CN108523873A - Electrocardiosignal feature extracting method based on Fourier Transform of Fractional Order and comentropy - Google Patents
Electrocardiosignal feature extracting method based on Fourier Transform of Fractional Order and comentropy Download PDFInfo
- Publication number
- CN108523873A CN108523873A CN201810093970.9A CN201810093970A CN108523873A CN 108523873 A CN108523873 A CN 108523873A CN 201810093970 A CN201810093970 A CN 201810093970A CN 108523873 A CN108523873 A CN 108523873A
- Authority
- CN
- China
- Prior art keywords
- order
- electrocardiosignal
- signal
- comentropy
- fourier transform
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000001228 spectrum Methods 0.000 claims abstract description 18
- 206010047281 Ventricular arrhythmia Diseases 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 5
- 230000003211 malignant effect Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000005611 electricity Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 230000000747 cardiac effect Effects 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 230000033764 rhythmic process Effects 0.000 description 13
- 206010003658 Atrial Fibrillation Diseases 0.000 description 8
- 206010049418 Sudden Cardiac Death Diseases 0.000 description 5
- 206010003119 arrhythmia Diseases 0.000 description 4
- 230000006793 arrhythmia Effects 0.000 description 4
- 241001269238 Data Species 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
Abstract
The invention discloses a kind of electrocardiosignal feature extracting method based on Fourier Transform of Fractional Order and comentropy, belongs to field of ECG signal processing.The Fourier Transform of Fractional Order under multiple orders is carried out after being pre-processed to pending former electrocardiosignal;It calculates the amplitude spectrum of each order signal and is normalized, then calculate the comentropy of each order amplitude spectrum, using the comentropy under these orders as cardiac electrical feature, select suitable grader that can carry out Classification and Identification etc. to electrocardiosignal.
Description
Technical field
The present invention proposes a kind of electrocardiosignal feature extracting method, is suitable for combining suitable grader, establishes classification mould
Type belongs to field of ECG signal processing.
Background technology
Surface electrocardiogram (electrocardiogram, ECG) is most common heart state non-invasive detection methods, electrocardio
It is abnormal to have close ties with malignant arrhythmia.
Entropy was generalized to by Shannon in information theory in 1948, is given entropy new physical meaning, that is, is indicated system
The uncertainty of (signal).Comentropy is defined as the probability of Discrete Stochastic event appearance.In general, the signal that a signal source is sent out
It is uncertain, can be weighed by the probability of appearance.Probability is bigger, and the chance of appearance is more, uncertain just smaller.
Conversely, the signal that signal source is sent out is more chaotic, the probability of the various Possible events of this segment signal is smaller, and entropy is bigger.Electrocardio is sent out
It is raw when changing, usually come at the cardiac electrical exception such as the increase of confusion degree, especially arrhythmia cordis, it is this it is chaotic under cover one
Fixed rule can carry out feature extraction by the method for nonlinear metric.Therefore this patent quasi-step matrix modern signal processing method
The confusion degree of ecg wave form is measured and described with comentropy, establish corresponding feature vector and carries out electrocardio class whereby
The identification and prediction of type can be used for electrocardio identification, monitoring and early warning etc..
Invention content:
In view of the time-frequency characteristics and nonlinear characteristic of electrocardiosignal.Present invention combination FRFT (Fractional Fourier
Transform, Fourier Transform of Fractional Order) time frequency analysis ability and comentropy to the measured capabilities of signal confusion degree, carry
A kind of electrocardiosignal feature extracting method based on Fourier Transform of Fractional Order and comentropy (also known as Shannon entropy) has been supplied, including
Following steps.
Step S1:One section of electrocardiosignal of acquisition is simultaneously pre-processed, and signal d is obtained;The pretreatment includes removal electrocardio
Hz noise, myoelectricity interference in signal and baseline drift.
Step S2:
S2-1:Signal d pretreated to step S1 carries out the Fourier Transform of Fractional Order of n order respectively, wherein dividing
I-th of order value of number rank Fourier transformation is i/n;Signal d is obtained after the Fourier Transform of Fractional Order of i-th of order
Signal Di;I=1~n;
S2-2:To each order i, signal D is calculatediAmplitude spectrum signal Fvi;
S2-3:By each amplitude spectrum signal FviIt using its max min as reference, is normalized, makes each
Amplitude spectrum signal FviEach point value in 0 to 1 section;Fractional order Fourier amplitude spectrum signal Fv2 after being normalizedi。
S2-4:Calculate signal Fv2iComentropy:
M subregion will be divided between 0 to 1;To the Fv2 under each orderiSignal calculates Fv2iThe numerical value of middle each point is fallen
Fv2 under the probability of each subregion, i-th of orderiIn signal each point fall j-th of subregion probability be pij=Nfvij/
Nfvi, j=1~m, wherein NfviIndicate the Fv2 under i-th of orderiTotal points, NfvijIndicate the Fv2 under i-th of orderiDecline
In the points of j-th of subregion, the fractional order Fourier amplitude spectrum signal Fv2 of i-th of order is calculated according to following formulaiInformation
Entropy Ei
It is bottom that logarithm, which generally takes 2, in formula, can also take other logarithm bottoms, can use the formula scales that refoot between them.
To the Fv2 under each orderiCorresponding comentropy E is all calculated in signali, n order obtain n comentropy altogether,
Vector [the E grown with n points1,…,Ei,…,En] as the feature extracted from this section of electrocardiosignal.
As the feature [E extracted1,…,Ei,…,En] for electrocardiosignal classification when, utilize extracted vector
[E1,…,Ei,…,En] feature vector, training grader is used as then to classify.
Further, when the feature extracted breaks out prediction for malignant ventricular arrhythmia in short term:To malignant ventricular
Arrhythmia cordis occur before electrocardio and never generation malignant ventricular arrhythmia electrocardio this two classes signal, extract feature respectively
[E1,…,Ei,…,En], training grader;The electrocardiosignal acquired is at least 30 seconds, when one section of electrocardiosignal is input to point
Class device, according to determined whether from the feature that this section of electrocardio is extracted by grader malignant ventricular arrhythmia occur before the heart
Electricity.
The prior art is compared, advantageous effect of the present invention is:On the basis of electrocardiosignal time frequency analysis, combining information entropy
Quantitative analysis method electrocardiosignal feature is analyzed, FRFT can have as time-frequency domain signal analysis method from different angles
Spend the feature of all angles in observation signal time-frequency reference axis.By the ability of the quantitative analysis signal confusion degree of comentropy,
The multiple dimensioned feature of signal can be captured, to extract ecg characteristics for carrying out Modulation recognition, to more accurately judge to work as
Preceding cardiomotility state.
Description of the drawings
Fig. 1 is the flow chart of the method for the invention;
Fig. 2 is each order amplitude spectrum signal of signal Fourier Transform of Fractional Order, and abscissa is sampling number, and ordinate is width
It is worth (by taking No. 19140 electrocardiogram (ECG) datas in NSRDB databases as an example, n takes 5, duration 10 seconds);
Fig. 3 electrocardios under each order of Fourier Transform of Fractional Order entropy chart (with No. 19140 electrocardio numbers in NSRDB databases
For, n takes 5, m to take 20, duration 10 seconds).
Specific implementation mode
The present invention will be described in detail below, at the same also describe technical solution of the present invention solve the technical issues of and
Advantageous effect, it should be pointed out that described example is intended merely to facilitate the understanding of the present invention, and does not play any restriction to it
Effect.
The present invention is described with reference to the drawings with for the classification of normal electrocardiosignal in electrocardiosignal before carrying out SCD and occur below
Specific implementation mode.Algorithm flow chart is shown in Fig. 1.Malignant arrhythmia (malignant arrhythmia) is sudden cardiac death
One of the main reason for (sudden cardiac death, SCD), seriously endangers people's health and life.SCD has prominent
Hair, rapid, unpredictable and high case fatality rate feature.Improve clinically to its predictability, early prevention and find in time and
Rescue is particularly important cardiac sudden death.
Step S1:Acquisition ECG signal is simultaneously pre-processed:This step includes:
Using or extraction needed for multiple electrocardiosignals for being all higher than 1 minute, select in this example and come from Sudden
Cardiac Death Holter Database, The MIT-BIH Atrial Fibrillation Database and The
The 48 number of cases evidences of MIT-BIH Normal Sinus Rhythm Database.Data 16 before wherein SCD occurs, normal electrocardio
Data 16, atrial fibrillation rhythm of the heart data 16.50Hz Hz noises, myoelectricity interference and baseline drift in ECG signal are removed first;Make
To be preferred, herein, 50Hz Hz noises, myoelectricity interference and baseline drift in ECG signal are removed using FIR bandpass filters,
Filter cutoff frequency is set as 5Hz and 15Hz.
It, will be from Sudden Cardiac Death Holter after obtaining pretreated data in original electrocardiographicdigital data
The 16 number of cases evidences selected in Database take 30 second datas on the 12nd minute before SCD occurs, while from The MIT-BIH
Normal Sinus Rhythm Database, The MIT-BIH Atrial Fibrillation Database databases are each
16 are selected at random, evidence takes 30 seconds long electrocardiogram (ECG) datas per number of cases.Electrocardiosignal is denoted as data d.
Step S2:Feature extraction:
S2-1:Signal d pretreated to step S1 carries out the Fourier Transform of Fractional Order of n order respectively, wherein dividing
I-th of order value of number rank Fourier transformation is i/n;Signal d is obtained after the Fourier Transform of Fractional Order of i-th of order
Signal Di;I=1~n;
In the present embodiment, the FRFT transformation (14 values are the preferred value that many experiments obtain) under 14 orders is carried out, respectively
Rank exponent number is respectively (i=1~14) i/14, and the formula of Fourier Transform of Fractional Order is as follows:
Wherein
Wherein α=p pi/2s, p are the exponent number (range 0~1) of Fourier Transform of Fractional Order, FpIndicate that fractional order Fourier becomes
Conversion.
S2-2:Obtained signal DiIt for complex signal, is further processed for convenience, calculates D under each orderiThe amplitude of signal
Spectrum.Obtain the fractional order Fourier amplitude spectrum signal Fv under n orderi;(i=1~14), see Fig. 2;
S2-3:By each amplitude spectrum signal FviIt using its max min as reference, is normalized, makes each
Amplitude spectrum signal FviEach point value 0 to 1 section (maximum value is normalized to 1);Signal Fv2 after being normalizedi。
S2-4:M=20 subregion will be divided between 0 to 1;To the Fv2 under each orderiSignal calculates Fv2iMiddle each point
Numerical value fall the probability in each subregion, the Fv2 under i-th of orderiIn signal each point fall j-th of subregion probability be pij=
Nfvij/Nfvi, j=1~m, wherein NfviIndicate the Fv2 under i-th of orderiTotal points, NfvijIt indicates under i-th of order
Fv2iDecline in the points of j-th of subregion, the fractional order Fourier amplitude spectrum signal of i-th of order is calculated according to following formula
Fv2iComentropy Ei
It is bottom that logarithm, which generally takes 2, in formula, can also take other logarithm bottoms, can use the formula scales that refoot between them.To each
Fv2 under orderiCorresponding comentropy E is all calculated in signali, 14 orders obtain 14 comentropies altogether, with 14 points grow to
Measure [E1,…,Ei,…,E14] as the feature extracted from electrocardiosignal.See Fig. 3.
Step S3:Point of electrocardiosignal and normal sinus rhythm electrocardiosignal and atrial fibrillation rhythm of the heart electrocardiosignal before SCD occurs
Class.
S3-1:Algorithm designed according to this invention calculates comentropy vector [E1,…,Ei,…,E14] as feature to
Amount.
S3-2:Electrocardiosignal and the normal sinus heart before SCD occurs are carried out using grader using the feature vector constructed
Restrain the classification of electrocardiosignal and atrial fibrillation rhythm of the heart electrocardiosignal.Due to the design object of grader be by after study, can be automatically
Data are assigned into known class, so for the difference of model, there is different graders;It the characteristics of according to physiological signal, can be with
The grader of use includes:Bayes graders, BP neural network grader, Self-organizing Maps, support vector machines (SVM) algorithm
Deng.Due in this example, normal sinus rhythm electrocardiosignal and atrial fibrillation rhythm of the heart electrocardiosignal being considered as a classification and (recognized
For non-SCD high-risk categories), need to solve is two classification problems, so using simple general-purpose and efficient SVM
Algorithm completes the classification of the rhythm of the heart and normal sinus rhythm electrocardiosignal and atrial fibrillation rhythm of the heart electrocardiosignal before SCD.
It is tested according to above-mentioned data, obtains SCD and preceding 12nd minute electrocardiosignal and normal sinus rhythm electrocardio occurs
Signal and atrial fibrillation rhythm of the heart electrocardiosignal classification accuracy rate, specificity, sensibility are respectively 94.25%, 97.39% and
91.47%.
This method can be used for the cardiac electrical identification of other types and classification.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
It is familiar with the people of the technology within the technical scope disclosed by the invention, it will be appreciated that the transformation and replacement expected should all be covered at this
Within the scope of invention, therefore, the scope of protection of the invention shall be subject to the scope of protection specified in the patent claim.
Claims (6)
1. the electrocardiosignal feature extracting method based on Fourier Transform of Fractional Order and comentropy, which is characterized in that including as follows
Step:
Step S1:One section of electrocardiosignal of acquisition is simultaneously pre-processed, and signal d is obtained;
Step S2:
S2-1:Signal d pretreated to step S1 carries out the Fourier Transform of Fractional Order of n order, wherein fractional order respectively
I-th of order value of Fourier transformation is i/n;Signal d obtains signal after the Fourier Transform of Fractional Order of i-th of order
Di;I=1~n;
S2-2:To each order i, signal D is calculatediAmplitude spectrum signal Fvi;
S2-3:By each amplitude spectrum signal FviIt using its max min as reference, is normalized, makes each amplitude spectrum
Signal FviEach point value in 0 to 1 section;Fractional order Fourier amplitude spectrum signal Fv2 after being normalizedi;
S2-4:Calculate signal Fv2iComentropy:
M subregion will be divided between 0 to 1;To the Fv2 under each orderiSignal calculates Fv2iThe numerical value of middle each point is fallen every
The probability of a subregion, the Fv2 under i-th of orderiIn signal each point fall j-th of subregion probability be pij=Nfvij/Nfvi, j=
1~m, wherein NfviIndicate the Fv2 under i-th of orderiTotal points, NfvijIndicate the Fv2 under i-th of orderiDecline at j-th
The points of subregion calculate the fractional order Fourier amplitude spectrum signal Fv2 of i-th of order according to following formulaiComentropy Ei
To the Fv2 under each orderiCorresponding comentropy E is all calculated in signali, n order obtains n comentropy altogether, with n
Long vector [the E of point1,…,Ei,…,En] as the feature extracted from this section of electrocardiosignal.
2. a kind of electrocardiosignal feature extraction side based on Fourier Transform of Fractional Order and comentropy according to claim 1
Method, which is characterized in that pretreatment described in step S1 includes Hz noise, myoelectricity interference and the baseline drift removed in electrocardiosignal
It moves.
3. a kind of electrocardiosignal feature extraction side based on Fourier Transform of Fractional Order and comentropy according to claim 1
Method, which is characterized in that as the feature [E extracted1,…,Ei,…,En] for electrocardiosignal classification when, utilize extracted to
Measure [E1,…,Ei,…,En] feature vector, training grader is used as then to classify.
4. a kind of electrocardiosignal feature extraction side based on Fourier Transform of Fractional Order and comentropy according to claim 1
Method, which is characterized in that when the feature extracted breaks out prediction for malignant ventricular arrhythmia in short term:To the malignant ventricular rhythm of the heart
Electrocardio before not normal generation and the electrocardio of malignant ventricular arrhythmia this two classes signal never occurs, extracts feature respectively
[E1,…,Ei,…,En], training grader;The electrocardiosignal acquired is at least 30 seconds, when one section of electrocardiosignal is input to point
Class device, according to determined whether from the feature that this section of electrocardio is extracted by grader malignant ventricular arrhythmia occur before the heart
Electricity.
5. a kind of electrocardiosignal feature extraction side based on Fourier Transform of Fractional Order and comentropy according to claim 4
Method, which is characterized in that when the feature extracted breaks out prediction for malignant ventricular arrhythmia in short term, n=14.
6. a kind of electrocardiosignal feature extraction side based on Fourier Transform of Fractional Order and comentropy according to claim 4
Method, which is characterized in that m=20.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810093970.9A CN108523873B (en) | 2018-01-31 | 2018-01-31 | Electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810093970.9A CN108523873B (en) | 2018-01-31 | 2018-01-31 | Electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108523873A true CN108523873A (en) | 2018-09-14 |
CN108523873B CN108523873B (en) | 2021-11-16 |
Family
ID=63486214
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810093970.9A Expired - Fee Related CN108523873B (en) | 2018-01-31 | 2018-01-31 | Electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108523873B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110179451A (en) * | 2019-06-10 | 2019-08-30 | 深圳市是源医学科技有限公司 | Electrocardiosignal quality determining method, device, computer equipment and storage medium |
CN111444832A (en) * | 2020-03-25 | 2020-07-24 | 哈尔滨工程大学 | Whale cry classification method based on convolutional neural network |
CN112545528A (en) * | 2020-12-28 | 2021-03-26 | 北京理工大学 | Electrocardio T wave feature extraction method based on fractional Fourier transform and tensor decomposition |
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 |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1951320A (en) * | 2006-11-16 | 2007-04-25 | 上海交通大学 | Abnormal electrocardiogram recognition method based on ultra-complete characteristics |
KR20110116537A (en) * | 2010-04-19 | 2011-10-26 | 경북대학교 산학협력단 | Signal estimating apparatus and signal estimating method thereof |
CN102835955A (en) * | 2012-09-08 | 2012-12-26 | 北京工业大学 | Method of automatically removing ocular artifacts from electroencephalogram signal without setting threshold value |
CN103578466A (en) * | 2013-11-11 | 2014-02-12 | 清华大学 | Voice and non-voice detection method based on fractional order Fourier transformation |
CN105320969A (en) * | 2015-11-20 | 2016-02-10 | 北京理工大学 | A heart rate variability feature classification method based on multi-scale Renyi entropy |
CN105411565A (en) * | 2015-11-20 | 2016-03-23 | 北京理工大学 | Heart rate variability feature classification method based on generalized scale wavelet entropy |
CN105496402A (en) * | 2015-11-20 | 2016-04-20 | 北京理工大学 | Electrocardio feature analyzing method based on point diagram and symbolic dynamics |
CN106092158A (en) * | 2016-08-19 | 2016-11-09 | 北京理工大学 | Physical parameter method of estimation, device and electronic equipment |
US20170168988A1 (en) * | 2015-12-09 | 2017-06-15 | The Aerospace Corporation | Signal/noise separation using frft rotational parameter obtained in relation to wigner distribution |
-
2018
- 2018-01-31 CN CN201810093970.9A patent/CN108523873B/en not_active Expired - Fee Related
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1951320A (en) * | 2006-11-16 | 2007-04-25 | 上海交通大学 | Abnormal electrocardiogram recognition method based on ultra-complete characteristics |
KR20110116537A (en) * | 2010-04-19 | 2011-10-26 | 경북대학교 산학협력단 | Signal estimating apparatus and signal estimating method thereof |
CN102835955A (en) * | 2012-09-08 | 2012-12-26 | 北京工业大学 | Method of automatically removing ocular artifacts from electroencephalogram signal without setting threshold value |
CN103578466A (en) * | 2013-11-11 | 2014-02-12 | 清华大学 | Voice and non-voice detection method based on fractional order Fourier transformation |
CN105320969A (en) * | 2015-11-20 | 2016-02-10 | 北京理工大学 | A heart rate variability feature classification method based on multi-scale Renyi entropy |
CN105411565A (en) * | 2015-11-20 | 2016-03-23 | 北京理工大学 | Heart rate variability feature classification method based on generalized scale wavelet entropy |
CN105496402A (en) * | 2015-11-20 | 2016-04-20 | 北京理工大学 | Electrocardio feature analyzing method based on point diagram and symbolic dynamics |
US20170168988A1 (en) * | 2015-12-09 | 2017-06-15 | The Aerospace Corporation | Signal/noise separation using frft rotational parameter obtained in relation to wigner distribution |
CN106092158A (en) * | 2016-08-19 | 2016-11-09 | 北京理工大学 | Physical parameter method of estimation, device and electronic equipment |
Non-Patent Citations (1)
Title |
---|
尚宇,徐婷,何永辉: "分数阶傅里叶变换在心电信号处理中的应用", 《电子科技》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110179451A (en) * | 2019-06-10 | 2019-08-30 | 深圳市是源医学科技有限公司 | Electrocardiosignal quality determining method, device, computer equipment and storage medium |
CN110179451B (en) * | 2019-06-10 | 2021-10-29 | 深圳市是源医学科技有限公司 | Electrocardiosignal quality detection method and device, computer equipment and storage medium |
CN111444832A (en) * | 2020-03-25 | 2020-07-24 | 哈尔滨工程大学 | Whale cry classification method based on convolutional neural network |
CN112545528A (en) * | 2020-12-28 | 2021-03-26 | 北京理工大学 | Electrocardio T wave feature extraction method based on fractional Fourier transform and tensor decomposition |
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 |
---|---|
CN108523873B (en) | 2021-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108652615B (en) | Electrocardio data pathological feature quantitative analysis method and device | |
CN108523873A (en) | Electrocardiosignal feature extracting method based on Fourier Transform of Fractional Order and comentropy | |
Bansal et al. | A review of measurement and analysis of heart rate variability | |
CN105320969A (en) | A heart rate variability feature classification method based on multi-scale Renyi entropy | |
Kelwade et al. | Radial basis function neural network for prediction of cardiac arrhythmias based on heart rate time series | |
CN108403107B (en) | Arrhythmia discrimination method and system | |
KR101366101B1 (en) | System and method for classificating normal signal of personalized ecg | |
Kelwade et al. | Prediction of cardiac arrhythmia using artificial neural network | |
CN112057087B (en) | Autonomic nerve function data processing method and device for high-risk schizophrenic people | |
Kelwade et al. | Prediction of heart abnormalities using particle swarm optimization in radial basis function neural network | |
Vuksanovic et al. | AR-based method for ECG classification and patient recognition | |
CN107088061A (en) | A kind of HRV on-line analysis systems and its method based on Shewhart control figures | |
CN114366060A (en) | Health early warning method and device based on heart rate variability and electronic equipment | |
KR101273652B1 (en) | A method to detect myocardial ischemia using comparison analysis of heart rate variability time and frequency domain features | |
Al-Mulla et al. | Statistical class separation using sEMG features towards automated muscle fatigue detection and prediction | |
Reddy et al. | Ecg signal characterization and correlation to heart abnormalities | |
Orozco-Duque et al. | Classification of premature ventricular contraction based on discrete wavelet transform for real time applications | |
Ding-Fei et al. | Study of feature extraction based on autoregressive modeling in EGG automatic diagnosis | |
Chumrit et al. | Ecg-based arrhythmia detection using average energy and zero-crossing features with support vector machine | |
Murthy et al. | Ecg signal denoising and ischemic event feature extraction using daubechies wavelets | |
Celin et al. | A novel method for ECG classification using polynomial based curve fitting | |
Dharma et al. | Hypertension Identification Using Naive Bayes Classification Method and Pan Tompkins Feature Extraction | |
Kelwade et al. | Comparative study of neural networks for prediction of cardiac arrhythmias | |
Talatov et al. | Methodology for processing and analysis of diagnostic indicators electrocardiogram based on Labview | |
Mandal et al. | Detection of Cardiac Arrhythmia based on feature fusion and Machine Learning algorithms |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20211116 |
|
CF01 | Termination of patent right due to non-payment of annual fee |