CN114098765A - Method and device for extracting parameters and features of multi-channel high-frequency brain wave coupled brain network - Google Patents
Method and device for extracting parameters and features of multi-channel high-frequency brain wave coupled brain network Download PDFInfo
- Publication number
- CN114098765A CN114098765A CN202111395249.3A CN202111395249A CN114098765A CN 114098765 A CN114098765 A CN 114098765A CN 202111395249 A CN202111395249 A CN 202111395249A CN 114098765 A CN114098765 A CN 114098765A
- Authority
- CN
- China
- Prior art keywords
- brain
- sub
- brain network
- network
- frequency
- 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.)
- Pending
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000008878 coupling Effects 0.000 claims abstract description 90
- 238000010168 coupling process Methods 0.000 claims abstract description 90
- 238000005859 coupling reaction Methods 0.000 claims abstract description 90
- 230000001360 synchronised effect Effects 0.000 claims abstract description 55
- 239000011159 matrix material Substances 0.000 claims abstract description 54
- 238000000605 extraction Methods 0.000 claims description 10
- 230000003595 spectral effect Effects 0.000 claims description 6
- 230000000638 stimulation Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 5
- 238000010276 construction Methods 0.000 abstract description 2
- 230000010354 integration Effects 0.000 abstract description 2
- 238000011160 research Methods 0.000 abstract description 2
- 230000001149 cognitive effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 230000003925 brain function Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000007177 brain activity Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000003920 cognitive function Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/372—Analysis of electroencephalograms
-
- 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
Abstract
The invention discloses a method and a device for extracting parameters and characteristics of a multi-channel high-frequency brain wave coupled brain network, belonging to the technical field of brain-computer interfaces and comprising the following steps: collecting electroencephalogram signals of a tested object and extracting sub-frequency bands from the electroencephalogram signals; acquiring a sub-band synchronous coupling characteristic matrix according to the sub-band; constructing a brain network by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix and extracting brain network parameters from the brain network; establishing a brain network characteristic parameter set through weighted summation of brain network parameters; the device comprises an acquisition unit, a brain network construction unit and a setting unit, improves the signal-to-noise ratio of components related to tasks in electroencephalogram signals, improves the accuracy of target identification under rapid sequence visual presentation, establishes the internal relation between brain networks and electroencephalogram response under the rapid sequence visual presentation task state, and can also help to research the brain resource integration mode in the brain cognitive behavior process.
Description
Technical Field
The invention belongs to the technical field of brain-computer interfaces, and particularly relates to a method and a device for extracting parameters and characteristics of a multi-channel high-frequency brain wave coupled brain network.
Background
RSVP-BCI is a human-computer hybrid brain-computer interface (BCI) system that implements image recognition using a Rapid Serial Visual Presentation (RSVP) experimental paradigm, which implements recognition and classification of target electroencephalograms by detecting the P300 component in electroencephalograms (EEG), and combines high resolution of the human Visual system and abstract thinking capability of the human brain with ultrahigh computing power of a computer, implementing an information processing system that has both high robustness and high efficiency.
RSVP-BCI image recognition systems typically comprise three parts: signal preprocessing, feature extraction and classifier classification. The extraction of the electroencephalogram signal features is a very important part in all BCI systems, and the quality of the extracted electroencephalogram features directly influences the accuracy of the system for decoding the electroencephalogram signals.
Analyzing the synchronous characteristics among multi-channel electroencephalogram signals is an important way for understanding the interconnection mechanism of different brain areas, and the method can be used for researching the brain function on a large scale. By analyzing the synchronous coupling state of the multi-channel high-frequency electroencephalogram signals under a specific task, the corresponding relation between the brain function and the coupling state is mined, and finally the mapping from the coupling characteristic to the task type is obtained, which is the basic principle of decoding brain activities based on the synchronous coupling characteristic of the multi-channel high-frequency electroencephalogram signals. The RSVP paradigm can induce event-related potentials related to cognitive functions of the brain, information transmission and function integration of different brain areas exist in the process, and synchronous coupling oscillation of brain electrical signals of different brain areas can be induced.
The invention provides a brain network parameter feature extraction method based on multi-channel high-frequency electroencephalogram coupling under rapid sequence visual presentation by analyzing the phase-locked value and consistency of multi-channel electroencephalogram signals according to the synchronous coupling oscillation phenomenon of RSVP electroencephalogram signals, and the accuracy of target identification under a rapid sequence visual presentation paradigm is improved by utilizing the mapping from the coupling features to task types.
Disclosure of Invention
In order to solve the defects, the invention provides a method and a device for extracting parameters and characteristics of a multi-channel high-frequency brain wave coupled brain network.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a method for extracting parameters and features of a multi-channel high-frequency brain wave coupled brain network comprises the following steps:
collecting electroencephalogram signals of a tested object and extracting sub-frequency bands from the electroencephalogram signals;
acquiring a sub-band synchronous coupling feature matrix according to the sub-band, wherein the sub-band synchronous coupling feature matrix is acquired by calculating the phase locking value and consistency between the sub-band synchronous coupling feature and the channel;
constructing a brain network by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix and extracting brain network parameters from the brain network;
and establishing a brain network characteristic parameter set through weighted summation of the brain network parameters.
The method is further improved in that: the acquiring of the brain electrical signals of the subject and the extracting of the sub-frequency bands from the brain electrical signals of the subject comprise: decomposing EEG signal X into N by using filters with different bandwidthsfSub-band signal Xf,f=1,2,…,Nf。
The method is further improved in that: the acquiring of the sub-band synchronous coupling feature matrix according to the sub-band, wherein the acquiring of the sub-band synchronous coupling feature matrix by calculating the phase-locked value and consistency between the sub-band synchronous coupling feature and the channel comprises: wherein, the phase locking value phi (t) has the following general formula:
where C is a fixed constant, frequency parameters m, n,andis the instantaneous phase, x, of the two channel signals at time t1And x2When the phase of (a) is in a synchronous state,
the consistency formula is as follows:
in the formula, sxxAnd syyIs the self-power spectral density, s, of channels x and y at frequency fxy(f) For channel x and y cross-power spectral density, cxyThe value range is [ 01 ] for the consistency between two channels]。
The method is further improved in that: the method for constructing the brain network by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix and extracting brain network parameters from the brain network comprises the following steps: and setting the coupling value with the coupling value larger than the threshold value in the sub-frequency synchronous coupling characteristic matrix as 1 by setting proper threshold value sparsification, and regarding the coupling value with the coupling value smaller than the threshold value as 0 as invalid connection.
The method is further improved in that: the establishing of the brain network characteristic parameter set through the weighted summation of the brain network parameters comprises the following steps: the information transmission process, the processing efficiency and the RSVP-EEG relation formula for describing the coupling characteristics under the two types of stimulation tasks according to the three network attributes of the clustering coefficient CC, the average function connection MFC and the global efficiency GE are as follows:
in the formula, CijFor the value of the network connection between any two nodes in the network, dijThe length of the shortest path between two nodes, n is the number of nodes in the network, and theta represents the set of all nodes.
The brain network parameter feature extraction device of multichannel high frequency brain wave coupling includes:
the acquisition unit is used for acquiring an electroencephalogram signal of a tested object and extracting a sub-band from the electroencephalogram signal;
the acquisition unit is used for acquiring a sub-band synchronous coupling feature matrix according to the sub-band, wherein the sub-band synchronous coupling feature matrix is acquired by calculating the phase locking value and consistency between the sub-band synchronous coupling feature and the channel;
the brain network constructing unit is used for constructing a brain network by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix;
and the establishing unit is used for weighting and summing the brain network parameters extracted from the brain network and establishing a brain network characteristic parameter set.
The device is further improved in that: the acquisition unit is also used for decomposing the EEG signal X into N by using filters with different bandwidthsfSub-band signal Xf,f=1,2,…,Nf。
The device is further improved in that: the device also comprises a setting unit, which is used for setting the coupling value of the coupling value larger than the threshold value in the sub-frequency synchronous coupling characteristic matrix as 1 through setting suitable threshold value sparsification, and regarding the coupling value smaller than the threshold value as 0, and regarding the coupling value as invalid connection.
Due to the adoption of the technical scheme, the invention has the technical progress that:
the method utilizes the mapping from the electroencephalogram coupling characteristics to the task types, improves the signal to noise ratio of components related to the tasks in the electroencephalogram signals, and improves the accuracy of target identification under the condition of rapid sequence visual presentation.
Drawings
FIG. 1 is a flow chart of electroencephalogram feature extraction according to the present invention;
FIG. 2 is a RSVP test image display process;
FIG. 3 is a graph showing the mean AUC values of ten subjects tested according to the example of the present invention;
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings:
the invention firstly divides gamma EEG signals into a plurality of frequency bands, then carries out phase-locked value and consistency synchronous coupling analysis on the signals of each frequency band, then uses the phase-locked value matrix and consistency matrix of the signals of each frequency band as connection matrix, constructs brain network after thinning the connection matrix, extracts the clustering coefficient, network efficiency and average function connection of the brain network as brain network characteristic parameters, and finally connects the weighted summation of the brain network characteristic parameters LDA of each frequency band in series as the final classification characteristic specific method as follows:
the invention provides a method for extracting parameters and characteristics of a brain network coupled by multichannel high-frequency brain waves, which comprises the following steps as shown in figure 1:
collecting electroencephalogram signals of a tested object and extracting sub-frequency bands from the electroencephalogram signals;
acquiring a sub-band synchronous coupling feature matrix according to the sub-band, wherein the sub-band synchronous coupling feature matrix is acquired by calculating the phase locking value and consistency between the sub-band synchronous coupling feature and the channel;
constructing a brain network by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix and extracting brain network parameters from the brain network;
and establishing a brain network characteristic parameter set through weighted summation of the brain network parameters.
Specifically, the method utilizes the mapping of electroencephalogram coupling characteristics to task types, improves the signal to noise ratio of components related to tasks in electroencephalogram signals, and improves the accuracy of target identification under rapid sequence visual presentation.
Further, the step of collecting the brain electrical signal of the tested object and extracting the sub-frequency band from the brain electrical signal comprises the following steps:
decomposing EEG signal X into N by using filters with different bandwidthsfSub-band signal Xf,f=1,2,…,Nf. Number of sub-bands N in the present embodimentfMay be set to 5. Each trial data is extracted from the electroencephalogram channel within 0-1s after the stimulation is started. The frequency range covers the whole gamma frequency band and is divided into five sub-bands of 30-40Hz, 40-50Hz, 50-60Hz, 60-70Hz and 70-80Hz by a band-pass filter. And each sub-band signal is divided and filtered by adopting a zero-phase Chebyshev I-type IIR digital low-pass filter.
Further, acquiring a sub-band synchronous coupling feature matrix according to the sub-band, wherein the acquiring of the sub-band synchronous coupling feature matrix by calculating a phase-locked value and consistency between the sub-band synchronous coupling feature and the channel comprises the following steps:
wherein, the phase locking value phi (t) has the following general formula:
where C is a fixed constant, frequency parameters m, n,andis the instantaneous phase, x, of the two channel signals at time t1And x2When the phase of (a) is in a synchronous state,
the consistency formula is as follows:
in the formula, sxxAnd syyIs the self-power spectral density, s, of channels x and y at frequency fxy(f) For channel x and y cross-power spectral density, cxyThe value range is [ 01 ] for the consistency between two channels]。
Further, the brain network is constructed by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix and brain network parameters are extracted from the brain network by the method comprising the following steps of:
setting a coupling value with a coupling value larger than a threshold value in a sub-frequency synchronous coupling characteristic matrix as 1 by setting appropriate threshold value sparsification, and regarding the coupling value with the coupling value smaller than the threshold value as effective connection, and regarding the coupling value with the coupling value smaller than the threshold value as 0;
since there is no connection relationship of the channel nodes themselves, the node-self coupling value is set to 0, that is, the diagonal element of the coupling matrix is set to 0. The threshold is selected by adopting a multi-time cross validation method, namely, the features are calculated under different thresholds to carry out multi-time cross classification validation, and the corresponding threshold when the classification accuracy is highest is selected. And the thinned subband coupling matrix is used as a connection matrix to construct a brain network.
Further, the establishing of the brain network characteristic parameter set through the weighted summation of the brain network parameters comprises the following steps:
the information transmission process, the processing efficiency and the RSVP-EEG relation formula for describing the coupling characteristics under the two types of stimulation tasks according to the three network attributes of the clustering coefficient CC, the average function connection MFC and the global efficiency GE are as follows:
in the formula, CijFor the value of the network connection between any two nodes in the network, dijThe length of the shortest path between two nodes, n is the number of nodes in the network, and theta represents the set of all nodes.
In fig. 2, an RSVP experimental image display process applied in the embodiment of the present invention is based on a psycopy building experimental platform, collected images are presented to a tested subject at a speed lasting for about 100ms each, in order to prevent a sudden loss of attention, a time interval between two target images is ensured to be greater than 500ms in the whole experimental process, and an observation image in fig. 2 is a schematic diagram of a target image and a non-target image. There were 100 trials of one experiment, first presenting a white '+' gaze point in the center of the screen, then 3, 2, 1 countdown in the screen presentation, then pictures presented randomly in the center of the screen. And synchronously recording the electroencephalogram data as soon as the countdown on the screen is finished until the last picture of the experiment is displayed and the record is finished, and simultaneously recording the appearance moment of each picture. Wherein, the target stimulation appears 4-7 times at random, and the non-target stimulation appears 93-96 times.
In order to verify the real classification performance of the electroencephalogram signal feature extraction and classification research in a rapid sequence image presentation (RSVP) experiment, in the machine learning theory, the classification result of an unbalanced sample is generally evaluated by using the size of the Area (AUC) Under the Receiver Operating characterization Curve (ROC), and the value range of the AUC is between 0.5 and 1. The more the AUC is close to 1.0, the higher the detection method effect is; when the value is 0.5, the effect is the worst. Fig. 3 shows the average AUC values of ten tested samples provided in the example of the present invention, where the average AUC values all reach above 0.9, which indicates that the method of the present invention can be used for feature extraction of rapid sequence image presentation (RSVP) electroencephalogram signals, and can effectively identify target images and non-target images.
The device of the method for extracting the brain network parameter features based on the multi-channel high-frequency brain wave coupling comprises the following steps: the device comprises an acquisition unit, a brain network construction unit and an establishment unit.
The acquisition unit is used for acquiring an electroencephalogram signal of a tested object and extracting a sub-band from the electroencephalogram signal; the acquisition unit is used for acquiring a sub-band synchronous coupling feature matrix according to the sub-band, wherein the sub-band synchronous coupling feature matrix is acquired by calculating the phase locking value and consistency between the sub-band synchronous coupling feature and the channel; the brain network constructing unit is used for constructing a brain network by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix; the establishing unit is used for weighting and summing the brain network parameters extracted from the brain network and establishing a brain network characteristic parameter set.
Furthermore, the acquisition unit is also used for decomposing the EEG signal X into N by using filters with different bandwidthsfSub-band signal Xf,f=1,2,…,Nf。
Further, the device further comprises a setting unit, which is used for setting the coupling value of the sub-frequency synchronous coupling characteristic matrix, which is greater than the threshold value, as 1 through setting suitable threshold value sparsification, and regarding the coupling value of the sub-frequency synchronous coupling characteristic matrix as an effective connection, and regarding the coupling value of the sub-frequency synchronous coupling characteristic matrix, which is less than the threshold value, as 0, and regarding the coupling value as an ineffective connection.
The above-mentioned embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solution of the present invention by those skilled in the art should fall within the protection scope defined by the claims of the present invention without departing from the spirit of the present invention.
Claims (8)
1. The method for extracting the parameters and the characteristics of the brain network coupled by the multichannel high-frequency brain waves is characterized by comprising the following steps of:
collecting electroencephalogram signals of a tested object and extracting sub-frequency bands from the electroencephalogram signals;
acquiring a sub-band synchronous coupling feature matrix according to the sub-band, wherein the sub-band synchronous coupling feature matrix is acquired by calculating the phase locking value and consistency between the sub-band synchronous coupling feature and the channel;
constructing a brain network by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix and extracting brain network parameters from the brain network;
and establishing a brain network characteristic parameter set through weighted summation of the brain network parameters.
2. The method for extracting parameters and features of a multi-channel high-frequency brain wave-coupled brain network according to claim 1, wherein the acquiring brain electrical signals of a subject and extracting sub-bands therefrom comprises: decomposing EEG signal X into N by using filters with different bandwidthsfSub-band signal Xf,f=1,2,…,Nf。
3. The method for extracting parameters of a multi-channel high-frequency brain wave coupled brain network according to claim 1, wherein the obtaining a sub-band synchronous coupling feature matrix according to sub-bands, wherein the obtaining of the sub-band synchronous coupling feature matrix by calculating phase-locked values and consistency between sub-band synchronous coupling features and channels comprises: wherein, the phase locking value phi (t) has the following general formula:
where C is a fixed constant, frequency parameters m, n,andis the instant of two channel signals at time tPhase, x1And x2When the phase of (a) is in a synchronous state,
the consistency formula is as follows:
in the formula, sxxAnd syyIs the self-power spectral density, s, of channels x and y at frequency fxy(f) For channel x and y cross-power spectral density, cxyThe value range is [ 01 ] for the consistency between two channels]。
4. The method for extracting parameters of a multi-channel high-frequency brain wave coupled brain network according to claim 1, wherein the constructing the brain network by thinning out the subband synchronous coupling feature matrix as a connection matrix and extracting parameters of the brain network comprises: and setting the coupling value with the coupling value larger than the threshold value in the sub-frequency synchronous coupling characteristic matrix as 1 by setting proper threshold value sparsification, and regarding the coupling value with the coupling value smaller than the threshold value as 0 as invalid connection.
5. The method for extracting parameters of a brain network coupled with multichannel high-frequency brain waves according to claim 1, wherein the establishing a set of parameters of the brain network parameters through weighted summation of the parameters of the brain network comprises: the information transmission process, the processing efficiency and the RSVP-EEG relation formula for describing the coupling characteristics under the two types of stimulation tasks according to the three network attributes of the clustering coefficient CC, the average function connection MFC and the global efficiency GE are as follows:
in the formula, CijFor the value of the network connection between any two nodes in the network, dijThe length of the shortest path between two nodes, n is the number of nodes in the network, and theta represents the set of all nodes.
6. The brain network parameter feature extraction device of multichannel high frequency brain wave coupling, its characterized in that includes:
the acquisition unit is used for acquiring an electroencephalogram signal of a tested object and extracting a sub-band from the electroencephalogram signal;
the acquisition unit is used for acquiring a sub-band synchronous coupling feature matrix according to the sub-band, wherein the sub-band synchronous coupling feature matrix is acquired by calculating the phase locking value and consistency between the sub-band synchronous coupling feature and the channel;
the brain network constructing unit is used for constructing a brain network by taking the sparse subband synchronous coupling characteristic matrix as a connection matrix;
and the establishing unit is used for weighting and summing the brain network parameters extracted from the brain network and establishing a brain network characteristic parameter set.
7. The multi-channel high-frequency brain wave coupled brain network parameter feature extraction device of claim 6, wherein the collection unit is further configured to decompose the brain electrical signal X into N by using filters with different bandwidthsfSub-band signal Xf,f=1,2,…,Nf。
8. The multi-channel high-frequency brain wave coupled brain network parameter feature extraction device according to claim 7, further comprising a setting unit configured to set a coupling value greater than a threshold in the sub-frequency synchronous coupling feature matrix to 1 for valid connection and set a coupling value less than the threshold to 0 for invalid connection by setting a suitable threshold for thinning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111395249.3A CN114098765A (en) | 2021-11-23 | 2021-11-23 | Method and device for extracting parameters and features of multi-channel high-frequency brain wave coupled brain network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111395249.3A CN114098765A (en) | 2021-11-23 | 2021-11-23 | Method and device for extracting parameters and features of multi-channel high-frequency brain wave coupled brain network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114098765A true CN114098765A (en) | 2022-03-01 |
Family
ID=80439941
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111395249.3A Pending CN114098765A (en) | 2021-11-23 | 2021-11-23 | Method and device for extracting parameters and features of multi-channel high-frequency brain wave coupled brain network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114098765A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114652331A (en) * | 2022-03-08 | 2022-06-24 | 山东大学 | System for testing and evaluating coordination between accurate grasping muscles based on mixed reality |
CN116058851A (en) * | 2023-02-20 | 2023-05-05 | 之江实验室 | Electroencephalogram data processing method, electroencephalogram data processing device, electroencephalogram data analysis system, electronic device and electroencephalogram data processing medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190328996A1 (en) * | 2018-04-30 | 2019-10-31 | Korea University Research And Business Foundation | Method and system for inducing sleep |
CN111712193A (en) * | 2018-02-14 | 2020-09-25 | 塞勒尼恩有限公司 | Apparatus and method for electroencephalography measurements |
CN113229818A (en) * | 2021-01-26 | 2021-08-10 | 南京航空航天大学 | Cross-subject personality prediction system based on electroencephalogram signals and transfer learning |
-
2021
- 2021-11-23 CN CN202111395249.3A patent/CN114098765A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111712193A (en) * | 2018-02-14 | 2020-09-25 | 塞勒尼恩有限公司 | Apparatus and method for electroencephalography measurements |
US20190328996A1 (en) * | 2018-04-30 | 2019-10-31 | Korea University Research And Business Foundation | Method and system for inducing sleep |
CN113229818A (en) * | 2021-01-26 | 2021-08-10 | 南京航空航天大学 | Cross-subject personality prediction system based on electroencephalogram signals and transfer learning |
Non-Patent Citations (1)
Title |
---|
JALILI M等: "Synchronization of EEG: Bivariate and Multivariate Measures", IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 15 October 2014 (2014-10-15), pages 212 - 221 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114652331A (en) * | 2022-03-08 | 2022-06-24 | 山东大学 | System for testing and evaluating coordination between accurate grasping muscles based on mixed reality |
CN116058851A (en) * | 2023-02-20 | 2023-05-05 | 之江实验室 | Electroencephalogram data processing method, electroencephalogram data processing device, electroencephalogram data analysis system, electronic device and electroencephalogram data processing medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110069958B (en) | Electroencephalogram signal rapid identification method of dense deep convolutional neural network | |
CN106909784B (en) | Epileptic electroencephalogram (eeg) identification device based on two-dimentional time-frequency image depth convolutional neural networks | |
CN111062250B (en) | Multi-subject motor imagery electroencephalogram signal identification method based on deep feature learning | |
CN114098765A (en) | Method and device for extracting parameters and features of multi-channel high-frequency brain wave coupled brain network | |
CN112120694B (en) | Motor imagery electroencephalogram signal classification method based on neural network | |
Dodia et al. | An efficient EEG based deceit identification test using wavelet packet transform and linear discriminant analysis | |
KR20190035368A (en) | Method and Apparatus for Recognizing Emotion Based on Image Converted from Brain Signal | |
US20070225932A1 (en) | Methods, systems and computer program products for extracting paroxysmal events from signal data using multitaper blind signal source separation analysis | |
KR101987225B1 (en) | Method and apparatus for measuring vr sickness | |
KR20190033972A (en) | Method and apparatus for an automatic artifact removal of EEG based on a deep leaning algorithm | |
CN110991406A (en) | RSVP electroencephalogram characteristic-based small target detection method and system | |
WO2022166401A1 (en) | Eemd-pca-based method and device for removing motion artifact from eeg signal | |
CN113331845A (en) | Electroencephalogram signal feature extraction and accuracy discrimination method based on continuous coherence | |
Saini et al. | Effective automated method for detection and suppression of muscle artefacts from single‐channel EEG signal | |
CN112450947A (en) | Dynamic brain network analysis method for emotional arousal degree | |
CN111428601B (en) | P300 signal identification method, device and storage medium based on MS-CNN | |
CN111142668B (en) | Interaction method based on Wi-Fi fingerprint positioning and activity gesture joint recognition | |
Lan et al. | Estimating cognitive state using EEG signals | |
CN113143291B (en) | Electroencephalogram feature extraction method under rapid sequence visual presentation | |
CN115919315A (en) | Cross-subject fatigue detection deep learning method based on EEG channel multi-scale parallel convolution | |
WO2021143538A1 (en) | Wearable workload measurement method, system and apparatus, and storage medium | |
CN114795247A (en) | Electroencephalogram signal analysis method and device, electronic equipment and storage medium | |
CN115089162A (en) | Breathing rate detection method and device based on unmanned aerial vehicle video | |
CN109670479B (en) | Intelligent monitoring method and system | |
CN113180663A (en) | Emotion recognition method and system based on convolutional neural network |
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 |