CN107029354A - The impact signal detection method of heart defibrillator - Google Patents
The impact signal detection method of heart defibrillator Download PDFInfo
- Publication number
- CN107029354A CN107029354A CN201611090903.9A CN201611090903A CN107029354A CN 107029354 A CN107029354 A CN 107029354A CN 201611090903 A CN201611090903 A CN 201611090903A CN 107029354 A CN107029354 A CN 107029354A
- Authority
- CN
- China
- Prior art keywords
- conversion
- detection method
- value
- signal
- signal detection
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/38—Applying electric currents by contact electrodes alternating or intermittent currents for producing shock effects
- A61N1/39—Heart defibrillators
- A61N1/3925—Monitoring; Protecting
- A61N1/3937—Monitoring output parameters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N1/00—Electrotherapy; Circuits therefor
- A61N1/18—Applying electric currents by contact electrodes
- A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
- A61N1/38—Applying electric currents by contact electrodes alternating or intermittent currents for producing shock effects
- A61N1/39—Heart defibrillators
- A61N1/395—Heart defibrillators for treating atrial fibrillation
Landscapes
- Health & Medical Sciences (AREA)
- Radiology & Medical Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Cardiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Electrotherapy Devices (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The impact signal detection method of heart defibrillator according to an embodiment of the invention may include steps of：Receive electrocardiosignal；First conversion is carried out to the electrocardiosignal of the receiving；Second is carried out to the electrocardiosignal by the described first conversion to convert；Utilize the signal of change characteristic value by the second conversion；And the characteristic value of the calculating is used as input value and impact signal is detected by Weighted Fuzzy membership function.
Description
Technical field
The present invention relates to it is a kind of can cripetura to sudden arrest of heart beat patient apply impact heart defibrillator carry out defibrillation
The impact signal detection method of the heart defibrillator of time before.
Background technology
Many people are dead because of heart arrest (Sudden Cardiac Arrest, SCA), and the death of wherein most is former
Because being due to the arrhythmia cordis of life-threatening.When there is the deep arrhythmia cordis of life-threatening degree, the survival rate of patient with
Rapid emergency measure is closely linked to.Thus, outer cardiac defibrillator (the Automated External of automaton
Defibrillator popularization extensive diffusive).The outer cardiac defibrillator of above-mentioned automaton is whether a kind of automatic decision needs application
The after-applied surge of surge, the device of electrocardiosignal is judged without medical professional.
Compared with the sudden arrest of heart beat patient of the other countries such as the U.S., the survival rate of South Korea country sudden arrest of heart beat patient is very low
, because the environment without enough rapid emergency measures of permission.It is preferred, therefore, that be not only rescue personnel but
Common people are also carried out to patient after automatic cardiac defibrillation at the scene using cardiac defibrillator outside automaton, and patient is moved to
Hospital.
It is most commonly that thick room is quivered (coarse ventricular in the type of the arrhythmia cordis of life-threatening degree
Fibrillation, coarse VF) or fast ventricular tachycardia (rapid ventricular tachycardia, rapid
VT).In the case of the sudden arrest of heart beat patient for above-mentioned coarse VF or rapid VT occur, carried out only within 10 minutes
Defibrillation could survive, and pass through over time, per minute 7 to 10% survival rate reduction, so that, by using heart outside automaton
Sirecard is next, and quickly survival rate can be improved by carrying out defibrillation.
Therefore, in order to perform defibrillation, the step of first needing to detect such as coarse VF and rapid VT impact signals.Arrive
Be used for detecting in the algorithm of above-mentioned impact signal so far, delay (Time-Delay) algorithm delivered in 2007 by
ECG signal sampling coarse VF between 8 seconds.Moreover, parameter set (Parameter Set) algorithm passed through between 10 seconds
Electrocardiosignal can detect coarse VF, rapid VT, NSR and N (other arrhythmia cordis).The radial direction base delivered in 2008
Function (Radial Basis Function, RBF) detection algorithm can detect VF/VT and NSR/N and strive for preferable knot
Really, but because being pre-selected there is the problem of generality is relatively low for the electrocardiosignal of experiment.
As described above, people are directed to being made internal disorder or usurp for shortening the grinding for method of time needed for performing defibrillation always.In reality
On border, also it is developed from the algorithm of the charging capacitor before detection electrocardiosignal to apply impact signal, but contracting
The short ECG signal sampling time in itself and improve accuracy in detection method be do not have also it is disclosed.
The content of the invention
It is an object of the invention to provide it is a kind of can cripetura to sudden arrest of heart beat patient apply impact heart defibrillator
The impact signal detection method of the heart defibrillator of time before defibrillation is carried out.
The impact signal detection method of heart defibrillator may include steps of according to an embodiment of the invention：Connect
By electrocardiosignal；First conversion is carried out to the electrocardiosignal of the receiving；Electrocardiosignal by the described first conversion is carried out
Second conversion；Utilize the signal of change characteristic value by the second conversion；And the characteristic value of the calculating is used as input value
And impact signal is detected by Weighted Fuzzy membership function.
The signal of the receiving can be digital form signal.
First conversion can be wavelet transformation.
Second conversion can be delay conversion (Time Delay Transform).
The delay conversion can be realized by formula " Y (x)=X (x+0.5)-X (x) ", in formula, and the X (x) can be warp
The signal of the first conversion is crossed, Y (x) can be the signal by the second conversion.
The impact signal detection method of the heart defibrillator may also include by using the conversion of process second
Signal judges whether asystolic step.
It is described to judge whether that asystolic step be included by using the signal value by the second conversion
The step of summation of absolute value is to be judged.
It is described judge whether asystolic step can include by using it is described by second conversion signal value it
Between distance to be judged the step of.
If it is determined that whether the asystolic judged result is no, it is possible to carry out the step of the calculating characteristic value
Suddenly.
The step of calculating characteristic value can include calculating set in the signal value by the second conversion in advance
The step of average distance between value in fixed amplitude interval.
The step of calculating characteristic value, can include calculating the connection straight line by the second signal value converted
The step of standard deviation of gradient.
The step of calculating characteristic value, can include number, the peak for calculating the peak value of the signal by the second conversion
The step of front and rear value of value, at least one being contained in the standard deviation of the peak value of scope set in advance.
The characteristic value of the calculating can be seven.
Impact signal detection method according to an embodiment of the invention has the effect that：By being detected in 7 seconds
The time needed for applying defibrillation shocks signal can be shortened to the impact signal according to electrocardiosignal.
Brief description of the drawings
Fig. 1 is the flow chart for showing impact signal detection method according to an embodiment of the invention.
Fig. 2 is the figure for showing the original input signal in impact signal detection method according to an embodiment of the invention
Table.
Fig. 3 a are to show in impact signal detection method according to an embodiment of the invention by the first conversion
The chart of signal.
Fig. 3 b are to show in impact signal detection method according to an embodiment of the invention by the second conversion
The chart of signal.
Fig. 4 a to Fig. 4 b are to show that the signal detection heartbeat for being converted from process second as shown in Figure 3 b stops
(Asystole) accompanying drawing of method.
Fig. 5 to Figure 10 is to show to calculate for detection impact signal when being not detected by heartbeat stopping according to Fig. 4 a to Fig. 4 b
The accompanying drawing of the exemplary process of characteristic value.
Embodiment
For the concrete structure explanation or specific work(of this specification or various embodiments of the present invention disclosed herein
It can illustrate to be provided according to the purpose of each embodiment of invention merely to explaining.Therefore, can according to each embodiment of invention
To be carried out in a variety of forms, and it is not intended to be limited to each reality illustrated in this specification or the application
Apply example.
Embodiments in accordance with the present invention can carry out numerous variations, can have multiple forms, particular implementation is illustrated in the accompanying drawings
Example is simultaneously described in detail in this specification or application.But, this does not really want that specific embodiment will be defined according to the present invention,
And the thought and technical scope for being understood to include the present invention are included has altered, equivalent substitution and substitute.
In the present invention, the first and/or second grade term can be used for explanation various assemblies, but the component is not limited to
The term.The term is only intended to distinguish a certain component and other assemblies, for example, not departing from according to idea of the invention
Rights protection scope in, first assembly can be named as the second component, similarly, and the second component can be named as first assembly.
When illustrating that certain structural element " is connected to " another structural element, both can be regarded as being directly connected in another structure will
Element, also is understood as centre and there is another structural element.On the contrary, when certain another knot of structural element " being directly connected in " of explanation
Structure is wanted " when, it is thus understood that another structural element is not present in centre.On the other hand, illustrate relation between structural element other
Term, i.e. " ... between ", " between just existing ... ", " being adjacent to ... " and " being directly adjacent to ... " etc. can also be managed in an identical manner
Solution.
Term as used herein is not limiting the present invention merely for the purpose for describing particular implementation.As herein
Used , Unit number forms formula is also including plural form, unless clearly dictated otherwise in context.It will also be appreciated that working as
Herein using term " including (comprise) ", " including (comprising) ", with (have) " and/or " have
(having) when ", the feature, numeral, step, operation, element, part and/or the presence of its combination are indicated, but be not excluded for
ー or other multiple features, numeral, step, operation, element, part and/or its presence or addition for combining.
Especially definition in the case of, herein used all terms including technology or scientific terminology including and
The meaning being generally understood that by general technical staff of the technical field of the invention has identical meaning.It is commonly used with
The identical term defined on dictionary, which should be interpreted that, has the meaning consistent with the meaning having on the context of correlation technique,
In the case of being not exactly defined in the application, the meaning for idealizing or excessively formalizing is not interpreted as.
Hereinafter, the preferred embodiments of the present invention are illustrated referring to the drawings, to describe the present invention in detail.In figure, to phase
Same composed component mark identical symbol.
Fig. 1 is the flow chart for showing impact signal detection method according to an embodiment of the invention.
Reference picture 1, impact signal detection method according to an embodiment of the invention can be detected by impact signal and filled
Put realization, and receiving unit, central control unit etc. that can be by constituting impact signal detection means be performed.
First, receive electrocardiosignal (S101) from the electronic pads for being attached to patient body, the electrocardiosignal received is entered
Row first is converted (S103).Second conversion (S105) is also carried out to the signal by the first conversion.Become by using by second
The signal changed judges whether that heartbeat stops (Asystole) (S107), judged result for it is no when, calculate multiple characteristic values
(S109).As an example, the characteristic value calculated can be seven.Features described above value turns into what is obtained by study in advance
The input value of Weighted Fuzzy membership function, can be from Weighted Fuzzy membership function detection impact signal (S111).
Heartbeat stops referring to the state because of heart stopping without applying defibrillation shocks.
In the case of existing method, determine whether heartbeat to stop by using the signal by the first conversion and calculate
Go out six characteristic values, but in the present case, difference with the prior art is characterised by, based on by the first conversion
Signal is carried out after the second conversion again, and based on the signal determining by the second conversion, whether heartbeat stops, and calculates seven features
Value.Also, it is also different to determine whether asystolic method.It was the peak point by the signal by the first conversion in the past
Average value determine whether that heartbeat stops, but in the present invention, will be big by the peak point of the signal of the second conversion by exporting
The input that the average value of the sum total of the distance between the sum total and peak point of small absolute value is used as input value has set in advance
The Weighted Fuzzy membership function of learning process determines whether that heartbeat stops.
The computational methods of above-mentioned multiple characteristic values can be according to the learning outcome due to Weighted Fuzzy membership function
Determine.
Fig. 2 is the figure for showing the original input signal in impact signal detection method according to an embodiment of the invention
Table, Fig. 3 a are to show the signal in impact signal detection method according to an embodiment of the invention by the first conversion
Chart, Fig. 3 b are to show the signal in impact signal detection method according to an embodiment of the invention by the second conversion
Chart.
Reference picture 2, graph representation as shown in Figure 2 is being Haar wavelet transform (HaarWavelet) conversion by the first conversion
One example of original input signal before.Fig. 3 a are the charts for representing the signal by the first conversion.By the first conversion
Signal also converted by second, with as with the signal in the form of shown in the chart such as Fig. 3 b.Second conversion can be under
Formula is realized.
Mathematical expression 1
Y (x)=X (x+0.5)-X (x)
In above formula, Y (x) parts represent the signal by the second conversion, and X (x) parts represent the signal by the first conversion.
Above-mentioned second conversion is realized using delay (Time Delay).As an example, the second conversion can be delay conversion
(Time Delay Transform, TDT).
First conversion is that wavelet transformation is by while analyzing the specific of locality in time in terms of signal transacting
Frequency characteristic at place carrys out the method that can make up the shortcoming for the Fourier transform for providing global frequencies characteristic information, discontinuous
Wavelet transformation can by T/F Signal separator into different scale discontinuous signal.By d1, d2, d3 grades of sequential signal
Peak point distribution increasingly become simple, so as to only show required signal.In above-mentioned wavelet transform result, to d3
Value carries out second and converted.
Fig. 4 a to Fig. 4 b are to show that the signal detection heartbeat for being converted from process second as shown in Figure 3 b stops
(Asystole) accompanying drawing of method.
Reference picture 4a and Fig. 4 b, Fig. 4 a show to judge whether that heartbeat stops the method for (Asystole), figure using absolute value
4b shows to judge whether that heartbeat stops the method for (Asystole) using the distance between signal value.As shown in Fig. 4 a and Fig. 4 b,
In order to judge whether that heartbeat stops, the signal by the second conversion can be used as primary signal (Original Signal).It is logical
Cross the method as shown in Fig. 4 a and Fig. 4 b and can decide whether that heartbeat stops (Asystole).Its detailed process is as described above.
Judge whether that heartbeat stops by method as shown in figures 4 a and 4b, if it is judged that when being, just need not
Apply impact, be judged as that impact conditions can not be applied, terminate subsequent step, or, it is transfused in new order or signal
In the case of, it can bring by the first conversion and the second change repeatedly again and judge whether asystolic step.
Fig. 5 to Figure 10 is shown, when it is no to judge whether asystolic judged result, in order to judge whether to apply
Impact (detection impact signal) and calculate the various exemplary process of multiple characteristic values.
Fig. 5 shows to calculate characteristic value using phase space reconfiguration (Phase Space Reconstruction, PSR) method
One example.The above method is the method for analyzing dynamic waveform or random signal based on phase space (Phase Space), its
Carry out being worth obtained from the second conversion using the d3 data to the signal by the first conversion, shaking when x-axis is represented as time t
Width unit (amplitude unit) value, amplitude unit (amplitude unit) value when y-axis is represented as time t+0.5,
So as to obtain two-dimensional diagram, characteristic value is obtained by the number of now represented frame (box).As shown in Fig. 5 upper left side,
In the case of normal waveform (Normal Sinus Rhythm, NSR), smaller space is occupied shown in following left side, but it is such as upper right
Shown in side, (quivered room in improper waveform：VF in the case of), larger space is occupied shown in following right side.Based on the phase constituted
Space (Phase Space), can try to achieve characteristic value (d) by following formula.
Mathematical expression 2
Fig. 6 is the accompanying drawing for showing to calculate the method for characteristic value by the number of peak point.In the electrocardio by the second conversion
In signal, the number of peak point can be extracted out.Normal waveform (Normal Sinus Rhythm, NSR) is shown on the left of Fig. 6
In the case of peak point number, the right side room of being shown in is quivered the number of the peak point in the case of (VF), it follows that having substantially
Difference.The point belonged to more than the average value entirely put is used as peak point.The number of above-mentioned peak point is used as characteristic value.
In the case of fig. 7, by using in and 2 points of rear side feature can be calculated at 2 points of the front side of peak point
Value.Peak point is found out in the signal by the second conversion and is tried to achieve in two values (p1, p2) of the front side of peak point and rear side
Two values (n1, n2), wherein can be by p1 values as characteristic value.
Fig. 8 is the chart for showing the standard deviation of the point inside and outside particular amplitude interval being used as the method for characteristic value, should
Method utilizes the standard deviation for the point being located inside and outside amplitude set in advance interval.As shown in figure 8, by normal waveform situation and
Room quiver (VT) situation comparison it is visible, be distributed according to the point of the amplitude of the signal by the second conversion different.
Fig. 9 is to show to utilize by the second signal converted and by between the point inside and outside amplitude set in advance interval
The average value of distance is used as the method for characteristic value.For example, when presetting the certain limit in amplitude interval, can calculate in model
The average distance of point in enclosing.Above range can be -50 to 50 or -200 to 200.
Figure 10 is to show the gradient between the point and point when the point connection of the signal by the second conversion is in line
Standard deviation be used as the method for characteristic value.Although features described above value is not utilized in the past, in the present invention, by above-mentioned spy
Value indicative is used as the input value of Weighted Fuzzy membership function, so as to shorten impact signal detection time and improve the standard of detection
Exactness.
Above-mentioned illustrative features value is used as the input feature vector of the neutral net based on Weighted Fuzzy membership function, with
Weighted Fuzzy membership function exports the judged result about whether impact signal.Nerve based on Weighted Fuzzy membership function
Network (Neural Network with Weighted Fuzzy Membership Function, NEWFM) be by using
The supervised classified from the boundary value of learnt Weighted Fuzzy membership function is inputted learns fuzzy neural network.
NEWFM structure by input (input), super box (hyper-box), class (class) three stratum compositions.Input
Stratum is made up of n input node, and a characteristic value is input into each input node.Chao He stratum are by m super box node structures
Into, first super box node B1 is connected with a class node, and with n fuzzy set.
By the above method, shorten the time judged whether needed for impact signal, with rapid in the environment of defibrillation is needed
Apply defibrillation, so as to improve the survival rate of patient.
In addition, above-mentioned impact signal detection method is implemented by computer readable code/instructions/program.For example, the side
Method can operationally be stated by using computer readable recording medium storing program for performing to be implemented on the general purpose digital computer of code/instructions/programs.
The example of above computer readable medium recording program performing includes magnetic-based storage media (e.g., CD, floppy disk, hard disk, tape etc.), optics can
Read medium (such as CD-ROM or DVD) and carrier wave (for example, the transmission for passing through internet) form storage medium.Also, this hair
Bright embodiment can be by (multiple) media realization built with computer-readable coding so that by multiple meters of network connection
Calculation machine system is handled and operated with a scattered manner.Moreover, by the present invention method realize function program, coding, coding section by
The programmer for belonging to the technical field of the present invention can easy inference.
Foregoing description only relates to the description of a specific embodiment of the technical spirit of the present invention, and art of the present invention
Technical staff must not depart from the essential characteristic of the present invention and carry out different modification or change.Therefore, it is presently disclosed
Embodiment is not limited to the technical spirit of the present invention, but in order to describe the technical spirit, and the scope of the present invention is not
It should be limited to the embodiment.Protection scope of the present invention should be determined by claim, and be owned in equivalent scope
The explanation of technical spirit should be fallen within the scope of the present invention.
Claims (13)
1. the impact signal detection method of a kind of heart defibrillator, it is characterised in that comprise the following steps：
Receive electrocardiosignal；
First conversion is carried out to the electrocardiosignal of the receiving；
Second is carried out to the electrocardiosignal by the described first conversion to convert；
Utilize the signal of change characteristic value by the second conversion；And
The characteristic value of the calculating is used as input value and impact signal is detected by Weighted Fuzzy membership function.
2. the impact signal detection method of heart defibrillator according to claim 1, it is characterised in that the receiving
Signal is digital form signal.
3. the impact signal detection method of heart defibrillator according to claim 1, it is characterised in that described first becomes
It is changed to wavelet transformation.
4. the impact signal detection method of heart defibrillator according to claim 1, it is characterised in that described second becomes
It is changed to delay conversion.
5. the impact signal detection method of heart defibrillator according to claim 4, it is characterised in that the delay becomes
Change and realized by formula " Y (x)=X (x+0.5)-X (x) ", in formula, the X (x) is the signal by the first conversion, and Y (x) is warp
Cross the signal of the second conversion.
6. the impact signal detection method of heart defibrillator according to claim 1, it is characterised in that also include：
Judge whether asystolic step by using the signal by the second conversion.
7. the impact signal detection method of heart defibrillator according to claim 6, it is characterised in that the judgement is
No asystolic step includes being judged by using the summation of the absolute value of the signal value by the second conversion
The step of.
8. the impact signal detection method of heart defibrillator according to claim 6, it is characterised in that the judgement is
No asystolic step is included by using the step judged by the distance between signal value of the second conversion
Suddenly.
9. the impact signal detection method of heart defibrillator according to claim 6, it is characterised in that if it is determined that being
The no asystolic judged result is no, the step of just carrying out the calculating characteristic value.
10. the impact signal detection method of heart defibrillator according to claim 1, it is characterised in that the calculating
The step of characteristic value including calculate it is described by second conversion signal value in amplitude set in advance interval in value it
Between average distance the step of.
11. the impact signal detection method of heart defibrillator according to claim 1, it is characterised in that the calculating
The step of characteristic value, connects the step of the standard deviation of the gradient of the straight line of the signal value by the second conversion including calculating
Suddenly.
12. the impact signal detection method of heart defibrillator according to claim 1, it is characterised in that the calculating
The step of characteristic value including calculate the number of peak value of the signal by the second conversion, the front and rear value of peak value, be contained in it is pre-
The step of at least one in the standard deviation of the peak value of the scope first set.
13. the impact signal detection method of heart defibrillator according to claim 1, it is characterised in that the calculating
Characteristic value be seven.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR10-2015-0181925 | 2015-12-18 | ||
| KR1020150181925A KR101751815B1 (en) | 2015-12-18 | 2015-12-18 | Method for detecting shockable signal of automated defibrillator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107029354A true CN107029354A (en) | 2017-08-11 |
Family
ID=59280770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611090903.9A Pending CN107029354A (en) | 2015-12-18 | 2016-12-01 | The impact signal detection method of heart defibrillator |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR101751815B1 (en) |
| CN (1) | CN107029354A (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102029181B1 (en) | 2018-12-12 | 2019-10-07 | 가천대학교 산학협력단 | A method and apparatus for selecting feature using neural network with weighted fuzzy membership function |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040162585A1 (en) * | 2003-02-19 | 2004-08-19 | Elghazzawi Ziad E. | CPR sensitive ECG analysis in an automatic external defibrillator |
| CN101461709A (en) * | 2009-01-12 | 2009-06-24 | 复旦大学 | Shockable rhythm recognition algorithm based on slope absolute value distribution dispersion |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101251081B1 (en) * | 2011-02-17 | 2013-04-05 | (의료)길의료재단 | A shockable signal detection method of automated external defibrillator using neural network with weighted fuzzy membership function |
| KR101367596B1 (en) | 2012-05-15 | 2014-02-26 | 주식회사 씨유메디칼시스템 | Automated external defibrillator including motion artifact measurement and deleting facility |
| KR101524596B1 (en) | 2014-02-28 | 2015-06-03 | 부산대학교 산학협력단 | PVC classification apparatus and method using QRS pattern, PVC pattern classification method and remote monitoring device |
-
2015
- 2015-12-18 KR KR1020150181925A patent/KR101751815B1/en active IP Right Grant
-
2016
- 2016-12-01 CN CN201611090903.9A patent/CN107029354A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040162585A1 (en) * | 2003-02-19 | 2004-08-19 | Elghazzawi Ziad E. | CPR sensitive ECG analysis in an automatic external defibrillator |
| CN101461709A (en) * | 2009-01-12 | 2009-06-24 | 复旦大学 | Shockable rhythm recognition algorithm based on slope absolute value distribution dispersion |
Non-Patent Citations (1)
| Title |
|---|
| 董红生: "《心电波形检测与心率变异性分析方法研究》", 《WWW.CNKI.NET》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| KR101751815B1 (en) | 2017-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiong et al. | ECG signal classification for the detection of cardiac arrhythmias using a convolutional recurrent neural network | |
| US10869610B2 (en) | System and method for identifying cardiac arrhythmias with deep neural networks | |
| Mathews et al. | A novel application of deep learning for single-lead ECG classification | |
| Eerikäinen et al. | Reduction of false arrhythmia alarms using signal selection and machine learning | |
| Goodfellow et al. | Towards understanding ECG rhythm classification using convolutional neural networks and attention mappings | |
| Amann et al. | Detecting ventricular fibrillation by time-delay methods | |
| Martis et al. | Computer aided diagnosis of atrial arrhythmia using dimensionality reduction methods on transform domain representation | |
| Anas et al. | Sequential algorithm for life threatening cardiac pathologies detection based on mean signal strength and EMD functions | |
| Xu et al. | Detection of ventricular tachycardia and fibrillation using adaptive variational mode decomposition and boosted-CART classifier | |
| Cheng et al. | Life-threatening ventricular arrhythmia detection with personalized features | |
| US20120173470A1 (en) | Prediction and prevention of postoperative atrial fibrillation in cardiac surgery patients | |
| Balasundaram et al. | A classification scheme for ventricular arrhythmias using wavelets analysis | |
| Risdal et al. | Automatic identification of return of spontaneous circulation during cardiopulmonary resuscitation | |
| Bodini et al. | Opening the black box: interpretability of machine learning algorithms in electrocardiography | |
| Kropf et al. | Cardiac anomaly detection based on time and frequency domain features using tree-based classifiers | |
| Parsi et al. | Prediction of sudden cardiac death in implantable cardioverter defibrillators: a review and comparative study of heart rate variability features | |
| KR20220077583A (en) | Method and apparatus of explainable multi electrocardiogram arrhythmia diagnosis | |
| Manibardo et al. | ECG-based random forest classifier for cardiac arrest rhythms | |
| Bárdossy et al. | Fuzzy logic-based diagnostic algorithm for implantable cardioverter defibrillators | |
| Ghaffari et al. | Atrial fibrillation identification based on a deep transfer learning approach | |
| Luongo et al. | Hybrid machine learning to localize atrial flutter substrates using the surface 12-lead electrocardiogram | |
| Li et al. | Domain knowledge guided deep atrial fibrillation classification and its visual interpretation | |
| Mahmoodabadi et al. | A fast expert system for electrocardiogram arrhythmia detection | |
| CN107029354A (en) | The impact signal detection method of heart defibrillator | |
| Firdous et al. | Handling of derived imbalanced dataset using XGBoost for identification of pulmonary embolism—a non-cardiac cause of cardiac arrest |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170811 |