CN112052874B - Physiological data classification method and system based on generation countermeasure network - Google Patents
Physiological data classification method and system based on generation countermeasure network Download PDFInfo
- Publication number
- CN112052874B CN112052874B CN202010761850.9A CN202010761850A CN112052874B CN 112052874 B CN112052874 B CN 112052874B CN 202010761850 A CN202010761850 A CN 202010761850A CN 112052874 B CN112052874 B CN 112052874B
- Authority
- CN
- China
- Prior art keywords
- data
- training
- virtual
- model
- countermeasure network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 50
- 238000003745 diagnosis Methods 0.000 claims abstract description 31
- 201000010099 disease Diseases 0.000 claims abstract description 17
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 17
- 238000012360 testing method Methods 0.000 claims description 11
- 238000007477 logistic regression Methods 0.000 claims description 9
- 238000013256 Gubra-Amylin NASH model Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 230000015654 memory Effects 0.000 claims description 4
- 230000007787 long-term memory Effects 0.000 claims description 2
- 230000006403 short-term memory Effects 0.000 claims description 2
- 206010012601 diabetes mellitus Diseases 0.000 abstract description 15
- 230000006870 function Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008485 antagonism Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 102000017011 Glycated Hemoglobin A Human genes 0.000 description 1
- 108010014663 Glycated Hemoglobin A Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000291 postprandial effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- 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
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a physiological data classification method based on a generated countermeasure network, which comprises the following steps: acquiring relevant diagnostic data of a certain disease to be predicted; training to generate an countermeasure network by using the diagnosis data, and generating a large number of virtual data sets; training a plurality of weak classifiers using the virtual data set; and inputting the acquired diagnosis data into a trained weak classifier to obtain different physiological data classification results. According to the technical scheme, a large amount of virtual diabetes diagnosis data is generated based on the generation countermeasure network, a large amount of weak classifiers are trained on the virtual data, and finally the weak classifiers are integrated to obtain a more accurate disease (diabetes) integrated diagnosis result.
Description
Technical Field
The invention belongs to the technical field of physiological data processing, and particularly relates to a physiological data classification method and system based on a generated countermeasure network.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
In the medical field, predictions for certain diseases require a large number of data samples to be correlated, however, in many cases it is difficult to obtain a large number of high quality data samples, which presents a significant hurdle to the training of subsequent models. The accurate prediction and classification of diseases are one of the keys of disease therapeutic intervention, for example, diabetes mellitus which is one of the common chronic diseases at present is predicted early and effective intervention is carried out, and about 6% -10% of patients can not develop diabetes mellitus each year, so that the efficient and accurate classification and prediction of diseases are particularly important.
Taking diabetes as an example, the existing diagnosis mode mainly comprises the steps of detecting postprandial blood sugar and glycosylated hemoglobin and evaluating, wherein the detection accuracy is high but the cost is also high; on the other hand, diagnosis can be performed through personal experience of doctors, but misdiagnosis and missed diagnosis can occur in a long time. In recent years, more and more researchers perform disease diagnosis according to clinical data through methods such as machine learning, statistical analysis and the like, and usually, the methods need complete data for model training, however, a large amount of manpower and material resources are needed for obtaining the clinical data, and the obtained physiological data often have the problems of small data quantity, poor data quality and the like, so that the traditional disease diagnosis mode based on the data is difficult to exert good performance.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a physiological data classification method based on a generated countermeasure network, which can obtain more accurate integrated diagnosis results.
To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:
in a first aspect, a physiological data classification method based on generating an antagonism network is disclosed, comprising:
acquiring relevant diagnostic data of a certain disease to be predicted;
training to generate an countermeasure network by using the diagnosis data, and generating a large number of virtual data sets;
training a plurality of weak classifiers using the virtual data set;
and inputting the acquired diagnosis data into a trained weak classifier to obtain different physiological data classification results.
In a second aspect, a physiological data classification system based on generating an antagonism network is disclosed, comprising:
a data acquisition module configured to: acquiring relevant diagnostic data of a certain disease to be predicted;
a virtual data set generation module configured to: training to generate an countermeasure network by using the diagnosis data, and generating a large number of virtual data sets;
a classification module configured to: training a plurality of weak classifiers using the virtual data set;
and inputting the acquired diagnosis data into a trained weak classifier to obtain different physiological data classification results.
The one or more of the above technical solutions have the following beneficial effects:
according to the technical scheme, a large amount of virtual disease diagnosis data is generated based on the generation countermeasure network, a large amount of weak classifiers are trained on the virtual data, and finally the weak classifiers are integrated to obtain a more accurate disease (diabetes) integrated diagnosis result.
The technical scheme of the disclosure introduces the ideas of generating the countermeasure network, generating a large amount of virtual data to train each sub-classifier of the integrated classifier, and the integrated prediction requires the similar and different results of each sub-classifier to be consistent with the ideas of generating the data similar and different to the countermeasure network.
The model provided by the technical scheme of the disclosure has less training data, is more suitable for the field with less data size such as diabetes prediction, and the effect of the trained integrated model is better than that of the original training algorithm.
The final training set of the prediction method provided by the invention does not participate in the integrated model training, the training result is basically the same as the test result, and the fitting problem does not exist.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a diagram of a model architecture of an integrated diabetes prediction system based on generation of an countermeasure network in accordance with an embodiment of the present invention;
FIG. 2 is a diagram of a model structure for generating a countermeasure network in an embodiment of the invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
The embodiment discloses a physiological data classification method based on generation of an countermeasure network, which is described by taking diagnosis of diabetes as an example, and is shown in fig. 1, and comprises the following steps:
s1, acquiring diabetes diagnosis data, and performing data preprocessing including missing data processing, data normalization and the like to obtain a diabetes diagnosis data set.
S2, the diagnosis data set is divided into a test set R and a training set S.
S3, training a GAN model by using the training set S, and generating a large number of virtual data sets.
And S4, inversely normalizing the virtual data set to obtain a normalized virtual data set V.
S5, training ten weak classifier models in the second-layer model by using the virtual data set V.
S6, training a third layer model by taking the weak classifier result as input, wherein the third layer model generally adopts a logistic regression model (LR), mainly weights each classifier of the second layer model, and the final result is obtained after the classification results of all the classifiers of the second layer are weighted and averaged.
The embodiment example of the disclosure is mainly directed to the problem of classifying based on a smaller data volume, and the classifying effect of the method is more advantageous when the data volume is smaller.
In step S1, diabetes diagnosis data including age, sex, pregnancy frequency, blood glucose level, blood pressure, body mass index, genetic index, whether or not diabetes is affected, etc. is obtained, data with a missing value of more than 50% is deleted, and the remaining data is subjected to missing value processing by multiple interpolation or the like.
Here, the clinical data of each patient contains several tens of items, but the items recorded by different doctors are different in different hospitals, and if more than 50% of patients do not detect the items in the data, the items are deleted.
Dividing the data set into a test set and a training set;
dividing a data set into a test set R and a training set S, normalizing the data of the test set, and training the model provided by the invention by using the training set, wherein the test set is used;
the formula for further normalizing the data is as follows:
wherein a is i，j As raw data, A i，j To normalize the data, max (a i，j ) And min (a) i，j ) Is the maximum and minimum of the original data. Wherein the sex equivalent boolean is converted to 0 and 1.
In step S2, 70% of the data randomly screened out is divided into training set S, and the remaining 30% is test set R.
Referring to fig. 2, in step S3, a generation countermeasure network (GAN) is composed of two parts, and a model G and a discrimination model D are generated. G is random noise with normal distribution and is output as virtual sample G (z) which obeys the real diabetes diagnosis data distribution P data To confuse D. D is input as a training set S and a virtual sample G (z) in real data, and output as a discrimination result scale E (0, 1), when scale is larger than 0.5, the input data is judged to be real data, and when scale is smaller than 0.5, the data is judged to be virtual data, and the quality of G generated data is judged. When the judgment results of D on the training set S and the virtual sample G (z) are 0.5, the training is finished. G and D can be nonlinear mapping functions, in the invention, the generator adopts a fully-connected neural network, and the discriminator adopts a long-term and short-term memory network.
Generating the countermeasure network includes two models, one for generating and one for discriminating, but they are generally divided into a generator and a discriminator.
First, the arbiter is optimized given the generator. The discriminant is a two-class model, the training discriminant is a process for realizing the minimization of cross entropy, and the loss function of the GAN model has the following formula:
e (·) is the expected value calculated, x is sampled in the true data distribution P data (x) For diagnostic data, z is sampled in a priori distribution P z (z), z is a random number. The generator is configured to learn the distribution of the data x by the a priori noise distribution P z (z) A mapping space G (z; θ) is constructed g ) The corresponding arbiter mapping function is D (x; θ d ) A scalar is output representing the probability that x is the true data.
Wherein,wherein x represents a real sample, and D (x) represents the probability that x is judged to be the real sample through a judging network; />Where z represents noise input to the generated sample, G (z) represents a sample generated by the noise z by the generation network, and D (G (z)) represents a probability that the generated sample passes through the discrimination network and is determined to be a true sample. The purpose of the network is to make the generated sample better as it gets closer to the real sample, i.e. D (G (z)) gets closer to 1, where V (D, G) becomes smaller; the purpose of the discrimination network is to have D (x) approach 1 and D (G (z)) approach 0.
Finally, by generating the countermeasure network, a large number of virtual data sets V are ultimately generated.
In step S4, the data is inversely normalized to obtain a data set formula as follows:
wherein a is i，j As raw data, A i，j To normalize the data, max (a i，j ) And min (a) i，j ) For the maximum and minimum values of the original data,for the virtual dataset v= { V 1 ，V 2 ...V n The virtual dataset includes clinical test features and diabetic conditions. n may increase infinitely with G generating virtual data, where G is allowed to generate 2000 copies of virtual data, i.e., n=2000.
The virtual dataset V was randomly divided into ten parts, m= { M 1 ，M 2 ...M 10 E V, where each subset contains 200 pieces of data.
In step S5, ten simple classification models are trained from ten sub-data sets, respectively, and these classifiers are Decision Tree (DT), random Forest (RF), extreme random tree (ET), adaBoost (ADB), support Vector Machine (SVM), multi-perceptron (MLP), naive Bayes (NBC), gaussian Naive Bayes (GNB), logistic Regression (LR), neural Network (NN), etc.
In step S6, the training set S is respectively put into the trained classification models in step S5, so as to obtain ten different classification results, and the results are used as input to train a third layer model Logistic Regression (LR), so that all model training is finally completed.
After training the model, the test set is normalized as well, and then the classification result is obtained through the invented model.
According to the technical scheme, the training set S is utilized to train and generate the countermeasure network (GAN), so that the generator G and the discriminator D in the GAN are in dynamic balance, namely the generator G can generate a virtual data set V with false and spurious, and V= { V 1 ，V 2 …V n }；
The system is divided into three layers of models, a large amount of virtual diabetes diagnosis data is generated based on an countermeasure network, a large amount of weak classifiers are trained by the virtual data, and finally the weak classifiers are integrated to obtain a more accurate diabetes integrated diagnosis result.
Based on the same inventive concept, the present embodiment discloses a physiological data classification system based on generation of an countermeasure network, including:
a data acquisition module configured to: acquiring relevant diagnostic data of a certain disease to be predicted;
a virtual data set generation module configured to: training to generate an countermeasure network by using the diagnosis data, and generating a large number of virtual data sets;
a classification module configured to: training a plurality of weak classifiers using the virtual data set;
and inputting the acquired diagnosis data into a trained weak classifier to obtain different physiological data classification results.
It is an object of the present embodiment to provide a computing device 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 the above embodiment when the program is executed.
An object of the present embodiment is to provide a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of the above example.
The steps involved in the apparatus of the above embodiment correspond to those of the first embodiment of the method, and the detailed description of the embodiment refers to the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media including one or more sets of instructions; it should also be understood to include any medium capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any one of the methods of the present invention.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented by general-purpose computer means, alternatively they may be implemented by program code executable by computing means, whereby they may be stored in storage means for execution by computing means, or they may be made into individual integrated circuit modules separately, or a plurality of modules or steps in them may be made into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (9)
1. A physiological data classification method based on generation of an countermeasure network, comprising:
acquiring relevant diagnostic data of a certain disease to be predicted;
training to generate an countermeasure network by using the diagnosis data, and generating a large number of virtual data sets;
training a plurality of weak classifiers using the virtual data set;
inputting the acquired diagnosis data into a trained weak classifier to acquire different physiological data classification results;
the specific operation steps are as follows: acquiring diagnostic data of a disease;
normalizing the acquired diagnostic data, and dividing the diagnostic data into a test set and a training set;
training a GAN model by using the training set, and generating a large number of virtual data sets;
inversely normalizing the virtual data set to obtain a normalized virtual data set;
training ten weak classifier models in the second layer model using the virtual dataset;
and training a third layer model by taking the weak classifier result as input, wherein the third layer model adopts a logistic regression model LR, mainly giving weight to each classifier of the second layer model, and obtaining a final result after weighted average of the classification results of all the classifiers of the second layer.
2. The method of claim 1, wherein generating the countermeasure network comprises generating a model and determining the model;
for random noise with normal distribution of the generated model input, outputting as a virtual sample;
the discrimination model is input as a training set and a virtual sample in the real data, and output as a discrimination result.
3. The method for classifying physiological data based on generation of a countermeasure network according to claim 2, wherein the training is ended when the determination results of the discrimination model on the training set and the virtual sample satisfy the set condition.
4. The physiological data classification method based on generation countermeasure network of claim 2, wherein the generation model adopts a fully connected neural network, and the discrimination model adopts a long-term and short-term memory network.
5. A physiological data classification method based on generating an countermeasure network according to claim 2, wherein the number of randomly divided virtual data sets is the same as the number of weak classifiers to be trained.
6. A method of establishing a disease diagnostic model, comprising:
obtaining a classification result using the physiological data classification method based on generation of an countermeasure network as claimed in any one of claims 1 to 5;
and inputting the classification result into a logistic regression model to obtain a trained diagnosis module.
7. A physiological data classification system based on generation of an countermeasure network, comprising:
a data acquisition module configured to: acquiring relevant diagnostic data of a certain disease to be predicted;
a virtual data set generation module configured to: training to generate an countermeasure network by using the diagnosis data, and generating a large number of virtual data sets;
a classification module configured to: training a plurality of weak classifiers using the virtual data set;
inputting the acquired diagnosis data into a trained weak classifier to acquire different physiological data classification results;
the specific operation steps are as follows: acquiring diagnostic data of a disease;
normalizing the acquired diagnostic data, and dividing the diagnostic data into a test set and a training set;
training a GAN model by using the training set, and generating a large number of virtual data sets;
inversely normalizing the virtual data set to obtain a normalized virtual data set;
training ten weak classifier models in the second layer model using the virtual dataset;
and training a third layer model by taking the weak classifier result as input, wherein the third layer model adopts a logistic regression model LR, mainly giving weight to each classifier of the second layer model, and obtaining a final result after weighted average of the classification results of all the classifiers of the second layer.
8. A computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the method of any of the preceding claims 1-5 when the program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, performs the steps of the method of any of the preceding claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010761850.9A CN112052874B (en) | 2020-07-31 | 2020-07-31 | Physiological data classification method and system based on generation countermeasure network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010761850.9A CN112052874B (en) | 2020-07-31 | 2020-07-31 | Physiological data classification method and system based on generation countermeasure network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112052874A CN112052874A (en) | 2020-12-08 |
| CN112052874B true CN112052874B (en) | 2023-11-17 |
Family
ID=73601368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010761850.9A Active CN112052874B (en) | 2020-07-31 | 2020-07-31 | Physiological data classification method and system based on generation countermeasure network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112052874B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113069124A (en) * | 2021-03-09 | 2021-07-06 | 浙江工业大学 | Electrocardio monitoring method based on CNN-ET model |
| CN113657623B (en) * | 2021-07-13 | 2023-09-29 | 国网河北省电力有限公司电力科学研究院 | Power equipment state diagnosis effect determining method, device, terminal and storage medium |
| CN113782182A (en) * | 2021-07-29 | 2021-12-10 | 北京理工大学 | Stress fracture prediction method based on electromyographic data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753998A (en) * | 2018-12-20 | 2019-05-14 | 山东科技大学 | The fault detection method and system, computer program of network are generated based on confrontation type |
| CN110580695A (en) * | 2019-08-07 | 2019-12-17 | 深圳先进技术研究院 | multi-mode three-dimensional medical image fusion method and system and electronic equipment |
| CN111436929A (en) * | 2019-01-17 | 2020-07-24 | 复旦大学 | Method for generating and identifying neurophysiological signals |
-
2020
- 2020-07-31 CN CN202010761850.9A patent/CN112052874B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753998A (en) * | 2018-12-20 | 2019-05-14 | 山东科技大学 | The fault detection method and system, computer program of network are generated based on confrontation type |
| CN111436929A (en) * | 2019-01-17 | 2020-07-24 | 复旦大学 | Method for generating and identifying neurophysiological signals |
| CN110580695A (en) * | 2019-08-07 | 2019-12-17 | 深圳先进技术研究院 | multi-mode three-dimensional medical image fusion method and system and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112052874A (en) | 2020-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pereira et al. | COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios | |
| CN111292853B (en) | Multi-parameter-based cardiovascular disease risk prediction network model and construction method thereof | |
| CN112052874B (en) | Physiological data classification method and system based on generation countermeasure network | |
| Sun et al. | Diagnosis and analysis of diabetic retinopathy based on electronic health records | |
| CN111009321A (en) | Application method of machine learning classification model in juvenile autism auxiliary diagnosis | |
| CN111080643A (en) | Method and device for classifying diabetes and related diseases based on fundus images | |
| CN112819045A (en) | Method, apparatus, electronic device and medium for user physiological state classification | |
| Pillai et al. | Prediction of heart disease using rnn algorithm | |
| CN111028232A (en) | Diabetes classification method and equipment based on fundus images | |
| Hamlili et al. | Transfer learning with Resnet-50 for detecting COVID-19 in chest X-ray images | |
| Parsons et al. | Automatic identification of Chagas disease vectors using data mining and deep learning techniques | |
| Shrestha et al. | Supervised machine learning for early predicting the sepsis patient: modified mean imputation and modified chi-square feature selection | |
| Popkes et al. | Interpretable outcome prediction with sparse Bayesian neural networks in intensive care | |
| Chen et al. | SE-ECGNet: multi-scale SE-Net for multi-lead ECG data | |
| CN116259415A (en) | Patient medicine taking compliance prediction method based on machine learning | |
| CN111047590A (en) | Hypertension classification method and device based on fundus images | |
| Molla et al. | A predictive analysis framework of heart disease using machine learning approaches | |
| Kafi et al. | A Lite-Weight Clinical Features Based Chronic Kidney Disease Diagnosis System Using 1D Convolutional Neural Network | |
| Xiao et al. | A deep feature fusion network for fetal state assessment | |
| Appiahene et al. | Application of ensemble models approach in anemia detection using images of the palpable palm | |
| CN114743619B (en) | Questionnaire quality evaluation method and system for disease risk prediction | |
| Dwivedi et al. | Microcell‐Net: A deep neural network for multi‐class classification of microscopic blood cell images | |
| Perng et al. | Analysis of the 72-h mortality of emergency room septic patients based on a deep belief network | |
| Rao et al. | Multimodal Approach for Predicting the Brain Stroke Using the Machine Learning Techniques | |
| Yue et al. | Comparison of several models for cardiovascular diseases prediction |
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 |