CN110458066A - A kind of age bracket classification method based on tranquillization state eeg data - Google Patents
A kind of age bracket classification method based on tranquillization state eeg data Download PDFInfo
- Publication number
- CN110458066A CN110458066A CN201910701028.0A CN201910701028A CN110458066A CN 110458066 A CN110458066 A CN 110458066A CN 201910701028 A CN201910701028 A CN 201910701028A CN 110458066 A CN110458066 A CN 110458066A
- Authority
- CN
- China
- Prior art keywords
- eeg data
- tranquillization state
- convolutional neural
- neural networks
- state eeg
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Psychiatry (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Fuzzy Systems (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention relates to a kind of age bracket classification methods based on tranquillization state eeg data, comprising the following steps: S1, the corresponding original tranquillization state eeg data of acquisition each age group；S2, original tranquillization state eeg data is pre-processed, obtains the tranquillization state eeg data of removal artefact；S3, building convolutional neural networks, and the tranquillization state eeg data for removing artefact is inputed into convolutional neural networks, convolutional neural networks are trained and are tested, trained convolutional neural networks are obtained；S4, age bracket classification is carried out to practical tranquillization state eeg data by trained convolutional neural networks.Compared with prior art, tranquillization state eeg data is divided by brain area and carries out artefact and handled by the present invention, extract the feature on Different brain region respectively by convolutional neural networks, to carry out age bracket classification according to the feature of Different brain region, the pretreated complexity of eeg data is not only reduced, also solves the problems, such as that appropriate model can not be selected for eeg data.
Description
Technical field
The present invention relates to deep learning neural networks and brain science technical field, are based on tranquillization state brain more particularly, to one kind
The age bracket classification method of electric data.
Background technique
In brain science, have a large number of studies show that the brain in all ages and classes stage has differences, has sent out within 2017 years
On the Nature periodical of table, there is article to study the brain of 286 subjects, the age distribution of these subjects is 20
Between~65 years old, these subjects are divided into three groups (young group, middle aged group and old groups) according to the age, by every group of subject
Different brain region state of activation visualized, the results showed that, the brain in all ages and classes stage is in visual web, kinesthesia
Hownet network and conspicuousness network facet have differences, and with advancing age, the function connects in these networks show
The trend being gradually reduced, specific manifestation are as follows: with advancing age, in brain constituent the size, quantity of nerve cell with
And difference can be all generated in neuroglia, and with cranial capacity, the variation of blood flow, the cognitive ability of brain also can be under
Drop.
Since the activation degree of Different brain region can be embodied in tranquillization state eeg data, tranquillization state eeg data energy
A reliable basis enough as age bracket classification, but the acquisition step that eeg data usually not standardizes, and there is performance to take out
As, be difficult to pretreated feature, so a conjunction can not be found when analyzing using machine learning method eeg data
Suitable model: firstly, can be difficult to carry out it in preprocessing process with many noises in the collection process of eeg data
Filter；Secondly, when selecting Machine learning classifiers, such as SVM or decision tree, different data predictions is to model
As a result different influences can be generated.
Age bracket classification is carried out by brain data, mainly brain constituent is ground by fMRI technology at present
Study carefully, and carries out the research of brain cognitive ability by performance of the observation subject under certain tasks, but both methods
It is not available tranquillization state eeg data to analyze and research, i.e., can not carry out point of age bracket by tranquillization state eeg data
Class.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind to be based on tranquillization state brain
The age bracket classification method of electric data.
The purpose of the present invention can be achieved through the following technical solutions: a kind of age bracket based on tranquillization state eeg data
Classification method, comprising the following steps:
S1, situation of being classified according to actual age section, the corresponding original tranquillization state eeg data of acquisition each age group；
S2, original tranquillization state eeg data is pre-processed, obtains the tranquillization state eeg data of removal artefact；
S3, building convolutional neural networks, and the tranquillization state eeg data for removing artefact is inputed into convolutional neural networks, it is right
Convolutional neural networks are trained and test, and obtain trained convolutional neural networks；
S4, age bracket classification is carried out to practical tranquillization state eeg data by trained convolutional neural networks.
Preferably, the step S2 specifically includes the following steps:
S21, original tranquillization state eeg data is subjected to brain area division, obtains including F, C, P, O and T totally five brain areas,
In, the eeg data of F brain area corresponds to visual web, and the eeg data of C brain area corresponds to motion perception network, the brain of P brain area
Electric data correspond to conspicuousness network, and the eeg data of O brain area has anti-noise ability；
S22, the data volume of eeg data in this four brain areas of F, C, P and O is unitized；
The electro-ocular signal of eeg data, obtains the tranquillization state brain of removal artefact in S23, removal this four brain areas of F, C, P and O
Electric data.
Preferably, the step S23 is specifically to use independent component analysis method, to the brain electricity of this four brain areas of F, C, P and O
Data are decomposed, the corresponding component of electro-ocular signal in eeg data after deletion is decomposed, to remove the eye telecommunications of eeg data
Number, obtain the tranquillization state eeg data of removal artefact.
Preferably, the step S3 specifically includes the following steps:
S31, building convolutional neural networks, the convolutional neural networks include sequentially connected convolutional layer, average pond layer
With softmax classifier；
S32, the tranquillization state eeg data for removing artefact is divided into training set and test set；
S33, training set is inputted into convolutional neural networks, is trained with preset exercise wheel number；
S34, the primary preset exercise wheel number of every completion, then input convolutional neural networks for test set, record a convolution
The accuracy rate of neural network output category result；
S35, step S34 is repeated, and judges whether the accuracy rate of convolutional neural networks output category result restrains, if receiving
It holds back, then the convolutional neural networks have trained, otherwise return step S33.
Preferably, convolutional layer is used to carry out feature extraction, the convolutional layer to tranquillization state eeg data in the step S31
It is made of multiple sub- convolutional layers.
Preferably, average pond layer is used to carry out dimension-reduction treatment to the feature of tranquillization state eeg data in the step S31,
And the tranquillization state eeg data feature input softmax classifier after dimensionality reduction is subjected to age bracket classification, with output category result.
Preferably, the accuracy rate of convolutional neural networks output category result is to pass through ratio in the step S34 and step S35
Real age section classification compared with convolutional neural networks output category result and test set obtains.
Preferably, the whether convergent tool of the accuracy rate of convolutional neural networks output category result is judged in the step S35
Body process are as follows: the record accurate rate score of n times, and successively compare the variation of i-th of accurate rate score and (i-1)-th accurate rate score
Rate obtains N-1 change rate, judges whether this N-1 change rate is respectively less than or is equal to preset convergence threshold, if being judged as
It is that then the accuracy rate of convolutional neural networks output category result has restrained, otherwise judges not restrain, wherein N >=5, i ∈ N.
Compared with prior art, the present invention is divided tranquillization state eeg data by brain area, and is extracted and corresponded respectively to
The eeg data of visual web, motion perception network and conspicuousness network extracts Different brain region midbrain by convolutional neural networks
The abstract characteristics of electric data realize the purpose that age bracket classification is carried out using tranquillization state eeg data；
The present invention has the O brain area eeg data of anti-noise ability by retaining, and can guarantee the complete of tranquillization state eeg data
Whole property, while artefact is carried out to the eeg data of Different brain region and is handled, the noise in tranquillization state eeg data is effectively reduced,
Overcome the pretreated complexity of tranquillization state eeg data；
The present invention learns to be suitable for brain electricity using the fitness of convolutional neural networks itself, using back-propagation algorithm automatically
The parameter of data, can the tranquillization state eeg data abstract to performance carry out modeling analysis, solve tranquillization state eeg data without
Method obtains the problem of appropriate model.
Detailed description of the invention
Fig. 1 is method flow schematic diagram of the invention；
Fig. 2 is the tranquillization state eeg data schematic diagram divided in embodiment by brain area；
Fig. 3 is the accuracy rate schematic diagram of convolutional neural networks output category result in embodiment.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.
As shown in Figure 1, a kind of age bracket classification method based on tranquillization state eeg data, comprising the following steps:
S1, situation of being classified according to actual age section, the corresponding original tranquillization state eeg data of acquisition each age group；
S2, original tranquillization state eeg data is pre-processed, obtains the tranquillization state eeg data of removal artefact；
S3, building convolutional neural networks, and the tranquillization state eeg data for removing artefact is inputed into convolutional neural networks, it is right
Convolutional neural networks are trained and test, and obtain trained convolutional neural networks；
S4, age bracket classification is carried out to practical tranquillization state eeg data by trained convolutional neural networks.
The present embodiment is to acquire its tranquillization state eeg data from 56 subjects comprising different age group, this 56 tested
The age bracket of person is classified and data set division (being divided into training set and test set) situation is as shown in table 1:
Table 1
| Age bracket | Total number of persons | Training set number | Test set number |
| 18~30 | 20 | 12 | 8 |
| 31~45 | 17 | 10 | 7 |
| 46~60 | 19 | 12 | 7 |
In the present embodiment, the detailed process of step S2 are as follows: when carrying out age bracket classification, tranquillization state eeg data is pressed into brain
Area is divided, and the eeg data of 32 leads corresponding to this five brain areas of F, C, P, O and T as shown in Figure 2 has been obtained,
In, it be central area, P brain area be top area, O brain area be occipital region, T brain area is temporo area that F brain area, which is frontal region, C brain area, F, C, P these three
Brain area corresponds respectively to visual web, motion perception network and conspicuousness network, and the eeg data of O brain area has anti-noise ability,
It is able to maintain the integrality of entire tranquillization state eeg data；
Present invention uses the eeg data of this four brain areas of F, C, P, O, the number of electrodes of P brain area is than other in embodiment
Brain area has more two, in order to guarantee the unification of each brain area eeg data amount, by two electrode removals of the P7 of P brain area and P8, to every
After a brain area electrode used therein determines, artefact is carried out to original eeg data and is handled, it all can be to collecting due to blinking every time
Tranquillization state eeg data have an impact, therefore to collected eeg data carry out eye electricity removal operation be it is very necessary,
Eeg data is decomposed using independent component analysis method first, it is corresponding to find electro-ocular signal in the eeg data after decomposing
Component, the corresponding component of electro-ocular signal is deleted from all eeg datas, so that it may complete in original eeg data eye electricity
Removal.
In the present embodiment, the convolutional neural networks structure in step S3 is as shown in table 2, includes the convolution of each layer of convolution
Core size, step-length, the data dimension for inputting convolutional layer and the data dimension for exporting convolutional layer:
Table 2
The detailed process of step S3 are as follows:
One, after pretreatment, tranquillization state eeg data is the numerical matrix of 1000 size of 28x, by it according to brain area
It is divided into four parts, is converted into the matrix of 4x 1000x 7, and inputs convolutional neural networks；
Two, since the port number of each convolution kernel on first convolutional layer is 7, convolution operation of every progress, volume
Product core can in complete observation to the brain area all leads data, complete the feature extraction to eeg data, age bracket classification
Parameter setting in network is as shown in table 2, it was proved that, under this parameter configuration, convolutional neural networks are to tranquillization state
The age bracket classification results of eeg data are best, and the input dimension of data is (4,1000,7) first, and convolutional layer 1 has 64 3*3
Convolution kernel, its step-length is [1,2], and after the filtering of convolutional layer 1, output data dimension is (2,499,64), is then counted
The convolutional layer 2_1 for being 1 according to the step-length for inputing to 32 1*1 convolution kernels, obtains the data of dimension (2,499,32), then sequentially input
The convolutional layer 3 that the step-length of convolutional layer 2_2 and 128 1*2 convolution kernels that step-length to 128 2*2 convolution kernels is 1 are 2, is tieed up
The output data of (1,249,128) is spent, subsequent data are sequentially input to 64 1*1 convolution kernels and 256 1*2 convolution kernels, step-length
It is 1 convolutional layer 4_1 and convolutional layer 4_2, the output data of dimension (1,248,256) is obtained, finally, data input to 256
The convolutional layer 6 that the step-length for the convolutional layer 5 and 3 1*2 convolution kernel that the step-length of a 1*2 convolution kernel is 2 is 1, obtain dimension (1,123,
3) output data, the dimension are that the output data of (1,123,3) is output to the progress of softmax classifier by average pond layer
Classification；
Three, the tranquillization state eeg data in convolutional neural networks model is input to having a size of 4x 1000x 7, each batch
Size be 32, convolutional neural networks model using Adam optimization method carry out model parameter update, learning rate initial value setting
It is 0.03, without using regularization in embodiment, as a result as shown in figure 3, abscissa represents the wheel number of training, ordinate generation in figure
The accuracy rate of table convolutional neural networks classification results, the preset exercise wheel number of the present embodiment are three-wheel, i.e., every three-wheel record is primary
The accuracy rate of convolutional neural networks classification results.During model training, every 3 epoch after training just on test set
It is once tested, from figure 3, it can be seen that convolutional neural networks are taken turns after training by 30, output category result is accurate
Rate reaches convergence, and the accuracy rate of output category result is 52% or more after the convergence of convolutional neural networks model, and the convolution
Test result is up to 60% in neural network model training process.
Embodiment the result shows that, in addition to remove artefact, no other machines learn frequently-used data preprocess method, than
It is proposed by the present invention to carry out age bracket classification using tranquillization state eeg data such as the use of the methods of normalization, standardization, dimensionality reduction
Method, preferable experimental result is achieved in embodiment.The present invention carries out tranquillization state brain electricity number using convolutional neural networks
According to analysis, according to the difference of the state of activation in the human brain area of different age group, and because the activation degree of Different brain region can be with
It is embodied among tranquillization state eeg data, the invention proposes the methods for using tranquillization state eeg data to carry out age bracket classification:
Tranquillization state eeg data is divided by brain area, and carries out artefact and handles, then extracts Different brain region using convolutional neural networks
Abstract characteristics, using convolutional neural networks itself to data have outstanding fitting performance, conventional machines can be overcome to learn
Classification method to the demanding problem of data prediction, the acquisition step that is not standardized especially for eeg data this one kind,
It is difficult to pre-process, show the data of the features such as abstract, modeling analysis can be carried out by convolutional neural networks, to realize benefit
The purpose of age bracket classification is carried out with tranquillization state eeg data.
Claims (8)
1. a kind of age bracket classification method based on tranquillization state eeg data, which comprises the following steps:
S1, situation of being classified according to actual age section, the corresponding original tranquillization state eeg data of acquisition each age group；
S2, original tranquillization state eeg data is pre-processed, obtains the tranquillization state eeg data of removal artefact；
S3, building convolutional neural networks, and the tranquillization state eeg data for removing artefact is inputed into convolutional neural networks, to convolution
Neural network is trained and tests, and obtains trained convolutional neural networks；
S4, age bracket classification is carried out to practical tranquillization state eeg data by trained convolutional neural networks.
2. a kind of age bracket classification method based on tranquillization state eeg data according to claim 1, which is characterized in that institute
State step S2 specifically includes the following steps:
S21, original tranquillization state eeg data is subjected to brain area division, obtains including F, C, P, O and T totally five brain areas, wherein F
The eeg data of brain area corresponds to visual web, and the eeg data of C brain area corresponds to motion perception network, the brain electricity number of P brain area
According to conspicuousness network is corresponded to, the eeg data of O brain area has anti-noise ability；
S22, the data volume of eeg data in this four brain areas of F, C, P and O is unitized；
The electro-ocular signal of eeg data, obtains the tranquillization state brain electricity number of removal artefact in S23, removal this four brain areas of F, C, P and O
According to.
3. a kind of age bracket classification method based on tranquillization state eeg data according to claim 2, which is characterized in that institute
Stating step S23 is specifically to use independent component analysis method, is decomposed to the eeg data of F, C, P and O this four brain areas, is deleted
The corresponding component of electro-ocular signal in eeg data after decomposition obtains removal artefact to remove the electro-ocular signal of eeg data
Tranquillization state eeg data.
4. a kind of age bracket classification method based on tranquillization state eeg data according to claim 1, which is characterized in that institute
State step S3 specifically includes the following steps:
S31, building convolutional neural networks, the convolutional neural networks include sequentially connected convolutional layer, average pond layer and
Softmax classifier；
S32, the tranquillization state eeg data for removing artefact is divided into training set and test set；
S33, training set is inputted into convolutional neural networks, is trained with preset exercise wheel number；
S34, the primary preset exercise wheel number of every completion, then input convolutional neural networks for test set, record a convolutional Neural
The accuracy rate of network output category result；
S35, step S34 is repeated, and judges whether the accuracy rate of convolutional neural networks output category result restrains, if convergence,
The convolutional neural networks have trained, otherwise return step S33.
5. a kind of age bracket classification method based on tranquillization state eeg data according to claim 4, which is characterized in that institute
It states convolutional layer in step S31 to be used to carry out feature extraction to tranquillization state eeg data, the convolutional layer is by multiple sub- convolutional layer groups
At.
6. a kind of age bracket classification method based on tranquillization state eeg data according to claim 4, which is characterized in that institute
It states in step S31 average pond layer and is used for feature progress dimension-reduction treatment to tranquillization state eeg data, and by the tranquillization after dimensionality reduction
State eeg data feature inputs softmax classifier and carries out age bracket classification, with output category result.
7. a kind of age bracket classification method based on tranquillization state eeg data according to claim 4, which is characterized in that institute
It is defeated by comparing convolutional neural networks for stating the accuracy rate of convolutional neural networks output category result in step S34 and step S35
The real age section classification of classification results and test set obtains out.
8. a kind of age bracket classification method based on tranquillization state eeg data according to claim 4, which is characterized in that institute
It states and judges the whether convergent detailed process of the accuracy rate of convolutional neural networks output category result in step S35 are as follows: record n times are quasi-
True rate score, and successively compare the change rate of i-th of accurate rate score and (i-1)-th accurate rate score, obtain N-1 variation
Rate, judges whether this N-1 change rate is respectively less than or is equal to preset convergence threshold, if being judged as YES, convolutional neural networks
The accuracy rate of output category result has restrained, and otherwise judges not restrain, wherein N >=5, i ∈ N.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910701028.0A CN110458066B (en) | 2019-07-31 | 2019-07-31 | Age group classification method based on resting electroencephalogram data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910701028.0A CN110458066B (en) | 2019-07-31 | 2019-07-31 | Age group classification method based on resting electroencephalogram data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110458066A true CN110458066A (en) | 2019-11-15 |
| CN110458066B CN110458066B (en) | 2022-11-18 |
Family
ID=68484215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910701028.0A Active CN110458066B (en) | 2019-07-31 | 2019-07-31 | Age group classification method based on resting electroencephalogram data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458066B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112070177A (en) * | 2020-09-18 | 2020-12-11 | 中国科学院自动化研究所 | Brain-computer interface system for improving target detection generalization capability based on multitask information |
| CN117462148A (en) * | 2023-12-28 | 2024-01-30 | 慧创科仪(北京)科技有限公司 | Lead configuration device, method and storage medium for electroencephalogram detection equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160289710A1 (en) * | 2008-04-30 | 2016-10-06 | Xyleco, Inc. | Processing biomass |
| CN108143411A (en) * | 2017-12-13 | 2018-06-12 | 东南大学 | A kind of tranquillization state brain electricity analytical system towards Autism Diagnostic |
| CN108427929A (en) * | 2018-03-19 | 2018-08-21 | 兰州大学 | A kind of depressed discriminance analysis system based on tranquillization state brain network |
| CN109784242A (en) * | 2018-12-31 | 2019-05-21 | 陕西师范大学 | EEG Noise Cancellation based on one-dimensional residual error convolutional neural networks |
| CN110069958A (en) * | 2018-01-22 | 2019-07-30 | 北京航空航天大学 | A kind of EEG signals method for quickly identifying of dense depth convolutional neural networks |
-
2019
- 2019-07-31 CN CN201910701028.0A patent/CN110458066B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160289710A1 (en) * | 2008-04-30 | 2016-10-06 | Xyleco, Inc. | Processing biomass |
| CN108143411A (en) * | 2017-12-13 | 2018-06-12 | 东南大学 | A kind of tranquillization state brain electricity analytical system towards Autism Diagnostic |
| CN110069958A (en) * | 2018-01-22 | 2019-07-30 | 北京航空航天大学 | A kind of EEG signals method for quickly identifying of dense depth convolutional neural networks |
| CN108427929A (en) * | 2018-03-19 | 2018-08-21 | 兰州大学 | A kind of depressed discriminance analysis system based on tranquillization state brain network |
| CN109784242A (en) * | 2018-12-31 | 2019-05-21 | 陕西师范大学 | EEG Noise Cancellation based on one-dimensional residual error convolutional neural networks |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112070177A (en) * | 2020-09-18 | 2020-12-11 | 中国科学院自动化研究所 | Brain-computer interface system for improving target detection generalization capability based on multitask information |
| CN117462148A (en) * | 2023-12-28 | 2024-01-30 | 慧创科仪(北京)科技有限公司 | Lead configuration device, method and storage medium for electroencephalogram detection equipment |
| CN117462148B (en) * | 2023-12-28 | 2024-05-14 | 慧创科仪(北京)科技有限公司 | Lead configuration device, method and storage medium for electroencephalogram detection equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110458066B (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389059B (en) | P300 detection method based on CNN-LSTM network | |
| CN104091172B (en) | A kind of feature extracting method of Mental imagery EEG signals | |
| CN111709267B (en) | Electroencephalogram signal emotion recognition method of deep convolutional neural network | |
| CN104586387B (en) | Method for extracting and fusing time, frequency and space domain multi-parameter electroencephalogram characters | |
| CN105654063B (en) | Mental imagery brain power mode recognition methods based on the optimization of artificial bee colony time and frequency parameter | |
| CN109645990B (en) | Computer mode identification method for electroencephalogram signals of epileptics | |
| CN108960182A (en) | A kind of P300 event related potential classifying identification method based on deep learning | |
| CN106963369B (en) | Electroencephalogram relaxation degree identification method and device based on neural network model | |
| CN104166548B (en) | Deep learning method based on Mental imagery eeg data | |
| CN114052735B (en) | Deep field self-adaption-based electroencephalogram emotion recognition method and system | |
| CN103996054B (en) | Electroencephalogram feature selecting and classifying method based on combined differential evaluation | |
| CN104794368A (en) | Rolling bearing fault classifying method based on FOA-MKSVM (fruit fly optimization algorithm-multiple kernel support vector machine) | |
| CN104809434A (en) | Sleep staging method based on single-channel electroencephalogram signal ocular artifact removal | |
| CN110399846A (en) | A kind of gesture identification method based on multichannel electromyography signal correlation | |
| CN107518894A (en) | A kind of construction method and device of animal brain electricity disaggregated model | |
| CN107468260A (en) | A kind of brain electricity analytical device and analysis method for judging ANIMAL PSYCHE state | |
| CN113128552A (en) | Electroencephalogram emotion recognition method based on depth separable causal graph convolution network | |
| CN113536882B (en) | Multi-class motor imagery electroencephalogram signal feature extraction and classification method | |
| CN110458066A (en) | A kind of age bracket classification method based on tranquillization state eeg data | |
| CN110575141A (en) | Epilepsy detection method based on generation countermeasure network | |
| CN109325410B (en) | Electroencephalogram EEG (electroencephalogram) feature extraction method based on convolutional neural network | |
| Bhardwaj et al. | An analysis of integration of hill climbing in crossover and mutation operation for eeg signal classification | |
| CN112990008A (en) | Emotion recognition method and system based on three-dimensional characteristic diagram and convolutional neural network | |
| Deepthi et al. | An intelligent Alzheimer’s disease prediction using convolutional neural network (CNN) | |
| CN113076878B (en) | Constitution identification method based on attention mechanism convolution network structure |
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 |