CN1317624C - Method of extracting brain machine interface control signa based on instantaneous vision sense induced electric potential - Google Patents
Method of extracting brain machine interface control signa based on instantaneous vision sense induced electric potential Download PDFInfo
- Publication number
- CN1317624C CN1317624C CNB2003101210333A CN200310121033A CN1317624C CN 1317624 C CN1317624 C CN 1317624C CN B2003101210333 A CNB2003101210333 A CN B2003101210333A CN 200310121033 A CN200310121033 A CN 200310121033A CN 1317624 C CN1317624 C CN 1317624C
- Authority
- CN
- China
- Prior art keywords
- brain
- signal
- computer interface
- visual
- vep
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 210000004556 brain Anatomy 0.000 title claims abstract description 13
- 230000000007 visual effect Effects 0.000 claims abstract description 57
- 230000000638 stimulation Effects 0.000 claims abstract description 25
- 230000001052 transient effect Effects 0.000 claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 239000000284 extract Substances 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 210000004761 scalp Anatomy 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims abstract description 3
- 230000004936 stimulating effect Effects 0.000 claims description 20
- 238000000354 decomposition reaction Methods 0.000 claims description 11
- 238000002474 experimental method Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 8
- 230000000750 progressive effect Effects 0.000 claims description 7
- 230000003321 amplification Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000003909 pattern recognition Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 abstract description 3
- 238000012935 Averaging Methods 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 241000176964 Mononeuron Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- GTKRFUAGOKINCA-UHFFFAOYSA-M chlorosilver;silver Chemical compound [Ag].[Ag]Cl GTKRFUAGOKINCA-UHFFFAOYSA-M 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000142 dyskinetic effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000000763 evoking effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention discloses a method for extracting control signals for a brain-machine interface based on potential induced by a transient vision sense. The present invention comprises the following procedures: a transient visual stimulator is arranged for generating visual stimulation signals which can induce potential signals which are induced by a visual sense; brain electricity is collected by a scalp electrode; magnification and A/D conversion are carried out for brain electric signals; the brain electric signals are processed by a computer; signal processing comprises accumulating, averaging, extracting eigenvector in a wavelet transformation domain, identifying by using the neural network of a sensor and a simple fuzzy mode, and extracting control signals for a brain-computer interface. The extraction of control signals for the brain-computer interface is a key technique for realizing the brain-computer interface. The brain-computer interface has application prospects in the fields of rehabilitation engineering, human-machine automatic control, etc. The method can accurately extract control signals for the brain-computer interface, and does not have strict requirements for the stability of stimulation frequency. The adoption of a software programming mode can flexibly realize various visual stimulation modes for the brain-computer interface on a computer screen.
Description
Technical field
The present invention relates to a kind of method, belong to biomedical engineering and automatic control technology field based on transient visual induced potential extraction brain-computer interface control signal.
Background technology
Based on the brain-computer interface of transient visual induced potential is to utilize vision induced EEG signals to realize a kind of direct communication and control approach between human brain and computing machine or other electronic equipments.This kind interface method without any need for language or action, and is directly realized and the exchanging or carry out device control of the external world by EEG signals.Have serious dyskinetic disabled person for those, brain-computer interface can be set up a kind of with extraneous communication modes for them, helps improving its life quality; In addition, brain-computer interface also has wide practical use in fields such as automation of man-machine.The extraction of brain-computer interface control signal is the gordian technique that realizes brain-computer interface, different application according to brain-computer interface, control signal can have different purposes, such as being used as the computer character input, mouse control or menu are selected, also can be used for controlling external unit, such as the switch of control TV, audio amplifier, electric light etc.
VEP is called for short VEP and is meant that nervous system accepts the certain electric activity that visual stimulus produces, as long as user's visual performance is normal, just may utilize VEP signal realization brain-computer interface.
According to the difference of frequency of stimulation, VEP can be divided into transient visual induced potential and stable state vision inducting current potential.Patent of invention " based on the control device of brain electricity steady-state induced response " (application number: 99122161.3) adopt stable state to stimulate and bring out VEP realization brain-computer interface, with fast fourier transform EEG signals is carried out frequency analysis, obtain the correspondent frequency composition, and then realize judging and control.This technology great advantage is that method for extracting signal is simple, realizes than being easier to.But also there is certain limitation in this technology.(1) the stable state vision inducting current potential is very strict to the frequency stability requirement of visual stimulator, and different targets must adopt different frequency of stimulation, and each frequency must be highly stable.If the frequency of stimulation instability, the spectrum peak that brings out electric potential signal can change, and will directly influence the accuracy that the brain-computer interface control signal is extracted.(2) stable state frequency of stimulation scope is generally 6～14Hz, and people's spontaneous brain electricity α wave frequency is 8-13Hz, and its signal amplitude is better than brings out current potential, selects frequency of stimulation also need avoid α ripple place frequency band, and the selection of visual stimulus frequency is subjected to certain restriction.(3) experiment is found, when the visual stimulus frequency is higher, part subject perception eyes discomfort is arranged, number of winks increases, and is difficult to continue to watch attentively stimulation target.In addition, also have minority experimenter's transient evoked potential bigger, but when frequency of stimulation is higher, its stable state vision inducting current potential amplitude is very little, in addition detection less than.This means because individual difference may have groups of people and can not utilize the stable state vision inducting current potential to realize brain-computer interface, then can attempt adopting transient visual induced potential to realize brain-computer interface.
Summary of the invention
The purpose of this invention is to provide and a kind ofly extract the method for brain-computer interface control signal, to reach higher correct judgment rate and higher communication speed based on transient visual induced potential.
The technical solution used in the present invention is such, and promptly a kind of method based on transient visual induced potential extraction brain-computer interface control signal comprises following step:
(1) set up the transient visual stimulator of frequency of stimulation less than per second 5 times, generation can induce the visual stimulus signal of VEP.
(2) by placing the scalp electrode of brain occipitalia, gather the EEG signals that comprises above-mentioned VEP signal.
(3) EEG signals of above-mentioned collection is amplified.
(4) signal after the amplification send data acquisition unit to carry out the A/D conversion.
(5) adopt computing machine that EEG signals is carried out Treatment Analysis, signal Processing comprises progressive mean, extract proper vector at wavelet transformed domain, proper vector input perceptron neural network, perceptron neural network is exported the degree of membership that signal to be identified is under the jurisdiction of VEP signal ambiguity collection, by Fuzzy Pattern Recognition, obtain the brain-computer interface control signal then based on maximum membership grade principle and threshold value principle;
The method that above-mentioned wavelet transformed domain extracts proper vector is that the progressive mean signal is carried out the one-dimensional discrete wavelet decomposition, adopt Mallat orthogonal wavelet transformation fast algorithm to calculate and determine the VEP principal character the coefficient of wavelet decomposition of corresponding frequency band, with this as proper vector;
The weights of said sensed device neural network and threshold value be the experimental data obtained through the brain-computer interface preliminary experiment as training set, the proper vector input perceptron that wavelet transformed domain is extracted has supervised training and obtains neural network.
Advantage of the present invention is as follows:
Relation (VEP appeared in the stimulation relatively-stationary time period of back) when (1) having strict lock owing to transient visual induced potential and between stimulating, can more accurately detect and bring out electric potential signal, help improving the accuracy rate of brain-computer interface control.
(2) extracting method of control signal is not strict with the stability of frequency of stimulation, adopts the software programming mode can produce the visual stimulus pattern on computer screen, and can realize multiple brain-computer interface visual stimulus pattern as required neatly.
(3) adopt scalp electrode to write down the cortex VEP of occipitalia, this recording mode does not have wound, and the user need not training or only needs seldom training, is accepted by the people easily.
Description of drawings
Fig. 1 is a system chart of the present invention;
Fig. 2 is the visual stimulus pattern diagram;
Fig. 3 is a kind of with frequency collective stimulus property sequential synoptic diagram;
Fig. 4 is the process flow diagram that produces the brain-computer interface control signal;
Fig. 5 is the structural representation of neural network.
Embodiment
Below in conjunction with accompanying drawing enforcement of the present invention is done as detailed below: adopt computer screen among the embodiment as visual stimulator, the module that a plurality of flickers are arranged on the screen, it is suitable that on behalf of multiple possible control, different modules select, and the experimenter is by keeping watching attentively one of them module and make one's options or controlling in the short time.Scalp electrode is gathered the EEG signals of occipitalia, EEG signals is converted to digital signal through data acquisition unit again by amplification, filtering, by computing machine EEG signals is carried out analyzing and processing, can determine the target that the experimenter watches attentively, thereby produce the brain-computer interface control signal.
The present invention adopts computer monitor as visual stimulator, and the mode by software programming under DOS or Windows environment produces the pictorial stimulus signal.The great advantage of this method is not need other special external hardware devices, just can produce different stimulus modalities neatly by simple programming, and modification and upgrading are also very convenient.
Adopt rectangular graph (square or pane) as visual stimulus module (stimulation target), with the mode of stimulating module flicker or the alternate of stimulating module color (as red/green alternately) cause visual stimulus, realize selecting or the expression of control information in stimulating module subscript explanatory notes word, symbol or the method for above stimulating module, inserting relevant figure.According to the needs of brain computer interface application, can on same screen, place a plurality of visual stimulus modules, realize multinomial selection or control.The experimenter realizes selecting or control by watching the target that needs selection attentively.When being used for the visual stimulus INTERFACE DESIGN of numeral input such as brain-computer interface, just can directly arabic numeral be labeled on the stimulating module with eye-catching color (as redness), this expression way is directly perceived, vivid, and the user understands easily and accepts.As shown in Figure 2.
Different visual stimulus modules, though label symbol difference on the module, stimulus modality identical (flicker or module color alternate), experiment shows that these different VEP signal waveforms that stimulating module produced are basic identical.Stimulating module such as mark " 1 " and " 0 " can both induce much at one VEP signal.In order to differentiate, to be not the waveform of distinguishing VEP, but to distinguish on the sequential of visual stimulus module a plurality of stimulus signals.
In order to distinguish the caused stimulation of different stimulated module, the moment of the flicker of each stimulating module is different on the screen.The present invention has adopted with frequency collective stimulus property mode, promptly the number of times of each stimulating module flicker is identical in the unit interval, promptly in a time period, there are a plurality of visual stimulus, in a thorn flyback cycle, all stimulating modules all glimmer once respectively, and the moment of each stimulating module flicker is different.Stimulating module per second flicker number of times is less than 5 times.Fig. 3 is a kind of synoptic diagram of the stimulation sequential with frequency collective stimulus property.Each stimulating module can adopt by fixed sequence program or pseudo-random sequence mode and glimmer.
When each module flicker, produce different stimulation sign (producing different digital signals during the disparate modules flicker) respectively, stimulate designation number signal and EEG signals synchronous recording, distinguish the moment that different stimulated produces when being convenient to signal Processing.
This stimulation mode, the flicker number of times of each stimulating module in the unit interval is identical, collective stimulus property alternately occurs, the stimulus intervals of adjacent two different stimulated modules can be smaller, in the relatively short time, all stimulating modules have all glimmered once, when alternative number of targets bigger, this mode can improve stimulation efficient effectively, helps improving the communication speed of brain-computer interface.
Scalp electrode adopts silver-silver chloride electrode, and recording electrode places the occipitalia scalp surface, can smear a little conducting resinl to increase electric conductivity, reduces scalp resistance.The eeg amplifier prime adopts instrumentation amplifier such as AD620, to increase input impedance, improves common-mode rejection ratio, after connect Hi-pass filter, amplifier and low-pass filter.The major parameter of amplifier is: gain: 1000～5000, and frequency band: 1～25Hz.
EEG signals after amplifying is sent into data acquisition unit, be converted into digital signal, deliver to computing machine and handle.Data acquisition unit can be selected general data collecting card for use, and wherein A/D converter selects 16, and sample frequency is made as 512Hz.
Signal processor adopts computer realization, and computing machine has stronger data-handling capacity, can satisfy the requirement of carrying out signal Processing in real time.At the detected VEP of brain occipitalia mainly is that the stimulation target of being watched attentively by the experimenter is caused.Though the square of a plurality of flickers is arranged on the screen, if the experimenter only watches one of them module attentively, have only the visual stimulus of being watched attentively module (select target) can produce the VEP signal, can not produce the VEP signal but not watch module (non-select target) attentively.Concern owing to stimulate and bring out when there is strict lock in current potential, the generation of brain-computer interface control signal is actually carries out pattern-recognition to EEG signals, in judgement and each visual stimulus time corresponding section, VEP whether occurs, and then judge the target that the experimenter watches attentively.The flow process of generation brain-computer interface control signal as shown in Figure 4.
Because the VEP signal belongs to the ultra-weak electronic signal under the strong noise background.At first need to adopt progressive mean to handle, improve signal to noise ratio (S/N ratio), carry out further digital filtering (wavelet filtering) then, extract VEP.
The proper vector of signal extracts in wavelet transformed domain.Wavelet decomposition adopts one dimension Mallat orthogonal wavelet transformation fast algorithm, and signal wavelet decomposition and formula are:
H in the following formula (n) and g (n) be the small echo conjugate lens as bank of filters, correspond respectively to the unit impulse response of low pass and Hi-pass filter.(1) formula is the wavelet decomposition formula, and signal f (t) can carry out progressively decomposed signal to the j+1 yardstick from the j yardstick
Its wavelet decomposition is { A
J dF, (D
jF)
1≤j≤J, J is a certain integer, A
J dF is at yardstick 2
jThe following approximation signal that obtains, the D of decomposing
jF is a yardstick 2
jThe following detail signal that obtains that decomposes.
(2) formula is the wavelet reconstruction formula.
The abstracting method of proper vector is that the progressive mean signal is carried out the one-dimensional discrete wavelet decomposition, and the wavelet decomposition that obtains the 4th yardstick and the 7th yardstick is approached coefficient CA
4, CA
7, use CA then
7Reconstruct its component CA on the 4th yardstick
74, at CA
4Middle deduction CA
74, just can obtain new coefficient of wavelet decomposition CA
4-7=CA
4-CA
74CA
4-7Cast out several end to end coefficients, can obtain 5～7 and can reflect the coefficient that brings out the electric potential signal feature, as the proper vector of signal to be identified.This method has realized denoising, dimensionality reduction and the feature extraction of signal, and more easily realizes.
In brain computer interface application, N alternative visual stimulus module arranged on screen, N the to be identified signal corresponding with stimulation then arranged.The method that produces the brain-computer interface control signal is:
(1) at first carries out the brain-computer interface preliminary experiment, the visual stimulus module that requires the experimenter to watch appointment as requested attentively during experiment, obtain experimental data (proper vector that comprises VEP signal and non-VEP signal) as training set, the wavelet coefficient that filters out is imported perceptron as proper vector,, be output as 1 for the VEP signal, for non-VEP signal, be output as 0, neural network is had supervised training, obtain the weights and the threshold value of neural network.
(2) respectively different stimulated is carried out progressive mean, extract its proper vector at wavelet transformed domain then.
(3) with the proper vector input perceptron neural network of signal to be identified, the output of perceptron neural network is (0,1) interval number, and this output regards that signal to be identified is under the jurisdiction of the degree of membership of VEP signal ambiguity collection as.
(4) at one group of signal to be identified, when the constant threshold (as 0.5) of its maximum membership degree greater than a certain setting, judge that then the signal with maximum membership degree is the VEP signal, what the judgement experimenter watched attentively in this time experiment is corresponding stimulation target, and the output control signal is the sequence number of stimulation target.According to threshold value criterion, if the degree of membership of all signals all is less than or equal to threshold value, think that then all signals to be identified all are not the VEP signals, judge that the experimenter does not do any selection in this time experiment, the output control signal is 0.
Neural network adopts mononeuron perceptron form, as shown in Figure 5.The feature vector, X that the is input as signal to be identified={ x of perceptron
1, x
2, Λ x
n, be output as
Wherein f (x) is a transport function, w
iBe respectively the weights and the threshold value of neural network with θ.Adopt the Sigmoid function
As transport function, perceptron is output as (0,1) interval number, and output valve is more near 1, and it is big more to illustrate that signal belongs to the degree of VEP, and output valve is more little, and it is more little to illustrate that signal belongs to the degree of VEP.
As the example of an enforcement, adopted said method to carry out extracting the experiment of brain-computer interface control signal based on transient visual induced potential in the laboratory.Utilize computer programming on computer screen, to produce visual stimulus, under the DOS environment, utilize Turbo C programming, can realize pictorial stimulus down in graphic model (640*480), the visual stimulus interface comprises 12 targets (visual stimulus module), as shown in Figure 2, simulation brain-computer interface numeral inputting interface.The experimenter watches numeral of any selection or symbol attentively, and watches corresponding stimulation target attentively, and off-line analysis experimenter's EEG signals can be judged selected numeral of experimenter or symbol.Visual stimulus designation number signal is exported by computer parallel port.
The ActiveOne physiological signal measurements system (electrode, amplifier, data acquisition unit, 8 bit digital triggers) that the Dutch Biosemi of experiment employing company produces finishes eeg signal acquisition, the moment that the parallel port of ActiveOne digital trigger input end and computing machine links and takes place with the record different stimulated, the signal that collects is carried out analyzing and processing, produce the brain-computer interface control signal.
The off-line experimental result shows, approximately only need 9-25 visual stimulus, just can produce the brain-computer interface control signal more exactly, the accuracy of control signal can reach 70%～100%, and can reach than higher communication speed, the Theoretical Calculation communication speed can reach per minute 10-40 bit, and the communication speed of international most of brain machine interface systems is a per minute 10-25 bit at present.Experimental result shows that the method based on transient visual induced potential extraction brain-computer interface control signal that the present invention proposes has feasibility and advance.
Claims (4)
1, a kind of method based on transient visual induced potential extraction brain-computer interface control signal, it is characterized in that: method comprises following step:
(1) set up the transient visual stimulator of frequency of stimulation less than per second 5 times, generation can induce the visual stimulus signal of VEP signal;
(2) by placing the scalp electrode of brain occipitalia, gather the EEG signals that comprises above-mentioned VEP signal;
(3) EEG signals of above-mentioned collection is amplified;
(4) signal after the amplification send data acquisition unit to carry out the A/D conversion;
(5) adopt computing machine that EEG signals is handled, signal Processing comprises progressive mean, extract proper vector at wavelet transformed domain, proper vector input perceptron neural network, perceptron neural network is exported the degree of membership that signal to be identified is under the jurisdiction of VEP signal ambiguity collection, by Fuzzy Pattern Recognition, obtain the brain-computer interface control signal then based on maximum membership grade principle and threshold value principle;
The method that above-mentioned wavelet transformed domain extracts proper vector is that the progressive mean signal is carried out-decomposition of Wei discrete wavelet, adopt Mallat orthogonal wavelet transformation fast algorithm to calculate and determine the VEP principal character the coefficient of wavelet decomposition of corresponding frequency band, with this as proper vector;
The weights of said sensed device neural network and threshold value be the experimental data obtained through the brain-computer interface preliminary experiment as training set, the proper vector input perceptron that wavelet transformed domain is extracted has supervised training and obtains neural network.
2, the method for extracting the brain-computer interface control signal based on transient visual induced potential according to claim 1, it is characterized in that: the rectangular graph that the transient visual stimulator shows with computer display produces the visual stimulus signal that can induce the VEP signal as the visual stimulus module with the mode of this stimulating module flicker or the alternate mode of stimulating module color.
3, the method based on transient visual induced potential extraction brain-computer interface control signal according to claim 1 is characterized in that: place a plurality of visual stimulus modules on the same display screen of transient visual stimulator, carry out multinomial selection or control.
4, the method for extracting the brain-computer interface control signal based on transient visual induced potential according to claim 1, it is characterized in that: the transient visual stimulator is to produce the visual stimulus signal that can induce the VEP signal with frequency collective stimulus property mode, promptly in a time period, there are a plurality of visual stimulus, in a thorn flyback cycle, all visual stimulus modules are all glimmered once respectively, and the moment of flicker is different; Stimulating module per second flicker number of times is less than 5 times; Each stimulating module adopts and glimmers by fixed sequence program or pseudo-random sequence mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2003101210333A CN1317624C (en) | 2003-12-31 | 2003-12-31 | Method of extracting brain machine interface control signa based on instantaneous vision sense induced electric potential |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2003101210333A CN1317624C (en) | 2003-12-31 | 2003-12-31 | Method of extracting brain machine interface control signa based on instantaneous vision sense induced electric potential |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1556450A CN1556450A (en) | 2004-12-22 |
| CN1317624C true CN1317624C (en) | 2007-05-23 |
Family
ID=34338373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2003101210333A Expired - Fee Related CN1317624C (en) | 2003-12-31 | 2003-12-31 | Method of extracting brain machine interface control signa based on instantaneous vision sense induced electric potential |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1317624C (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009010001A1 (en) * | 2007-07-19 | 2009-01-22 | Zhiping Meng | A method and system for encryption and personal idendification based on brain wave |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102988059B (en) * | 2006-10-13 | 2014-09-17 | 鲁特格斯州立大学 | Method and system for obtaining auditory or visual sense of babies with normal growth |
| JP4392465B2 (en) * | 2007-10-29 | 2010-01-06 | パナソニック株式会社 | Activation device, method and computer program for an electroencephalogram interface system |
| US8155736B2 (en) * | 2009-03-16 | 2012-04-10 | Neurosky, Inc. | EEG control of devices using sensory evoked potentials |
| CN101576772B (en) * | 2009-05-14 | 2011-07-27 | 天津工程师范学院 | Brain-computer interface system based on virtual instrument steady-state visual evoked potentials and control method thereof |
| CN102098639B (en) * | 2010-12-28 | 2013-09-11 | 中国人民解放军第三军医大学野战外科研究所 | Brain-computer interface short message sending control device and method |
| US8516568B2 (en) | 2011-06-17 | 2013-08-20 | Elliot D. Cohen | Neural network data filtering and monitoring systems and methods |
| CN102309380A (en) * | 2011-09-13 | 2012-01-11 | 华南理工大学 | Intelligent wheelchair based on multimode brain-machine interface |
| CN102631192B (en) * | 2012-04-24 | 2014-01-15 | 南方医科大学 | A Deconvolution Method for Extracting Evoked Potentials at High Stimulation Rates |
| CN102789441B (en) * | 2012-08-09 | 2015-03-18 | 上海海事大学 | Asynchronous brain-computer interface system based on steady state evoked potential and method for realizing asynchronous brain-computer interface system |
| CN103019383B (en) * | 2012-12-18 | 2016-01-13 | 北京大学 | A kind of Steady State Visual Evoked Potential brain-machine interface signal recognition methods |
| CN103294192A (en) * | 2013-04-25 | 2013-09-11 | 常州大学 | LED lamp switch control device and control method thereof based on motor imagery |
| CN103405230B (en) * | 2013-08-07 | 2015-04-15 | 清华大学 | System and method for detecting color perception based on electroencephalogram evoked potential |
| CN104524689A (en) * | 2014-12-03 | 2015-04-22 | 上海交通大学 | A system and method for controlling allogeneic organisms through a brain-brain interface |
| CN106580320A (en) * | 2016-12-16 | 2017-04-26 | 长春大学 | EEG signal feature analysis method and system based on visual inducement |
| CN106842949A (en) * | 2017-03-07 | 2017-06-13 | 天津大学 | Thalamus cortex discharge condition Varied scope fuzzy control system based on FPGA |
| CN109938727A (en) * | 2017-12-20 | 2019-06-28 | 中国科学院深圳先进技术研究院 | Non-human primate three-dimensional visual stimulation experimental system and method |
| CN109002798B (en) * | 2018-07-19 | 2021-07-16 | 大连理工大学 | A single-lead visual evoked potential extraction method based on convolutional neural network |
| CN115390655A (en) * | 2021-05-24 | 2022-11-25 | 华为技术有限公司 | Man-machine interaction method, man-machine interaction device and storage medium |
| CN114298099B (en) * | 2021-12-27 | 2024-08-09 | 华中科技大学 | A training method for brain-computer interface model and an electroencephalogram signal recognition method |
| CN116491960B (en) * | 2023-06-28 | 2023-09-19 | 南昌大学第一附属医院 | Brain transient monitoring device, electronic device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08131413A (en) * | 1994-11-08 | 1996-05-28 | Nec Corp | Device for estimating living body ental state |
| CN1248426A (en) * | 1999-10-29 | 2000-03-29 | 清华大学 | Controller based on brain electricity steady-state induced response |
| KR20030017124A (en) * | 2001-08-24 | 2003-03-03 | 림스테크널러지주식회사 | Radio telemetric system and method using brain potentials for remote control of toy |
| US6572560B1 (en) * | 1999-09-29 | 2003-06-03 | Zargis Medical Corp. | Multi-modal cardiac diagnostic decision support system and method |
| US20030105409A1 (en) * | 2001-11-14 | 2003-06-05 | Donoghue John Philip | Neurological signal decoding |
| US20030176905A1 (en) * | 2002-03-14 | 2003-09-18 | Nicolelis Miguel A.L. | Miniaturized high-density multichannel electrode array for long-term neuronal recordings |
-
2003
- 2003-12-31 CN CNB2003101210333A patent/CN1317624C/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08131413A (en) * | 1994-11-08 | 1996-05-28 | Nec Corp | Device for estimating living body ental state |
| US6572560B1 (en) * | 1999-09-29 | 2003-06-03 | Zargis Medical Corp. | Multi-modal cardiac diagnostic decision support system and method |
| CN1248426A (en) * | 1999-10-29 | 2000-03-29 | 清华大学 | Controller based on brain electricity steady-state induced response |
| KR20030017124A (en) * | 2001-08-24 | 2003-03-03 | 림스테크널러지주식회사 | Radio telemetric system and method using brain potentials for remote control of toy |
| US20030105409A1 (en) * | 2001-11-14 | 2003-06-05 | Donoghue John Philip | Neurological signal decoding |
| US20030176905A1 (en) * | 2002-03-14 | 2003-09-18 | Nicolelis Miguel A.L. | Miniaturized high-density multichannel electrode array for long-term neuronal recordings |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009010001A1 (en) * | 2007-07-19 | 2009-01-22 | Zhiping Meng | A method and system for encryption and personal idendification based on brain wave |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1556450A (en) | 2004-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1317624C (en) | Method of extracting brain machine interface control signa based on instantaneous vision sense induced electric potential | |
| CN109299751B (en) | EMD data enhancement-based SSVEP electroencephalogram classification method of convolutional neural model | |
| Kim et al. | A wavelet-based method for action potential detection from extracellular neural signal recording with low signal-to-noise ratio | |
| CN114533086B (en) | A motor imagery EEG decoding method based on spatial feature time-frequency transformation | |
| CN103793058B (en) | A kind of active brain-computer interactive system Mental imagery classification of task method and device | |
| CN107961007A (en) | A kind of electroencephalogramrecognition recognition method of combination convolutional neural networks and long memory network in short-term | |
| CN109965869B (en) | MI-EEG identification method based on brain source domain space | |
| CN111067514B (en) | A multi-channel EEG coupling analysis method based on multi-scale and multi-variable transfer entropy | |
| CN106919956A (en) | Brain wave age forecasting system based on random forest | |
| CN109674468A (en) | Automatic sleep stage dividing method for single-channel electroencephalogram | |
| CN111523601A (en) | Latent emotion recognition method based on knowledge guidance and generation counterstudy | |
| CN104965584A (en) | Mixing method for brain-computer interface based on SSVEP and OSP | |
| CN109034015B (en) | FSK-SSVEP demodulation system and demodulation algorithm | |
| CN103699226A (en) | Tri-modal serial brain-computer interface method based on multi-information fusion | |
| CN114081506B (en) | A classification method of steady-state visual evoked potential based on long short-term memory network | |
| CN1552284A (en) | Children's Cognitive Function Development Test System | |
| CN116400800B (en) | A human-computer interaction system and method for ALS patients based on brain-computer interface and artificial intelligence algorithm | |
| CN113951903A (en) | Recognition method of overload state of high-speed railway dispatchers based on EEG data measurement | |
| CN112884063A (en) | P300 signal detection and identification method based on multivariate space-time convolution neural network | |
| CN115886841A (en) | A steady-state visually evoked EEG dynamic onset classification method based on brain region linkage | |
| CN116910623B (en) | SSVEP brain-computer interface target recognition method based on subject transfer | |
| CN111067513A (en) | A method for determining key brain regions for sleep quality detection based on feature weight self-learning | |
| CN115099274A (en) | Electroencephalogram signal identification method | |
| CN118013308B (en) | Adaptive tree-based spatiotemporal enhanced neural electrical pulse signal clustering method and system | |
| CN119917836A (en) | An EEG encoding method based on generative adversarial technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20070523 Termination date: 20100201 |