CN114711787A - Neural network-based classification diagnosis method for heart health state of driver - Google Patents
Neural network-based classification diagnosis method for heart health state of driver Download PDFInfo
- Publication number
- CN114711787A CN114711787A CN202210238767.2A CN202210238767A CN114711787A CN 114711787 A CN114711787 A CN 114711787A CN 202210238767 A CN202210238767 A CN 202210238767A CN 114711787 A CN114711787 A CN 114711787A
- Authority
- CN
- China
- Prior art keywords
- neural network
- driver
- heart
- diagnosis
- diagnosing
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 36
- 238000003745 diagnosis Methods 0.000 title claims abstract description 30
- 230000005189 cardiac health Effects 0.000 title claims abstract description 27
- 238000012544 monitoring process Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000013136 deep learning model Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000013135 deep learning Methods 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 12
- 230000009977 dual effect Effects 0.000 claims description 9
- 230000036541 health Effects 0.000 claims description 7
- 206010003658 Atrial Fibrillation Diseases 0.000 claims description 6
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- 239000012634 fragment Substances 0.000 claims description 5
- 230000003862 health status Effects 0.000 claims description 5
- 208000000418 Premature Cardiac Complexes Diseases 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 208000010125 myocardial infarction Diseases 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000033764 rhythmic process Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 230000007774 longterm Effects 0.000 abstract description 2
- 238000012774 diagnostic algorithm Methods 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 5
- 230000005802 health problem Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000718 qrs complex 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]
- A61B5/346—Analysis of electrocardiograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Cardiology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to a neural network-based method for classifying and diagnosing the heart health state of a driver, which comprises the following steps: after the cloud algorithm server obtains the electrocardio monitoring data, firstly, the cloud algorithm server calls a preprocessing algorithm to filter the electrocardio monitoring data so as to improve the quality of the electrocardio monitoring data; then, selecting the electrocardiosignal segment with the maximum signal-to-noise ratio in the electrocardio monitoring data by self by taking the signal-to-noise ratio as a standard; finally, calculating relevant expert characteristics for subsequent deep learning model diagnosis on the preprocessed electrocardiosignal segments by using a statistical learning method and a signal time-frequency domain correlation method; an analysis diagnostic algorithm based on deep learning is invoked to detect the cardiac health level of the driver. The invention provides a set of feasible technical solutions for solving the sudden heart health problem of a driver in the daily driving process and the failure of diagnosis and monitoring of the long-term daily heart health problem.
Description
Technical Field
The invention belongs to the field of health monitoring, and particularly relates to a neural network-based method for classifying and diagnosing the heart health state of a driver.
Background
Traditional heart health monitoring modes, such as twelve-lead electrocardiogram monitoring and the like, cannot effectively monitor the heart health state of a driver in real time and daily. Meanwhile, the acquired electrocardiogram data needs to be diagnosed and analyzed by professional medical staff, so that the heart health detection process needs to be separated from a daily driving scene, and the detection frequency cannot be guaranteed due to actual conditions, and the detection cost is a burden for a driver. Thus, the low frequency and difficult cardiac health detection increases the risk of sudden health problems for the driver, often resulting in an overlooking of the health status of the driver.
The daily health state of the driver is monitored by the classification diagnosis method for the daily heart health state of the driver based on the vehicle-mounted electrocardio monitoring equipment, so that the method is one of the most effective modes for reducing the health risk of the driver, and the continuous detection solution can effectively avoid the sudden health problem in the daily driving process.
Disclosure of Invention
The invention provides a neural network-based classification diagnosis method for the heart health state of a driver, which is used for solving the problem that the electrocardiogram data cannot be classified and diagnosed automatically in real time in the daily driving process of the driver.
In order to solve the above problems, the invention specifically provides the following technical scheme: a method for classifying and diagnosing the health state of the heart of a driver based on a neural network comprises the following steps: after the cloud algorithm server acquires the electrocardio monitoring data,
firstly, the cloud server calls a preprocessing algorithm to filter the electrocardiogram monitoring data so as to improve the quality of the electrocardiogram monitoring data;
then, selecting the electrocardiosignal segment with the maximum signal-to-noise ratio in the electrocardio monitoring data by self by taking the signal-to-noise ratio as a standard;
finally, calculating relevant expert characteristics for subsequent deep learning model diagnosis on the preprocessed electrocardiosignal segments by using a statistical learning method and a signal time-frequency domain correlation method;
after the cloud server completes the preprocessing algorithm, the heart health level of the driver can be detected by calling an analysis and diagnosis algorithm based on deep learning.
Further, the deep learning analysis and diagnosis algorithm in the deep learning model consists of three parts:
the first part is characterized by further feature fusion of the expert features extracted before by a feedforward neural network;
the second part is to carry on the characteristic extraction end to the preprocessed electrocardiosignal by the improved one-dimensional ResNet, so adopt the one-dimensional neural network because the electrocardiosignal is one-dimensional sequence data in essence, adopt the one-dimensional neural network can catch the sequence characteristic in the electrocardiosignal well, this kind of sequence characteristic has very big effects to diagnosing atrial fibrillation and premature beat, design the convolution kernel of different yardstick in every layer of network in the one-dimensional neural network to extract different characteristics in the electrocardiosignal end to end at the same time, embed the jump structure of ResNet in the framework of the one-dimensional neural network, make the one-dimensional neural network can avoid the problem of the gradient attenuation and then promote the diagnostic accuracy of the algorithm integrally;
and the third part integrates the fusion characteristics obtained by the two parts to carry out decision analysis, maps electrocardiosignals with different characteristics to the heart health state of the driver in a probability mode, and provides classification diagnosis results of 'normal', 'vertical branch obstruction', 'sinus rhythm', 'atrial fibrillation' and 'myocardial infarction'.
Further, the data generated in the deep learning model is processed by the following steps: the cloud algorithm server carries two parts of processing algorithms, the preprocessing algorithm firstly carries out filtering cleaning on original electrocardio data so as to improve the quality of electrocardio signals to a great extent, and the signals f (t) are transformed as follows:
in the formula, xi (xi)>0)、
Respectively for mother wavelet
Scaling, translation factor.
Further, the electrocardio segment with the largest signal-to-noise ratio is selected from the electrocardio signals, and the electrocardio segment with the high signal-to-noise ratio is used as the input of the deep learning model for further analysis and diagnosis.
Further, the specific process of analyzing and diagnosing the input electrocardiogram fragments through the deep learning model is as follows:
s31, firstly, the electrocardiogram fragments are input into a convolutional layer for convolution operation to realize the compression and feature extraction of the electrocardiogram data, and the calculation of the convolutional layer is as follows:
therein, Ψj lIs the activation value, Γ, of the jth feature map of the ith layerjIs the number of feature maps of the layer, Ψi l-1Is the jth feature map of the ith layer, Φij lAs a weight matrix, qj lIs a bias term, "# is a convolution operator, and Y (·) is a non-linear activation function.
Further, the feature obtained by convolution layer calculation is compressed by the maximum pooling layer to obtain a feature FMAiming at reducing the parameter quantity of the model needing to be trained and avoiding the occurrence of the over-fitting phenomenon, the calculation process of the maximum pooling layer is as follows:
wherein the content of the first and second substances,
in order to be a function of down-sampling,
is the characteristic value after the maximum pooling operation.
Further, feature FMFurther feature extraction is carried out through a dual residual error module, and the specific process of the dual residual error module is as follows:
characteristic FMFirstly, extracting the characteristics through the residual block, and extracting the characteristics
And FMCarrying out addition calculation on the elements of the corresponding positions of the features to obtain the features
Followed by
Inputting the data into the residual block for further feature extraction to obtain features
And adopting the mode of jump connection to obtain the characteristics
And FMCarrying out addition calculation on the elements of the corresponding positions of the features to obtain the features
Wherein the content of the first and second substances,
and representing the addition calculation of the corresponding position elements of the matrix.
Further, features derived by dual residual modules
Sequentially flowing through the maximum pooling layer and the full-connection layer to obtain a final diagnosis result.
The invention relates to a neural network-based method for classifying and diagnosing the heart health state of a driver, which is particularly suitable for classifying and diagnosing the daily health state of the driver in the driving process. The invention provides a set of feasible technical solutions for solving the sudden heart health problem of a driver in the daily driving process and the failure of diagnosis and monitoring of the long-term daily heart health problem.
Drawings
FIG. 1 is a schematic view of the flow structure of the present invention.
Detailed Description
As shown in fig. 1, a neural network-based method for diagnosing the heart health status of a driver by classification comprises the following steps:
after the cloud algorithm server acquires the electrocardio monitoring data, firstly, the cloud server calls a preprocessing algorithm to filter the electrocardio monitoring data so as to improve the quality of the electrocardio monitoring data to a large extent, then, an electrocardiosignal segment with the largest signal-to-noise ratio in the electrocardio monitoring data is selected by self by taking the signal-to-noise ratio as a standard, and finally, relevant expert features (such as RR intervals of the electrocardiosignals, the width of a QRS complex and the like) are calculated on the preprocessed electrocardiosignal segment by utilizing a statistical learning method and a signal time-frequency domain related method for subsequent deep learning model diagnosis. After the cloud server completes the preprocessing algorithm, the heart health level of the driver can be detected by calling an analysis and diagnosis algorithm based on deep learning.
The deep learning analysis diagnosis algorithm consists of three parts:
the first part is characterized by further feature fusion of the expert features extracted before by a feedforward neural network;
the second part is to carry on the characteristic extraction end to the preprocessed electrocardiosignal by the improved one-dimensional ResNet, so adopt the one-dimensional neural network because the electrocardiosignal is one-dimensional sequence data in essence, adopt the one-dimensional neural network can catch the sequence characteristic in the electrocardiosignal well, this kind of sequence characteristic has very big effects to diagnosing atrial fibrillation and premature beat, design the convolution kernel of different yardstick in every layer of network in the one-dimensional neural network to extract different characteristics in the electrocardiosignal end to end at the same time, embed the jump structure of ResNet in the framework of the one-dimensional neural network, make the one-dimensional neural network can avoid the problem of the gradient attenuation and then promote the diagnostic accuracy of the algorithm integrally;
and the third part integrates the fusion characteristics obtained by the two parts to carry out decision analysis, maps electrocardiosignals with different characteristics to the heart health state of the driver in a probability mode, and provides classification diagnosis results of 'normal', 'vertical branch obstruction', 'sinus rhythm', 'atrial fibrillation' and 'myocardial infarction'.
In particular, the steps of the data processing method provided by the invention are executed.
The method comprises the following steps: the cloud algorithm server carries two parts of processing algorithms, the preprocessing algorithm firstly carries out filtering cleaning on original electrocardio data so as to improve the quality of electrocardio signals to a great extent, and the signals f (t) are transformed as follows:
in the formula, xi (xi)>0)、
Respectively for mother wavelet
Scaling, translation factor.
Step two: and secondly, selecting the electrocardio segment with the largest signal-to-noise ratio from the electrocardio signals, and finally, taking the electrocardio segment with the high signal-to-noise ratio as the input of the deep learning model for further analysis and diagnosis. The deep learning algorithm carried by the cloud server can extract the representation in the original electrocardiosignals end to end, meanwhile, part of expert characteristics are utilized to perform auxiliary diagnosis, finally, analysis and diagnosis are performed according to the characteristics learned by the neural network and the expert characteristics so as to analyze the heart health state of a driver, and the final diagnosis result of the cloud server model is sent to an intelligent wireless communication terminal (APP terminal).
The method for classifying and diagnosing the health state of the daily heart of the driver based on the vehicle-mounted electrocardio monitoring equipment is characterized in that in the step S3, the specific process of analyzing and diagnosing the input electrocardio segments through a deep learning model is as follows:
s31, firstly, the electrocardiogram fragments are input into a convolutional layer for convolution operation to realize the compression and feature extraction of the electrocardiogram data, and the calculation of the convolutional layer is as follows:
therein, Ψj lIs the activation value, Γ, of the jth feature map of the ith layerjIs the number of feature maps of the layer, Ψi l-1Is the jth feature map of the ith layer, Φij lAs a weight matrix, qj lIs a bias term, "# is a convolution operator, and Y (·) is a non-linear activation function.
S32: compressing the feature size of the features obtained by convolution layer calculation through the maximum pooling layer to obtain features FMAiming at reducing the parameter quantity of the model needing to be trained and avoiding the occurrence of the over-fitting phenomenon, the calculation process of the maximum pooling layer is as follows:
wherein the content of the first and second substances,
in order to be a function of down-sampling,
is the characteristic value after the maximum pooling operation;
s33: characteristic FMFurther feature extraction is carried out through a dual residual error module, and the specific process of the dual residual error module is as follows:
s331: characteristic FMFirstly, extracting the characteristics through the residual block, and extracting the characteristics
And FMCarrying out addition calculation on the elements of the corresponding positions of the features to obtain the features
S332: followed by
Inputting the data into the residual block for further feature extraction to obtain features
And adopting the mode of jump connection to obtain the characteristics
And FMCarrying out addition calculation on the elements of the corresponding positions of the features to obtain the features
Wherein the content of the first and second substances,
the addition calculation of the corresponding position elements of the representation matrix;
s34: features to be derived by dual residual modules
Sequentially flowing through the maximum pooling layer and the full-connection layer to obtain a final diagnosis result.
Claims (8)
1. A method for classifying and diagnosing the health state of the heart of a driver based on a neural network is characterized by comprising the following steps: the method comprises the following steps: after the cloud algorithm server acquires the electrocardio monitoring data,
firstly, the cloud server calls a preprocessing algorithm to filter the electrocardiogram monitoring data so as to improve the quality of the electrocardiogram monitoring data;
then, selecting the electrocardiosignal segment with the maximum signal-to-noise ratio in the electrocardio monitoring data by self by taking the signal-to-noise ratio as a standard;
finally, calculating relevant expert characteristics for subsequent deep learning model diagnosis on the preprocessed electrocardiosignal segments by using a statistical learning method and a signal time-frequency domain correlation method;
after the cloud server completes the preprocessing algorithm, the heart health level of the driver can be detected by calling an analysis and diagnosis algorithm based on deep learning.
2. The neural network-based method for diagnosing the health status of the heart of the driver based on the classification as claimed in claim 1, wherein the deep learning analysis and diagnosis algorithm in the deep learning model is composed of three parts:
the first part is characterized by further feature fusion of the expert features extracted before by a feedforward neural network;
the second part is to carry on the characteristic extraction end to the preprocessed electrocardiosignal by the improved one-dimensional ResNet, so adopt the one-dimensional neural network because the electrocardiosignal is one-dimensional sequence data in essence, adopt the one-dimensional neural network can catch the sequence characteristic in the electrocardiosignal well, this kind of sequence characteristic has very big effects to diagnosing atrial fibrillation and premature beat, design the convolution kernel of different yardstick in every layer of network in the one-dimensional neural network to extract different characteristics in the electrocardiosignal end to end at the same time, embed the jump structure of ResNet in the framework of the one-dimensional neural network, make the one-dimensional neural network can avoid the problem of the gradient attenuation and then promote the diagnostic accuracy of the algorithm integrally;
and the third part integrates the fusion characteristics obtained by the two parts to carry out decision analysis, maps electrocardiosignals with different characteristics to the heart health state of the driver in a probability mode, and provides classification diagnosis results of 'normal', 'vertical branch obstruction', 'sinus rhythm', 'atrial fibrillation' and 'myocardial infarction'.
3. The neural network-based method for diagnosing the heart health status of the driver based on the neural network as claimed in claim 2, wherein the data generated in the deep learning model is processed by the following steps: the cloud algorithm server carries two parts of processing algorithms, the preprocessing algorithm firstly carries out filtering cleaning on original electrocardio data so as to improve the quality of electrocardio signals to a great extent, and the signals f (t) are transformed as follows:
in the formula, xi (xi)>0)、
Respectively for mother wavelet
Scaling, translation factor.
4. The neural network-based classification diagnosis method for the heart health state of the driver is characterized in that an electrocardio segment with the largest signal-to-noise ratio is selected from the electrocardio signals, and the electrocardio segment with the high signal-to-noise ratio is used as the input of a deep learning model for further analysis and diagnosis.
5. The neural network-based classification diagnosis method for the heart health state of the driver as claimed in claim 2, wherein the specific process of analyzing and diagnosing the input electrocardiogram fragments through the deep learning model is as follows:
s31, firstly, the electrocardiogram fragments are input into a convolutional layer for convolution operation to realize the compression and feature extraction of the electrocardiogram data, and the calculation of the convolutional layer is as follows:
therein, Ψj lIs the activation value, Γ, of the jth feature map of the ith layerjIs the number of feature maps of the layer, Ψi l-1Is the jth feature map of the ith layer, Φij lAs a weight matrix, qj lIs a bias term, "# is a convolution operator, and Y (·) is a non-linear activation function.
6. The neural network-based method for classifying and diagnosing the health status of the heart of the driver as claimed in claim 5, wherein the features obtained by the convolution layer calculation are compressed in feature size through a maximum pooling layer to obtain features FMAiming at reducing the parameter quantity of the model needing to be trained and avoiding the occurrence of the over-fitting phenomenon, the calculation process of the maximum pooling layer is as follows:
wherein the content of the first and second substances,
in order to be a function of down-sampling,
is the characteristic value after the maximum pooling operation.
7. The neural network-based method for classifying and diagnosing the health status of the heart of the driver as claimed in claim 6, wherein the feature FMFurther feature extraction is carried out through a dual residual error module, and the specific process of the dual residual error module is as follows:
characteristic FMFirstly, extracting the characteristics through the residual block, and extracting the characteristics
And FMCarrying out addition calculation on the elements of the corresponding positions of the features to obtain the features
Followed by
Inputting the data into the residual block for further feature extraction to obtain features
And adopting the mode of jump connection to obtain the characteristics
And FMCarrying out addition calculation on the elements of the corresponding positions of the features to obtain the features
Wherein the content of the first and second substances,
and representing the addition calculation of the corresponding position elements of the matrix.
8. The neural network-based method for classifying and diagnosing the health status of the heart of the driver as claimed in claim 7, wherein the features obtained by the dual residual error module
Sequentially flowing through the maximum pooling layer and the full-connection layer to obtain a final diagnosis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210238767.2A CN114711787A (en) | 2022-03-11 | 2022-03-11 | Neural network-based classification diagnosis method for heart health state of driver |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210238767.2A CN114711787A (en) | 2022-03-11 | 2022-03-11 | Neural network-based classification diagnosis method for heart health state of driver |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114711787A true CN114711787A (en) | 2022-07-08 |
Family
ID=82237409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210238767.2A Withdrawn CN114711787A (en) | 2022-03-11 | 2022-03-11 | Neural network-based classification diagnosis method for heart health state of driver |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114711787A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229607A (en) * | 2023-05-09 | 2023-06-06 | 深圳市城市交通规划设计研究中心股份有限公司 | Prediction method of running carbon emission of motor vehicle, electronic equipment and storage medium |
-
2022
- 2022-03-11 CN CN202210238767.2A patent/CN114711787A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229607A (en) * | 2023-05-09 | 2023-06-06 | 深圳市城市交通规划设计研究中心股份有限公司 | Prediction method of running carbon emission of motor vehicle, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110403600B (en) | Intelligent analysis method and system for paroxysmal atrial fibrillation based on difference time scatter diagram | |
| CN111053549A (en) | Intelligent biological signal abnormality detection method and system | |
| CN108511055B (en) | Ventricular premature beat recognition system and method based on classifier fusion and diagnosis rules | |
| CN109480824B (en) | Method and device for processing electrocardio waveform data and server | |
| CN108090509B (en) | Data length self-adaptive electrocardiogram classification method | |
| US11331034B2 (en) | Automatic method to delineate or categorize an electrocardiogram | |
| CN111956208B (en) | ECG signal classification method based on ultra-lightweight convolutional neural network | |
| CN113080994A (en) | Multi-lead electrocardiosignal classification method based on convolutional neural network | |
| CN112587153A (en) | End-to-end non-contact atrial fibrillation automatic detection system and method based on vPPG signal | |
| CN111358459A (en) | Arrhythmia identification method, device, equipment and storage medium | |
| CN110638430A (en) | Multi-task cascade neural network ECG signal arrhythmia disease classification model and method | |
| CN112617849A (en) | Atrial fibrillation detection and classification method based on CNN + LSTM | |
| CN112674782B (en) | Device and method for detecting epileptic-like electrical activity of epileptic during inter-seizure period | |
| CN109887594A (en) | A kind of multi-lead arrhythmia cordis intelligent diagnosing method based on MODWT and TDCNN | |
| CN111481192A (en) | Electrocardiosignal R wave detection method based on improved U-Net | |
| CN111772628A (en) | Electrocardiosignal atrial fibrillation automatic detection system based on deep learning | |
| CN103970975A (en) | Electrocardio data processing method and electrocardio data processing system | |
| CN113133768A (en) | Cardiovascular disease auxiliary diagnosis model and training method based on federal learning | |
| CN114711787A (en) | Neural network-based classification diagnosis method for heart health state of driver | |
| CN110507311B (en) | Image information based electrocardiogram analysis method, device, equipment and medium | |
| CN108577831A (en) | Singly lead heart patch data long-range monitoring and diagnosis system and its processing method | |
| CN108926343B (en) | CNN neural network-based acute myocardial infarction qualitative automatic discrimination system | |
| CN110537907B (en) | Electrocardiosignal compression and identification method based on singular value decomposition | |
| CN114041800A (en) | Electrocardiosignal real-time classification method and device and readable storage medium | |
| CN114557705A (en) | Resting electrocardio analysis method 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220708 |