CN113143288B - Depression brain electric nerve feedback method and system - Google Patents
Depression brain electric nerve feedback method and system Download PDFInfo
- Publication number
- CN113143288B CN113143288B CN202110274032.0A CN202110274032A CN113143288B CN 113143288 B CN113143288 B CN 113143288B CN 202110274032 A CN202110274032 A CN 202110274032A CN 113143288 B CN113143288 B CN 113143288B
- Authority
- CN
- China
- Prior art keywords
- brain
- index
- window
- rest period
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Psychiatry (AREA)
- Engineering & Computer Science (AREA)
- Educational Technology (AREA)
- Biomedical Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Physics & Mathematics (AREA)
- Child & Adolescent Psychology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Developmental Disabilities (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a depression brain electric nerve feedback method and a system, which adopt an optimized quadratic programming characteristic selection method to effectively select an optimal electrode in a global range, and reduce 64 leads to 20 leads, thereby greatly reducing subsequent calculated amount and improving the real-time performance of feedback. Then, capturing the transient variation of the amplitude of the brain electrical signal by adopting a rapid transition process method, and further calculating a structural synchronization index and a brain connection asymmetry index; finally, the brain area is adaptively adjusted based on the calculated brain connection asymmetry index, so that the cooperative control degree between the left hemisphere network and the right hemisphere network of the brain can be reflected, and the nerve mechanism of depression can be better analyzed from the index change angle.
Description
Technical Field
The invention relates to a depression electroencephalogram nerve feedback method and system, and belongs to the technical field of brain function diagnosis.
Background
Brain science has become one of the hot spots in the field of modern scientific research, and has wide application in clinical diagnosis due to its characteristics of non-invasiveness, high time resolution and the like. When the human body is stimulated by, for example, vision, hearing, touch, etc., the potential of an Electroencephalogram (EEG) will change regularly. The brain function connection is widely applied to the research of various medical problems because the brain function connection can reflect the interaction of different brain areas. Therefore, the brain function connection research and analysis of EEG not only reduces the psychological burden of the tested, but also can reflect the coordination of brain areas calculated at different times
Depression has become a major problem in global psychological problems today, but less nerve feedback is studied and clinically performed using brain functional connections.
Disclosure of Invention
The invention aims to provide a depression brain electrical nerve feedback method and system, which are used for selecting an optimal electrode by using an optimized QPFS, calculating an asymmetric index of brain connection aiming at the optimal electrode, and realizing self-adjustment of a tested person according to the displayed index.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
the invention provides a system for calculating a connecting index of an electroencephalogram nerve feedback function of depression, which comprises the following components:
selecting left and right brain optimal electrodes based on the brain electrical signals of the rest period;
carrying out rapid transition identification on the electroencephalogram signals collected by each selected optimal electrode in a non-rest period;
calculating the structure synchronization index of each optimal electrode according to the identification result;
calculating a brain connection asymmetry index based on the calculated structural synchronization index;
the brain region is adaptively adjusted based on the calculated brain connection asymmetry index.
Further, the selecting the left and right brain optimal electrodes based on the electroencephalogram signals in the rest period comprises:
in the rest period, calculating the time domain characteristics of each lead in a brain region by adopting a detrack fluctuation analysis method;
and sequencing the time domain features according to the weight from large to small by adopting an optimized quadratic programming feature selection method, finding out 10 electrodes in the calculated brain region through the optimal features, and selecting 10 electrodes of another brain region symmetrical to the 10 electrodes to be used as optimal electrodes together.
Further, the optimized quadratic programming characteristic selection method comprises the following steps:
and (3) calculating the time domain characteristics of all the leads by adopting an optimized quadratic programming characteristic selection method as follows:
where f is an n×1 matrix, f= [ I (X 1 ；C),…,I(X n ；C)] T Is a time domain feature correlation vector, n represents the number of lead time domain features, X i Representing the ith time domain feature, C is the actual number of classifications, I (X i The method comprises the steps of carrying out a first treatment on the surface of the C) Representing the measurement of X by mutual information i Is used for the correlation of the (c) and (d),
h is an n×n matrix, h= [ I (X i ；X j )] i.j＝1,…,n Is a positive semi-definite matrix, I (X i ；X j ) Representing a redundant matrix that employs a mutual information approach to represent features,
βx is the constraint term added, β is the penalty factor,
x is an n×1 matrix, x= [ x ] 1 ,x 2 ,…,x n ] T Represents relative feature weights, an
Further, the performing rapid transition identification on the electroencephalogram signals acquired by each selected optimal electrode in the non-rest period includes:
defining 40ms as the a window, 1000ms as the b window,
comparing the average value of EEG amplitude absolute values in the window a with the average value of EEG amplitude absolute values in the window b;
if the EEG average amplitude absolute value of the window a is larger than that of the window b, the last five data points of the RTP have statistical differences between the average amplitude absolute values of the window a and the window b;
the a window is a fast transition process RTP; the window a is an RTP point;
the above procedure is used to determine the RTP sequence for each 30s data segment for each optimal electrode.
Further, the RTPseg tool is used for rapid transition identification.
Further, the calculating the structural synchronization index of each optimal electrode according to the identification result includes:
the lead with the least number of RTP points in an RTP sequence formed by 10 optimal electrodes of a brain region is used as a reference lead, and each RTP point is surrounded by a window of 54 milliseconds;
if the RTP points of the remaining leads of the brain region fall within the window, a structural synchronization index ISS for EEG leads is calculated.
Further, the calculating the brain connection asymmetry index based on the calculated structural synchronization index includes:
wherein mot is an index of asymmetry of brain connection, subscripts left and right are optimal electrode numbers selected by left and right brain regions respectively, and electrodes with the same numbers are symmetrical to each other.
Further, the adaptively adjusting the brain region based on the calculated brain connection asymmetry index includes:
and carrying out self-regulation according to the brain connection asymmetry index, and continuously carrying out rapid transition identification and brain connection asymmetry index calculation on the brain electrical signal generated in the regulation process until the brain connection asymmetry index is regulated to a preset minimum range.
Furthermore, the patient with depression is taken as a tested object, and the brain electrical signals of the patient in the rest period and the non-rest period are collected;
the rest period means that the tested object does not react at all;
the non-rest period refers to the subject making a happy recall.
The invention also provides a depression brain electrical nerve feedback system, comprising:
the selection module is used for selecting left and right brain optimal electrodes based on the brain electrical signals in the rest period;
the identification module is used for carrying out rapid transition identification on the electroencephalogram signals collected by each selected optimal electrode in the non-rest period;
the calculating module is used for calculating the structure synchronization index of each optimal electrode according to the identification result; calculating a brain connection asymmetry index based on the calculated structural synchronization index;
and the adjusting module is used for adaptively adjusting the brain region based on the calculated brain connection asymmetry index.
The beneficial effects achieved by the invention are as follows:
(1) According to the invention, the optimal electrode can be effectively selected in a global range by the quadratic programming characteristic selection method, and 64 leads are reduced to 20 leads, so that the subsequent calculated amount is greatly reduced, and the real-time performance of feedback is improved. Meanwhile, the optimal electrode can be selected based on data driving according to different tested and different experimental stages, and the electrode has certain self-adaptability.
(2) According to the invention, the ISS is calculated through RTP synchronization, and the brain connection asymmetry index is further constructed according to the ISS value, so that the cooperative control degree between the left hemisphere network and the right hemisphere network of the brain can be reflected, and the nerve mechanism of depression can be better analyzed from the index change angle.
Drawings
Fig. 1 is a schematic diagram of a method for feeding back brain electrical nerve for depression according to the present invention.
Detailed Description
The invention is further described below. The following examples are only for more clearly illustrating the technical solution of the present invention and are not intended to limit the scope of the present invention.
The invention provides a depression brain electrical nerve feedback method, which comprises the following steps:
selecting left and right brain optimal electrodes based on the brain electrical signals of the rest period;
carrying out rapid transition identification on the electroencephalogram signals collected by each selected optimal electrode in a non-rest period;
calculating the structure synchronization index of each optimal electrode according to the identification result;
calculating a brain connection asymmetry index based on the calculated structural synchronization index;
the brain region is adaptively adjusted based on the calculated brain connection asymmetry index.
Specifically, selecting left and right brain optimal electrodes based on brain electrical signals of a rest period comprises:
in the rest period, calculating the time domain characteristics of each lead in a brain region (left brain region or right brain region) by adopting a detrack fluctuation analysis method;
sequencing time domain features from large to small according to a weight result by adopting an optimized Quadratic Programming Feature Selection (QPFS) method, finding out the calculated brain region through the optimal features, selecting 10 corresponding electrodes, and selecting 10 electrodes of another brain region symmetrical to the electrodes to be used as optimal electrodes together;
the time domain features of all leads are calculated using QPFS as follows:
where f is an n×1 matrix, f= [ I (X 1 ；C),…,I(X n ；C)] T Is a time domain feature correlation vector, n represents the number of lead time domain features, X i Representing the ith time domain feature, C is the actual number of classifications (for normal and improved efficiency, the system will store the data features of the existing normal and depression patients, thus its value is set to 2), I (X n The method comprises the steps of carrying out a first treatment on the surface of the C) Then X is measured by its mutual information i Is used for the correlation of the (c) and (d),
h is an n×n matrix, h= [ I (X i ；X j )] i.j＝1,…,n Is a positive semi-definite matrix, I (X i ；X j ) Representing a redundant matrix that employs a mutual information approach to represent features,
beta x is the added constraint term, beta is the penalty factor, the weight of the useful feature is increased,
x is an n×1 matrix, x= [ x ] 1 ,x 2 ,…,x n ] T Representing relative characteristic weights, the values of which are all greater than or equal to 0, and
x is calculated, and in matlab, the value thereof can be found by using quadprog ().
Specifically, the fast transition recognition of the electroencephalogram signals collected by each selected optimal electrode in the non-rest period comprises the following steps:
RTP captures the instants at which the EEG amplitude varies significantly, so its length is small and can be regarded approximately as a point. The average of the absolute values of the EEG amplitude in the a window (40 ms) is compared with the average of the absolute values of the amplitude in the b window (1000 ms).
The RTP is estimated to satisfy the following two conditions: (1) The EEG average amplitude absolute maximum value of the window a is smaller than that of the window b; (2) The last five data points of RTP need to have a statistical difference between the average amplitudes of the a-window and the b-window.
The method may determine the RTP sequence for each EEG lead for each 30s data segment.
In the invention, an RTPseg tool is adopted for rapid transition identification.
Specifically, calculating the structural synchronization index of each optimal electrode according to the identification result includes:
the leads with the least number of RTP's are taken as reference leads, each RTP is surrounded by a 54 ms window, and the RTP's of the other leads are considered to be coincident if they fall within the window. From this, the structural synchronisation index ISS for the EEG leads can be calculated, and further the ISS values with significant differences (p < 0.05) are counted for subsequent calculations.
Specifically, calculating the brain connection asymmetry index based on the calculated structural synchronization index includes:
wherein mot is an index of asymmetry of brain connection, subscripts left and right are optimal electrode numbers selected by left and right brain regions respectively, and electrodes with the same numbers are symmetrical to each other.
Specifically, performing adaptive adjustment on a brain region based on the calculated brain connection asymmetry index includes:
the tested person carries out self-regulation under the guidance of professional staff, and continuously carries out rapid transition identification and calculation of brain connection asymmetry index on the brain electrical signal generated in the regulation process until the brain connection asymmetry index is regulated to a preset minimum range.
In combination with the paradigm proposed by Mehler, the test needs to write 5-6 distractions for recall before the whole nerve feedback training begins. The first part is a training part, and under the introduction of professionals, the tested person can be familiar with a paradigm, and follow-up formal experiment contents can be better carried out. The second part is the formal experiment stage, which includes rest, happy recall, and count three contents, which will be cycled twice. The test does not need to make any reaction when resting; recall happily, namely recall according to the happy thing written before training, at the same time, the tested needs to adjust the numerical value according to the column bar appearing in the screen at the instruction of the professional; the count, i.e. the number subtracted from the count module is different each time it is required to count from 300 to 0. It should be noted that the feedback index is only required to be displayed in the happy recall section. The last part is a transmission part, the content of the part is consistent with that of the second part, but the part does not need to be circulated twice and only needs to be circulated once, and meanwhile, the feedback index does not need to be displayed in the happy recall part. Thus, the count modules total 4, subtracting 3, 4, 6, 7 at a time, respectively.
The invention also provides a depression brain electrical nerve feedback system, comprising:
the selection module is used for selecting left and right brain optimal electrodes based on the brain electrical signals in the rest period;
the identification module is used for carrying out rapid transition identification on the electroencephalogram signals collected by each selected optimal electrode in the non-rest period;
the calculating module is used for calculating the structure synchronization index of each optimal electrode according to the identification result; calculating a brain connection asymmetry index based on the calculated structural synchronization index;
and the adjusting module is used for adaptively adjusting the brain region based on the calculated brain connection asymmetry index.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (7)
1. A method of brain electrical nerve feedback for depression, comprising:
selecting left and right brain optimal electrodes based on the brain electrical signals of the rest period, comprising: in the rest period, calculating the time domain characteristics of each lead in a brain region by adopting a detrack fluctuation analysis method; sequencing time domain features according to the weight from large to small by adopting an optimized quadratic programming feature selection method, finding 10 electrodes in the calculated brain region through the optimal features, and selecting 10 electrodes of another brain region symmetrical to the 10 electrodes to be used as optimal electrodes together;
the optimized quadratic programming characteristic selection method is adopted to calculate the time domain characteristics of all leads as follows:
where f is an n×1 matrix, f= [ I (X 1 ；C),…,I(X n ；C)] T Is a time domain feature correlation vector, n represents the number of lead time domain features, X i Representing the ith time domain feature, C is the actual number of classifications, I (X i The method comprises the steps of carrying out a first treatment on the surface of the C) Representing the measurement of X by mutual information i Is used for the correlation of the (c) and (d),
h is an n×n matrix, h= [ I (X i ；X j )] i.j＝1,…,n Is a positive semi-definite matrix, I (X i ；X j ) Representing a redundant matrix that employs a mutual information approach to representing features,
βx is the constraint term added, β is the penalty factor,
x is an n×1 matrix, x= [ x ] 1 ,x 2 ,…,x n ] T Represents relative feature weights, an
Carrying out rapid transition identification on the electroencephalogram signals collected by each selected optimal electrode in a non-rest period;
calculating the structure synchronization index of each optimal electrode according to the identification result;
calculating a brain connection asymmetry index based on the calculated structural synchronization index as follows:
wherein mot is an index of brain connection asymmetry, subscripts left and right are optimal electrode numbers selected by left and right brain regions respectively, and electrodes with the same numbers are mutually symmetrical;
the brain region is adaptively adjusted based on the calculated brain connection asymmetry index.
2. The method of claim 1, wherein the fast transition recognition of the electroencephalogram signal acquired by each selected optimal electrode during the non-rest period comprises:
defining 40ms as the a window, 1000ms as the b window,
comparing the average value of EEG amplitude absolute values in the window a with the average value of EEG amplitude absolute values in the window b;
if the EEG average amplitude absolute value of the window a is larger than that of the window b, the last five data points of the RTP have statistical differences between the average amplitude absolute values of the window a and the window b;
the a window is a fast transition process RTP; the window a is an RTP point;
the above procedure is used to determine the RTP sequence for each 30s data segment for each optimal electrode.
3. The method of claim 2, wherein the rapid transition identification is performed using an RTPseg tool.
4. The method for feeding back the brain nerve for depression according to claim 2, wherein the calculating the structural synchronization index of each optimal electrode according to the recognition result comprises:
in an RTP sequence formed by 10 optimal electrodes of a brain region, a lead with the least number of RTP points is used as a reference lead, and each RTP point of the reference lead is surrounded by a window of 54 milliseconds;
if the RTP points of the remaining leads of the brain region fall within the window, a structural synchronization index ISS for EEG leads is calculated.
5. The method of claim 1, wherein the adaptively adjusting the brain region based on the calculated brain connection asymmetry index comprises:
and carrying out self-regulation according to the brain connection asymmetry index, and continuously carrying out rapid transition identification and brain connection asymmetry index calculation on the brain electrical signal generated in the regulation process until the brain connection asymmetry index is regulated to a preset minimum range.
6. The method for feeding back the brain electrical nerve of the depression according to any one of claims 1 to 5, wherein the patient with the depression is taken as a tested object, and brain electrical signals of the patient with the depression are collected in a rest period and a non-rest period;
the rest period means that the tested object does not react at all;
the non-rest period refers to the subject making a happy recall.
7. A depressive brain electrical nerve feedback system for implementing the depressive brain electrical nerve feedback method of claim 1, the system comprising:
the selection module is used for selecting left and right brain optimal electrodes based on the brain electrical signals in the rest period;
the identification module is used for carrying out rapid transition identification on the electroencephalogram signals collected by each selected optimal electrode in the non-rest period;
the calculating module is used for calculating the structure synchronization index of each optimal electrode according to the identification result; calculating a brain connection asymmetry index based on the calculated structural synchronization index;
and the adjusting module is used for adaptively adjusting the brain region based on the calculated brain connection asymmetry index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110274032.0A CN113143288B (en) | 2021-03-15 | 2021-03-15 | Depression brain electric nerve feedback method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110274032.0A CN113143288B (en) | 2021-03-15 | 2021-03-15 | Depression brain electric nerve feedback method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113143288A CN113143288A (en) | 2021-07-23 |
| CN113143288B true CN113143288B (en) | 2023-06-06 |
Family
ID=76887353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110274032.0A Active CN113143288B (en) | 2021-03-15 | 2021-03-15 | Depression brain electric nerve feedback method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113143288B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113855023B (en) * | 2021-10-26 | 2023-07-04 | 深圳大学 | Iterative tracing-based lower limb movement BCI electrode selection method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5280793A (en) * | 1992-05-13 | 1994-01-25 | Rosenfeld J Peter | Method and system for treatment of depression with biofeedback using left-right brain wave asymmetry |
| US5450855A (en) * | 1992-05-13 | 1995-09-19 | Rosenfeld; J. Peter | Method and system for modification of condition with neural biofeedback using left-right brain wave asymmetry |
| CN102542283A (en) * | 2010-12-31 | 2012-07-04 | 北京工业大学 | Optimal electrode assembly automatic selecting method of brain-machine interface |
| CN102609618A (en) * | 2012-02-07 | 2012-07-25 | 清华大学 | Method for calculating brain asymmetric index based on information flow gain |
| CN106073708A (en) * | 2016-06-01 | 2016-11-09 | 哈尔滨工业大学深圳研究生院 | A kind of EEG feature extraction and means of interpretation |
| WO2020060111A1 (en) * | 2018-09-17 | 2020-03-26 | 인제대학교 산학협력단 | Method for predicting suicidal behavior in major depressive disorders based on frontal alpha asymmetry and frontal lobe activity asymmetry |
| CN111568421A (en) * | 2020-04-30 | 2020-08-25 | 深圳市神经科学研究院 | Method, system, equipment and storage medium for detecting asymmetry of left and right hemispheres of brain |
-
2021
- 2021-03-15 CN CN202110274032.0A patent/CN113143288B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5280793A (en) * | 1992-05-13 | 1994-01-25 | Rosenfeld J Peter | Method and system for treatment of depression with biofeedback using left-right brain wave asymmetry |
| US5450855A (en) * | 1992-05-13 | 1995-09-19 | Rosenfeld; J. Peter | Method and system for modification of condition with neural biofeedback using left-right brain wave asymmetry |
| CN102542283A (en) * | 2010-12-31 | 2012-07-04 | 北京工业大学 | Optimal electrode assembly automatic selecting method of brain-machine interface |
| CN102609618A (en) * | 2012-02-07 | 2012-07-25 | 清华大学 | Method for calculating brain asymmetric index based on information flow gain |
| CN106073708A (en) * | 2016-06-01 | 2016-11-09 | 哈尔滨工业大学深圳研究生院 | A kind of EEG feature extraction and means of interpretation |
| WO2020060111A1 (en) * | 2018-09-17 | 2020-03-26 | 인제대학교 산학협력단 | Method for predicting suicidal behavior in major depressive disorders based on frontal alpha asymmetry and frontal lobe activity asymmetry |
| CN111568421A (en) * | 2020-04-30 | 2020-08-25 | 深圳市神经科学研究院 | Method, system, equipment and storage medium for detecting asymmetry of left and right hemispheres of brain |
Non-Patent Citations (6)
| Title |
|---|
| Andrew A. Fingelkurts 等.Impaired Functional Connectivity at EEG Alpha and Theta Frequency Bands in Major Depression.《Wiley InterScience》.2006, * |
| Effective Global Approaches for Mutual Information Based Feature Selection;Nguyen Xuan Vinh 等;《ACM》;20140827;第1-3章 * |
| Impaired Functional Connectivity at EEG Alpha and Theta Frequency Bands in Major Depression;Andrew A. Fingelkurts 等;《Wiley InterScience》;20060615;正文第249-253页 * |
| Nonstationary nature of the brain activity as revealed by EEG/MEG: Methodological, practical and conceptual challenges;Alexander Ya. Kaplan 等;《Elsevier》;20050728;全文 * |
| Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI;Mahnaz Arvaneh等;《IEEE》;20110630;全文 * |
| 基于互信息的属性选择算法研究;郭衍奎;《北京交通大学 硕士学位论文》;20151015;第4-5章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113143288A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Citi et al. | P300-based BCI mouse with genetically-optimized analogue control | |
| Kira et al. | A neural implementation of Wald’s sequential probability ratio test | |
| Sorger et al. | A real-time fMRI-based spelling device immediately enabling robust motor-independent communication | |
| Vidal | Real-time detection of brain events in EEG | |
| Aydin et al. | P300-based asynchronous brain computer interface for environmental control system | |
| CN109091138B (en) | Arrhythmia origin point judging device and mapping system | |
| CN109190682B (en) | Method and equipment for classifying brain abnormalities based on 3D nuclear magnetic resonance image | |
| Jalali et al. | Atrial fibrillation prediction with residual network using sensitivity and orthogonality constraints | |
| CN114732419B (en) | Exercise electrocardiogram data analysis method and device, computer equipment and storage medium | |
| JP2010502308A (en) | Automatic noise reduction system for predicting death due to arrhythmia | |
| Gallego-Carracedo et al. | Local field potentials reflect cortical population dynamics in a region-specific and frequency-dependent manner | |
| CN113143288B (en) | Depression brain electric nerve feedback method and system | |
| WO2015164300A1 (en) | Biomedical system variably configured based on estimation of information content of input signals | |
| CN114732418A (en) | High-frequency QRS waveform curve analysis method and device, computer equipment and storage medium | |
| CN111445978A (en) | Motion scheme reactivity prediction model, modeling method and electronic equipment | |
| Cabiati et al. | Computer analysis of saccadic eye movements | |
| Lee et al. | Decoding finger tapping with the affected hand in chronic stroke patients during motor imagery and execution | |
| Ogino et al. | Semi-supervised learning for auditory event-related potential-based brain–computer interface | |
| CN117133404B (en) | Intelligent rehabilitation nursing device to thorax export syndrome | |
| Reutter et al. | Individual patterns of visual exploration predict the extent of fear generalization in humans. | |
| CN115349833B (en) | Real-time functional magnetic resonance nerve feedback regulation and control system and device based on decoding | |
| Aydin et al. | Region based Brain Computer Interface for a home control application | |
| US11752349B2 (en) | Meeting brain-computer interface user performance expectations using a deep neural network decoding framework | |
| JPH11137530A (en) | Detector for characteristic brain electromagnetic-wave | |
| CN114742113B (en) | High-frequency QRS waveform curve analysis method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |