CN105496402A - Electrocardio feature analyzing method based on point diagram and symbolic dynamics - Google Patents

Electrocardio feature analyzing method based on point diagram and symbolic dynamics Download PDF

Info

Publication number
CN105496402A
CN105496402A CN201510809814.4A CN201510809814A CN105496402A CN 105496402 A CN105496402 A CN 105496402A CN 201510809814 A CN201510809814 A CN 201510809814A CN 105496402 A CN105496402 A CN 105496402A
Authority
CN
China
Prior art keywords
sequence
scatterplot
method based
hrv
electrocardio
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201510809814.4A
Other languages
Chinese (zh)
Other versions
CN105496402B (en
Inventor
辛怡
赵一璋
母远慧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN201510809814.4A priority Critical patent/CN105496402B/en
Publication of CN105496402A publication Critical patent/CN105496402A/en
Application granted granted Critical
Publication of CN105496402B publication Critical patent/CN105496402B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • 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]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/352—Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
    • 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]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/366—Detecting abnormal QRS complex, e.g. widening

Abstract

The invention discloses an electrocardio feature analyzing method based on point diagram and symbolic dynamics and belongs to the field of electrocardio signal processing. A to-be-processed original electrocardio signal is pre-processed and then R-wave positioned; an HRV sequence is acquired according to calculation of intervals of adjacent R-waves; an electrocardio point diagram is drawn and divided by a group of 45-degree parallel lines; according to orders of each splash point corresponding to RR intervals, zone numbers of divided zones where each splash point lies are formed in a sequence, encoded and converted in a number-system way to acquire a decimalism sequence; and the sequence information entropy is calculated to build a feature vector, so the electrocardio signal can be classified and identified.

Description

Based on the ecg characteristics analytical method of scatterplot and symbolic dynamics
Technical field
The present invention proposes a kind of heart rate variance analyzing method, in conjunction with the grader be applicable to, effectively can complete the discriminator to variety classes electrocardiosignal, belong to ECG's data compression field.
Background technology
Heart rate variability (heartratevariability, HRV) refers to the change of divergence of successively IBI time span in sinus rhythm certain hour.HRV analysis is the method for a class qualitative assessment autonomic nerve and heart state.By the analyzing and processing to HRV signal, the state of heart, sympathetic nerve, vagus nerve etc. and mutual containing situation can be obtained.Numerous method is applied in HRV research in recent years, but mainly traditional time-domain and frequency-domain analytical method of extensive use at present.Because human body is a complicated nonlinear system, heart is also a nonlinear dynamic system in essence, and therefore nonlinear analysis method more contributes to the essence disclosing Cardiac Power system.
Poincare scatterplot, as a kind of important means of HRV nonlinear analysis, starts to be applied in the assistant analysis to heart rate variability already.In May, 2011, the academic summit of first electrocardio scatterplot is held in Beijing, discusses scatterplot and heart rate variability, the problem such as scatterplot and arrhythmia, and has set up electrocardio scatterplot group.As can be seen here, the HRV based on electrocardio scatterplot analyzes and day by day comes into one's own, and electrocardio scatterplot, as the nonlinear analytical method of one, is the important indicator describing heart rate variability.Conventional Poincare scatterplot uses continuous RR interval (R n, R n+1) in rectangular coordinate system, do scatterplot as loose point coordinates.It can reflect the change of adjacent R R interval, while display HRV global feature, can demonstrate again the change successively between heartbeat, disclose the nonlinear characteristic of heart rate variability.But Poincare scatterplot has lacked the time sequence information in former electrocardiogram, can not reflect the time trend of HRV.In order to more effective classification is carried out to the not normal rhythm of the heart and retain electrocardiosignal with time sequence information, we propose to utilize electrocardio scatterplot combined symbol kinetics entropy to extract the new method of electrocardiosignal feature, can carry out detection and the classification of relevant disease, conclusion can be used in clinical monitoring and tele-medicine.
Summary of the invention:
In view of the nonlinear characteristic that HRV signal has, and traditional electrocardio Discrete point analysis method can lack the time sequence information in original electrocardiogram (ECG) data, the present invention is on the basis of classical electrocardio scatterplot, and combined symbol kinetics and comentropy, propose a kind of new ecg characteristics analytical method.
In order to realize object of the present invention, the invention provides the ecg characteristics analytical method of a kind of scatterplot and symbolic dynamics, comprising the steps:
Step S1: gather ECG signal and carry out pretreatment, carries out R ripple location and obtains HRV sequence by the interval calculating adjacent R ripple;
Step S2: feature extraction:
S2-1: the HRV sequence first using step S1 to obtain draws electrocardio scatterplot, namely with (R n, R n+1) as the loose point coordinates in rectangular coordinate system, wherein R nrepresent the n-th RR interval length, and with one group of 45 ° of parallel lines, subregion is carried out to electrocardio scatterplot, number of partitions is M, the area code of each subregion is made to be m=0 ~ M-1, the quantity of parallel lines is M-1, subregion pressed 45 ° of diagonal axis symmetries of initial point, and the width of each subregion between two parallel lines is defined as the distance between these partition boundaries parallel lines, is followed successively by D from upper left to bottom right 1, D 2..., D m-2;
As preferably, adopt four subregions, be namely followed successively by 0th district from upper left to bottom right in scatterplot, 1st district, 2nd district, 3rd district.
As preferably, make the width of all subregions between two parallel lines equal.
S2-2: according to the order of each loose point corresponding RR interval, by each loose point with the area code composition sequence of this loose some place subregion, then every q position is regarded as a M system code, a rear coding has j position overlapping with previous coding, and j is less than q; After encoding, by former Sequence Transformed be a new sequence be made up of several q position M system code; Then each M system code is converted into decimal number, obtains a decimal sequence;
As preferably, j=1;
S2-3: sequence of calculation comentropy: because described decimal sequence is transformed by a series of q positions M system number, numerical value all in the decimal sequence therefore obtained is all at 0-(M q-1) between; Calculate 0-(M q-1) probability that all numbers between occur in the sequence, utilizes following formula to calculate the comentropy of this sequence:
H = - Σ i = 1 a p i logp i
Wherein, p iit is the probability that i-th numerical value occurs; A is the numerical value sum number that possible occur, is M herein q.
Step S3: classification:
S3-1: utilize the information entropy calculating gained to carry out structural feature vector;
S3-2: utilize the characteristic vector constructed, carry out the classification of electrocardiosignal.
As preferably, adopt grader to carry out the classification of different classes of electrocardiosignal, the grader of employing comprises one of following: Bayes grader, BP neural network classifier, Self-organizing Maps, support vector machine.
As preferably, step S1 comprises:
S1-1: first remove the Hz noise in ECG signal, myoelectricity interference and baseline drift;
S1-2: carry out QRS wave group location to the ECG signal that step S1-1 obtains, calculates the interval of adjacent R ripple, and is numbered thus obtain original HRV signal sequence; As preferably, Pan-Tompkins algorithm is adopted to detect QRS wave group, location R ripple;
Contrast prior art, beneficial effect of the present invention is: on the basis of electrocardio scatterplot, in conjunction with the content of the symbolic dynamics in nonlinear kinetics and comentropy, carries out nonlinear analysis to HRV sequence.Make us more efficientlyly can find the various contacts behind of complicated HRV signal.Data coding is in fact to the value symbolization in sequence, and its basic thought is removed detailed information, data being classified in centrifugal pump, being transformed to only several mutually different symbol sebolic addressing there being the data existence form of a lot of probability.This is " coarse " process, and its energy let us captures the large-scale characteristics of data, thus reduces noise to the impact of signal.And comentropy is commonly used to the uncertainty of representation system, in HRV analyzes, we can be used for the confusion degree of better analysis of cardiac active state.
Accompanying drawing explanation
Fig. 1 is the flow chart of the method for the invention;
Fig. 2 electrocardio scatterplot schematic diagram (predicting p7 data instance in challenge data storehouse with PAF);
Fig. 3 electrocardio scatterplot 4 subregion schematic diagram (predicting p7 data instance in challenge data storehouse with PAF).
Fig. 4 symbolic dynamics cataloged procedure (predicting p7 data instance in challenge data storehouse with PAF).
Fig. 5 electrocardio scatterplot 6 subregion schematic diagram (predicting p7 data instance in challenge data storehouse with PAF).
Detailed description of the invention
To be described in detail the present invention below, and also describe technical problem and the beneficial effect of technical solution of the present invention solution simultaneously, it is pointed out that described example is only intended to be convenient to the understanding of the present invention, and any restriction effect is not play to it.
Below to carry out atrial fibrillation and normal electrocardiosignal is categorized as example, accompanying drawings the specific embodiment of the present invention.Algorithm flow chart is shown in Fig. 1.
Step S1: gather ECG signal and carry out pretreatment, obtains HRV sequence: this step comprises:
S1-1: gather or extract required multiple electrocardiosignal being all greater than 5 minutes, in this example, we carry out two groups of experiments altogether, select respectively from PAF (predictingparoxysmalatrialfibrillation) predict challenge data storehouse 75 number of cases certificates and the 20 number of cases certificates of MIT-BIH data base.Wherein PAF predicts that the HRV sample of signal of the known PAF in challenge data storehouse is 25 examples, and normal cardiac electrical HRV sample of signal is 50 examples, cardiac electrical HRV sample of signal 10 example of known premature beat in MIT-BIH data base, normal cardiac electrical HRV sample of signal 10 example.
First 50Hz Hz noise in ECG signal, myoelectricity interference and baseline drift is removed; As preferably, here, adopt FIR band filter to remove 50Hz Hz noise in ECG signal, myoelectricity interference and baseline drift, filter cutoff frequency is set to 5Hz and 15Hz.
S1-2: the QRS ripple in the ECG signal obtained after carrying out pretreatment to S1-2 positions, calculates the interval of adjacent R ripple, and is numbered and be original HRV signal sequence; Here we adopt Pan-Tompkins algorithm (Ref:JiapuPan, WillisJ.Tompkins.AReal-TimeQRSDetectionAlgorithm, IEEETransactionsonBiomedicalEngineering, 1985) R ripple is located, calculate the interval of RR ripple, just can obtain original HRV signal sequence.
Step S2: feature extraction:
S2-1: after obtaining RR interval series from original electrocardiographicdigital data, draws electrocardio scatterplot.Next, subregion is carried out to electrocardio scatterplot, because data used are 5min data, consider electrocardio scatterplot to be divided into four regions.Subregion sign is 3 45 ° of parallel lines, and about zero crossing 45 ° of line symmetries.Distance between parallel lines is equal and can regulate, from upper left toward bottom right by region successively called after 0 district, and 1st district, 2nd district, 3rd district.
S2-2: the result according to subregion can be seen, all loose points all fall in the drawings in certain region, all loose points are numbered acquisition sequence according to RR interval order by the area code of its region, such as, obtain following sequence:
…0,2,3,1,2,1,3,2,2,1,3,2,1,0,0,3,1,2,3,2,1,2,1,3,0,0…
After obtaining sequence, adjacent three numberings are set to a quaternary coding, and adjacent two codings there is 1 overlap, see Fig. 4.
After encoding, by former Sequence Transformed be a new sequence be made up of a series of 3 long quaternary codes.
…023，312，213，322，213，321，100，031，123，321，121，130…
Conveniently entropy is asked to sequence, each 3 long codings are regarded as the quaternary number of 3, quaternary number is converted into decimal number and just can obtains a new decimal sequence.
…11,54,39,58,39,57,16,13,27,57,25,28…
S2-3: because sequence is transformed, between numerical value equal 0-63 all in the decimal sequence therefore obtained by 3 long quaternary numbers.Calculate the probability that all numbers between 0-63 occur in decimal sequence, thus calculate the comentropy H of this decimal sequence, computing formula is as follows:
H = E [ - log e P i ] = - Σ i = 1 a p i logp i
Wherein, Pi is the probability that i-th numerical value occurs; A is the numerical value sum number that possible occur, is 64 herein.
Step S3: the classification of atrial fibrillation and normal sinus rhythm category signal.
S3-1: algorithm compute sign power entropy designed according to this invention, structural feature vector.
S3-2: utilize the characteristic vector constructed to adopt grader to carry out the classification of Paroxysmal Atrial Fibrillation signal and sinus rhythm electrocardiosignal.Because the design object of grader is by after study, automatically data can be assigned to known class, so for the difference of model, have different graders; According to the feature of physiological signal, the grader that can adopt comprises: Bayes grader, BP neural network classifier, Self-organizing Maps, support vector machine (SVM) algorithm etc.Due in this example, what we needed to solve is two classification problems, so we have employed simple general-purpose and the high SVM algorithm of efficiency, completes the classification of the not normal rhythm of the heart and normal sinus rhythm.
For in the 20 routine samples of MIT-BIH data base, the mode of 5 folding cross validations is adopted to carry out test of heuristics.Be described as follows, 10 routine premature beat signals and the normal electrocardio of 10 examples are randomly drawed first separately and be divided into 5 parts, every part comprises 4 data samples.When support vector cassification, adopt each four parts of every type, 16 samples are as training set altogether, and all the other samples are test set.Circulate 5 times, intersection is carried out, and each test set is not identical.
Obtaining classification accuracy rate by said process (4 subregion) is 90.00%.
When predicting that the 75 routine samples in challenge data storehouse are tested for PAF, we have employed the mode of 6 subregions, there is the region on border still to adopt the width of equidistant i.e. each subregion between two parallel lines all equal, normal electrocardiosignal and PAF signal are classified.6 subregion schematic diagrams are as Fig. 5.
Obtaining classification accuracy rate by said process is 86.67%.
The above; be only the specific embodiment of the present invention; but protection scope of the present invention is not limited thereto; any people being familiar with this technology is in the technical scope disclosed by the present invention; the conversion and replacement expected can be understood; all should be encompassed in and of the present inventionly comprise within scope, therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.

Claims (7)

1., based on the ecg characteristics analytical method of scatterplot and symbolic dynamics, it is characterized in that, comprise following steps:
Step S1: gather ECG signal and carry out pretreatment, carries out R ripple location and obtains HRV sequence by the interval calculating adjacent R ripple;
Step S2: feature extraction:
S2-1: the HRV sequence first using step S1 to obtain draws electrocardio scatterplot, namely with (R n, R n+1) as the loose point coordinates in rectangular coordinate system, wherein R nrepresent the n-th RR interval length, and with one group of 45 ° of parallel lines, subregion is carried out to electrocardio scatterplot, number of partitions is M, the area code of each subregion is made to be m=0 ~ M-1, the quantity of parallel lines is M-1, subregion pressed 45 ° of diagonal axis symmetries of initial point, and the width of each subregion between two parallel lines is defined as the distance between these partition boundaries parallel lines, is followed successively by D from upper left to bottom right 1, D 2..., D m-2;
S2-2: according to the order of each loose point corresponding RR interval, by each loose point with the area code composition sequence of this loose some place subregion, then every q position is regarded as a M system code, a rear coding has j position overlapping with previous coding, and j is less than q; After encoding, by former Sequence Transformed be a new sequence be made up of several q position M system code; Then each M system code is converted into decimal number, obtains a decimal sequence;
S2-3: sequence of calculation comentropy: because described decimal sequence is transformed by a series of q positions M system number, numerical value all in the decimal sequence therefore obtained is all at 0-(M q-1) between; Calculate 0-(M q-1) probability that all numbers between occur in the sequence, utilizes following formula to calculate the comentropy of this sequence:
H = - Σ i = 1 a p i logp i
Wherein, p iit is the probability that i-th numerical value occurs; A is the numerical value sum number that possible occur, is M herein q.
Step S3: classification:
S3-1: utilize the information entropy calculating gained to carry out structural feature vector;
S3-2: utilize the characteristic vector constructed, carry out the classification of electrocardiosignal.
2. a kind of ecg characteristics analytical method based on scatterplot and symbolic dynamics according to claim 1, it is characterized in that, step S1 comprises:
S1-1: first remove the Hz noise in ECG signal, myoelectricity interference and baseline drift;
S1-2: carry out QRS wave group location to the ECG signal that step S1-1 obtains, calculates the interval of adjacent R ripple, and is numbered thus obtain original HRV signal sequence;
S1-3: remove the artifact and ectopic pacemaker that exist in HRV signal, thus obtain HRV sequence to be analyzed.
3. a kind of ecg characteristics analytical method based on scatterplot and symbolic dynamics according to claim 1, is characterized in that, in step S2-1, make the width of all subregions between two parallel lines equal.
4. a kind of ecg characteristics analytical method based on scatterplot and symbolic dynamics according to claim 2, is characterized in that, adopt Pan-Tompkins algorithm to detect QRS wave group in step S1-2, location R ripple.
5. a kind of ecg characteristics analytical method based on scatterplot and symbolic dynamics according to claim 1, it is characterized in that, in step S3-2, grader is adopted to carry out the classification of different classes of electrocardiosignal, the grader adopted comprises one of following: Bayes grader, BP neural network classifier, Self-organizing Maps, support vector machine.
6. a kind of ecg characteristics analytical method based on scatterplot and symbolic dynamics according to claim 1, is characterized in that, in step S2-1, adopt four subregions, be namely followed successively by 0th district from upper left to bottom right in scatterplot, 1st district, 2nd district, 3rd district.
7. a kind of ecg characteristics analytical method based on scatterplot and symbolic dynamics according to claim 1, is characterized in that, in step S2-2, and j=1.
CN201510809814.4A 2015-11-20 2015-11-20 Ecg characteristics analysis method based on scatter diagram and symbolic dynamics Expired - Fee Related CN105496402B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510809814.4A CN105496402B (en) 2015-11-20 2015-11-20 Ecg characteristics analysis method based on scatter diagram and symbolic dynamics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510809814.4A CN105496402B (en) 2015-11-20 2015-11-20 Ecg characteristics analysis method based on scatter diagram and symbolic dynamics

Publications (2)

Publication Number Publication Date
CN105496402A true CN105496402A (en) 2016-04-20
CN105496402B CN105496402B (en) 2018-03-02

Family

ID=55704974

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510809814.4A Expired - Fee Related CN105496402B (en) 2015-11-20 2015-11-20 Ecg characteristics analysis method based on scatter diagram and symbolic dynamics

Country Status (1)

Country Link
CN (1) CN105496402B (en)

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105902266A (en) * 2016-04-22 2016-08-31 江苏物联网研究发展中心 Electrocardiographic signal classification method based on self-organizing neural network
CN107715273A (en) * 2017-10-12 2018-02-23 西南大学 Alarm clock implementing method, apparatus and system
CN107865655A (en) * 2017-09-19 2018-04-03 深圳星康医疗科技有限公司 Ecg wave form figure display methods and device
CN107874753A (en) * 2016-09-29 2018-04-06 中国科学院微电子研究所 Pulse condition recognition methods and device
CN107898454A (en) * 2017-11-13 2018-04-13 湖北科技学院 A kind of non-linear Lorentz scatter diagram morphology computational methods
CN108108654A (en) * 2017-09-19 2018-06-01 东华大学 A kind of Freehandhand-drawing track reconstructing method based on multi-channel surface myoelectric signal
CN108403105A (en) * 2017-02-09 2018-08-17 深圳市理邦精密仪器股份有限公司 A kind of methods of exhibiting and displaying device of electrocardio scatterplot
CN108523873A (en) * 2018-01-31 2018-09-14 北京理工大学 Electrocardiosignal feature extracting method based on Fourier Transform of Fractional Order and comentropy
CN108577831A (en) * 2018-03-19 2018-09-28 武汉海星通技术股份有限公司 Singly lead heart patch data long-range monitoring and diagnosis system and its processing method
CN108577832A (en) * 2018-02-11 2018-09-28 东南大学 A kind of atrial fibrillation method of discrimination
CN108784680A (en) * 2018-03-19 2018-11-13 武汉海星通技术股份有限公司 Electrocardiogram intelligent analysis method based on scatter plot and system
CN108960113A (en) * 2018-06-26 2018-12-07 江苏师范大学 A kind of heart rate variability recognition methods based on support vector machines
CN109106397A (en) * 2017-06-25 2019-01-01 吴健康 A kind of monitoring of fetal heart sound and analysis system
CN109452938A (en) * 2018-12-29 2019-03-12 中国矿业大学 A kind of HFECG signal characteristic frequency detecting method based on multiple dimensioned multi-fractal
CN109480816A (en) * 2018-12-18 2019-03-19 安徽华米信息科技有限公司 Rhythm of the heart monitoring method, device, electronic equipment and computer readable storage medium
CN109770859A (en) * 2019-03-28 2019-05-21 广州视源电子科技股份有限公司 The treating method and apparatus of electrocardiosignal, storage medium, processor
CN109770893A (en) * 2019-03-08 2019-05-21 东南大学 The method and device of atrial fibrillation position are quickly positioned in a kind of Holter analysis system
CN109875550A (en) * 2019-04-02 2019-06-14 东北大学 A kind of sequences of ventricular depolarization critical point detection method
TWI672127B (en) * 2018-12-06 2019-09-21 國立勤益科技大學 Algorithm of qrs detection based on wavelet transformation
CN110840443A (en) * 2019-11-29 2020-02-28 京东方科技集团股份有限公司 Electrocardiosignal processing method, electrocardiosignal processing device and electronic equipment
CN110840450A (en) * 2018-08-20 2020-02-28 中国移动通信有限公司研究院 Visual fatigue detection method, device and storage medium
CN110916648A (en) * 2019-12-13 2020-03-27 南京信息职业技术学院 Method for quantitatively detecting T wave alternation based on dispersion of scatter diagram
CN112716498A (en) * 2020-12-29 2021-04-30 北京理工大学 Electrocardiosignal feature extraction method based on dynamic time warping and symbolic dynamics
CN110179456B (en) * 2019-05-23 2021-11-02 中国航天员科研训练中心 Electrocardio noise recognition model training and electrocardio noise detection method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101176660A (en) * 2007-12-06 2008-05-14 山东大学 Detector methods and apparatus of cardiovascular system combining with variability guideline
US20110160603A1 (en) * 2008-06-13 2011-06-30 The Parkinson's Institute Diagnosis of neurogenerative disorders
CN103271737A (en) * 2013-05-23 2013-09-04 山东师范大学 Heart rate turbulence tendency extraction method based on cloud model and scatter diagram
US20150313553A1 (en) * 2014-05-01 2015-11-05 Ki H. Chon Detection and monitoring of atrial fibrillation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101176660A (en) * 2007-12-06 2008-05-14 山东大学 Detector methods and apparatus of cardiovascular system combining with variability guideline
US20110160603A1 (en) * 2008-06-13 2011-06-30 The Parkinson's Institute Diagnosis of neurogenerative disorders
CN103271737A (en) * 2013-05-23 2013-09-04 山东师范大学 Heart rate turbulence tendency extraction method based on cloud model and scatter diagram
US20150313553A1 (en) * 2014-05-01 2015-11-05 Ki H. Chon Detection and monitoring of atrial fibrillation

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
BABAK MOHAMMADZADEH ASL 等: "Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal", 《ARTIFICIAL INTELLIGENCE IN MEDICINE》 *
J PISKORSKI 等: "Geometry of the Poincaré plot of RR intervals and its asymmetry in healthy adults", 《PHYSIOLOGICAL MEASUREMENT》 *
MARYAM MOHEBBI 等: "Prediction of paroxysmal atrial fibrillation based on non-linear analysis and spectrum and bispectrum features of the heart rate variability signal", 《COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE》 *
陈煜 等: "基于多尺度小波熵的阵发性房颤识别方法", 《航天医学与医学工程》 *
霍铖宇 等: "基于Poincare差值散点图的心率变异性分析方法研究", 《物理学报》 *

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105902266A (en) * 2016-04-22 2016-08-31 江苏物联网研究发展中心 Electrocardiographic signal classification method based on self-organizing neural network
CN107874753A (en) * 2016-09-29 2018-04-06 中国科学院微电子研究所 Pulse condition recognition methods and device
CN108403105A (en) * 2017-02-09 2018-08-17 深圳市理邦精密仪器股份有限公司 A kind of methods of exhibiting and displaying device of electrocardio scatterplot
CN109106397A (en) * 2017-06-25 2019-01-01 吴健康 A kind of monitoring of fetal heart sound and analysis system
CN107865655A (en) * 2017-09-19 2018-04-03 深圳星康医疗科技有限公司 Ecg wave form figure display methods and device
CN108108654A (en) * 2017-09-19 2018-06-01 东华大学 A kind of Freehandhand-drawing track reconstructing method based on multi-channel surface myoelectric signal
CN107715273A (en) * 2017-10-12 2018-02-23 西南大学 Alarm clock implementing method, apparatus and system
CN107898454A (en) * 2017-11-13 2018-04-13 湖北科技学院 A kind of non-linear Lorentz scatter diagram morphology computational methods
CN108523873A (en) * 2018-01-31 2018-09-14 北京理工大学 Electrocardiosignal feature extracting method based on Fourier Transform of Fractional Order and comentropy
CN108577832A (en) * 2018-02-11 2018-09-28 东南大学 A kind of atrial fibrillation method of discrimination
CN108577831A (en) * 2018-03-19 2018-09-28 武汉海星通技术股份有限公司 Singly lead heart patch data long-range monitoring and diagnosis system and its processing method
CN108784680A (en) * 2018-03-19 2018-11-13 武汉海星通技术股份有限公司 Electrocardiogram intelligent analysis method based on scatter plot and system
CN108577831B (en) * 2018-03-19 2021-02-09 武汉海星通技术股份有限公司 Single-guide-core-paste data long-range monitoring and diagnosing system and processing method thereof
CN108960113A (en) * 2018-06-26 2018-12-07 江苏师范大学 A kind of heart rate variability recognition methods based on support vector machines
CN110840450B (en) * 2018-08-20 2022-07-29 中国移动通信有限公司研究院 Visual fatigue detection method, device and storage medium
CN110840450A (en) * 2018-08-20 2020-02-28 中国移动通信有限公司研究院 Visual fatigue detection method, device and storage medium
TWI672127B (en) * 2018-12-06 2019-09-21 國立勤益科技大學 Algorithm of qrs detection based on wavelet transformation
CN109480816A (en) * 2018-12-18 2019-03-19 安徽华米信息科技有限公司 Rhythm of the heart monitoring method, device, electronic equipment and computer readable storage medium
CN109452938A (en) * 2018-12-29 2019-03-12 中国矿业大学 A kind of HFECG signal characteristic frequency detecting method based on multiple dimensioned multi-fractal
CN109770893A (en) * 2019-03-08 2019-05-21 东南大学 The method and device of atrial fibrillation position are quickly positioned in a kind of Holter analysis system
CN109770859A (en) * 2019-03-28 2019-05-21 广州视源电子科技股份有限公司 The treating method and apparatus of electrocardiosignal, storage medium, processor
CN109875550A (en) * 2019-04-02 2019-06-14 东北大学 A kind of sequences of ventricular depolarization critical point detection method
CN109875550B (en) * 2019-04-02 2020-08-04 东北大学 Ventricular depolarization key point detection method
CN110179456B (en) * 2019-05-23 2021-11-02 中国航天员科研训练中心 Electrocardio noise recognition model training and electrocardio noise detection method and device
CN110840443A (en) * 2019-11-29 2020-02-28 京东方科技集团股份有限公司 Electrocardiosignal processing method, electrocardiosignal processing device and electronic equipment
WO2021103796A1 (en) * 2019-11-29 2021-06-03 京东方科技集团股份有限公司 Electrocardiosignal processing method, electrocardiosignal processing apparatus, and electronic device
CN110916648A (en) * 2019-12-13 2020-03-27 南京信息职业技术学院 Method for quantitatively detecting T wave alternation based on dispersion of scatter diagram
CN112716498A (en) * 2020-12-29 2021-04-30 北京理工大学 Electrocardiosignal feature extraction method based on dynamic time warping and symbolic dynamics

Also Published As

Publication number Publication date
CN105496402B (en) 2018-03-02

Similar Documents

Publication Publication Date Title
CN105496402A (en) Electrocardio feature analyzing method based on point diagram and symbolic dynamics
CN103690156B (en) The processing method of a kind of heart rate acquisition methods and electrocardiosignal
Monasterio et al. A multilead scheme based on periodic component analysis for T-wave alternans analysis in the ECG
Zhang et al. A multi-dimensional association information analysis approach to automated detection and localization of myocardial infarction
CN103006206B (en) Method for quantitatively detecting microvolt T-wave alternans
US9451901B2 (en) Method and device for evaluation of myocardial damages based on the current density variations
CN101616629A (en) Be used to predict the automatic noise reduction system of arrhythmia death
CN108403107B (en) Arrhythmia discrimination method and system
Ciaccio et al. A new transform for the analysis of complex fractionated atrial electrograms
CN106874872A (en) Industrial frequency noise filtering device and method
CN105411579B (en) A kind of electrocardiogram R wave detection method and device
CN111920399A (en) Analysis method and device for heart rate variability
Loppini et al. Thermal effects on cardiac alternans onset and development: A spatiotemporal correlation analysis
Jeong et al. Optimal length of heart rate variability data and forecasting time for ventricular fibrillation prediction using machine learning
CN104473633B (en) Judging method and device of abnormal electrocardio data
WO2012173583A1 (en) Method and device for evaluation of myocardial ischemia based on current density maps
Martínez et al. Alteration of the P-wave non-linear dynamics near the onset of paroxysmal atrial fibrillation
Censi et al. On the resolution of ECG acquisition systems for the reliable analysis of the P-wave
Colli Franzone et al. Dynamical effects of myocardial ischemia in anisotropic cardiac models in three dimensions
Gómez-Extremera et al. Differences in nonlinear heart dynamics during rest and exercise and for different training
Al-Zaiti et al. The role of automated 12-lead ECG interpretation in the diagnosis and risk stratification of cardiovascular disease
CN113854985A (en) Method and device for obtaining machine learning model samples for blood pressure prediction
CN103637797B (en) Shown and localization method based on the myocardial blood sector of ST section injury vector compass
CN113855007A (en) Method and device for obtaining machine learning model samples for blood glucose prediction
RU2489964C2 (en) Method of determining indices of variability of operator's heart rate in real-time mode and device for its realisation

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20180302

Termination date: 20211120

CF01 Termination of patent right due to non-payment of annual fee