CN112545534A - Method, device, medium and electronic equipment for determining lead electrode arrangement position - Google Patents
Method, device, medium and electronic equipment for determining lead electrode arrangement position Download PDFInfo
- Publication number
- CN112545534A CN112545534A CN202011419900.1A CN202011419900A CN112545534A CN 112545534 A CN112545534 A CN 112545534A CN 202011419900 A CN202011419900 A CN 202011419900A CN 112545534 A CN112545534 A CN 112545534A
- Authority
- CN
- China
- Prior art keywords
- lead
- data
- target
- lead data
- samples
- 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- Withdrawn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
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to a method, a device, a medium and electronic equipment for determining the arrangement position of a lead electrode, which relate to the technical field of brain wave acquisition and comprise the following steps: acquiring standard lead data of a target user; inputting the lead criteria data to a lead determination model to derive target lead electrode placement location data for the target user for at least one target lead task; the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training and supervised samples. Therefore, the lead electrode arrangement position can be selected based on the target lead task, the reasonability of lead electrode arrangement is improved, redundant brain wave data are reduced, the target lead electrode arrangement position data of the target lead task for a target user are accurately given, and the time cost can be reduced.
Description
Technical Field
The invention relates to the technical field of brain wave acquisition, in particular to a method, a device, a medium and electronic equipment for determining the arrangement position of a lead electrode.
Background
In electroencephalogram application, brain wave acquisition is the basis of all electroencephalogram applications, the brain wave acquisition is mainly realized by arranging lead electrodes on the brain, the arrangement positions of the lead electrodes are usually determined based on standard lead distribution of a 10-20 system electrode placement method, and then brain waves of brain activities can be acquired, and the electrophysiological activities of brain nerve cells on the surface of the cerebral cortex or the scalp can be generally reflected based on the acquired brain waves.
In a related scene, the lead electrodes are arranged in a standard lead distribution, namely the skull is taken as a reference, and the arrangement positions of 21 lead electrodes on the left side of the brain, the right side of the brain and the like are not determined differently due to the difference of the head circumference or the head shape of an individual. However, the brain waves acquired by the standard lead distribution include a large amount of repetition and ineffectiveness of information, which results in further reduction of the signal-to-noise ratio of the brain waves, which is inherently low in signal-to-noise ratio, and increases time cost and material cost for acquiring the brain waves. However, based on the grid search mode, a traversing method is adopted, one lead electrode is added, a lot of time is consumed, and the time cost is increased when the lead electrodes are placed under different lead combinations are tested.
Disclosure of Invention
The present invention is directed to a method, an apparatus, a medium and an electronic device for determining a lead electrode layout position, so as to solve the above-mentioned problems.
In order to achieve the above object, in a first aspect of embodiments of the present invention, there is provided a method for determining a lead electrode arrangement position, including:
acquiring standard lead data of a target user;
inputting the lead criteria data to a lead determination model to derive target lead electrode placement location data for the target user for at least one target lead task;
wherein the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training samples and supervised samples.
Preferably, the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training samples and supervised samples, including:
selecting a first number of the supervised samples for the standard lead data;
determining the training samples from the standard lead data and the first number of supervised samples, wherein the total number of sets of standard lead data is equal to the sum of a supervised set of supervised samples and a training set of training samples;
training an initial model by taking the training samples as model input to obtain predicted lead data and an original loss function aiming at the supervision samples;
selectively removing a second amount of removed lead data from the predicted lead data to yield target predicted lead data;
determining mutual information loss of the target prediction lead data and original lead data in the supervision sample, and obtaining a seed loss function according to the mutual information loss and the original loss function;
determining a degree of correlation of the removed lead data with the original lead data according to the seed loss function, and determining the target lead electrode placement location data for the target user for at least one target lead task according to the degree of correlation.
Preferably, the original loss function I (A; B) is obtained by the following resolution:
wherein, A is a supervision set formed by the supervision samples, and B is a training set formed by the training samples.
Preferably, said selectively removing a second amount of removed lead data from said predicted lead data yields target predicted lead data, comprising: randomly removing a second amount of removed lead data from the predicted lead data a plurality of times to obtain target predicted lead data after each removal;
the determining mutual information loss of the target predicted lead data and original lead data in the supervised sample, and obtaining a seed loss function according to the mutual information loss and the original loss function, includes:
determining each said mutual information loss for each said target predicted lead data and original lead data in said supervised sample;
obtaining a corresponding seed loss function according to each mutual information loss and the original loss function;
the determining a degree of correlation of the removed lead data with the original lead data according to the seed loss function comprises: determining a degree of association of the corresponding removed lead data with the original lead data according to each seed loss function;
said determining target lead electrode arrangement location data for the target user for at least one target lead task from the degree of association comprises: determining target lead electrode arrangement location data for the target user for at least one target lead task from each of the degrees of association.
In a second aspect of the embodiments of the present invention, there is provided a device for determining the lead electrode arrangement position, including:
the acquisition module is used for acquiring standard lead data of a target user;
an input module for inputting the lead criteria data to a lead determination model to derive target lead electrode placement location data for the target user for at least one target lead task;
wherein the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training samples and supervised samples.
Preferably, the lead determination model comprises:
a selection submodule for selecting a first number of the supervised samples for the standard lead data;
a determination submodule for determining the training samples from the standard lead data and the first number of supervised samples, wherein the total number of sets of standard lead data is equal to the sum of a supervised set of supervised samples and a training set of training samples;
an input sub-module for training an initial model with the training samples as model inputs to obtain predicted lead data and an original loss function for the supervised samples;
a removal sub-module for selectively removing a second amount of removed lead data from the predicted lead data to yield target predicted lead data;
a generation submodule, configured to determine mutual information loss between the target predicted lead data and original lead data in the supervised sample, and obtain a seed loss function according to the mutual information loss and the original loss function;
a correlation sub-module for determining a degree of correlation of the removed lead data with the original lead data according to the seed loss function;
an output sub-module for determining the target lead electrode arrangement location data of the target user for the at least one target lead task in dependence on the degree of correlation.
Preferably, the original loss function I (A; B) is obtained by the following resolution:
wherein, A is a supervision set formed by the supervision samples, and B is a training set formed by the training samples.
Preferably, the removal sub-module is configured to randomly select a second number of removed lead data from the predicted lead data a plurality of times to obtain target predicted lead data after each removal;
said generation sub-module for determining each said mutual information loss of each said target predicted lead data and original lead data in said supervised sample;
the correlation submodule is used for obtaining a corresponding seed loss function according to each mutual information loss and the original loss function, and determining the correlation degree of the corresponding removed lead data and the original lead data according to each seed loss function;
the output sub-module is configured to determine target lead electrode placement location data for the target user for at least one target lead task according to each of the degrees of association.
In a third aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, wherein the program is configured to, when executed by a processor, implement the steps of the method according to any one of the first aspect.
In a fourth aspect of the embodiments of the present invention, there is provided an electronic device, including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any one of the first aspect.
In the technical scheme, the standard lead data of the target user can be acquired; inputting the lead criteria data to a lead determination model to derive target lead electrode placement location data for the target user for at least one target lead task; the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training and supervised samples. Therefore, the lead electrode arrangement position can be selected based on the target lead task, the reasonability of lead electrode arrangement is improved, redundant brain wave data are reduced, the target lead electrode arrangement position data of the target lead task for a target user are accurately given, and the time cost can be reduced.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
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 principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method of determining lead electrode placement locations in accordance with an exemplary embodiment of the present invention.
FIG. 2 is a flow chart illustrating generation of target lead electrode placement location data by a lead determination model in accordance with an exemplary embodiment of the present invention.
FIG. 3 is a block diagram of a lead electrode placement location determination apparatus in accordance with an exemplary embodiment of the present invention.
FIG. 4 is a block diagram of a lead determination model in accordance with an exemplary embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
Before describing the method, the apparatus, the medium, and the electronic device for determining the lead electrode arrangement position provided by the present invention, an application scenario of the present invention will be described first. The embodiments provided by the invention can be used for processing the craniocerebral tomography images. More relevant features may be determined based on the patient's craniocerebral tomography images and the evolution of the model may be advanced based on the image features.
The inventor finds that, in the related art, lead electrode arrangement corresponding to a brain area most relevant to a task type is selected according to the task type and the corresponding relation between the brain area and the standard brain electricity arrangement. The selection of the arrangement position of the lead electrode has insufficient specificity, the problem of information redundancy still exists, and the selection method has poor universality due to the limitation of human brain partition recognition and the subtle difference of brain functional areas among individuals.
And by adopting a traversal method, one lead electrode is added, part of leads are added into the calculation process of the machine learning model randomly or according to a specified sequence based on a grid search mode, and finally selected leads are selected according to the output result of the model. Therefore, in this method, all computations of a complete machine learning algorithm are performed on each grid node or a pilot combination, and the time cost is also increased.
To this end, the present invention provides a method for determining lead electrode placement positions, which is illustrated with reference to the flow chart of the method for determining lead electrode placement positions shown in fig. 1, and comprises the following steps:
s11, acquiring standard lead data of a target user;
preferably, the standard lead data may be standard lead data of a target user acquired by arranging lead electrodes according to a standard lead distribution of 10-20 system electrode placement.
S12, inputting the lead standard data to a lead determination model to obtain target lead electrode arrangement position data of the target user for at least one target lead task;
wherein the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training samples and supervised samples.
Preferably, the target lead electrode arrangement position data is used for guiding an operator to select corresponding target lead electrode arrangement position data according to the target lead task, and then lead electrodes are arranged according to the target lead task of the target user.
Preferably, a flow chart for generating target lead electrode placement location data with reference to a lead determination model illustrated in FIG. 2 includes:
s21, selecting a first number of the supervision samples according to the standard lead data;
s22, determining the training samples according to the standard lead data and the first number of the supervised samples, wherein the total number of the sets of the standard lead data is equal to the sum of the supervised set of the supervised samples and the training set of the training samples;
s23, training an initial model by taking the training samples as model input to obtain predicted lead data and an original loss function aiming at the supervision samples;
s24, selecting a second number of removed lead data to be removed from the predicted lead data to obtain target predicted lead data;
s25, determining mutual information loss of the target prediction lead data and original lead data in the supervision sample, and obtaining a seed loss function according to the mutual information loss and the original loss function;
s26, determining the correlation degree of the removed lead data and the original lead data according to the seed loss function;
s27, determining target lead electrode placement position data of the target user for the at least one target lead task according to the relevance.
Preferably, the original loss function I (A; B) is obtained by the following resolution:
wherein, A is a supervision set formed by the supervision samples, and B is a training set formed by the training samples.
Specifically, N standard lead data of a target user are obtained, and a first number M of supervision samples are selected according to the N standard lead data to obtain a supervision set formed by the supervision samples
Obtaining N-M training samples to obtain a training set composed of the training samples
Further, a training set formed by training samples
Inputting into an initial model, training to obtain predicted lead data, and obtaining a predicted lead set (x) composed of the predicted lead dataN-M+1,xN-M+2,ΛxN) And a primary loss function
Further obtain the regression relationship of the model as
Further, a predicted lead set (x) of predicted lead dataN-M+1,xN-M+2,ΛxN) Removing n pieces of removed lead data randomly to obtain target predicted lead data, calculating final predicted output
And actual data
When the mutual information is lost, the seed loss function
Representing the original lead data in a supervised set of n removed and supervised samples
The degree of association between them.
It can be stated that the selection of M and n is arbitrary, and if M and n are taken as 1, the physical meaning is the same as the mutual information between the leads directly calculated. However, the direct calculation method cannot measure the relationship between the lead set and the lead set, or the correlation between the lead set and a single lead can only be used as one-to-one correlation estimation, so that after distribution fitting is performed through a deep learning model, the lead information is integrated, when M is greater than 1 and n is 1, the multi-to-one correlation prediction is represented, and when M is greater than 1 and n is greater than 1, the multi-to-multi correlation estimation is represented.
The selection of specific values for M and n is illustrated here for one case only. Assuming that in order to find the lowest mutual information lead of the left and right brains in a Motor Imagery (MI) task, the total number of standard lead data N is equal to 6, the set is formed into a left brain and a right brain (C6C 5C 4C 3C 2C 1), the first number M of the supervised samples is taken as 3, the set is formed into a supervised set of the right brain (C2C 4C 6), a dynamic programming method is used, firstly, N is taken as 1, the calculation results of the leads of the left brain C1C 3C 5 are respectively and sequentially removed, and then, N is taken as 23 … in sequence to obtain the optimal result. Because the model only executes the inference process, the output time of the AI method is in millisecond order, and the optimal lead arrangement result can be quickly screened out by combining the dynamic programming method.
Preferably, said selectively removing a second amount of removed lead data from said predicted lead data yields target predicted lead data, comprising: randomly removing a second amount of removed lead data from the predicted lead data a plurality of times to obtain target predicted lead data after each removal;
the determining mutual information loss of the target predicted lead data and original lead data in the supervised sample, and obtaining a seed loss function according to the mutual information loss and the original loss function, includes:
determining each said mutual information loss for each said target predicted lead data and original lead data in said supervised sample;
obtaining a corresponding seed loss function according to each mutual information loss and the original loss function;
the determining a degree of correlation of the removed lead data with the original lead data according to the seed loss function comprises: determining a degree of association of the corresponding removed lead data with the original lead data according to each seed loss function;
said determining target lead electrode arrangement location data for the target user for at least one target lead task from the degree of association comprises: determining target lead electrode arrangement location data for the target user for at least one target lead task from each of the degrees of association.
Based on the same inventive concept, an embodiment of the present invention further provides a lead electrode arrangement position determining apparatus, and fig. 3 is a block diagram of a lead electrode arrangement position determining apparatus according to an exemplary embodiment of the present invention, where the apparatus 300 includes: an acquisition module 310 and an input module 320.
The acquisition module 310 is configured to acquire standard lead data of a target user;
an input module 320 for inputting the lead criteria data to a lead determination model to derive target lead electrode placement location data for the target user for at least one target lead task;
wherein the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training samples and supervised samples.
Preferably, FIG. 4 is a block diagram of a lead determination model, shown in an exemplary embodiment of the invention, the lead determination model 400 comprising:
a selection sub-module 410 for selecting a first number of the supervised samples for the standard lead data;
a determination submodule 420 for determining the training samples from the standard lead data and the first number of the supervised samples, wherein the total number of sets of standard lead data is equal to the sum of the supervised set of supervised samples and the training set of training samples;
an input sub-module 430 for training an initial model using the training samples as model inputs to obtain predicted lead data and an original loss function for the supervised samples;
a removal sub-module 440 for selectively removing a second amount of removed lead data from the predicted lead data to obtain target predicted lead data;
a generation sub-module 450, configured to determine mutual information loss between the target predicted lead data and original lead data in the supervised sample, and obtain a seed loss function according to the mutual information loss and the original loss function;
a correlation sub-module 460 for determining a degree of correlation of the removed lead data with the original lead data according to the seed loss function;
an output sub-module 470 for determining the target lead electrode arrangement location data of the target user for the at least one target lead task from the degree of correlation.
Preferably, the original loss function I (A; B) is obtained by the following resolution:
wherein, A is a supervision set formed by the supervision samples, and B is a training set formed by the training samples.
Preferably, the removal sub-module 440 is configured to randomly select a second number of removed lead data from the predicted lead data a plurality of times to obtain target predicted lead data after each removal;
the generating sub-module 450 is configured to determine each mutual information loss of each target predicted lead data and the original lead data in the supervised sample, and obtain a corresponding seed loss function according to each mutual information loss and the original loss function;
the correlation sub-module 460 is configured to determine a correlation degree between the removed lead data and the original lead data according to each seed loss function;
the output sub-module 470 for determining the target lead electrode placement location data for the target user for at least one target lead task according to each of the degrees of association.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of any of the methods.
An embodiment of the present invention further provides an electronic device, including:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of any of the methods.
The preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, however, the present invention is not limited to the specific details of the above embodiments, and various simple modifications can be made to the technical solution of the present invention within the technical idea of the present invention, and these simple modifications are within the protective scope of the present invention.
It should be noted that the various technical features described in the above embodiments can be combined in any suitable manner without contradiction, and the invention is not described in any way for the possible combinations in order to avoid unnecessary repetition.
In addition, any combination of the various embodiments of the present invention is also possible, and the same should be considered as the content of the present invention as long as it does not depart from the gist of the present invention.
Claims (10)
1. A method of determining lead electrode placement locations, comprising:
acquiring standard lead data of a target user;
inputting the lead criteria data to a lead determination model to derive target lead electrode placement location data for the target user for at least one target lead task;
wherein the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training samples and supervised samples.
2. The determination method according to claim 1, wherein the lead determination model generates the target lead electrode arrangement location data for the target user for at least one target lead task by dividing the standard lead data into training samples and supervised samples, comprising:
selecting a first number of the supervised samples for the standard lead data;
determining the training samples from the standard lead data and the first number of supervised samples, wherein the total number of sets of standard lead data is equal to the sum of a supervised set of supervised samples and a training set of training samples;
training an initial model by taking the training samples as model input to obtain predicted lead data and an original loss function aiming at the supervision samples;
selectively removing a second amount of removed lead data from the predicted lead data to yield target predicted lead data;
determining mutual information loss of the target prediction lead data and original lead data in the supervision sample, and obtaining a seed loss function according to the mutual information loss and the original loss function;
determining a degree of correlation of the removed lead data with the original lead data according to the seed loss function;
determining target lead electrode placement location data for the target user for at least one target lead task from the degree of association.
3. The method according to claim 2, characterized in that the original loss function I (A; B) is obtained by the following resolution:
wherein, A is a supervision set formed by the supervision samples, and B is a training set formed by the training samples.
4. The method according to claim 3, wherein said selectively removing a second number of removed lead data from the predicted lead data results in target predicted lead data comprising: randomly removing a second amount of removed lead data from the predicted lead data a plurality of times to obtain target predicted lead data after each removal;
the determining mutual information loss of the target predicted lead data and original lead data in the supervised sample, and obtaining a seed loss function according to the mutual information loss and the original loss function, includes:
determining each said mutual information loss for each said target predicted lead data and original lead data in said supervised sample;
obtaining a corresponding seed loss function according to each mutual information loss and the original loss function;
the determining a degree of correlation of the removed lead data with the original lead data according to the seed loss function comprises: determining a degree of association of the corresponding removed lead data with the original lead data according to each seed loss function;
said determining target lead electrode arrangement location data for the target user for at least one target lead task from the degree of association comprises: determining target lead electrode arrangement location data for the target user for at least one target lead task from each of the degrees of association.
5. A lead electrode placement location determination apparatus, comprising:
the acquisition module is used for acquiring standard lead data of a target user;
an input module for inputting the lead criteria data to a lead determination model to derive target lead electrode placement location data for the target user for at least one target lead task;
wherein the lead determination model generates the target lead electrode placement location data for the target user for at least one target lead task by dividing the standard lead data into training samples and supervised samples.
6. The determination apparatus of claim 5, wherein the lead determination model comprises:
a selection submodule for selecting a first number of the supervised samples for the standard lead data;
a determination submodule for determining the training samples from the standard lead data and the first number of supervised samples, wherein the total number of sets of standard lead data is equal to the sum of a supervised set of supervised samples and a training set of training samples;
an input sub-module for training an initial model with the training samples as model inputs to obtain predicted lead data and an original loss function for the supervised samples;
a removal sub-module for selectively removing a second amount of removed lead data from the predicted lead data to yield target predicted lead data;
a generation submodule, configured to determine mutual information loss between the target predicted lead data and original lead data in the supervised sample, and obtain a seed loss function according to the mutual information loss and the original loss function;
a correlation sub-module for determining a degree of correlation of the removed lead data with the original lead data according to the seed loss function;
an output sub-module for determining the target lead electrode arrangement location data of the target user for the at least one target lead task in dependence on the degree of correlation.
7. The apparatus of claim 6, wherein the original loss function I (A; B) is obtained by the following resolution:
wherein, A is a supervision set formed by the supervision samples, and B is a training set formed by the training samples.
8. The apparatus according to claim 6 wherein the removal sub-module is operative to randomly select a second number of removed lead data to be removed from the predicted lead data a plurality of times resulting in target predicted lead data for each removal;
said generation sub-module for determining each said mutual information loss of each said target predicted lead data and original lead data in said supervised sample;
the correlation submodule is used for obtaining a corresponding seed loss function according to each mutual information loss and the original loss function, and determining the correlation degree of the corresponding removed lead data and the original lead data according to each seed loss function;
the output sub-module is configured to determine target lead electrode placement location data for the target user for at least one target lead task according to each of the degrees of association.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011419900.1A CN112545534A (en) | 2020-12-08 | 2020-12-08 | Method, device, medium and electronic equipment for determining lead electrode arrangement position |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011419900.1A CN112545534A (en) | 2020-12-08 | 2020-12-08 | Method, device, medium and electronic equipment for determining lead electrode arrangement position |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112545534A true CN112545534A (en) | 2021-03-26 |
Family
ID=75059340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011419900.1A Withdrawn CN112545534A (en) | 2020-12-08 | 2020-12-08 | Method, device, medium and electronic equipment for determining lead electrode arrangement position |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112545534A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113679394A (en) * | 2021-09-26 | 2021-11-23 | 华东理工大学 | Correlation-based motor imagery lead selection method and device |
| 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 |
-
2020
- 2020-12-08 CN CN202011419900.1A patent/CN112545534A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113679394A (en) * | 2021-09-26 | 2021-11-23 | 华东理工大学 | Correlation-based motor imagery lead selection method and device |
| CN113679394B (en) * | 2021-09-26 | 2022-09-27 | 华东理工大学 | Correlation-based motor imagery lead selection method and device |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2653513C (en) | Neuropsychological spatiotemporal pattern recognition | |
| CN111317468B (en) | Electroencephalogram signal classification method, electroencephalogram signal classification device, computer equipment and storage medium | |
| CN112545534A (en) | Method, device, medium and electronic equipment for determining lead electrode arrangement position | |
| CN109091138B (en) | Arrhythmia origin point judging device and mapping system | |
| Ainsworth et al. | oi-VAE: Output interpretable VAEs for nonlinear group factor analysis | |
| Yang et al. | Subject-specific channel selection using time information for motor imagery brain–computer interfaces | |
| CA2388595A1 (en) | Methods and devices for identifying patterns in biological systems and methods for uses thereof | |
| US10499823B2 (en) | Selection of electroencephalography (EEG) channels valid for determining cognitive load of a subject | |
| EP3718473A1 (en) | Intracerebral network activity estimation system, intracerebral network activity estimation method, intracerebral network activity estimation program, and learned brain activity estimation model | |
| Too et al. | Opposition based competitive grey wolf optimizer for EMG feature selection | |
| CN109498037B (en) | Brain cognition measurement method based on deep learning extraction features and multiple dimension reduction algorithm | |
| CN112508902B (en) | White matter high signal grading method, electronic equipment and storage medium | |
| CN108573227A (en) | ECG data quality evaluating method and device | |
| Grosse-Wentrup | Understanding brain connectivity patterns during motor imagery for brain-computer interfacing | |
| Fujiwara et al. | Estimating image bases for visual image reconstruction from human brain activity | |
| CN111222578A (en) | Online processing method of motor imagery EEG signal | |
| Elgharabawy et al. | Decoding of finger movement using kinematic model classification and regression model switching | |
| CN114816076A (en) | Brain-computer interface computing processing and feedback system and method | |
| Qian et al. | Cq-vae: Coordinate quantized vae for uncertainty estimation with application to disk shape analysis from lumbar spine mri images | |
| Park et al. | Improved filter selection method for filter bank common spatial pattern for eeg-based bci systems | |
| Cîmpanu et al. | Genetic feature selection for large EEG data with commutation between multiple classifiers | |
| Khorasani et al. | Agricultural Harvester Sound Classification using Convolutional Neural Networks and Spectrograms | |
| Medina et al. | Genetic algorithm for clustering temporal data-application to the detection of stress from ecg signals | |
| KR20210010769A (en) | Method and apparatus for identifying anomaly area of image using encoder | |
| Lynn et al. | Blind Noisy Image Quality Assessment Using Spatial, Frequency and Wavelet Statistical Features |
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 |
Application publication date: 20210326 |
|
| WW01 | Invention patent application withdrawn after publication |