CN108523873B - Electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy - Google Patents
Electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy Download PDFInfo
- Publication number
- CN108523873B CN108523873B CN201810093970.9A CN201810093970A CN108523873B CN 108523873 B CN108523873 B CN 108523873B CN 201810093970 A CN201810093970 A CN 201810093970A CN 108523873 B CN108523873 B CN 108523873B
- Authority
- CN
- China
- Prior art keywords
- signal
- fractional fourier
- fourier transform
- information entropy
- electrocardiosignals
- 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.)
- Expired - Fee Related
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 8
- 238000001228 spectrum Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 11
- 230000000747 cardiac effect Effects 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 10
- 238000005192 partition Methods 0.000 claims description 9
- 206010047281 Ventricular arrhythmia Diseases 0.000 claims description 7
- 230000003211 malignant effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 230000002861 ventricular Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 3
- 206010049418 Sudden Cardiac Death Diseases 0.000 description 14
- 230000033764 rhythmic process Effects 0.000 description 14
- 206010003658 Atrial Fibrillation Diseases 0.000 description 6
- 206010003119 arrhythmia Diseases 0.000 description 4
- 230000006793 arrhythmia Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000003183 myoelectrical effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009396 hybridization Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses an electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy, and belongs to the field of electrocardiosignal processing. Preprocessing an original electrocardiosignal to be processed and then performing fractional Fourier transform under multiple orders; calculating the amplitude spectrum of each order of signal and normalizing, then calculating the information entropy of each order of amplitude spectrum, taking the information entropy under the orders as the characteristics of electrocardio, selecting a proper classifier to classify and identify the electrocardio signal, and the like.
Description
Technical Field
The invention provides an electrocardiosignal feature extraction method, which is suitable for establishing a classification model by combining a proper classifier and belongs to the field of electrocardiosignal processing.
Background
Body surface Electrocardiogram (ECG) is the most common noninvasive detection method for cardiac states, and cardiac anomalies are closely related to the occurrence of malignant arrhythmia.
Entropy was popularized by Shannon in 1948 into information theory, giving entropy a new physical meaning, i.e. representing the uncertainty of the system (signal). The entropy of information is defined as the probability of the occurrence of a discrete random event. Generally, the signal from a signal source is uncertain and can be measured by the probability of occurrence. The greater the probability, the more opportunities for occurrence and the less uncertainty. Conversely, the more chaotic the signal from the signal source is, the smaller the probability of various possible events of the signal is, and the larger the entropy value is. When the electrocardio changes, the chaos degree is increased, especially the abnormal electrocardio such as arrhythmia, and a certain rule is hidden in the chaos, and the characteristic extraction can be carried out by a nonlinear measurement method. Therefore, the method is combined with the modern signal processing method and the information entropy to measure and describe the chaotic degree of the electrocardiogram waveform, establish the corresponding characteristic vector and identify and predict the electrocardiogram type, and can be used for electrocardiogram identification, monitoring, early warning and the like.
The invention content is as follows:
considering time-frequency characteristics and nonlinear characteristics of electrocardiosignals. The invention provides an electrocardiosignal feature extraction method based on Fractional Fourier Transform and information entropy (also called Shannon entropy) by combining the time-frequency analysis capability of FRFT (Fractional Fourier Transform) and the measurement capability of the information entropy on the signal chaos degree, which comprises the following steps.
Step S1: acquiring a section of electrocardiosignals and preprocessing the electrocardiosignals to obtain a signal d; the preprocessing comprises the removal of power frequency interference, myoelectric interference and baseline drift in the electrocardiosignals.
Step S2:
s2-1: respectively performing fractional Fourier transform of n orders on the signal d preprocessed in the step S1, wherein the ith order value of the fractional Fourier transform is i/n; the signal D is subjected to ith order fractional Fourier transform to obtain a signal Di;i=1~n;
S2-2: for each order i, a signal D is calculatedi(iv) amplitude spectrum signal Fvi;
S2-3: each amplitude spectrum signal FviNormalizing the maximum and minimum values to obtain each amplitude spectrum signal FviEach point of (1) is in the interval of 0 to 1; obtaining a normalized fractional Fourier magnitude spectrum signal Fv2i。
S2-4: calculation signal Fv2iThe information entropy of (2):
equally dividing the space between 0 and 1 into m partitions; for Fv2 at each orderiSignal, calculate Fv2iProbability of the value of each point falling in each partition, Fv2 at the ith orderiThe probability that each point in the signal falls in the jth partition is pij=Nfvij/NfviJ is 1 to m, wherein NfviRepresents Fv2 at the ith orderiTotal number of points of (N)fvijRepresents Fv2 at the ith orderiThe point number of the ith division is calculated according to the following formula, and the fractional Fourier amplitude spectrum signal Fv2 of the ith order is calculatediInformation entropy E ofi
The logarithm in the formula generally takes 2 as the base, and can also take other logarithm bases, and the logarithm bases can be converted by a base-changing formula.
For Fv2 at each orderiThe signals are all calculated to obtain corresponding information entropy EiN orders obtain n information entropies in total, with a vector [ E ] n points long1,…,Ei,…,En]As a feature extracted from the segment of cardiac signals.
When the feature extracted [ E ]1,…,Ei,…,En]For classification of ECG signals, using the extracted vector E1,…,Ei,…,En]As feature vectors, classifiers are trained and then classified.
Further, when the extracted features are used for short-term onset prediction of malignant ventricular arrhythmias: respectively extracting characteristics [ E ] of electrocardio before malignant ventricular arrhythmia and electrocardio without malignant ventricular arrhythmia1,…,Ei,…,En]Training a classifier; the collected electrocardiosignals are at least 30 seconds, and when a section of electrocardiosignals is input into the classifier, the classifier judges whether the electrocardiosignals are the electrocardiosignals before the malignant ventricular arrhythmia occurs according to the characteristics extracted from the section of electrocardiosignals.
Compared with the prior art, the invention has the beneficial effects that: on the basis of the time-frequency analysis of the electrocardiosignal, the electrocardiosignal characteristics are analyzed by combining a quantitative analysis method of information entropy, and the FRFT is used as a time-frequency domain signal analysis method, so that the characteristics of each angle on a signal time-frequency coordinate axis can be observed from different angles. By the aid of the capacity of quantitatively analyzing the signal chaos degree of the information entropy, multi-scale features of the signals can be captured, so that the electrocardio features are extracted and used for signal classification, and the current heart activity state is judged more accurately.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
fig. 2 shows the signal of the amplitude spectrum of each order of fractional fourier transform, the abscissa is the number of sampling points, and the ordinate is the amplitude (for example, the electrocardiographic data No. 19140 in the NSRDB database, n is 5, and the duration is 10 seconds);
FIG. 3 is an entropy diagram of the electrocardiograph at each order of fractional Fourier transform (taking electrocardiographic data No. 19140 in NSRDB database as an example, n is 5, m is 20, and duration is 10 seconds).
Detailed Description
The present invention will be described in detail below while describing the technical problems and advantages solved by the technical solutions of the present invention, and it should be noted that the described examples are only intended to facilitate the understanding of the present invention, but do not limit the present invention in any way.
The following describes an embodiment of the present invention with reference to the drawings, taking as an example classification of an electrical cardiac signal before SCD generation and a normal electrical cardiac signal. The algorithm flow chart is shown in figure 1. Malignant arrhythmia (malignan arrhythmia) is one of the main causes of Sudden Cardiac Death (SCD), and seriously harms people's health and life. SCD is characterized by burst, rapidity, unpredictability, and high mortality. The method improves the clinical predictability of the sudden cardiac death, and is especially important for early prevention, timely discovery and rescue of the sudden cardiac death.
Step S1: ECG signals were acquired and pre-processed: this step includes:
the electrocardiosignals required for more than 1 minute are taken or extracted, in this example 48 cases of data from Sudden Cardiac layered Holter Database, The MIT-BIH orthogonal hybridization Database and The MIT-BIH Normal Sinus Rhythm Database are selected. The data before SCD generation is 16 cases, the data of normal electrocardio is 16 cases, and the data of atrial fibrillation and heart rhythm is 16 cases. Firstly, removing 50Hz power frequency interference, myoelectricity interference and baseline drift in ECG signals; preferably, the 50Hz power frequency interference, the myoelectric interference and the baseline shift in the ECG signal are removed by an FIR band-pass filter, and the filter cut-off frequency is set to be 5Hz and 15 Hz.
After preprocessing data is obtained from original electrocardiogram data, 16 cases of data selected from Sudden Cardiac Death Holter Database are taken 30 seconds from 12 minutes before SCD occurs, 16 cases of data are randomly selected from The MIT-BIH Normal sine Rhythm Database and The MIT-BIH orthogonal filtration Database, and 30 seconds of long electrocardiogram data are taken from each case of data. The electrocardiographic signal is recorded as data d.
Step S2: feature extraction:
S2-1:respectively performing fractional Fourier transform of n orders on the signal d preprocessed in the step S1, wherein the ith order value of the fractional Fourier transform is i/n; the signal D is subjected to ith order fractional Fourier transform to obtain a signal Di;i=1~n;
In this embodiment, FRFT transformation is performed at 14 orders (14 is an optimized value obtained by a large number of experiments), each order is i/14(i is 1 to 14), and a formula of fractional fourier transformation is as follows:
wherein
Wherein alpha is p pi/2, p is the order of fractional Fourier transform (range 0-1), FpRepresenting a fractional fourier transform operator.
S2-2: the resulting signal DiFor complex signals, D is calculated at each order for further processingiAmplitude spectrum of the signal. Obtaining fractional Fourier magnitude spectrum signals Fv under n ordersi(ii) a (i 1-14), see fig. 2;
s2-3: each amplitude spectrum signal FviNormalizing the maximum and minimum values to obtain each amplitude spectrum signal FviThe value of each point of (1) is in the interval of 0 to 1 (the maximum value is normalized to 1); obtaining a normalized signal Fv2i。
S2-4: equally dividing the space between 0 and 1 into 20 partitions; for Fv2 at each orderiSignal, calculate Fv2iProbability of the value of each point falling in each partition, Fv2 at the ith orderiThe probability that each point in the signal falls in the jth partition is pij=Nfvij/NfviJ is 1 to m, wherein NfviRepresents Fv2 at the ith orderiTotal number of points of (N)fvijRepresents Fv2 at the ith orderiMiddle dropThe point number of the j-th subarea is used for calculating the fractional Fourier amplitude spectrum signal Fv2 of the ith order according to the following formulaiInformation entropy E ofi
The logarithm in the formula generally takes 2 as the base, and can also take other logarithm bases, and the logarithm bases can be converted by a base-changing formula. For Fv2 at each orderiThe signals are all calculated to obtain corresponding information entropy Ei14 orders of 14 obtain 14 information entropies in total, with a 14-point long vector [ E1,…,Ei,…,E14]As features extracted from the cardiac signal. See fig. 3.
Step S3: SCD produces a classification of the pre-cardiac electrical signals from normal sinus rhythm and atrial fibrillation rhythm cardiac electrical signals.
S3-1: calculating information entropy vector [ E ] according to algorithm designed by the invention1,…,Ei,…,E14]As a feature vector.
And S3-2, classifying the pre-SCD electrocardiosignals, the normal sinus rhythm electrocardiosignals and the atrial fibrillation rhythm electrocardiosignals by using the constructed feature vector and a classifier. Since the design goal of a classifier is to automatically classify data into known classes after learning, there are different classifiers for different models; depending on the characteristics of the physiological signal, classifiers may be employed that include: bayes classifier, BP neural network classifier, self-organizing map, Support Vector Machine (SVM) algorithm, etc. In the example, the normal sinus rhythm electrocardiosignals and the atrial fibrillation rhythm electrocardiosignals are regarded as one category (namely regarded as a non-SCD high-risk category), and a binary category problem needs to be solved, so that the classification of the SCD pre-rhythm electrocardiosignals, the normal sinus rhythm electrocardiosignals and the atrial fibrillation rhythm electrocardiosignals is completed by adopting a simple, universal and efficient SVM algorithm.
Experiments are carried out according to the data, and the classification accuracy, specificity and sensitivity of the electrocardiosignals before the SCD occurs, the normal sinus rhythm electrocardiosignals and the atrial fibrillation rhythm electrocardiosignals are respectively 94.25%, 97.39% and 91.47%.
The method can also be used for identifying and classifying other types of electrocardios.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can understand that the modifications and substitutions within the technical scope of the present invention disclosed by the present invention should be covered within the scope of the present invention, and therefore, the scope of the present invention should be subject to the protection scope of the claims.
Claims (6)
1. An electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy is characterized by comprising the following steps:
step S1: acquiring a section of electrocardiosignals and preprocessing the electrocardiosignals to obtain a signal d;
step S2:
s2-1: respectively performing fractional Fourier transform of n orders on the signal d preprocessed in the step S1, wherein the ith order value of the fractional Fourier transform is i/n; the signal D is subjected to ith order fractional Fourier transform to obtain a signal Di;i=1~n;
S2-2: for each order i, a signal D is calculatedi(iv) amplitude spectrum signal Fvi;
S2-3: each amplitude spectrum signal FviNormalizing the maximum and minimum values to obtain each amplitude spectrum signal FviEach point of (1) is in the interval of 0 to 1; obtaining a normalized fractional Fourier magnitude spectrum signal Fv2i;
S2-4: calculation signal Fv2iThe information entropy of (2):
equally dividing the space between 0 and 1 into m partitions; for Fv2 at each orderiSignal, calculate Fv2iProbability of the value of each point falling in each partition, Fv2 at the ith orderiThe probability that each point in the signal falls in the jth partition is pij=Nfvij/NfviJ is 1 to m, wherein NfviRepresents Fv2 at the ith orderiOfNumber of points, NfvijRepresents Fv2 at the ith orderiThe point number of the ith division is calculated according to the following formula, and the fractional Fourier amplitude spectrum signal Fv2 of the ith order is calculatediInformation entropy E ofi
For Fv2 at each orderiThe signals are all calculated to obtain corresponding information entropy EiN orders obtain n information entropies in total, with a vector [ E ] n points long1,…,Ei,…,En]As a feature extracted from the segment of cardiac signals.
2. The method for extracting features of electrocardiosignals based on fractional Fourier transform and information entropy as claimed in claim 1, wherein the preprocessing of step S1 includes removing power frequency interference, electromyographic interference and baseline wander in electrocardiosignals.
3. The method for extracting features of electrocardiosignals based on fractional Fourier transform and information entropy as claimed in claim 1, wherein when the features [ E ] are extracted1,…,Ei,…,En]For classification of ECG signals, using the extracted vector E1,…,Ei,…,En]As feature vectors, classifiers are trained and then classified.
4. The method for extracting features of electrocardiosignals based on fractional Fourier transform and information entropy as claimed in claim 1, wherein when the extracted features are used for the prediction of short-term onset of malignant ventricular arrhythmia: respectively extracting characteristics [ E ] of electrocardio before malignant ventricular arrhythmia and electrocardio without malignant ventricular arrhythmia1,…,Ei,…,En]Training a classifier; the collected electrocardiosignals are at least 30 seconds, and when one section of electrocardiosignals is input into the classifier, the root isThe classifier judges whether the electrocardiogram is before malignant ventricular arrhythmia according to the features extracted from the section of electrocardiogram.
5. The method for extracting electrocardiosignal features based on fractional Fourier transform and information entropy as claimed in claim 4, wherein n is 14 when the extracted features are used for the prediction of the short-term onset of malignant ventricular arrhythmia.
6. The method for extracting features of electrocardiosignals based on fractional Fourier transform and information entropy as claimed in claim 4, wherein m is 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 CN108523873A (en) | 2018-09-14 |
CN108523873B true 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) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN112545528B (en) * | 2020-12-28 | 2022-07-12 | 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 (4)
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 |
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 |
CN106092158A (en) * | 2016-08-19 | 2016-11-09 | 北京理工大学 | Physical parameter method of estimation, device and electronic equipment |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110116537A (en) * | 2010-04-19 | 2011-10-26 | 경북대학교 산학협력단 | Signal estimating apparatus and signal estimating method thereof |
CN105411565B (en) * | 2015-11-20 | 2018-12-04 | 北京理工大学 | Heart rate variability tagsort method based on broad sense multi-scale wavelet entropy |
CN105496402B (en) * | 2015-11-20 | 2018-03-02 | 北京理工大学 | Ecg characteristics analysis method based on scatter diagram and symbolic dynamics |
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 |
US9804999B2 (en) * | 2015-12-09 | 2017-10-31 | 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 (4)
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 |
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 |
CN106092158A (en) * | 2016-08-19 | 2016-11-09 | 北京理工大学 | Physical parameter method of estimation, device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN108523873A (en) | 2018-09-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Nayak et al. | A review on the nonlinear dynamical system analysis of electrocardiogram signal | |
CN108523873B (en) | Electrocardiosignal feature extraction method based on fractional Fourier transform and information entropy | |
Mahajan et al. | Cardiac rhythm classification from a short single lead ECG recording via random forest | |
Shao et al. | Detection of atrial fibrillation from ECG recordings using decision tree ensemble with multi-level features | |
Kelwade et al. | Radial basis function neural network for prediction of cardiac arrhythmias based on heart rate time series | |
DİKER et al. | A diagnostic model for identification of myocardial infarction from electrocardiography signals | |
Henzel et al. | Atrial fibrillation episodes detection based on classification of heart rate derived features | |
Kelwade et al. | Prediction of cardiac arrhythmia using artificial neural network | |
Rangappa et al. | Classification of cardiac arrhythmia stages using hybrid features extraction with k-nearest neighbour classifier of ecg signals | |
Khan et al. | Electrocardiogram heartbeat classification using convolutional neural networks for the detection of cardiac Arrhythmia | |
Kumari et al. | Performance evaluation of neural networks and adaptive neuro fuzzy inference system for classification of Cardiac Arrhythmia | |
Vuksanovic et al. | AR-based method for ECG classification and patient recognition | |
Mayapur | Classification of Arrhythmia from ECG Signals using MATLAB | |
Kaya | Classification of PVC beat in ECG using basic temporal features | |
Al-Masri | Detecting ECG heartbeat abnormalities using artificial neural networks | |
CN112716498A (en) | Electrocardiosignal feature extraction method based on dynamic time warping and symbolic dynamics | |
Kelwade et al. | Comparative study of neural networks for prediction of cardiac arrhythmias | |
Lin et al. | Nonlinear interpolation fractal classifier for multiple cardiac arrhythmias recognition | |
Utkarsh et al. | Classification of atrial arrhythmias using neural networks | |
Dharma et al. | Hypertension Identification Using Naive Bayes Classification Method and Pan Tompkins Feature Extraction | |
Mandal et al. | Detection of Cardiac Arrhythmia based on feature fusion and Machine Learning algorithms | |
Aulia et al. | Abnormal ECG classification using empirical mode decomposition and entropy | |
Haiying et al. | Real-time automatic ecg diagnosis method dedicated to pervasive cardiac care | |
Ouelli et al. | Electrocardiogram features extraction and classification for arrhythmia detection | |
Du et al. | A novel method for diagnosing premature ventricular contraction beat based on chaos theory |
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 |