core leading role, belong to intelligent medical technical field.
Background technique
Cardiovascular disease is unhealthful important killer, in June, 2017《Chinese cardiovascular disease report 2016》Publication.Report
It points out:Currently, cardiovascular death accounts for the first place of the total cause of death of urban and rural residents, and 10 years from now on cardiovascular disease numbers of patients are still
By rapid growth.In addition, will be about 23,300,000 people according to the report of the World Health Organization to the year two thousand thirty and died of cardiovascular disease.
In face of this trend, the early diagnosis and prevention of cardiovascular disease are particularly important.
Traditional diagnostic method is patient to hospital, and doctor carries out ECG examination to it, and then provides diagnostic result, is appointed
It is engaged in heavy and doctor is needed to have clinical experience abundant and professional knowledge;And rare medical resource, it is difficult to meet substantial amounts
The requirement of PATIENT POPULATION.In order to improve medical efficiency, convenience and agility, there is automated diagnostic technology, assist doctor
It is diagnosed.
Heart rate variability refers to the time-variance number between cardiac cycle, and research object is cardiac cycle rather than heart rate.
The heart rate of people be not it is unalterable, there is small time differences between heartbeat twice, calculate the difference of cardiac cycle, i.e.,
It can be appreciated that heart rate variability (Heart rate variability, HRV).
Heart rate variability can assess the influence of cardiac sympathetic nerve and parasympathetic nerve to cardiovascular activity, contain the heart
Bulk information in terms of blood vessel.Clinical research shows that the reduction of heart rate variability is the hearts such as myocardial infarction, hypertension, angina pectoris
The symptom of vascular morbidity.Therefore, the research of heart rate variability, in evaluation systema cariovasculare functional, prediction cardiovascular disease
Breaking-out, and have great importance for the early diagnosis of cardiovascular disease.
Poincare scatter plot is a kind of important research method of heart rate variability:Existed by using continuous heartbeat interval
Graphing in rectangular coordinate system reflects the variation of adjacent heartbeat interval, can show the feature of heartbeat interval;Poincare scatterplot
For figure there are many form, including comet formation, sector etc., different shapes reflects different heart states.
Although Poincare scatter plot is a kind of effective heart rate variance analyzing method, it can not be embodied at any time
Between the trend that changes, its heart rate variability property cannot be embodied well for certain cardiovascular diseases, physical condition etc..
Then, some scholars propose improvement strategy, i.e. first order difference plot, draw scatterplot by the difference of adjacent heartbeat interval
Figure.However, this method is lost the absolute value information of original heartbeat interval again;Therefore, and scholar combines the two,
A kind of RdR scatter plot is proposed, come with this while reflecting heartbeat interval and its variation.
Currently, many for the heart rate variability analysis of different cardiovascular diseases;But how according to scatter plot come automatic
It identifies, to distinguish different cardiovascular diseases then relatively deficient.
Summary of the invention
The object of the invention is that providing a kind of RdR scatter plot based on sparse core leading role to solve the above-mentioned problems
Recognition methods, can automatic recognition classification RdR scatter plot, perform an analysis to heart rate variability, for realize automated diagnostic, alleviate it is tight
The waste of scarce medical resource, reduction medical resource improves medical efficiency offer basis.
The present invention is achieved through the following technical solutions above-mentioned purpose:A kind of RdR scatter plot knowledge based on sparse core leading role
Other method, includes the following steps:
Step 1) obtains electrocardiosignal, is filtered denoising to electrocardiosignal, extracts R crest value position;
Step 2) draws RdR scatter plot using heartbeat interval, can be drawn by MATLAB tool;
Step 3) zooms in and out RdR scatter plot, grayscale image is changed into, and image data is normalized, to subtract
Few calculation amount;
The scatter plot sample of acquisition is marked in step 4);
Step 5) randomly selects wherein 80% data as training sample respectively to every class specimen sample, remaining
20% is used as test sample;
Step 6) selects different parameters, solves approximate base to every class sample respectively;
Each test sample is calculated core leading role with approximate base respectively by step 7), and value the maximum is set as the pre- of test sample
Classification is surveyed, compared with concrete class, assesses the performance of classifier, the step 8) if meeting performance indicator, otherwise return step 6)
Reparametrization;
Step 8) obtains disaggregated model, and algorithm terminates.
The basic skills of sparse core leading role:
Leading role (Principal Angle, PA) is a kind of parameter for relationship between metric data collection, studies two numbers
The correlation of data is analyzed according to the minimum angle of subspace;
Assuming that X and Y are the stochastic variable of two zero-means, [a1,...,aN] and [b1,...,bM] it is in X and Y respectively
Two samples;Enable A=[a1,...,aN], B=[b1,...,bM], it is U there are two subspaceA=span { a1,...,aNAnd UB=
span{b1,...,bMIt is two sub-spaces;θ is the leading role of the two subspaces, is met:
For convenient for calculating, formula (1) is newly defined as:
The Lagrangian of structural formula (2):
Above formula asks local derviation to obtain x, y:
α and β is the unique variable in two local derviation formulas respectively, thus 2 α in local derviation formula and 2 β can be newly defined as α and
β, it is easy to derive to draw a conclusion:
Eigenvalue problem below is summarized as to solve:
Further two formulas are merged into:
The shortcomings that in order to solve the problems, such as nonlinear correlation, overcome conventional linear leading role's method, numerous scholars draw kernel function
Enter in leading role, produces core leading role (Kernel Principal Angle, KPA);
Assuming that Nonlinear Mapping T is by the vector a of the input spacekIt is mapped in high-dimensional feature space, then hasWithFormula (2) can be write as:
Be converted to eigenvalue problem:
After introducing Kernel-Based Methods,It can be described with nuclear matrix, formula (9)
Maximum eigenvalue λl, i.e. λl=cos θ is characterized subspace UAAnd UBThe cosine value of angle;And when sample number is larger, it solves
It will appear difficulty, in addition, core leading role is easy to appear overfitting, it is therefore desirable to sparse core leading role (Sparse Kernel
Principal Angle,SKPA);
According to formula (2) it can be found that Ax and yTBTIt is the linear combination of sample space, if finding the base of sample A and B, just
Ax and y can be replaced with the linear combination of baseTBT;Without loss of generality, it is assumed thatIt may determine that by following formula
It can be by ΦAIn the linear combination table of other samples show:
Solution procedure is as follows:
By Lagrange conditionObtain -2K0λ=0+2K, wherein K0=(k (x1,xk),…,k(xl,xk))T, the side of being K
It structures the formation, Kij=k (xi,xj);When kernel function is gaussian radial basis function, matrix K positive definite obtains λmin=K-1K0。
It is comprised the concrete steps that in the step 6) like what base solved:
A. set is establishedFor approximate Maximum independent group, XA=φ;
B. for k=2 ..., N'sMinimizing value;
C. if obtaining minimum value≤ε, corresponding element is added in XA, is otherwise Xl;
ε is linearly related truncated error, asks the base of infinite dimensional space almost without sparsity in limited sample, therefore
Select approximate calculation;
Return step B), until completing all calculating, calculating terminates;
It is solved by approximate base, ΦAIt is split into two set Xl、XA, XlIn element Line independent, XAIn element can be with
By XlLinear combination indicates, even if ε will lead to error, but according to Statistical Learning Theory, to control the learning ability of core leading role;ΦB
Similarly, BlIn element Line independent;At this point, formula (8) solution is simplified, it is equivalent to solve eigenvalue problem below:
It is sparse core leading role.
Compared with prior art, the present invention is ground using sparse core leading role method by the minimum angle between metric data
Study carefully its correlation and carrys out automatic recognition classification RdR scatter plot.It is performed an analysis using the method for the present invention to heart rate variability, can be real
Existing automated diagnostic, the waste alleviated medical resource in short supply, reduce medical resource, the medical efficiency of raising provide some bases.
Detailed description of the invention
Fig. 1 is specific method flow chart of the present invention;
Fig. 2 is RdR scatter plot;
Fig. 3 is the partial test result figure with test data testing classification device performance.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Fig. 1, a kind of RdR scatter plot recognition methods based on sparse core leading role, includes the following steps:
Step 1) obtains electrocardiosignal, is filtered denoising to electrocardiosignal, extracts R crest value position;
Step 2) draws RdR scatter plot using heartbeat interval, can be drawn by MATLAB tool;
Step 3) zooms in and out RdR scatter plot, grayscale image is changed into, and image data is normalized, to subtract
Few calculation amount;
The scatter plot sample of acquisition is marked in step 4);
Step 5) randomly selects wherein 80% data as training sample respectively to every class specimen sample, remaining
20% is used as test sample;
Step 6) selects different parameters, solves approximate base to every class sample respectively;
Each test sample is calculated core leading role with approximate base respectively by step 7), and value the maximum is set as the pre- of test sample
Classification is surveyed, compared with concrete class, assesses the performance of classifier, the step 8) if meeting performance indicator, otherwise return step 6)
Reparametrization;
Step 8) obtains disaggregated model, and algorithm terminates.
Wherein, the basic skills of sparse core leading role:
Leading role (Principal Angle, PA) is a kind of parameter for relationship between metric data collection, studies two numbers
The correlation of data is analyzed according to the minimum angle of subspace;
Assuming that X and Y are the stochastic variable of two zero-means, [a1,...,aN] and [b1,...,bM] it is in X and Y respectively
Two samples;Enable A=[a1,...,aN], B=[b1,...,bM], it is U there are two subspaceA=span { a1,...,aNAnd UB=
span{b1,...,bMIt is two sub-spaces;θ is the leading role of the two subspaces, is met:
For convenient for calculating, formula (1) is newly defined as:
The Lagrangian of structural formula (2):
Above formula asks local derviation to obtain x, y:
α and β is the unique variable in two local derviation formulas respectively, thus 2 α in local derviation formula and 2 β can be newly defined as α and
β, it is easy to derive to draw a conclusion:
Eigenvalue problem below is summarized as to solve:
Further two formulas are merged into:
The shortcomings that in order to solve the problems, such as nonlinear correlation, overcome conventional linear leading role's method, numerous scholars draw kernel function
Enter in leading role, produces core leading role (Kernel Principal Angle, KPA);
Assuming that Nonlinear Mapping T is by the vector a of the input spacekIt is mapped in high-dimensional feature space, then hasWithFormula (2) can be write as:
Be converted to eigenvalue problem:
After introducing Kernel-Based Methods,It can be described with nuclear matrix, formula (9)
Maximum eigenvalue λl, i.e. λl=cos θ is characterized subspace UAAnd UBThe cosine value of angle;And when sample number is larger, it solves
It will appear difficulty, in addition, core leading role is easy to appear overfitting, it is therefore desirable to sparse core leading role (Sparse Kernel
Principal Angle,SKPA);
According to formula (2) it can be found that Ax and yTBTIt is the linear combination of sample space, if finding the base of sample A and B, just
Ax and y can be replaced with the linear combination of baseTBT;Without loss of generality, it is assumed thatIt may determine that by following formula
It can be by ΦAIn the linear combination table of other samples show:
Solution procedure is as follows:
By Lagrange conditionObtain -2K0λ=0+2K, wherein K0=(k (x1,xk),…,k(xl,xk))T, the side of being K cloth
Battle array, Kij=k (xi,xj);When kernel function is gaussian radial basis function, matrix K positive definite obtains λmin=K-1K0。
Wherein, it is comprised the concrete steps that in the step 6) like what base solved:
A. set is establishedFor approximate Maximum independent group, XA=φ;
B. for k=2 ..., N'sMinimizing value;
C. if obtaining minimum value≤ε, corresponding element is added in XA, is otherwise Xl;
ε is linearly related truncated error, asks the base of infinite dimensional space almost without sparsity in limited sample, therefore
Select approximate calculation;
Return step 2), until completing all calculating, calculating terminates;
It is solved by approximate base, ΦAIt is split into two set Xl、XA, XlIn element Line independent, XAIn element can be with
By XlLinear combination indicates, even if ε will lead to error, but according to Statistical Learning Theory, to control the learning ability of core leading role;ΦB
Similarly, BlIn element Line independent;At this point, formula (8) solution is simplified, it is equivalent to solve eigenvalue problem below:
It is sparse core leading role.
Using the electrocardiogram (ECG) data in MIT-BIH database, to make schematically analysis with the data of this database convenient for narration
It introduces.
Fig. 2 is the RdR scatter plot that MIT-BIH electrocardiogram (ECG) data is drawn by MATLAB.RdR scatter plot can effectively reflect
Heartbeat interval changes with time trend, contains a large amount of clinical information, can show different heartbeat features.Experiment display, makes
Identification classification is carried out to it with the method for the present invention, effect is preferable.
Fig. 3 is that method, the result display diagram of part classifying test display according to the present invention, and accuracy rate is higher, in figure, ginseng
Number true is actual sample class, and predicted is the classification of classifier prediction, and the image shown in figure is RdR scatter plot.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (3)
1. a kind of RdR scatter plot recognition methods based on sparse core leading role, which is characterized in that include the following steps:
Step 1) obtains electrocardiosignal, is filtered denoising to electrocardiosignal, extracts R crest value position;
Step 2) draws RdR scatter plot using heartbeat interval, can be drawn by MATLAB tool;
Step 3) zooms in and out RdR scatter plot, changes into grayscale image, and image data is normalized, in terms of reducing
Calculation amount;
The scatter plot sample of acquisition is marked in step 4);
Step 5) respectively to every class specimen sample, make as training sample, remaining 20% by the data for randomly selecting wherein 80%
For test sample;
Step 6) selects different parameters, solves approximate base to every class sample respectively;
Each test sample is calculated core leading role with approximate base respectively by step 7), and value the maximum is set as the prediction class of test sample
Not, compared with concrete class, the performance of classifier is assessed, the step 8) if meeting performance indicator, otherwise return step 6) again
Parameter is set;
Step 8) obtains disaggregated model, and algorithm terminates.
2. a kind of RdR scatter plot recognition methods based on sparse core leading role according to claim 1, it is characterised in that:It is dilute
Dredge the basic skills of core leading role:
Leading role (Principal Angle, PA) is a kind of parameter for relationship between metric data collection, studies two data
The minimum angle in space analyzes the correlations of data;
Assuming that X and Y are the stochastic variable of two zero-means, [a1,...,aN] and [b1,...,bM] it is two samples in X and Y respectively
This;Enable A=[a1,...,aN], B=[b1,...,bM], it is U there are two subspaceA=span { a1,...,aNAnd UB=span
{b1,...,bMIt is two sub-spaces;θ is the leading role of the two subspaces, is met:
For convenient for calculating, formula (1) is newly defined as:
The Lagrangian of structural formula (2):
Above formula asks local derviation to obtain x, y:
α and β is the unique variable in two local derviation formulas respectively, therefore 2 α in local derviation formula and 2 β can be newly defined as α and β, very
It is easy to derive to draw a conclusion:
Eigenvalue problem below is summarized as to solve:
Further two formulas are merged into:
The shortcomings that in order to solve the problems, such as nonlinear correlation, overcome conventional linear leading role's method, kernel function is introduced by numerous scholars
In leading role, core leading role (Kernel Principal Angle, KPA) is produced;
Assuming that Nonlinear Mapping T is by the vector a of the input spacekIt is mapped in high-dimensional feature space, then hasWithFormula (2) can be write as:
Be converted to eigenvalue problem:
After introducing Kernel-Based Methods,It can be described with nuclear matrix, formula (9) is most
Big eigenvalue λl, i.e. λl=cos θ is characterized subspace UAAnd UBThe cosine value of angle;And when sample number is larger, solution can go out
Existing difficulty, in addition, core leading role is easy to appear overfitting, it is therefore desirable to sparse core leading role (Sparse Kernel Principal
Angle,SKPA);
According to formula (2) it can be found that Ax and yTBTIt is the linear combination of sample space, if finding the base of sample A and B, so that it may
Ax and y are replaced with the linear combination of baseTBT;Without loss of generality, it is assumed thatIt may determine that by following formulaIt can
By ΦAIn the linear combination table of other samples show:
Solution procedure is as follows:
By Lagrange conditionObtain -2K0λ=0+2K, wherein K0=(k (x1,xk),…,k(xl,xk))T, the side of being K structures the formation,
Kij=k (xi,xj);When kernel function is gaussian radial basis function, matrix K positive definite obtains λmin=K-1K0。
3. a kind of RdR scatter plot recognition methods based on sparse core leading role according to claim 1, it is characterised in that:Institute
It is comprised the concrete steps that in the step 6) stated like what base solved:
A. set is establishedFor approximate Maximum independent group, XA=φ;
B. for k=2 ..., N'sMinimizing value;
C. if obtaining minimum value≤ε, corresponding element is added in XA, is otherwise Xl;
ε is linearly related truncated error, asks the base of infinite dimensional space almost without sparsity in limited sample, therefore is selected
Approximate calculation;
Return step B), until completing all calculating, calculating terminates;
It is solved by approximate base, ΦAIt is split into two set Xl、XA, XlIn element Line independent, XAIn element can be by Xl
Linear combination indicates, even if ε will lead to error, but according to Statistical Learning Theory, to control the learning ability of core leading role;ΦBTogether
Reason, BlIn element Line independent;At this point, formula (8) solution is simplified, it is equivalent to solve eigenvalue problem below:
It is sparse core leading role.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810756125.5A CN108922619A (en) | 2018-07-11 | 2018-07-11 | A kind of RdR scatter plot recognition methods based on sparse core leading role |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810756125.5A CN108922619A (en) | 2018-07-11 | 2018-07-11 | A kind of RdR scatter plot recognition methods based on sparse core leading role |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108922619A true CN108922619A (en) | 2018-11-30 |
Family
ID=64412365
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810756125.5A Pending CN108922619A (en) | 2018-07-11 | 2018-07-11 | A kind of RdR scatter plot recognition methods based on sparse core leading role |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108922619A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110083715A (en) * | 2019-03-20 | 2019-08-02 | 杭州电子科技大学 | A kind of threedimensional model classification retrieving method based on nuclear sparse expression |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106073755A (en) * | 2016-05-27 | 2016-11-09 | 成都信汇聚源科技有限公司 | The implementation method that in a kind of miniature holter devices, atrial fibrillation identifies automatically |
CN108021881A (en) * | 2017-12-01 | 2018-05-11 | 腾讯数码(天津)有限公司 | A kind of skin color segmentation method, apparatus and storage medium |
-
2018
- 2018-07-11 CN CN201810756125.5A patent/CN108922619A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106073755A (en) * | 2016-05-27 | 2016-11-09 | 成都信汇聚源科技有限公司 | The implementation method that in a kind of miniature holter devices, atrial fibrillation identifies automatically |
CN108021881A (en) * | 2017-12-01 | 2018-05-11 | 腾讯数码(天津)有限公司 | A kind of skin color segmentation method, apparatus and storage medium |
Non-Patent Citations (2)
Title |
---|
甘良志 等: ""集成主角及其在故障检测中的应用"", 《控制理论与应用》 * |
陆宏伟 等: ""基于RdR新型散点图心率变异性研究"", 《生物医学工程学杂志》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110083715A (en) * | 2019-03-20 | 2019-08-02 | 杭州电子科技大学 | A kind of threedimensional model classification retrieving method based on nuclear sparse expression |
CN110083715B (en) * | 2019-03-20 | 2021-05-25 | 杭州电子科技大学 | Three-dimensional model classification retrieval method based on kernel sparse representation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Xing et al. | Combination data mining methods with new medical data to predicting outcome of coronary heart disease | |
Daniel et al. | Assessment of cardiac stress from massive pulmonary embolism with 12-lead ECG | |
CN109447940A (en) | Convolutional neural networks training method, ultrasound image recognition positioning method and system | |
CN107730497A (en) | A kind of plaque within blood vessels property analysis method based on depth migration study | |
WO2009005734A2 (en) | Diagnostic and predictive system and methodology using multiple parameter electrocardiography superscores | |
CN109157211A (en) | A kind of portable cardiac on-line intelligence monitoring diagnosis system design method | |
CN109925002A (en) | Artificial intelligence echocardiogram data collection system and its collecting method | |
CN108766555A (en) | The computer diagnosis method and system of Pancreatic Neuroendocrine Tumors grade malignancy | |
Stracina et al. | Golden standard or obsolete method? Review of ECG applications in clinical and experimental context | |
Cheng et al. | Atrial fibrillation identification with PPG signals using a combination of time-frequency analysis and deep learning | |
CN112906748A (en) | 12-lead ECG arrhythmia detection classification model construction method based on residual error network | |
CN112508884A (en) | Comprehensive detection device and method for cancerous region | |
CN111816270B (en) | Attribute parallel reduction Spark method for large-scale liver electronic medical record lesion classification | |
US8775093B2 (en) | Pattern recognition system for classifying the functional status of patients with pulmonary hypertension, including pulmonary arterial and pulmonary vascular hypertension | |
Shen et al. | Risk prediction for cardiovascular disease using ECG data in the China Kadoorie Biobank | |
Ling et al. | Quantitative measurements of zebrafish heartrate and heart rate variability: A survey between 1990–2020 | |
Dongdong et al. | Semantic clustering fuzzy c means spectral model based comparative analysis of cardiac color ultrasound and electrocardiogram in patients with left ventricular heart failure and cardiomyopathy | |
Chou et al. | Extracting drug utilization knowledge using self-organizing map and rough set theory | |
Li et al. | Automatic heartbeat classification using S-shaped reconstruction and a squeeze-and-excitation residual network | |
CN115005768A (en) | Skin disease picture classification method, device, product and storage medium | |
CN108922619A (en) | A kind of RdR scatter plot recognition methods based on sparse core leading role | |
CN102565316B (en) | Analytical method of nuclear texture of peripheral blood mononuclear cell | |
Ali et al. | Comparative evaluation for two and five classes ECG signal classification: applied deep learning | |
CN109119158A (en) | A kind of RdR scatter plot recognition methods based on sparse kernel principle component analysis | |
El Rafaie et al. | On the use of SPECT imaging datasets for automated classification of ventricular heart disease |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181130 |
|
WD01 | Invention patent application deemed withdrawn after publication |