CN110169767A - A kind of search method of electrocardiosignal - Google Patents
A kind of search method of electrocardiosignal Download PDFInfo
- Publication number
- CN110169767A CN110169767A CN201910611770.2A CN201910611770A CN110169767A CN 110169767 A CN110169767 A CN 110169767A CN 201910611770 A CN201910611770 A CN 201910611770A CN 110169767 A CN110169767 A CN 110169767A
- Authority
- CN
- China
- Prior art keywords
- data
- electrocardiosignal
- retrieved
- retrieval
- electrocardiogram
- 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
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
- A61B5/24—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
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Cardiology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention relates to a kind of search method of electrocardiosignal, method is the following steps are included: a, calculate the feature of target data and data to be retrieved；B, the electrocardiosignal similarity measurement of DTW is improved based on TBD；C, search result is evaluated by the susceptibility and positive inspection rate that calculate retrieval；D, the amplitude Characteristics of electrocardiogram (ECG) data are retrieved；E, the morphological feature of electrocardiogram (ECG) data is retrieved.Processing through the method for the present invention, the clean electrocardiosignal after denoising have not only effective filtered out noise, and have restored electrocardiosignal characteristics of low-frequency wave, remain the effective information of electrocardiosignal.Present invention retrieval is broadly divided into the amplitude Characteristics retrieval to electrocardiogram (ECG) data and retrieves to the morphological feature of electrocardiogram (ECG) data.Processing through the method for the present invention makes full use of the respective advantage of the two to solve electrocardiosignal similarity measurement problem encountered, realizes the retrieval to electrocardiosignal.
Description
Technical field
Automatic detection and analytical technology the present invention relates to electrocardiosignal, specifically a kind of retrieval side of electrocardiosignal
Method.
Background technique
The diagnosis cardiovascular disease mainly judgement according to doctor for the electrocardiogram of patient at present.But cardiovascular disease
Huge number, individual difference is strong, so that performance of the same disease on different patient's electrocardiograms is also not quite similar.Therefore
To all individuals using the ways of same template and unreasonable, this is also the faced clinical problem of automatic diagnosis.Nowadays face
The magnanimity electrocardiogram generated in bed and tele-medicine increases the workload of doctor, therefore how to assist doctor in real time and quick
Interested electrocardiogram (ECG) data is found into urgent problem to be solved in ground.
In order to greatly save doctor's time, diagnosis efficiency is improved, the retrieval of ecg signal data is very necessary.
Summary of the invention
It is an object of the invention to provide a kind of search methods of electrocardiosignal, similar to solve existing search method progress
There are the retrieval precision of electrocardiosignal characteristic wave and hand-designed feature generalization ability difference and intrinsic dimensionality are superfluous greatly when degree measurement
Problem more than remaining information.
The present invention is implemented as follows: a kind of search method of electrocardiosignal, comprising the following steps:
A, the feature of target data and data to be retrieved is calculated；
B, the electrocardiosignal similarity measurement of DTW is improved based on TBD；
C, search result is evaluated by the susceptibility and positive inspection rate that calculate retrieval；
D, the amplitude Characteristics of electrocardiogram (ECG) data are retrieved；
E, the morphological feature of electrocardiogram (ECG) data is retrieved.
The detailed process of step a are as follows:
A-1, determine that length is the target data a=[a of l1,a2,...al], wherein the amplitude Characteristics vector of a is it
Body；
A-2, data b to be retrieved is intercepted on electrocardiosignal X according to the length l of target data a1,b2,...bm, to be retrieved
It selects step-length for k when data cutout, and calculates the expression formula of data to be retrieved are as follows:It is to be checked
Rope data b1,b2,...bmAmplitude Characteristics vector be itself；
A-3, target data morphological feature vector expression formula beWherein k is positive integer, number to be retrieved
According to morphological feature vector expression formula beWherein k is positive integer.
The detailed process of step b are as follows:
B-1, the calculating using TBD to the click-through row distance in two sequences: selection target data Q=(q1,q2,
...qm), calculate data C=(c1,c2,...cnThe distance between) and Q each point, TBD is defined asThen Q and C are brought intoWherein k is positive integer, is obtained
To the Distance matrix D of m*n；
B-2, optimal path from S point to E point is looked in distance matrix network, every bit is accumulative in Distance matrix D
Distance r (i, j) is itself and the sum of the shortest distance for reaching this point, expression formula are as follows: r (i, j)=dTBD(qi,cj)+min(r
(i-1,j-1),r(i-1,j),r(i,j-1))；
B-3, the shortest distance between the data and target data to be retrieved of selection is calculated using the method that TBD improves DTW
Characterize the similarity between two data, innovatory algorithm similarity definition is
The detailed process of step c are as follows: calculate retrieval susceptibility and positive inspection rate:
Susceptibility calculation formula are as follows:
Positive inspection rate calculation formula are as follows:
Wherein TP is true positives number of samples, and FN is false negative number of samples, and FP is false positive number of samples.
In step d: carrying out retrieval to the amplitude Characteristics of electrocardiogram (ECG) data includes the retrieval that holocentric claps electrocardiosignal amplitude Characteristics
With the retrieval of random length electrocardiosignal amplitude Characteristics.
In step e: carrying out retrieval to the morphological feature of electrocardiogram (ECG) data includes the retrieval that holocentric claps electrocardiosignal morphological feature
With the retrieval of random length electrocardiosignal morphological feature.
The invention discloses a kind of search method for improving dynamic time warping based on the graceful divergence of total Donald Bragg, retrieval is main
It is divided into both of which: A) amplitude Characteristics of electrocardiogram (ECG) data are retrieved；B) morphological feature of electrocardiogram (ECG) data is retrieved.Through present invention side
The processing of method both makes full use of respective advantage to solve electrocardiosignal similarity measurement problem encountered, realizes pair
The retrieval of electrocardiosignal.
Detailed description of the invention
Fig. 1 holocentric amplitude of beat value searching algorithm flow chart.
Fig. 2 holocentric claps modality retrieval algorithm flow chart.
Fig. 3 heart claps interception schematic diagram.
Fig. 4 random length electrocardiosignal amplitude searching algorithm flow chart.
Fig. 5 random length electrocardiosignal modality retrieval algorithm flow chart.
Specific embodiment
Below in conjunction with attached drawing, present invention is further described in detail, and those skilled in the art can be as disclosed by this specification
Content realize the present invention.
The present embodiment inside saves as 128.00GB, Win7,64 bit manipulation in Intel Xeon CPU E5-2697 2.70GHz
It is realized in the computer of system, entire electrocardiosignal Algorithms for Automatic Classification is realized using Matlab language.
In conjunction with figure 1 above, 2,3, implementation process of the invention is as follows:
A the electrocardiosignal of human body) is obtained, and is filtered, the R wave of the electrocardiosignal after detection filter:
1. signal acquisition: acquiring human body electrocardio original signal with the frequency acquisition of 1000Hz, and be stored as the number of TXT document
According to form, then the electrocardio original signal data that the TXT document stores is read in computer with Matlab software；
2. handling the electrocardio original signal data:
QRS complex is found on scale 4 by wavelet decomposition, under the premise of QRS complex determines, then carries out R crest value
The detection of point.QRS complex is protruded using the transformation of energy window again, it is bent to obtain different signal energies that the size of window is arranged
Line searches out the peak point of energy in the energy curve of acquirement, carries out screening to the R crest value future position obtained at this time, will
It is unsatisfactory for the removal of condition, to obtain the accurate location of R crest value point.
Energy window transformation for mula:
Retain R crest value point meets condition formula: 0.4*RRmean<RR<1.6*RRmean。
B) similarity measurement:
The shortest distance between the data and target data to be retrieved of selection is calculated come table using the method that TBD improves DTW
The similarity between two data is levied, heart beat of data similar with target data is marked by the setting of threshold value δ.
C) holocentric claps the retrieval of electrocardiosignal feature:
1. intercepting the heart to clap:
90 sampled points are taken before R wave position, after take 165 sampled points to carry out the interception of heart beat of data, selection target
The heart, which is clapped, is used as matching template.
The selection target heart, which is clapped, is used as matching template, and the suitable retrieval character of reselection calculates remaining heart beat of data and mesh
Mark the feature vector similarity of data.
Target data a and data b to be retrieved1,b2,...bmAmplitude Characteristics vector is itself；Target data and to be checked
The morphological feature vector of rope data is the variation tendency that the first derivative values using electrocardiosignal at each point represent this point, is constituted
The morphological feature vector of data.
The morphological feature vector calculation expression of target data and data to be retrieved:
2. experimental data select MIT-BIH arrhythmia cordis database in No. 100, No. 102, No. 105, No. 106, No. 107,
No. 109, No. 116, No. 119, No. 124, No. 209, No. 212, No. 214, No. 215, No. 220, No. 221, No. 232 and No. 234 17 groups
Data.
Take respectively Euclidean distance, TBD, tradition DTW and set forth herein algorithm carry out amplitude and form retrieval, obtain
Retrieve positive inspection rate and susceptibility.
In conjunction with Fig. 4,5, implementation process of the invention is as follows:
A it) pre-processes:
B suitable retrieval character) is selected, the Similarity measures of target heart beat of data and heart beat of data to be retrieved are carried out.
1. the retrieval of random length electrocardiosignal does not have to the interception for carrying out heart bat, length can be selected arbitrarily, in data acquisition
When the divisions of data to be retrieved is carried out according to the length of target data, select step-length to be examined for 20 sampled points by test
Rope.
2. the ecg signal data that input is come in is intercepted further according to the length l of target data a to obtain number to be retrieved
According to b1,b2,...bm, target data is retrieved by the similarity of calculating data to be retrieved and target data.Still to the heart
Electric signal amplitude Characteristics and morphological feature both wave characters are retrieved, and the overall flow and holocentric of experiment clap retrieval class
Seemingly.
Electrocardiosignal searching algorithm can retrieve target data well, still have after noise is added and calculate compared to general
The stronger stability of method, the method proposed are suitable for the retrieval of electrocardiosignal.
Claims (6)
1. a kind of search method of electrocardiosignal, characterized in that the following steps are included:
A, the feature of target data and data to be retrieved is calculated；
B, the electrocardiosignal similarity measurement of DTW is improved based on TBD；
C, search result is evaluated by the susceptibility and positive inspection rate that calculate retrieval；
D, the amplitude Characteristics of electrocardiogram (ECG) data are retrieved；
E, the morphological feature of electrocardiogram (ECG) data is retrieved.
2. the search method of electrocardiosignal according to claim 1, characterized in that the detailed process of step a are as follows:
A-1, determine that length is the target data a=[a of l1, a2... al], wherein the amplitude Characteristics vector of a is itself；
A-2, data b to be retrieved is intercepted on electrocardiosignal X according to the length l of target data a1, b2... bm, data to be retrieved
It selects step-length for k when interception, and calculates the expression formula of data to be retrieved are as follows:Number to be retrieved
According to b1, b2... bmAmplitude Characteristics vector be itself；
A-3, target data morphological feature vector expression formula beK is positive integer, the form of data to be retrieved
Feature vector expression formula isK is positive integer.
3. the search method of electrocardiosignal according to claim 2, characterized in that the detailed process of step b are as follows:
B-1, the calculating using TBD to the click-through row distance in two sequences: selection target data Q=(g1, g2... qm), meter
It counts according to C=(c1, c2... cnThe distance between) and Q each point, TBD is defined asThen Q and C are brought intoIn, obtain m*n apart from square
Battle array D；
B-2, optimal path from S point to E point is looked in distance matrix network, the cumulative distance r of every bit in Distance matrix D
(i, j) is itself and the sum of the shortest distance for reaching this point, expression formula are as follows:
R (i, j)=dTBD(qi, cj)+min (r (i-1, j-1), r (i-1, j), r (i, j-1))；
B-3, the shortest distance between the data and target data to be retrieved of selection is calculated come table using the method that TBD improves DTW
The similarity between two data is levied, innovatory algorithm similarity definition is
4. the search method of electrocardiosignal according to claim 3, characterized in that the detailed process of step c are as follows: calculate inspection
The susceptibility of rope and positive inspection rate:
Susceptibility calculation formula are as follows:
Positive inspection rate calculation formula are as follows:
Wherein TP is true positives number of samples, and FN is false negative number of samples, and FP is false positive number of samples.
5. the search method of electrocardiosignal according to claim 4, characterized in that in step d: to the amplitude of electrocardiogram (ECG) data
It includes that holocentric claps the retrieval of electrocardiosignal amplitude Characteristics and the retrieval of random length electrocardiosignal amplitude Characteristics that feature, which carries out retrieval,.
6. the search method of electrocardiosignal according to claim 4, characterized in that in step e: to the form of electrocardiogram (ECG) data
It includes that holocentric claps the retrieval of electrocardiosignal morphological feature and the retrieval of random length electrocardiosignal morphological feature that feature, which carries out retrieval,.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910611770.2A CN110169767B (en) | 2019-07-08 | 2019-07-08 | Retrieval method of electrocardiosignals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910611770.2A CN110169767B (en) | 2019-07-08 | 2019-07-08 | Retrieval method of electrocardiosignals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110169767A true CN110169767A (en) | 2019-08-27 |
| CN110169767B CN110169767B (en) | 2021-09-21 |
Family
ID=67699934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910611770.2A Active CN110169767B (en) | 2019-07-08 | 2019-07-08 | Retrieval method of electrocardiosignals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110169767B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111685759A (en) * | 2020-05-12 | 2020-09-22 | 河北大学 | P, T characteristic wave detection method of electrocardiosignals |
| CN115177267A (en) * | 2022-09-13 | 2022-10-14 | 合肥心之声健康科技有限公司 | Heart beat artifact identification method and system |
| CN116028914A (en) * | 2023-03-27 | 2023-04-28 | 深圳市魔样科技有限公司 | Intelligent finger ring identity authentication method and system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5715829A (en) * | 1995-11-29 | 1998-02-10 | Hewlett-Packard Company | Method and apparatus for detecting heartbeats in an ECG waveform using an activity function and on-time search |
| CN1242693A (en) * | 1997-08-26 | 2000-01-26 | 精工爱普生株式会社 | Measuring, sensing and diagnosing apparatus and method relating to wave pulse, cardiac function, and motion intensity |
| US20070276270A1 (en) * | 2006-05-24 | 2007-11-29 | Bao Tran | Mesh network stroke monitoring appliance |
| CN103156599A (en) * | 2013-04-03 | 2013-06-19 | 河北大学 | Detection method of electrocardiosignal R characteristic waves |
| CN103345600A (en) * | 2013-06-24 | 2013-10-09 | 中国科学院深圳先进技术研究院 | Electrocardiosignal data processing method |
| CN104523266A (en) * | 2015-01-07 | 2015-04-22 | 河北大学 | Automatic classification method for electrocardiogram signals |
| CN106203324A (en) * | 2016-07-07 | 2016-12-07 | 中国矿业大学(北京) | The quick personal identification method of electrocardiosignal based on random tree |
| US20160361021A1 (en) * | 2015-06-09 | 2016-12-15 | University Of Connecticut | Method and apparatus for removing motion artifacts from biomedical signals |
| CN106889984A (en) * | 2017-01-22 | 2017-06-27 | 河北大学 | A kind of automatic noise-reduction method of electrocardiosignal |
| CN107390194A (en) * | 2017-07-20 | 2017-11-24 | 中国人民解放军国防科学技术大学 | A kind of radar target detection method based on the graceful divergence of full Donald Bragg |
| CN108883279A (en) * | 2016-04-06 | 2018-11-23 | 心脏起搏器股份公司 | The confidence level of arrhythmia detection |
| CN108926344A (en) * | 2018-07-26 | 2018-12-04 | 上海移视网络科技有限公司 | A kind of acute myocardial infarction AMI positioning automatic discrimination system based on CNN neural network |
-
2019
- 2019-07-08 CN CN201910611770.2A patent/CN110169767B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5715829A (en) * | 1995-11-29 | 1998-02-10 | Hewlett-Packard Company | Method and apparatus for detecting heartbeats in an ECG waveform using an activity function and on-time search |
| CN1242693A (en) * | 1997-08-26 | 2000-01-26 | 精工爱普生株式会社 | Measuring, sensing and diagnosing apparatus and method relating to wave pulse, cardiac function, and motion intensity |
| US20070276270A1 (en) * | 2006-05-24 | 2007-11-29 | Bao Tran | Mesh network stroke monitoring appliance |
| CN103156599A (en) * | 2013-04-03 | 2013-06-19 | 河北大学 | Detection method of electrocardiosignal R characteristic waves |
| CN103345600A (en) * | 2013-06-24 | 2013-10-09 | 中国科学院深圳先进技术研究院 | Electrocardiosignal data processing method |
| CN104523266A (en) * | 2015-01-07 | 2015-04-22 | 河北大学 | Automatic classification method for electrocardiogram signals |
| US20160361021A1 (en) * | 2015-06-09 | 2016-12-15 | University Of Connecticut | Method and apparatus for removing motion artifacts from biomedical signals |
| CN108883279A (en) * | 2016-04-06 | 2018-11-23 | 心脏起搏器股份公司 | The confidence level of arrhythmia detection |
| CN106203324A (en) * | 2016-07-07 | 2016-12-07 | 中国矿业大学(北京) | The quick personal identification method of electrocardiosignal based on random tree |
| CN106889984A (en) * | 2017-01-22 | 2017-06-27 | 河北大学 | A kind of automatic noise-reduction method of electrocardiosignal |
| CN107390194A (en) * | 2017-07-20 | 2017-11-24 | 中国人民解放军国防科学技术大学 | A kind of radar target detection method based on the graceful divergence of full Donald Bragg |
| CN108926344A (en) * | 2018-07-26 | 2018-12-04 | 上海移视网络科技有限公司 | A kind of acute myocardial infarction AMI positioning automatic discrimination system based on CNN neural network |
Non-Patent Citations (3)
| Title |
|---|
| LIU, MEIZHU: "Total Bregman Divergence and its Applications to Shape Retrieval", 《TOTAL BREGMAN DIVERGENCE AND ITS APPLICATIONS TO SHAPE RETRIEVAL》 * |
| WARD, C.R.: "Dynamic time warp distances as feedback for EEG feature density", 《2015 IEEE SIGNAL PROCESSING IN MEDICINE AND BIOLOGY SYMPOSIUM (SPMB)》 * |
| 杨立才: "基于PLR-DTW的ECG身份识别方法", 《生物医学工程学杂志》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111685759A (en) * | 2020-05-12 | 2020-09-22 | 河北大学 | P, T characteristic wave detection method of electrocardiosignals |
| CN115177267A (en) * | 2022-09-13 | 2022-10-14 | 合肥心之声健康科技有限公司 | Heart beat artifact identification method and system |
| CN116028914A (en) * | 2023-03-27 | 2023-04-28 | 深圳市魔样科技有限公司 | Intelligent finger ring identity authentication method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110169767B (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110840402B (en) | Atrial fibrillation signal identification method and system based on machine learning | |
| CN104523266B (en) | A kind of electrocardiosignal automatic classification method | |
| CN105411565B (en) | Heart rate variability tagsort method based on broad sense multi-scale wavelet entropy | |
| Álvarez et al. | A comparison of three QRS detection algorithms over a public database | |
| CN110169767A (en) | A kind of search method of electrocardiosignal | |
| WO2019161611A1 (en) | Ecg information processing method and ecg workstation | |
| CN105550659A (en) | Real-time electrocardiogramclassification method based on random projection | |
| Kaya et al. | Feature selection using genetic algorithms for premature ventricular contraction classification | |
| CN109875548B (en) | Electrocardiogram characteristic waveform clustering method based on multi-lead comprehensive analysis | |
| CN110313894A (en) | Arrhythmia cordis sorting algorithm based on convolutional neural networks | |
| CN112257518A (en) | ECG identity recognition method based on WT and WOA-PNN algorithm | |
| CN112932498A (en) | T wave morphology classification system with strong generalization capability based on deep learning | |
| CN112107310A (en) | ECG identity recognition method based on IWT and AGA-BP models | |
| Bruun et al. | Automatic atrial fibrillation detection: A novel approach using discrete wavelet transform and heart rate variability | |
| CN109907751B (en) | Laboratory chest pain data inspection auxiliary identification method based on artificial intelligence supervised learning | |
| Lahiri et al. | Analysis of ECG signal by chaos principle to help automatic diagnosis of myocardial infarction | |
| CN114469041A (en) | Heart rate change data characteristic analysis method in exercise process | |
| Li et al. | A novel abnormal ECG beats detection method | |
| CN116089862B (en) | ECG arrhythmia classification method based on correction mechanism and self-adjusting ant colony algorithm | |
| CN113069124A (en) | Electrocardio monitoring method based on CNN-ET model | |
| CN115486849A (en) | Electrocardiosignal quality evaluation method, device and equipment | |
| Emrich et al. | Accelerated sample-accurate r-peak detectors based on visibility graphs | |
| Wang et al. | MS-MLP: Multi-scale sampling MLP for ECG classification | |
| Deng et al. | Atrial fibrillation classification using convolutional neural networks and time domain features of ECG sequence | |
| CN114027847B (en) | Electrocardiosignal analysis method based on time-frequency analysis |
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 |