CN110037681B - Method and device for recognizing heart rhythm type based on improved self-encoder network - Google Patents
Method and device for recognizing heart rhythm type based on improved self-encoder network Download PDFInfo
- Publication number
- CN110037681B CN110037681B CN201910199065.6A CN201910199065A CN110037681B CN 110037681 B CN110037681 B CN 110037681B CN 201910199065 A CN201910199065 A CN 201910199065A CN 110037681 B CN110037681 B CN 110037681B
- Authority
- CN
- China
- Prior art keywords
- electrocardiosignals
- neural network
- encoder
- self
- matrix
- 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.)
- Active
Links
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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Cardiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a method and a device for recognizing a heart rhythm type based on an improved self-encoder network, a computer device and a storage medium, wherein the method comprises the following steps: acquiring an electrocardiosignal to be identified; preprocessing the electrocardiosignals to obtain electrocardiosignals meeting the identification requirements; inputting the preprocessed electrocardiosignals into a pre-trained neural network for recognition, and outputting the heart rhythm type corresponding to the electrocardiosignals, wherein the neural network adopts a self-encoder of a structure-invariant weight matrix during translation. The invention uses the self-encoder which is not changed in translation (namely, the weight matrix with the unchanged structure in translation) to quickly determine the recording starting point, and can ensure that higher accuracy can be obtained under the condition of using less electrocardiosignal training data compared with the existing random matrix.
Description
Technical Field
The invention relates to the technical field of deep learning, in particular to a method and a device for recognizing a heart rhythm type based on an improved self-encoder network, computer equipment and a storage medium.
Background
Arrhythmia refers to irregular rhythms caused by disturbance in the activation or conduction of the heart, which may cause the whole or part of the heart to move too fast or too slow. Arrhythmia is generally classified clinically according to electrophysiology, and because the heart structure is complex, the types of arrhythmia are also many, which causes great obstacle to intelligent diagnosis of electrocardiosignals by using a computer.
In recent years, deep learning obtains unusual effect in a plurality of fields, and a new idea is provided for intelligent classification of arrhythmia. However, since the electrocardiographic signals vary from person to person and the recording start point of the electrocardiographic signals is not constant as time-series signals, a waveform characteristic containing a large amount of information may occur at different positions. Therefore, when diagnosing arrhythmia using deep learning, a large amount of clinical electrocardiographic signals are required as training data, and it takes a long time.
Disclosure of Invention
The invention aims to solve the problems that a large amount of clinical electrocardiosignals are needed as training data and the time consumption is long due to the fact that the recording starting point of the electrocardiosignals is not constant in the prior art, and provides a method, a device, computer equipment and a storage medium for recognizing the heart rhythm type based on an improved self-encoder network.
In one aspect of the invention, a method for identifying a heart rhythm type based on an improved self-encoder network is provided, which comprises the following steps: acquiring an electrocardiosignal to be identified; preprocessing the electrocardiosignals to obtain electrocardiosignals meeting the identification requirements; inputting the preprocessed electrocardiosignals into a pre-trained neural network for recognition, and outputting the heart rhythm type corresponding to the electrocardiosignals, wherein the neural network adopts a self-encoder of a structure-invariant weight matrix during translation.
Optionally, the neural network comprises 1 input layer, a plurality of the self-encoder layers and 1 classifier layer.
Optionally, the weight matrix is:
wherein, W1，W2，...Wi，...WmIs a matrix with a translation time invariant structure, m is a translation time invariant structure matrix WiThe number of (i ═ 1,2,. m), 0 is a matrix of 0.
Optionally, the formula of the coefficient matrix is:
wherein, a0，a1，...，aN-1Are weight coefficients.
Optionally, the preprocessing the cardiac signal includes:
and filtering the electrocardiosignal by adopting a filter with a preset cut-off frequency.
Optionally, the preprocessing the cardiac signal includes: judging whether the sampling frequency of the electrocardiosignals is a preset frequency or not; and when the sampling frequency is not the preset frequency, resampling the electrocardiosignals into the electrocardiosignals with the preset frequency by adopting an interpolation method.
Optionally, before inputting the preprocessed electrocardiographic signal to a pre-trained neural network for recognition, the method further includes: obtaining a training sample of the electrocardiosignal; inputting the training sample into a pre-established initial neural network for training to obtain a trained neural network, wherein the initial neural network adopts a self-encoder model of a weight matrix with an unchanged structure during translation, and each coefficient in the weight matrix is obtained by training.
In another aspect of the embodiments of the present invention, there is also provided an apparatus for identifying a heart rhythm type based on an improved self-encoder network, including: the acquisition module is used for acquiring the electrocardiosignals to be identified; the preprocessing module is used for preprocessing the electrocardiosignals to obtain the electrocardiosignals meeting the identification requirements; and the recognition module is used for inputting the preprocessed electrocardiosignals into a pre-trained neural network for recognition and outputting the heart rhythm type corresponding to the electrocardiosignals, wherein the neural network adopts a self-encoder of a translation time structure invariant weight matrix.
In another aspect of the embodiments of the present invention, there is also provided a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method when executing the computer program.
In another aspect of the embodiments of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored, which when executed by a processor implements the steps of the above-mentioned method.
In the embodiment of the invention, a pre-trained neural network is adopted to identify the electrocardiosignals so as to identify the heart rhythm type corresponding to the electrocardiosignals and determine whether the electrocardiosignals are arrhythmia or not. Specifically, the neural network is trained according to the heart rhythm type in advance, and because the recording starting point of the electrocardiosignal is not constant, the embodiment uses the invariant self-encoder during translation to quickly determine the recording starting point, so that higher accuracy can be obtained under the condition of using less electrocardiosignal training data compared with the existing random matrix.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for identifying a heart rhythm type based on an improved self-encoder network in an embodiment of the present invention;
FIG. 2 is a diagram of a message queue according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a neural network according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an apparatus for identifying a heart rhythm type based on an improved self-encoder network according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. 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.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Before the embodiments of the present invention are described, the relevant contents of the self-encoder will be described.
Specifically, an Auto Encoder (AE) is a 3-layer neural network, as shown in fig. 1.
The essence of the auto-encoder is an unsupervised learning algorithm, using a back-propagation algorithm to train the network so that the output is equal to the input-i.e., first expressing X ═ X1,x2,L,xnEncoding as a new expression Y ═ Y1,y2,L,ynThen decode Y back to
Where L denotes an omission of an intermediate term, e.g., X ═ { X1,x2,L,xnMay be expressed as X ═ X1,x2…xnThe same applies below and will not be described again. Expressed by the formula:
wherein, b1、b2For biasing, W, φ are weight matrices, f (-) and g (-) are excitation functions. In the prior art, a weight matrix W in a traditional self-encoder is a random matrix, and all weight coefficients need to be learned during training, so that the calculation amount is large and the structure is not available.
The embodiment of the invention provides a method for identifying a heart rhythm type based on an improved self-encoder network, as shown in fig. 2, the method comprises the following steps:
step S201, acquiring an electrocardiosignal to be identified. The electrocardiosignal is a signal acquired by acquisition equipment.
Step S202, preprocessing the electrocardiosignals to obtain the electrocardiosignals meeting the identification requirements. Because the electrocardiosignals acquired by different acquisition devices have differences, before identification, the electrocardiosignals need to be processed into signals with unified standards so as to meet the identification requirements. The preprocessing can be filtering, resampling and other processing modes.
As an optional implementation manner, in an embodiment of the present invention, the preprocessing the cardiac signal includes: and filtering the electrocardiosignal by adopting a filter with a preset cut-off frequency. For example, the cardiac electrical signal to be identified is filtered by a fir filter with a cut-off frequency of [0.1Hz,100Hz ], so as to reduce the influence of noise on the identification result and improve the identification accuracy.
As another optional implementation manner, the preprocessing the electrocardiographic signal according to the embodiment of the present invention may further include: judging whether the sampling frequency of the electrocardiosignals is a preset frequency or not; and when the sampling frequency is not the preset frequency, resampling the electrocardiosignals into the electrocardiosignals with the preset frequency by adopting an interpolation method. For example, if the sampling frequency of the cardiac signal is not 500Hz, the signal is resampled to 500Hz by nearest neighbor interpolation.
Step S203, inputting the preprocessed electrocardiosignals into a pre-trained neural network for recognition, and outputting the heart rhythm type corresponding to the electrocardiosignals, wherein the neural network adopts a self-encoder of a translation time structure invariant weight matrix.
In the embodiment of the invention, a pre-trained neural network is adopted to identify the electrocardiosignals so as to identify the heart rhythm type corresponding to the electrocardiosignals and determine whether the electrocardiosignals are arrhythmia or not. Specifically, the neural network is trained in advance according to the type of the cardiac rhythm (such as abnormal or normal, wherein the abnormal rhythm can be classified into a plurality of categories), and since the recording starting point of the electrocardiosignal is not constant, the embodiment uses the translation-time invariant self-encoder (that is, the translation-time invariant weight matrix is used) to quickly determine the recording starting point, so that a higher accuracy can be ensured under the condition of using less electrocardiosignal training data compared with the existing random matrix.
Optionally, the neural network according to an embodiment of the present invention includes 1 input layer, a plurality of the self-encoder layers, and 1 classifier layer, and the structure of the neural network is shown in fig. 3.
The self-encoder layer adopts the self-encoder of the embodiment of the invention, and the classifier layer adopts the softmax classifier. In one specific example, the input layer may employ 5000 neurons, the number of self-encoder layers is 10, and the number of neurons of the 10 translation-time invariant self-encoder layers is 4500, 4000, 3500, 3000, 2500, 2000, 1500, 1000, 500, and 250, respectively. The self-coding layer excitation functions all adopt sigmoid functions, and the number of neurons in the output layer is consistent with the number of types of arrhythmia to be classified.
Optionally, in the identification process, a Dropout regularization method is used for regularization, and a regularization parameter is set to 0.7. All variable parameters in the network are obtained by training, 5 ten thousand arrhythmia electrocardiosignals with labels and uniform quantity can be adopted for training during training, and any training algorithm can be adopted.
As an optional implementation manner of the embodiment of the present invention, the weight matrix in the embodiment of the present invention is:
wherein, W1，W2，...Wi，...WmIs a matrix with a translation time invariant structure, m is a translation time invariant structure matrix WiThe number of (i ═ 1,2,. m), 0 is a matrix of 0.
Further optionally, the formula of the coefficient matrix is:
wherein, a0，a1，...，aN-1Are weight coefficients. The weight coefficients are obtained by training.
As an optional implementation manner, in an embodiment of the present invention, before inputting the preprocessed electrocardiographic signal to a pre-trained neural network for recognition, the method further includes: obtaining a training sample of the electrocardiosignal; inputting the training sample into a pre-established initial neural network for training to obtain a trained neural network, wherein the initial neural network adopts a self-encoder model of a weight matrix with an unchanged structure during translation, and each coefficient in the weight matrix is obtained by training.
In the embodiment of the invention, the initial neural network has the same structure as the pre-trained neural network, and the difference is only in variable parameters (including weight coefficients and the like), each variable parameter in the initial neural network is an initially set parameter, and after model training, a final parameter is obtained and used as a parameter of the final neural network. Therefore, the self-encoder structure adopted by the initial neural network is the same as that of the final neural network, which may be referred to the above description specifically and will not be described herein again.
The embodiment of the present invention also provides an apparatus for identifying a heart rhythm type based on an improved self-encoder network, which may be used to perform the method according to the embodiment of the present invention, as shown in fig. 4, and the apparatus includes:
the obtaining module 401 is configured to obtain an electrocardiograph signal to be identified.
The preprocessing module 402 is configured to preprocess the electrocardiographic signal to obtain an electrocardiographic signal meeting an identification requirement.
The identification module 403 is configured to input the preprocessed electrocardiographic signals into a pre-trained neural network for identification, and output a heart rhythm type corresponding to the electrocardiographic signals, where the neural network adopts a self-encoder with a structure invariant weight matrix during translation.
Optionally, the neural network comprises 1 input layer, a plurality of the self-encoder layers and 1 classifier layer.
Optionally, the weight matrix is:
wherein, W1，W2，...Wi，...WmIs a matrix with a structure which is invariant when translated, m is translationTime invariant structure matrix WiThe number of (i ═ 1,2,. m), 0 is a matrix of 0.
Optionally, the formula of the coefficient matrix is:
wherein, a0，a1，...，aN-1Are weight coefficients.
Optionally, the preprocessing module comprises: and the filtering unit is used for filtering the electrocardiosignal by adopting a filter with preset cut-off frequency.
Optionally, the preprocessing module comprises: the judging unit is used for judging whether the sampling frequency of the electrocardiosignals is a preset frequency or not; and when the sampling frequency is not the preset frequency, resampling the electrocardiosignals into the electrocardiosignals with the preset frequency by adopting an interpolation method.
Optionally, the apparatus further comprises: the sample acquisition module is used for acquiring a training sample of the electrocardiosignal; and the training module is used for inputting the training samples into a pre-established initial neural network for training to obtain a trained neural network, wherein the initial neural network adopts a self-encoder model of a weight matrix with an unchanged structure during translation, and each coefficient in the weight matrix is obtained by training.
For specific description, reference is made to the above method embodiments, which are not described herein again.
The present embodiment also provides a computer device, such as a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including an independent server or a server cluster composed of multiple servers) capable of executing programs. The computer device 20 of the present embodiment includes at least, but is not limited to: a memory 21, a processor 22, which may be communicatively coupled to each other via a system bus, as shown in FIG. 5. It is noted that fig. 5 only shows a computer device 20 with components 21-22, but it is to be understood that not all shown components are required to be implemented, and that more or fewer components may be implemented instead.
In the present embodiment, the memory 21 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 20, such as a hard disk or a memory of the computer device 20. In other embodiments, the memory 21 may also be an external storage device of the computer device 20, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device 20. Of course, the memory 21 may also include both internal and external storage devices of the computer device 20. In this embodiment, the memory 21 is generally used for storing an operating system and various types of application software installed in the computer device 20, such as program codes of the apparatus for recognizing a heart rhythm based on a cardiac electrical signal according to the embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 20. In this embodiment, the processor 22 is configured to execute the program code stored in the memory 21 or process data, for example, execute a device for identifying a heart rhythm based on an ecg signal, so as to implement the method for identifying a heart rhythm type based on the improved self-encoder network of the embodiment.
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium of the embodiment is used for storing a device for identifying a heart rhythm based on electrocardiosignals, and when being executed by a processor, the device realizes the method for identifying the type of the heart rhythm based on the improved self-encoder network of the embodiment.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications of this invention are intended to be covered by the present application.
Claims (6)
1. A method for recognizing the type of heart rhythm based on improved self-encoder network,
the method comprises the following steps:
acquiring an electrocardiosignal to be identified;
preprocessing the electrocardiosignals to obtain electrocardiosignals meeting the identification requirements;
inputting the preprocessed electrocardiosignals into a pre-trained neural network for recognition, and outputting the heart rhythm type corresponding to the electrocardiosignals, wherein the neural network comprises 1 input layer, a plurality of self-encoder layers and 1 classifier layer, and the neural network adopts a self-encoder with a structure invariant weight matrix during translation;
the weight matrix is:
wherein, W1，W2，…，Wi，…，WmIs a matrix with a translation time invariant structure, m is a translation time invariant structure matrix WiThe number of (i ═ 1, 2.., m), 0 is a matrix of 0;
the formula of the coefficient matrix is:
wherein, a0，a1，…，aN-1Are weight coefficients.
2. The method of claim 1, wherein preprocessing the cardiac electrical signal comprises:
and filtering the electrocardiosignal by adopting a filter with a preset cut-off frequency.
3. The method of claim 1, wherein preprocessing the cardiac electrical signal comprises:
judging whether the sampling frequency of the electrocardiosignals is a preset frequency or not;
when the sampling frequency is not the preset frequency, the electrocardiosignal is repeated by adopting an interpolation method
And sampling the electrocardiosignals with the preset frequency.
4. The method of claim 1, wherein the preprocessed electrocardiosignals are processed
Before inputting the signal into the pre-trained neural network for recognition, the method further comprises the following steps:
obtaining a training sample of the electrocardiosignal;
inputting the training sample into a pre-established initial neural network for training to obtain a trained neural network, wherein the initial neural network adopts a self-encoder model of a weight matrix with an unchanged structure during translation, and each coefficient in the weight matrix is obtained by training.
5. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1 to 4 when executing the computer program.
6. A computer-readable storage medium having stored thereon a computer program, characterized in that:
the computer program when executed by a processor implements the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910199065.6A CN110037681B (en) | 2019-03-15 | 2019-03-15 | Method and device for recognizing heart rhythm type based on improved self-encoder network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910199065.6A CN110037681B (en) | 2019-03-15 | 2019-03-15 | Method and device for recognizing heart rhythm type based on improved self-encoder network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110037681A CN110037681A (en) | 2019-07-23 |
| CN110037681B true CN110037681B (en) | 2021-07-09 |
Family
ID=67273777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910199065.6A Active CN110037681B (en) | 2019-03-15 | 2019-03-15 | Method and device for recognizing heart rhythm type based on improved self-encoder network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110037681B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112826479A (en) * | 2019-11-22 | 2021-05-25 | 华为技术有限公司 | Heart state evaluation method and device, terminal equipment and storage medium |
| CN111084621B (en) * | 2019-12-30 | 2022-09-06 | 上海数创医疗科技有限公司 | QRS wave group form identification method and device based on depth self-encoder |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106725428A (en) * | 2016-12-19 | 2017-05-31 | 中国科学院深圳先进技术研究院 | A kind of electrocardiosignal sorting technique and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8233972B2 (en) * | 2010-02-12 | 2012-07-31 | Siemens Medical Solutions Usa, Inc. | System for cardiac arrhythmia detection and characterization |
| CN104398252A (en) * | 2014-11-05 | 2015-03-11 | 深圳先进技术研究院 | Electrocardiogram signal processing method and device |
| US10426364B2 (en) * | 2015-10-27 | 2019-10-01 | Cardiologs Technologies Sas | Automatic method to delineate or categorize an electrocardiogram |
| CN107811626A (en) * | 2017-09-10 | 2018-03-20 | 天津大学 | A kind of arrhythmia classification method based on one-dimensional convolutional neural networks and S-transformation |
| CN108594660B (en) * | 2018-05-07 | 2021-04-30 | 华侨大学 | Working modal parameter identification method and system of time invariant structure |
-
2019
- 2019-03-15 CN CN201910199065.6A patent/CN110037681B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106725428A (en) * | 2016-12-19 | 2017-05-31 | 中国科学院深圳先进技术研究院 | A kind of electrocardiosignal sorting technique and device |
Non-Patent Citations (2)
| Title |
|---|
| Deep Gaussian Mixture-Hidden Markov Model for Classification of EEG Signals;Min Wang 等;《IEEE Transactions On Emerging Topics In Computational Intelligence》;20180831;第2卷(第3期);278-287 * |
| 基于深度神经网络的房颤检测研究与实现;袁婵;《武汉理工大学硕士学位论文》;20170301;第18页第1段至第27页第3段，第41页第1段至第50页第4段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110037681A (en) | 2019-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230131876A1 (en) | Systems and methods of identity analysis of electrocardiograms | |
| CN111772619B (en) | Heart beat identification method based on deep learning, terminal equipment and storage medium | |
| CN110037681B (en) | Method and device for recognizing heart rhythm type based on improved self-encoder network | |
| CN110547792A (en) | atrial fibrillation detection method and device, computer equipment and storage medium | |
| CN114332500B (en) | Image processing model training method, device, computer equipment and storage medium | |
| KR20220053662A (en) | Neural network to identify radio technologies | |
| KR20220033007A (en) | Real-time facial landmark detection | |
| CN108281184A (en) | Myocardial ischemia based on machine learning examines method, storage medium and electronic equipment in advance | |
| CN111291727A (en) | Method and device for detecting signal quality by photoplethysmography | |
| Al Rahhal et al. | Automatic premature ventricular contractions detection for multi-lead electrocardiogram signal | |
| CN114519370A (en) | Left ventricular hypertrophy detection method and system based on deep learning early-arrest mechanism | |
| CN114692809A (en) | Data processing method and device based on neural cluster, storage medium and processor | |
| CN110008881B (en) | Method and device for identifying cow behaviors of multiple moving targets | |
| CN117113269A (en) | Motor imagery identification method and system based on multi-scale convolution and transformation | |
| CN111968087A (en) | Plant disease area detection method | |
| CN113229798B (en) | Model migration training method, device, computer equipment and readable storage medium | |
| US20230058548A1 (en) | System and method for predicting blood-glucose concentration | |
| CN116522070A (en) | Non-supervision intelligent fault diagnosis method and system for mechanical parts | |
| CN116090618A (en) | Operation situation sensing method and device for power communication network | |
| CN114386457A (en) | Electrocardiosignal abnormality detection method, system, device and storage medium | |
| CN112001481B (en) | P-wave identification method based on countermeasure learning, terminal equipment and storage medium | |
| CN114626408A (en) | Electroencephalogram signal classification method and device, electronic equipment, medium and product | |
| KR20230096392A (en) | Method and apparatus for classifying heartbeat, and method for learning heartbeat classification model | |
| CN113974649A (en) | Method, apparatus and medium for classification of heart beat signals and training of deep learning models for classification of heart beat signals | |
| CN112214750B (en) | Character verification code recognition method, system, electronic equipment and storage medium |
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 |