CN108491879A - It is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods - Google Patents
It is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods Download PDFInfo
- Publication number
- CN108491879A CN108491879A CN201810240279.9A CN201810240279A CN108491879A CN 108491879 A CN108491879 A CN 108491879A CN 201810240279 A CN201810240279 A CN 201810240279A CN 108491879 A CN108491879 A CN 108491879A
- Authority
- CN
- China
- Prior art keywords
- electrocardiosignal
- support vector
- order statistic
- vector machines
- heart
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/245—Classification techniques relating to the decision surface
- G06F18/2453—Classification techniques relating to the decision surface non-linear, e.g. polynomial classifier
-
- 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
- A61B5/72—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Fuzzy Systems (AREA)
- Nonlinear Science (AREA)
- Cardiology (AREA)
- Electrotherapy Devices (AREA)
Abstract
The embodiment of the invention discloses a kind of based on order statistic and support vector machines can the recognition methods of the defibrillation rhythm of the heart and device, it solves existing ShR/NshR recognition methods to need to acquire longer electrocardiosignal, usually 8 seconds, it just can guarantee certain classification performance, result in the technical issues of delaying defibrillation rescue time.Present invention method includes：S1, calculus of differences is carried out to collected first electrocardiosignal, obtains the second electrocardiosignal；S2, ascending order arrangement is carried out to second electrocardiosignal, obtains order statistic；S3, the order statistic is input in Nonlinear Classifier, obtains the classification results of ShR and NshR.
Description
Technical field
The present invention relates to technical field of medical equipment more particularly to it is a kind of based on order statistic and support vector machines can
Defibrillation rhythm of the heart recognition methods.
Background technology
According to the publication of national cardiovascular disease center《Chinese cardiovascular disease report 2016》It has been shown that, annual China's sudden cardiac death
Number of the infected is more than 540,000, is equivalent to daily about 1500 people because sudden cardiac death is passed away.Sudden cardiac death is mainly quivered by room
Caused by (Ventricular Fibrillation, VF) and room speed (Ventricular Tachycardia, VT).Wherein, VF
Breaking-out is often without omen, and the electrical activity of ventricle loses synchronism when breaking-out, and cardiac pumping function is lost, and such as takes measures to turn not in time
The rhythm of the heart is answered, will cause to die suddenly within several minutes.It is clinically unique reliable and wide to implement electric defibrillation within the shortest time
The general room used, which is quivered, turns compound method.
Defibrillation success rate is closely related with the defibrillation time.When VF arrhythmia cordis occurs for patient, implement to remove in 1 minute
It quivers, success rate 100%；The defibrillation in 3 points of kinds, success rate 90%；Defibrillation in 5 minutes, success rate are then down to 30%；If
VF is more than 10 minutes, and defibrillation success rate is almost nil.Therefore, it is the gold for implementing defibrillation rescue life within VF breaks out 3 minutes
Time.However, most of sudden cardiac death events are happened at except medical institutions, patient, which hardly results in, timely and effectively robs treatment
It treats.For the problem, European and American developed countries have been developed that automated external defibrillator (Automatic External
Defibrillator, AED), and it is widely deployed in the big public place of flow of the people, it is effectively improved depositing for VF patient
Motility rate, and China just had first AED to be deployed in the Capital Airport by 2006.
The key technology of AED is can the Electrical Cardioversion rhythm of the heart (Shockable Rhythms, ShR) and can not the Electrical Cardioversion heart
Restrain the recognition methods of (Non-shockable Rhythms, NshR).ShR includes VF and VT；NshR include sinus rhythm, room flutter,
Atrial fibrillation, room escape etc..It, need not if implementing to patient because AED operating personnel are mainly a lack of the public of first aid experience outside institute
The electric defibrillation wanted may cause human heart fatefulue damage, so American Heart Association (American Heart
Association, AHA) formulate professional standard, it is specified that AED products should be higher than that 90% to the identification sensibility of ShR, for
The identification specificity of NshR should be higher than that 95%.
Existing ShR/NshR recognition methods needs to acquire longer electrocardiosignal, usually 8 seconds, just can guarantee certain
Classification performance results in the technical issues of delaying defibrillation rescue time.
Invention content
The present invention provides a kind of based on order statistic and support vector machines can the recognition methods of the defibrillation rhythm of the heart and device,
It solves existing ShR/NshR recognition methods to need to acquire longer electrocardiosignal, usually 8 seconds, just can guarantee certain point
Class performance results in the technical issues of delaying defibrillation rescue time.
The present invention provides a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods, including：
S1, calculus of differences is carried out to collected first electrocardiosignal, obtains the second electrocardiosignal；
S2, ascending order arrangement is carried out to second electrocardiosignal, obtains order statistic；
S3, the order statistic is input in Nonlinear Classifier, obtains the classification results of ShR and NshR.
Optionally, the step S1 is specifically included：
To collected first electrocardiosignalCalculus of differences is carried out, the second electrocardiosignal is obtainedWherein n is time sampling point sum.
Optionally, the step S2 is specifically included：
To second electrocardiosignalAscending order arrangement is carried out, order statistic is obtained
Optionally, the Nonlinear Classifier includes：Gaussian kernel support vector machines, Gauss kernel Fisher discriminant analysis or god
Through network.
Optionally, the Gaussian kernel support vector machines is specially that Gaussian kernel is supportedTo
Amount machine.
The present invention provides a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart identification device, including：
Difference unit obtains the second electrocardiosignal for carrying out calculus of differences to collected first electrocardiosignal；
Sequencing unit obtains order statistic for carrying out ascending order arrangement to second electrocardiosignal；
Taxon obtains the classification of ShR and NshR for the order statistic to be input in Nonlinear Classifier
As a result.
Optionally, the difference unit is additionally operable to collected first electrocardiosignalCarry out difference
Operation obtains the second electrocardiosignalWherein n is time sampling point sum.
Optionally, the sequencing unit is additionally operable to second electrocardiosignalAscending order arrangement is carried out, order statistics are obtained
Amount
Optionally, the Nonlinear Classifier includes：Gaussian kernel support vector machines, Gauss kernel Fisher discriminant analysis or god
Through network.
Optionally, the Gaussian kernel support vector machines is specially that Gaussian kernel is supportedTo
Amount machine.
As can be seen from the above technical solutions, the present invention has the following advantages：
The present invention provides a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods, including：
S1, calculus of differences is carried out to collected first electrocardiosignal, obtains the second electrocardiosignal；S2, to second electrocardiosignal
Ascending order arrangement is carried out, order statistic is obtained；S3, the order statistic is input in Nonlinear Classifier, obtain ShR and
The classification results of NshR.
The first electrocardiosignal of the present invention couple carries out difference and sorts, although calculating simply, is effectively demonstrated by the heart
The distribution of electric signal localised waving, and the main performance of the exception of the distribution exactly VF and VT, and adopted needed for order statistic
Collecting electrocardiogram (ECG) data end, recognition accuracy is high, solves existing ShR/NshR recognition methods and needs to acquire longer electrocardiosignal,
It usually 8 seconds, just can guarantee certain classification performance, result in the technical issues of delaying defibrillation rescue time.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without having to pay creative labor, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
Fig. 1 be it is provided by the invention it is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods
The flow diagram of one embodiment；
Fig. 2 be it is provided by the invention it is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart identification device
The flow diagram of one embodiment；
Fig. 3 is electrocardiosignal original amplitude and taking for order statistic to avenge differentiation rate comparison diagram.
Specific implementation mode
What an embodiment of the present invention provides a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods
And device, it solves existing ShR/NshR recognition methods and needs to acquire longer electrocardiosignal, usually 8 seconds, just can guarantee
Certain classification performance results in the technical issues of delaying defibrillation rescue time.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Range.
Referring to Fig. 1, what the present invention provides a kind of based on order statistic and support vector machines can the identification of the defibrillation rhythm of the heart
One embodiment of method, including：
101, calculus of differences is carried out to collected first electrocardiosignal, obtains the second electrocardiosignal；
Specifically, to collected first electrocardiosignalCalculus of differences is carried out, the second electrocardio is obtained
SignalWherein n is time sampling point sum；
On the one hand calculus of differences eliminates the baseline drift in single electrocardiosignal sequence, on the other hand eliminate different people
Amplification level difference between electrocardiosignal.Electrocardiosignal amplitude becomes between calculus of differences substantially reflects adjacent time sampled point
The degree of change.
102, ascending order arrangement is carried out to the second electrocardiosignal, obtains order statistic；
Specifically, to the second electrocardiosignalAscending order arrangement is carried out, order statistic is obtained
Relative to common quartile and median etc., the ordered series of numbers after sequence is a kind of order statistic the most careful.
Difference is carried out to electrocardiosignal and is sorted, although calculating simply, effectively embodies point of electrocardiosignal localised waving
Cloth.And the major embodiment of the exception of the distribution exactly VF and VT.The embodiment of the present invention is weighed not using Wasserstein distances
Difference between being distributed with electrocardiosignal localised waving.Below with three public data collection VFDB, CUDB and AHADB (totally 1696
Group ShR, 7086 groups of NshR) in, it is examined in the embodiment of the present invention for the electrocardiogram (ECG) data that 4 seconds sample rates of duration are 250Hz
The differentiation performance of extracted feature.As shown in figure 3, the order statistic of the present inventionTake snow differentiation rate (Fisher ' s
Discriminant Ratio, FDR) substantially it is higher than the first electrocardiosignal amplitudeFDR.
If f (x) and g (y) are probability density functions, h (x, y) is joint distribution function, f (x)=∫ h (x, y) dy, g (y)
=∫ h (x, y) dx, then the Wasserstein distance definitions between probability distribution f and g be：
Wherein, d (x, y) is distance measure, p >=1,It indicates under all possible joint distribution function h condition, [∫
d(x,y)ph(x,y)dxdy]1/pInfimum.In practical applications, the calculating of formula (1) is often discretization, for appointing
Meaning distribution μ, can be approached with δ distributions：
Wherein δ is distributed as：
Then two isometric arraysWithBetween Wasserstein distances
It is represented by：
When d (x, y)=| x-y | and when p=2, formula (4) can be further converted into：
Wherein, 1,2 σ ..., any arrangement of n.
Inference：When d (x, y)=| x-y | and when p=2, two isometric arraysWith
Between Wasserstein distance for they distinguish ascending orders arrangementAverage two norms afterwards away from
From that is,：
Card：Assuming that arrayIn it is any to ascending order arrangement element yiAnd yj(yi≤yj, i ＜ j) and reversing of position, then exchange position
It postponesIncrementss be：
Therefore forHaveAgain because of f
(θ)=θ1/2(θ >=0) is the monotonic function about θ, so：
Card is finished.
103, order statistic is input in Nonlinear Classifier, obtains the classification results of ShR and NshR；
Specifically, Nonlinear Classifier includes：Gaussian kernel support vector machines, Gauss kernel Fisher discriminant analysis or nerve net
Network；
Gaussian kernel support vector machines is specially that Gaussian kernel is supportedVector machine；
It is to understand that Gaussian kernel support vector machines, Gauss kernel Fisher discriminant analysis or neural network, which are selected, as grader
Certainly ShR samples and the case where NshR samples incomplete linear separability in feature space.
Order statistic can preferably reflect the pathological information of VT and VF, and required acquisition electrocardiogram (ECG) data is short, and identification is accurate
Rate is high, can be rescued for defibrillation and provide reliable distinguishing rule, and tried to gain time precious to one.The method of the present invention open number at three
According to being tested on collection VFDB, CUDB and AHADB (including 1696 groups of ShR, 7086 groups of NshR), using the flat of 10 retransposings verification
Classification performance indicator is as shown in table 1.From table 1：When only with 1 second electrocardiogram (ECG) data, the sensibility of this method is
The standard 90% of 82.50%, not up to AHA, reason are that 1 second time is too short, often fail to collect complete cardiac electrical cycle；
When using 2 seconds electrocardiogram (ECG) datas, the sensibility of this method is 96.87%, and specificity is 98.38%, and the mark of AHA has been fully achieved
Accurate (sensibility>90%, specificity>95%)；When signal length is 4 seconds or 8 seconds, the sensibility of the method for the present invention>98.2%,
Specificity>99.1%, better than other current published related works.
Table 1 is directed to the electrocardiogram (ECG) data of different durations, and of the invention can defibrillation rhythm of the heart recognition performance
| 8 seconds | 4 seconds | 2 seconds | 1 second | |
| ShR sensibility | 98.54% | 98.21% | 96.87% | 82.50% |
| NshR specificity | 99.72% | 99.17% | 98.38% | 98.08% |
Although the present invention is weighed using the Wasserstein distances of coring between different electrocardiosignal localised waving distributions
Difference, but calculating is extremely simple, only need to carry out difference to electrocardiosignal and ascending order arranges, then substitute into support vector machines, institute
Need calculation resources few, it is low in energy consumption.Therefore, the present invention program can be embedded into wearable device, such as in bracelet and wrist-watch, to the heart
It restrains not normal people at highest risk and carries out long-time monitoring.
The first electrocardiosignal of the present invention couple carries out difference and sorts, although calculating simply, is effectively demonstrated by the heart
The distribution of electric signal localised waving, and the main performance of the exception of the distribution exactly VF and VT, and adopted needed for order statistic
Collecting electrocardiogram (ECG) data end, recognition accuracy is high, solves existing ShR/NshR recognition methods and needs to acquire longer electrocardiosignal,
It usually 8 seconds, just can guarantee certain classification performance, result in the technical issues of delaying defibrillation rescue time.
Be above to it is provided by the invention it is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart identification side
The explanation that one embodiment of method carries out, below will be to provided by the invention a kind of based on order statistic and support vector machines
Can one embodiment of defibrillation rhythm of the heart identification device illustrate.
Referring to Fig. 2, what the present invention provides a kind of based on order statistic and support vector machines can the identification of the defibrillation rhythm of the heart
One embodiment of device, including：
Difference unit 201 obtains the second electrocardiosignal for carrying out calculus of differences to collected first electrocardiosignal；
Specifically, difference unit 201 is additionally operable to collected first electrocardiosignalCarry out difference
Operation obtains the second electrocardiosignalWherein n is time sampling point sum；
Sequencing unit 202 obtains order statistic for carrying out ascending order arrangement to the second electrocardiosignal；
Specifically, sequencing unit 202 is additionally operable to the second electrocardiosignalAscending order arrangement is carried out, order statistic is obtained
Taxon 203 obtains the classification of ShR and NshR for order statistic to be input in Nonlinear Classifier
As a result.
Specifically, Nonlinear Classifier includes：Gaussian kernel support vector machines, Gauss kernel Fisher discriminant analysis or nerve net
Network；
Gaussian kernel support vector machines is specially that Gaussian kernel is supportedVector machine.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be the indirect coupling by some interfaces, device or unit
It closes or communicates to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can be stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention
Portion or part steps.And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to before
Stating embodiment, invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to preceding
The technical solution recorded in each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
Modification or replacement, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. it is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods, which is characterized in that including：
S1, calculus of differences is carried out to collected first electrocardiosignal, obtains the second electrocardiosignal；
S2, ascending order arrangement is carried out to second electrocardiosignal, obtains order statistic；
S3, the order statistic is input in Nonlinear Classifier, obtains the classification results of ShR and NshR.
2. it is according to claim 1 based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods, it is special
Sign is that the step S1 is specifically included：
To collected first electrocardiosignalCalculus of differences is carried out, the second electrocardiosignal is obtainedWherein n is time sampling point sum.
3. it is according to claim 2 based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods, it is special
Sign is that the step S2 is specifically included：
To second electrocardiosignalAscending order arrangement is carried out, order statistic is obtained
4. it is according to claim 3 based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods, it is special
Sign is that the Nonlinear Classifier includes：Gaussian kernel support vector machines, Gauss kernel Fisher discriminant analysis or neural network.
5. it is according to claim 4 based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods, it is special
Sign is that the Gaussian kernel support vector machines is specially that Gaussian kernel is supportedVector machine.
6. it is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart identification device, which is characterized in that including：
Difference unit obtains the second electrocardiosignal for carrying out calculus of differences to collected first electrocardiosignal；
Sequencing unit obtains order statistic for carrying out ascending order arrangement to second electrocardiosignal；
Taxon obtains the classification knot of ShR and NshR for the order statistic to be input in Nonlinear Classifier
Fruit.
7. it is according to claim 6 based on order statistic and support vector machines can defibrillation rhythm of the heart identification device, it is special
Sign is that the difference unit is additionally operable to collected first electrocardiosignalCalculus of differences is carried out, is obtained
To the second electrocardiosignalWherein n is time sampling point sum.
8. it is according to claim 7 based on order statistic and support vector machines can defibrillation rhythm of the heart identification device, it is described
Sequencing unit is additionally operable to second electrocardiosignalAscending order arrangement is carried out, order statistic is obtained
9. it is according to claim 8 based on order statistic and support vector machines can defibrillation rhythm of the heart identification device, it is described
Nonlinear Classifier includes：Gaussian kernel support vector machines, Gauss kernel Fisher discriminant analysis or neural network.
10. it is according to claim 9 based on order statistic and support vector machines can defibrillation rhythm of the heart identification device, it is described
Gaussian kernel support vector machines is specially that Gaussian kernel is supportedVector machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810240279.9A CN108491879A (en) | 2018-03-22 | 2018-03-22 | It is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810240279.9A CN108491879A (en) | 2018-03-22 | 2018-03-22 | It is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108491879A true CN108491879A (en) | 2018-09-04 |
Family
ID=63319254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810240279.9A Pending CN108491879A (en) | 2018-03-22 | 2018-03-22 | It is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108491879A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102379694A (en) * | 2011-10-12 | 2012-03-21 | 中国科学院苏州纳米技术与纳米仿生研究所 | Electrocardiogram R wave detection method |
| CN102779234A (en) * | 2012-06-28 | 2012-11-14 | 中国科学院苏州纳米技术与纳米仿生研究所 | Electrocardiogram classified processing method and device |
| CN105656826A (en) * | 2016-03-18 | 2016-06-08 | 清华大学 | Modulation recognizing method and system based on order statistics and machine learning |
-
2018
- 2018-03-22 CN CN201810240279.9A patent/CN108491879A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102379694A (en) * | 2011-10-12 | 2012-03-21 | 中国科学院苏州纳米技术与纳米仿生研究所 | Electrocardiogram R wave detection method |
| CN102779234A (en) * | 2012-06-28 | 2012-11-14 | 中国科学院苏州纳米技术与纳米仿生研究所 | Electrocardiogram classified processing method and device |
| CN105656826A (en) * | 2016-03-18 | 2016-06-08 | 清华大学 | Modulation recognizing method and system based on order statistics and machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 李健: "应用非线性动力技术室颤算法及其实现", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109171712B (en) | Atrial fibrillation identification method, atrial fibrillation identification device, atrial fibrillation identification equipment and computer readable storage medium | |
| JP6786536B2 (en) | Cascade binary classifier to identify rhythms in Faraday paradoxical (ECG) signals | |
| KR102451795B1 (en) | ECG signal detection method | |
| Tripathy et al. | Detection of shockable ventricular arrhythmia using variational mode decomposition | |
| CN110811609B (en) | Epileptic spike intelligent detection device based on self-adaptive template matching and machine learning algorithm fusion | |
| Cheng et al. | Life-threatening ventricular arrhythmia detection with personalized features | |
| CN109171708B (en) | Defibrillation heart rhythm recognition device | |
| Shao et al. | Detection of atrial fibrillation from ECG recordings using decision tree ensemble with multi-level features | |
| de Chazal et al. | Automatic classification of ECG beats using waveform shape and heart beat interval features | |
| CN107595276B (en) | Atrial fibrillation detection method based on single-lead electrocardiosignal time-frequency characteristics | |
| Kumari et al. | Heart rhythm abnormality detection and classification using machine learning technique | |
| CN108852347A (en) | For extracting the method for the characteristic parameter of cardiac arrhythmia, the device and computer-readable medium of cardiac arrhythmia for identification | |
| CN106108880B (en) | Automatic heart beat identification method and system | |
| Smisek et al. | Multi-stage SVM approach for cardiac arrhythmias detection in short single-lead ECG recorded by a wearable device | |
| CN109124620A (en) | A kind of atrial fibrillation detection method, device and equipment | |
| CN115486855A (en) | Electrocardiogram heart beat classification method based on QRS wave group indefinite cycle superposition | |
| Chen et al. | The feasibility of predicting impending malignant ventricular arrhythmias by using nonlinear features of short heartbeat intervals | |
| CN110751131A (en) | Arrhythmia detection device | |
| CN108523873B (en) | Electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy | |
| Rahman et al. | Identifying hypertrophic cardiomyopathy patients by classifying individual heartbeats from 12-lead ECG signals | |
| Sady et al. | Symbolic features and classification via support vector machine for predicting death in patients with Chagas disease | |
| EP3881767A1 (en) | Systems and methods for atrial fibrillation (af) and cardiac disorders detection from biological signals | |
| Anas et al. | Exploiting correlation of ECG with certain EMD functions for discrimination of ventricular fibrillation | |
| Tuboly et al. | Atrial fibrillation detection based on poincaré plot and P wave analysis | |
| CN108491879A (en) | It is a kind of based on order statistic and support vector machines can defibrillation rhythm of the heart recognition methods |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |
|
| RJ01 | Rejection of invention patent application after publication |