CN112515651A - BCG-based arrhythmia identification method and device - Google Patents
BCG-based arrhythmia identification method and device Download PDFInfo
- Publication number
- CN112515651A CN112515651A CN202011377594.XA CN202011377594A CN112515651A CN 112515651 A CN112515651 A CN 112515651A CN 202011377594 A CN202011377594 A CN 202011377594A CN 112515651 A CN112515651 A CN 112515651A
- Authority
- CN
- China
- Prior art keywords
- bcg
- module
- arrhythmia
- graph
- identification method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 206010003119 arrhythmia Diseases 0.000 title claims abstract description 31
- 230000006793 arrhythmia Effects 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 15
- 239000013307 optical fiber Substances 0.000 claims abstract description 12
- 238000004891 communication Methods 0.000 claims abstract description 10
- 238000010586 diagram Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000006185 dispersion Substances 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 abstract description 7
- 238000013135 deep learning Methods 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 208000000418 Premature Cardiac Complexes Diseases 0.000 description 4
- 206010003658 Atrial Fibrillation Diseases 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000002763 arrhythmic effect Effects 0.000 description 2
- 230000002861 ventricular Effects 0.000 description 2
- 206010047302 ventricular tachycardia Diseases 0.000 description 2
- 206010015856 Extrasystoles Diseases 0.000 description 1
- 208000010496 Heart Arrest Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 206010061592 cardiac fibrillation Diseases 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002600 fibrillogenic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 208000028867 ischemia Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000033764 rhythmic process 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
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Physiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a BCG-based arrhythmia identification method and a device, wherein the identification device comprises a BCG acquisition sensor, a hardware module is integrated at the upper end of the left side of the BCG acquisition sensor and is connected with a power adapter through a connecting port formed on the hardware module, and the hardware module consists of a 4G/WIFI communication module, a local storage module, an optical fiber signal processing module and a laser connecting module; according to the BCG-based arrhythmia identification method and device, a deep learning algorithm in the field of artificial intelligence is combined with non-contact BCG signal acquisition, difficulty and complexity of arrhythmia event monitoring based on electrocardiosignals can be greatly reduced, accuracy of classification of the BCG-based heart rate scattergram is improved by using a traditional calculating method of the heart rate scattergram in electrocardio, and meanwhile, the problems that known characteristics of the BCG signals are less relative to the ECG signals, characteristic extraction is difficult and the like are solved by using the super-strong learning capacity, automatic characteristic extraction, automatic characteristic distribution relation analysis and other advantages of the deep learning algorithm.
Description
Technical Field
The invention relates to the field of arrhythmia identification of BCG, in particular to an arrhythmia identification method and device based on BCG.
Background
Electrocardiographic (ECG) monitoring of cardiac events such as ischemia and arrhythmias is important for detecting the health status of a patient. Arrhythmia events of clinical interest include the onset and termination of atrial fibrillation or fibrillation (atrial fibrillation), ventricular tachycardia (ventricular tachycardia), asystole, and the like.
However, the use of ECG techniques often requires human contact, which is relatively more cumbersome and expensive in maintaining a stable and effective acquisition of the ECG signal. On one hand, more work is brought to doctors and nurses in the clinical use process, and convenient and high-precision electrocardiosignal acquisition is difficult to realize in a home scene; on the other hand, the occurrence of arrhythmia events is generally difficult to capture, and more potential health risks are often discovered only by continuous and stable signal acquisition;
therefore, a BCG-based arrhythmia identification method and device are provided.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a BCG-based arrhythmia identification method and device, wherein the identification device comprises a BCG acquisition sensor, a hardware module is integrated at the upper end of the left side of the BCG acquisition sensor, a power adapter is connected through a connecting port formed in the hardware module, and the hardware module consists of a 4G/WIFI communication module, a local storage module, an optical fiber signal processing module and a laser connecting module.
A BCG-based arrhythmia identification method, the identification method comprising the steps of:
s1: acquiring and filtering vibration signals by adopting a BCG acquisition sensor and a hardware module, and transmitting the filtered BCG signals to a cloud platform;
s2: acquiring sensor signals of 8 hours all night, and processing and obtaining BCG data through filtering and denoising;
s3: extracting a JJ interval (in milliseconds) from the BCG signal;
s4: drawing a heart rate scatter diagram according to the JJ intervals of each time period of the continuous BCG signals;
s5: and establishing a scoring model of the heart rate scatter diagram form according to the classification characteristics shown in the heart rate scatter diagram, performing algorithm convolution neural network classifier training on the image result by taking indexes such as the length of a long axis and a short axis of the graph, the width of the graph, the area of the graph, the dispersion degree and the like as input, and identifying the probability corresponding to the distribution form in the graph 4.
S6: when the image is identified to be not in a racket shape of a distribution stick of an image A, identification and slope calculation of lines B, C and D in a three-distribution graph, a four-distribution graph and a five-distribution graph are calculated by using an algorithm two, a corresponding specific arrhythmia event is identified, and risk value estimation corresponding to the arrhythmia event is output.
Preferably, the denoising process includes the following steps:
removing baseline drift noise by adopting a high-pass filter;
secondly, determining whether the noise is too high based on the standard variance of the PQ section signal and a threshold value method;
and step three, removing noise interference by using a low-pass Butterworth filter when the noise is too high.
Preferably, the method for extracting the JJ interval from the BCG signal includes the steps of:
firstly, finding the position of J wave in each period;
and secondly, calculating the point number between two adjacent J waves, and calculating the interval time of each J wave according to the point number and the sampling frequency.
Preferably, the 4G/WIFI communication module, the local storage module, the optical fiber signal processing module and the laser connection module are all integrated inside the hardware module, the 4G/WIFI communication module is installed on the left side of the local storage module, the laser connection module is installed below the local storage module, and the optical fiber signal processing module is installed on the left side of the laser connection module.
Compared with the prior art, the invention has the following beneficial effects: the arrhythmia identification method and device based on the BCG combine the deep learning algorithm in the field of artificial intelligence with non-contact BCG signal acquisition, can greatly reduce the difficulty and complexity of arrhythmia event monitoring based on electrocardiosignals, improve the accuracy of classification of the BCG-based heart rate scattergram by utilizing the traditional calculating method of the heart rate scattergram in electrocardio, and simultaneously make up the problems of less known characteristics of the BCG signals relative to the ECG signals, difficult characteristic extraction and the like by utilizing the superior learning capability, automatic characteristic extraction, automatic characteristic distribution relation analysis and other advantageous capabilities of the deep learning algorithm.
Drawings
Fig. 1 is a schematic overall structure diagram of a BCG acquisition sensor of the BCG-based arrhythmia identification method and apparatus of the present invention;
FIG. 2 is a schematic diagram of the overall structure of the hardware module of the present invention;
FIG. 3 is a heart rate scatter plot of the present invention;
FIG. 4 is a probability chart of the distribution profile of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-4, the identification device comprises a BCG acquisition sensor, a hardware module is integrated at the upper end of the left side of the BCG acquisition sensor, and is connected with a power adapter through a connector formed on the hardware module, and the hardware module comprises a 4G/WIFI communication module, a local storage module, an optical fiber signal processing module and a laser connection module.
A BCG-based arrhythmia identification method, the identification method comprising the steps of:
s1: acquiring and filtering vibration signals by adopting a BCG acquisition sensor and a hardware module, and transmitting the filtered BCG signals to a cloud platform;
s2: acquiring sensor signals of 8 hours all night, and processing and obtaining BCG data through filtering and denoising;
s3: extracting a JJ interval (in milliseconds) from the BCG signal;
s4: drawing a heart rate scatter diagram according to the JJ intervals of each time period of the continuous BCG signals;
s5: and establishing a scoring model of the heart rate scatter diagram form according to the classification characteristics shown in the heart rate scatter diagram, performing algorithm convolution neural network classifier training on the image result by taking indexes such as the length of a long axis and a short axis of the graph, the width of the graph, the area of the graph, the dispersion degree and the like as input, and identifying the probability corresponding to the distribution form in the graph 4.
S6: when the image is identified to be not in a racket shape of a distribution stick of an image A, identification and slope calculation of lines B, C and D in a three-distribution graph, a four-distribution graph and a five-distribution graph are calculated by using an algorithm two, a corresponding specific arrhythmia event is identified, and risk value estimation corresponding to the arrhythmia event is output.
Preferably, the denoising process includes the following steps:
removing baseline drift noise by adopting a high-pass filter;
secondly, determining whether the noise is too high based on the standard variance of the PQ section signal and a threshold value method;
and step three, removing noise interference by using a low-pass Butterworth filter when the noise is too high.
The method for extracting the JJ interval from the BCG signal comprises the following steps:
firstly, finding the position of J wave in each period;
and secondly, calculating the point number between two adjacent J waves, and calculating the interval time of each J wave according to the point number and the sampling frequency.
The 4G/WIFI communication module, the local storage module, the optical fiber signal processing module and the laser device connecting module are all integrated in the hardware module, the 4G/WIFI communication module is installed on the left side of the local storage module, the laser device connecting module is installed below the local storage module, and the optical fiber signal processing module is installed on the left side of the laser device connecting module.
It is noted that the present invention proposes to detect arrhythmic events by continuous monitoring and identification of bcg (ballistocardiogram) signals. The detected events can be used to provide warnings and reminders to non-users.
The BCG acquisition sensor shown in fig. 1 is adopted to receive and extract BCG signals and characteristics thereof from the BCG acquisition sensor, and the sensor can be a piezoelectric sensor or an optical fiber sensor.
If the optical fiber sensor is adopted, the circuit module shown in fig. 2 is adopted to collect and filter the vibration signals, and the filtered BCG signals are transmitted to the cloud platform.
Based on the BCG signal, the following steps of analysis were performed:
the method comprises the following steps: and acquiring sensor signals of 8 hours all night, and processing and acquiring BCG data through filtering and denoising. The denoising treatment comprises the following steps: 1. removing baseline drift noise by adopting a high-pass filter; 2. confirming whether the noise is too high or not based on the standard deviation of the PQ section signal and a threshold value method; 3. when the noise is too high, a low-pass Butterworth filter is used for removing noise interference.
Step two: the JJ interval (in milliseconds) is extracted from the BCG signal. The specific extraction method comprises the following steps: the method comprises the steps of firstly finding the position of the J wave in each period, then calculating the point number between two adjacent J waves, and calculating the interval time of each J wave according to the point number and the sampling frequency.
Step three: and drawing a heart rate scatter diagram according to the JJ intervals of each time section of the continuous BCG signals. As shown in fig. 3.
Step four: establishing a scoring model of the heart rate scatter diagram form according to classification characteristics shown in the heart rate scatter diagram, performing algorithm convolution neural network classifier training on an image result by taking indexes such as the length of a long axis and a short axis of the graph, the width of the graph, the area of the graph, the dispersion degree and the like as input, and identifying the probability corresponding to the distribution form in the graph 4;
wherein in fig. 4 a is sinus rhythm pattern (one bar-bat-shape), B is supraventricular premature beat (three-distribution), C-F are ventricular premature beats (three-distribution, four-distribution and five-distribution patterns, respectively), G is supraventricular premature beat with differential conduction (four-distribution) H and I is atrial fibrillation with ventricular premature beat (fan-shaped composite pattern);
step five: when identifying the racket shape of the distribution stick of the image other than the A picture, the identification and slope calculation of the B line, the C line and the D line in the three-distribution, four-distribution and five-distribution pictures are calculated by using an algorithm two, and the corresponding specific arrhythmia event is identified. A risk value estimate corresponding to the arrhythmic event is output.
The arrhythmia identification method and device based on the BCG combine the deep learning algorithm in the field of artificial intelligence with non-contact BCG signal acquisition, can greatly reduce the difficulty and complexity of arrhythmia event monitoring based on electrocardiosignals, improve the accuracy of classification of the BCG-based heart rate scattergram by utilizing the traditional calculating method of the heart rate scattergram in electrocardio, and simultaneously make up the problems of less known characteristics of the BCG signals relative to the ECG signals, difficult characteristic extraction and the like by utilizing the superior learning capability, automatic characteristic extraction, automatic characteristic distribution relation analysis and other advantageous capabilities of the deep learning algorithm.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. An arrhythmia recognition device based on BCG, the recognition device comprising a BCG acquisition sensor, characterized in that: the upper end of the left side of the BCG acquisition sensor is integrated with a hardware module, a power adapter is connected through a connector arranged on the hardware module, and the hardware module is composed of a 4G/WIFI communication module, a local storage module, an optical fiber signal processing module and a laser connecting module.
2. The BCG-based arrhythmia identification method as claimed in claim 1, wherein: the identification method comprises the following steps:
s1: acquiring and filtering vibration signals by adopting a BCG acquisition sensor and a hardware module, and transmitting the filtered BCG signals to a cloud platform;
s2: acquiring sensor signals of 8 hours all night, and processing and obtaining BCG data through filtering and denoising;
s3: extracting a JJ interval (in milliseconds) from the BCG signal;
s4: drawing a heart rate scatter diagram according to the JJ intervals of each time period of the continuous BCG signals;
s5: and establishing a scoring model of the heart rate scatter diagram form according to the classification characteristics shown in the heart rate scatter diagram, performing algorithm convolution neural network classifier training on the image result by taking indexes such as the length of a long axis and a short axis of the graph, the width of the graph, the area of the graph, the dispersion degree and the like as input, and identifying the probability corresponding to the distribution form in the graph 4.
S6: when the image is identified to be not in a racket shape of a distribution stick of an image A, identification and slope calculation of lines B, C and D in a three-distribution graph, a four-distribution graph and a five-distribution graph are calculated by using an algorithm two, a corresponding specific arrhythmia event is identified, and risk value estimation corresponding to the arrhythmia event is output.
3. The BCG-based arrhythmia identification method as claimed in claim 1, wherein: the denoising processing comprises the following steps:
removing baseline drift noise by adopting a high-pass filter;
secondly, determining whether the noise is too high based on the standard variance of the PQ section signal and a threshold value method;
and step three, removing noise interference by using a low-pass Butterworth filter when the noise is too high.
4. The BCG-based arrhythmia identification method as claimed in claim 1, wherein: the method for extracting the JJ interval from the BCG signal comprises the following steps:
firstly, finding the position of J wave in each period;
and secondly, calculating the point number between two adjacent J waves, and calculating the interval time of each J wave according to the point number and the sampling frequency.
5. The BCG-based arrhythmia identification device of claim 1, wherein: the 4G/WIFI communication module, the local storage module, the optical fiber signal processing module and the laser device connecting module are all integrated in the hardware module, the 4G/WIFI communication module is installed on the left side of the local storage module, the laser device connecting module is installed below the local storage module, and the optical fiber signal processing module is installed on the left side of the laser device connecting module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011377594.XA CN112515651A (en) | 2020-11-30 | 2020-11-30 | BCG-based arrhythmia identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011377594.XA CN112515651A (en) | 2020-11-30 | 2020-11-30 | BCG-based arrhythmia identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112515651A true CN112515651A (en) | 2021-03-19 |
Family
ID=74995415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011377594.XA Pending CN112515651A (en) | 2020-11-30 | 2020-11-30 | BCG-based arrhythmia identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112515651A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113499059A (en) * | 2021-06-01 | 2021-10-15 | 武汉理工大学 | BCG signal processing system and method based on optical fiber sensing non-contact |
| CN114469133A (en) * | 2021-12-14 | 2022-05-13 | 中国科学院深圳先进技术研究院 | Undisturbed atrial fibrillation monitoring method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102469958A (en) * | 2009-07-31 | 2012-05-23 | 皇家飞利浦电子股份有限公司 | Method and apparatus for the analysis of a ballistocardiogram signal |
| 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 |
| CN109222946A (en) * | 2018-08-28 | 2019-01-18 | 中国科学院电子学研究所 | Physio-parameter detection system and detection method based on optical fiber pad |
| CN111091116A (en) * | 2019-12-31 | 2020-05-01 | 华南师范大学 | Signal processing method and system for judging arrhythmia |
| CN111449622A (en) * | 2020-03-20 | 2020-07-28 | 复旦大学 | Atrial fibrillation recognition system based on BCG detection |
| WO2020155078A1 (en) * | 2019-02-01 | 2020-08-06 | 深圳市大耳马科技有限公司 | Method and device for monitoring arrhythmia event |
-
2020
- 2020-11-30 CN CN202011377594.XA patent/CN112515651A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102469958A (en) * | 2009-07-31 | 2012-05-23 | 皇家飞利浦电子股份有限公司 | Method and apparatus for the analysis of a ballistocardiogram signal |
| 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 |
| CN109222946A (en) * | 2018-08-28 | 2019-01-18 | 中国科学院电子学研究所 | Physio-parameter detection system and detection method based on optical fiber pad |
| WO2020155078A1 (en) * | 2019-02-01 | 2020-08-06 | 深圳市大耳马科技有限公司 | Method and device for monitoring arrhythmia event |
| CN111091116A (en) * | 2019-12-31 | 2020-05-01 | 华南师范大学 | Signal processing method and system for judging arrhythmia |
| CN111449622A (en) * | 2020-03-20 | 2020-07-28 | 复旦大学 | Atrial fibrillation recognition system based on BCG detection |
Non-Patent Citations (1)
| Title |
|---|
| 席乐乐: "基于混沌理论的BCG信号非线性特性分析", 《中国优秀博硕士学位论文全文数据库（硕士）医药卫生科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113499059A (en) * | 2021-06-01 | 2021-10-15 | 武汉理工大学 | BCG signal processing system and method based on optical fiber sensing non-contact |
| CN114469133A (en) * | 2021-12-14 | 2022-05-13 | 中国科学院深圳先进技术研究院 | Undisturbed atrial fibrillation monitoring method |
| CN114469133B (en) * | 2021-12-14 | 2023-10-03 | 中国科学院深圳先进技术研究院 | Undisturbed atrial fibrillation monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106214145B (en) | Electrocardiogram classification method based on deep learning algorithm | |
| US8909332B2 (en) | Method and device for estimating morphological features of heart beats | |
| CN113749664A (en) | Reducing intracardiac electrocardiogram noise using an autoencoder and refining intracardiac and body surface electrocardiograms using a deep learning training loss function | |
| CN111772628B (en) | Electrocardiosignal atrial fibrillation automatic detection system based on deep learning | |
| CN104921722A (en) | Double-lead combined with electrocardiogram QRS wave detection method | |
| KR101308609B1 (en) | R-peak detection method of ECG signal using Adaptive Local Threshold | |
| AU2019313480B2 (en) | Systems and methods for maternal uterine activity detection | |
| CN112515651A (en) | BCG-based arrhythmia identification method and device | |
| EP2654557A1 (en) | Automatic online delineation of a multi-lead electrocardiogram bio signal | |
| CN110353704B (en) | Emotion evaluation method and device based on wearable electrocardiogram monitoring | |
| Malek et al. | Automated detection of premature ventricular contraction in ECG signals using enhanced template matching algorithm | |
| CA3165289A1 (en) | Device and process for ecg measurements | |
| Lai et al. | A real-time QRS complex detection algorithm based on differential threshold method | |
| CN112022143A (en) | Mobile robot monitoring system and method based on vital sign parameter analysis | |
| Lee et al. | ECG measurement system for vehicle implementation and heart disease classification using machine learning | |
| CN109259745A (en) | A kind of wearable cardiovascular and cerebrovascular disease intelligent monitor system and method | |
| Murthy et al. | ECG signal denoising and ischemic event feature extraction using Daubechies wavelets | |
| Khavas et al. | Robust heartbeat detection using multimodal recordings and ECG quality assessment with signal amplitudes dispersion | |
| CN110960207A (en) | Tree model-based atrial fibrillation detection method, device, equipment and storage medium | |
| Islam et al. | A non-invasive technique of early heart diseases prediction from photoplethysmography signal | |
| Ghosal et al. | Ecg beat quality assessment using self organizing map | |
| Liu et al. | Automatic arrhythmia detection based on convolutional neural networks | |
| CN113349753A (en) | Arrhythmia detection method based on portable dynamic electrocardiogram monitor | |
| She et al. | Recognition of Myocardial Ischemia Electrocardiogram Signal Based on Deep Learning | |
| CN114081502B (en) | Non-invasive heart disease diagnosis method and device based on machine learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210319 |