CN103019383B - A kind of Steady State Visual Evoked Potential brain-machine interface signal recognition methods - Google Patents
A kind of Steady State Visual Evoked Potential brain-machine interface signal recognition methods Download PDFInfo
- Publication number
- CN103019383B CN103019383B CN201210551943.4A CN201210551943A CN103019383B CN 103019383 B CN103019383 B CN 103019383B CN 201210551943 A CN201210551943 A CN 201210551943A CN 103019383 B CN103019383 B CN 103019383B
- Authority
- CN
- China
- Prior art keywords
- picture
- eeg signals
- testee
- attentively
- visual stimulus
- 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
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of Steady State Visual Evoked Potential brain-machine interface signal recognition methods.This method is: 1) shown by a visual stimulus unit with different flicker frequency by some different pictures simultaneously, and gathers the EEG signals that testee watches this visual stimulus unit attentively; 2) data processing unit carries out noise estimation and noise reduction process to EEG signals, then carries out feature extraction and judgement, tentatively determines the picture that this testee watches attentively; 3) upset the flicker frequency Showed Picture, gather EEG signals; Then noise estimation and noise reduction process are carried out to the EEG signals that this gathers, then feature extraction and judgement are carried out to the EEG signals after process, determine the picture that this testee watches attentively, if the picture this time determined is identical with step 2, then this picture is exported as the identifying information finally determined; If different, then judge that this testee does not watch any width picture of this visual stimulus unit display attentively.The present invention can improve the accuracy of EEG's Recognition effectively.
Description
Technical field
The invention belongs to neural field of engineering technology, be specifically related to Steady State Visual Evoked Potential and brain-computer interface signal recognition method.
Background technology
Brain-computer interface (Brain-ComputerInterface, BCI) is the system realizing brain and computing machine or other equipment Direct Communications and control based on EEG signals.The information that brain-computer interface can send brain is directly converted to and can drives peripheral command, and the limbs etc. of people can be replaced to realize exchanging of people and the external world and the control to external environment condition.The brain that brain-computer interface system is behaved opens a brand-new approach carrying out communication and control with the external world, makes the idea utilizing people's brain signal directly to control external unit become possibility.
Current brain-computer interface system also exists intrusive mood and the large class of non-intrusion type two.The signal accuracy that the brain-computer interface of intrusive mood obtains is relatively high, and signal to noise ratio (S/N ratio) is high, is easy to analyzing and processing, but need to carry out operation of opening cranium to user, be not easy to long signals collecting, and easily cause infection or damage to the brain of user, danger is larger.Although its brain signal noise obtained of the brain-computer interface of non-intrusion type is large, the ga s safety degree of signal characteristic is poor, but its signal relatively easily obtains simultaneously, can not damage the brain of user, and along with the continuous progress of signal processing method and technology, can reach certain level to the process of scalp EEG signal (electroencephalogram, EEG), making the brain-computer interface system of non-intrusion type enter real life application becomes possibility.In recent years, brain-computer interface technical development is very fast, embodies important value in biomedicine, virtual reality, Entertainment, rehabilitation project and the field such as space flight, military affairs.
Event related potential (EventRelatedPotentials, ERPs) refers to the average rear viewed a series of potential change of EEG signals that is relevant with stimulation event and same stimulation locking in time.It not only depends on the physical attribute of environmental stimuli, also processes with the subjectivity of brain and cognitive state has close relationship.VEP (VisualEvokedPotential, VEP) is a kind of widely used event related potential composition, and it refers to the certain electric activity that nervous system accepts visual stimulus (such as figure or flash stimulation) and produces.When visual stimulus is fixed as some frequencies (being generally greater than 6Hz), its VEP caused overlaps in time, brain visual cortex can produce Steady State Visual Evoked Potential (SteadyStateVEP, SSVEP), this Evoked ptential signal presents the periodicity consistent with visual stimulus, can realize the visual stimulus under different frequency and out of phase condition by the frequency spectrum analyzing this signal, be a kind of brain-computer interface input signal having using value.
Brain-computer interface system using Steady State Visual Evoked Potential as input signal has the advantages such as rate of information transmission is high, the training time is short, feature is easily extracted; but because EEG signals is very unstable and often have the interference of electromyographic signal, thus cause often there will be some mistakes during classification.Propose the mode that a kind of active confirms herein, effectively can reduce false determination ratio.
Summary of the invention
The object of this invention is to provide a kind of Steady State Visual Evoked Potential brain-computer interface signal recognition method, namely screen presents multiple flicker picture, testee only watches a certain width picture wherein attentively, when detecting that testee watches certain width picture attentively, utilizes the mode initiatively confirmed, upset the flicker frequency (image content is constant) of all pictures, again detect, if twice identical, then we think that previous detection is correct, if different, be then once error detection before thinking.
Technical scheme of the present invention is:
A kind of Steady State Visual Evoked Potential brain-computer interface signal recognition method, the steps include:
1) a visual stimulus unit is set up, for showing the picture of some different contents, when watching attentively for testee;
2) picture of some different contents is shown by this visual stimulus unit with different flicker frequency simultaneously, and gather the EEG signals that this testee watches this visual stimulus unit attentively, be stored into data processing unit;
3) this data processing unit carries out noise estimation and noise reduction process to gathered EEG signals;
4) to step 3) process after EEG signals carry out feature extraction and judgement, tentatively determine the picture that this testee watches attentively;
5) upset the flicker frequency of picture shown by this visual stimulus unit, and gather the EEG signals that this testee watches this visual stimulus unit attentively, be stored into data processing unit; Then this data processing unit carries out noise estimation and noise reduction process to this EEG signals gathered;
6) to step 5) process after EEG signals carry out feature extraction and judgement, determine the picture that this testee watches attentively, if the picture that the picture this time determined and step 4 are determined is identical, then using this picture as finally determine identifying information output; If not identical, then judge that this testee does not watch any width picture of this visual stimulus unit display attentively.
Further, step 2) before, first visual stimulus unit is shown as blank screen, gathers testee and watch the EEG signals in this visual stimulus unit blank screen setting duration attentively and be stored into data processing unit; Then when this data processing unit utilizes tranquillization EEG signals average frequency spectrum to the EEG signals of adopting carry out noise estimation.
Further, described setting duration is 10s.
Further, the method gathering described EEG signals is: at this testee's head occipital lobe O
zposition of sound production one EEG electrode, side auricle position of sound production reference electrode, opposite side auricle position of sound production ground-electrode, by the signal of electrode collection by obtaining the EEG signals of testee after differential amplifier, analog to digital converter.
Further, tentatively determine that the method for the picture that this testee watches attentively is: by step 3) process the energy that rear EEG signals corresponds to each picture, as the EEG signals feature of corresponding picture; Choose EEG signals eigenwert the maximum to compare with setting threshold value, when exceeding this setting threshold value, then what preliminary judgement testee watched attentively is the picture that this EEG signals eigenwert the maximum is corresponding; Then otherwise judge that testee does not watch any width picture attentively, step 2 is repeated) ~ 4).
Further, step 3) in, the signal of this data processing unit to EEG electrode collection in gathered EEG signals carries out noise estimation and noise reduction process.
This Steady State Visual Evoked Potential brain-computer interface system initiatively confirm device, comprise with lower module (as Fig. 1):
1. stimulating module: stimulating module mainly comprises a large display screen.Object utilizes display screen to show in the picture containing certain content, when watching attentively for testee (as Fig. 2).
2. signal acquisition module: signal acquisition module mainly comprises electrode, differential amplifier, analog to digital converter (as Fig. 3).Object is the EEG signals gathering testee, and utilizes wireless transmission that EEG signals is passed to receiving end.
3. signal processing module: signal processing module mainly comprises noise and estimates and noise reduction process, feature extraction and classification (as Fig. 4).Because EEG signals is unstable, and the interference of the signals such as myoelectricity may be had, so in order to promote signal to noise ratio (S/N ratio), make system more robust, we need to carry out noise estimation and noise reduction process after receiving data, utilize each frequency energy as feature afterwards, classify, thus obtain the picture that testee watches attentively.
4. initiatively confirm module: after a subseries judgement, we initiatively upset picture flicker frequency, then carry out noise reduction, classification and a judgement, if result is once identical with front, then before thinking, once judgement accurately, thus reaches an object confirmed.
Compared with prior art, good effect of the present invention is:
The present invention not only maintains the advantage of Steady State Visual Evoked Potential system, and namely rate of information transmission is high, and the training time is short, and feature is easily extracted, but also proposes the mode of a kind of active confirmation, improves classification accuracy rate whereby.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention;
Fig. 2 stimulates interface schematic diagram (stimulating the order of picture display and quantity to change according to demand);
Fig. 3 is signal acquisition module process flow diagram;
Fig. 4 is signal processing module process flow diagram.
Embodiment
Referring to accompanying drawing of the present invention, most preferred embodiment of the present invention is described in more detail.
Based on the brain-computer interface method of the Steady State Visual Evoked Potential initiatively confirmed, comprise the following steps:
Step one: at testee's head occipital lobe O
zposition of sound production electroencephalograph electrode (EEG electrode), side auricle position of sound production reference electrode, opposite side auricle position of sound production ground-electrode, the signal gathered by electrode is by obtaining the EEG signals (as Fig. 2 and Fig. 3) of testee after differential amplifier, analog to digital converter, and utilize wireless device and computing machine to carry out data transmission, utilize the EEG signals that computer stored gathers.
Step 2: utilizing display screen to show stimulates picture, and first display screen can show the blank screen of 10s, and object is the EEG signals in order to record during tranquillization, to carry out noise estimation and noise reduction process below.(number can increase and can subtract by 6 afterwards, fixed with demand) (such as drink water containing certain content, have a meal, see TV etc.) the flicker picture of different frequency present on a display screen simultaneously, position of appearing respectively screen upper left, on, upper right, lower-left, under, bottom right, testee's head distance display screen is 50 ~ 100 centimetres (as Fig. 2).
Step 3: testee watches the middle section (namely not watching wherein any width picture attentively) of in above-mentioned 6 pictures or screen attentively.
Step 4: to EEG electrode the signal adopted carry out noise estimation and noise reduction process, the average frequency spectrum of EEG signals when noise is estimated to adopt tranquillization, available noise-reduction method is a lot, provides some simple implementation methods here.
Spectrum subtracts (SpectralSubtraction) and was proposed in 1979 by Boll, composing the ultimate principle cut algorithm is suppose that noise is incoherent, extra to target EEG signals, the short-time magnitude spectrum deducting noise from noisy EEG signals obtains the short-time magnitude spectrum of echo signal, and the estimation of its noise signal be by when experimenter is quiet (when front 10s notes blank screen) record.Fundamental formular is as follows
|X(k)|＝|S(k)|+|N(k)|
Wherein X (k) is noisy EEG signals frequency spectrum, and S (k) is target EEG signals frequency spectrum, and N (k) is noise spectrum.After estimation N (k) obtaining noise amplitude spectrum, just can obtain the estimation of the amplitude spectrum of target EEG signals
Except above-mentioned spectrum substantially cuts algorithm, Berouti etc. revise it: time (1) deducts noise spectrum, the degree subtracted is regulated according to signal to noise ratio (S/N ratio), be multiplied by the parameter that is greater than l to noise spectrum when being subtracted by spectrum, make the noise spectrum of the value compared estimate deducted when spectral substraction more (2) in the larger place of noise amplitude, the spectrum of signal to be estimated is not set to 0, and introduce the concept of noise floor (SpectralFloor), at these local a little noises of reservation.The estimation of the target EEG signals short-time spectrum after amendment becomes
|S(k)|＝max{|X(k)|-α|N(k)|，βN(k)}
Wherein α > 1 is less when signal to noise ratio (S/N ratio) is larger, and 0≤β < < 1 is a fixed value.
Certainly, available method also has a lot, the short-time magnitude Power estimation of such as optimum MMSE, MMSE logarithmic spectrum amplitude Estimation, and nonlinear spectral subtracts etc., merely provides two kinds of methods being simple and easy to realize here and exemplarily realizes noise estimation and noise reduction process.
Step 5: feature extraction and judgement are carried out to the EEG signals after denoising.We first obtain the energy of these 6 frequencies corresponding in denoising brain electricity, are designated as E
1~ E
6.Because the EEG signals of different people is strong and weak different, so we are respectively with the E extracted
1~ E
6divided by they and (namely carrying out a normalized process), be designated as e
1~ e
6, and it can be used as feature.The method of judgement also has a lot, only provides a method being simple and easy to realize here exemplarily.We first select e
1~ e
6in the maximum, then compare with threshold value, this threshold value is determined by test experiment, gather in test experiment a small amount of testee watch the stimulation picture state of 6 kinds of frequencies respectively attentively under EEG signals, this threshold value is that the population mean of the feature of above-mentioned EEG signals is multiplied by a coefficient rule of thumb determined, when exceeding this threshold value we just preliminary judgement testee watches attentively is the picture of that frequency scintillation of its representative; If lower than threshold value, we think that testee does not watch any width picture attentively and sees, get back to step 3 and start new round experiment.
Step 6: when preliminary judgement testee stares at a certain width picture, we need to utilize a process initiatively confirmed again to determine the picture that testee watches attentively, at this moment the flicker frequency (but not changing its position) of 6 width figure is upset at random, it (can be the picture just now watched attentively that testee watches a certain width picture attentively, may not be) or center Screen, afterwards a step 4 and step 5 (in step 5, set threshold value is constant) are carried out again to the EEG signals newly collected, if twice we judge that the picture that testee watches attentively is identical, what then think that testee watches attentively really is the picture that we judge, screen just can show this width picture with animation form, simultaneity factor can send the voice that are consistent with image content (such as: you will drink water/have a meal ...) feed back to testee as a result, at this moment the content (certain width picture or center Screen) that testee tells us to watch attentively for twice is the picture that we judge, to verify the accuracy that our system judges, get back to step 3 afterwards and start new round experiment, if twice different, it may be once error detection before then thinking, testee does not watch any width picture attentively and sees, simultaneity factor can send voice message (such as: you do not watch the picture in screen attentively), at this moment testee is still allowed to tell the content that we watch attentively for twice, to verify the accuracy that our system judges, still get back to step 3 afterwards and start new round experiment.
Claims (6)
1. Steady State Visual Evoked Potential brain-machine interface signal recognition methods, the steps include:
1) a visual stimulus unit is set up, for showing the picture of some different contents, when watching attentively for testee;
2) picture of some different contents is shown by this visual stimulus unit with different flicker frequency simultaneously, and gather the EEG signals that this testee watches this visual stimulus unit attentively, be stored into data processing unit;
3) this data processing unit carries out noise estimation and noise reduction process to gathered EEG signals;
4) to step 3) process after EEG signals carry out feature extraction and judgement, tentatively determine the picture that this testee watches attentively;
5) upset the flicker frequency of picture shown by this visual stimulus unit, and gather the EEG signals that this testee watches this visual stimulus unit attentively, be stored into data processing unit; Then this data processing unit carries out noise estimation and noise reduction process to this EEG signals gathered;
6) to step 5) process after EEG signals carry out feature extraction and judgement, determine the picture that this testee watches attentively, if picture and the step 4 this time determined) picture determined is identical, then this picture exported as the identifying information finally determined; If not identical, then judge that this testee does not watch any width picture of this visual stimulus unit display attentively.
2. the method for claim 1, is characterized in that step 2) before, first visual stimulus unit is shown as blank screen, gathers testee and watch the EEG signals in this visual stimulus unit blank screen setting duration attentively and be stored into data processing unit; Then when this data processing unit utilizes tranquillization EEG signals average frequency spectrum to the EEG signals of adopting carry out noise estimation.
3. method as claimed in claim 2, is characterized in that described setting duration is 10s.
4. the method as described in claim 1 or 2 or 3, is characterized in that the method gathering described EEG signals is: at this testee's head occipital lobe O
zposition of sound production one EEG electrode, side auricle position of sound production reference electrode, opposite side auricle position of sound production ground-electrode, by the signal of EEG electrode, reference electrode and ground-electrode collection by obtaining the EEG signals of testee after differential amplifier, analog to digital converter.
5. the method as described in claim 1 or 2 or 3, is characterized in that the method tentatively determining the picture that this testee watches attentively is: by step 3) process the energy that rear EEG signals corresponds to each picture, as the EEG signals feature of corresponding picture; Choose EEG signals eigenwert the maximum to compare with setting threshold value, when exceeding this setting threshold value, then what preliminary judgement testee watched attentively is the picture that this EEG signals eigenwert the maximum is corresponding; Otherwise, then judge that testee does not watch any width picture attentively, repeat step 2) ~ 4).
6. method as claimed in claim 2 or claim 3, is characterized in that step 3) in, the signal of this data processing unit to EEG electrode collection in gathered EEG signals carries out noise estimation and noise reduction process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210551943.4A CN103019383B (en) | 2012-12-18 | 2012-12-18 | A kind of Steady State Visual Evoked Potential brain-machine interface signal recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210551943.4A CN103019383B (en) | 2012-12-18 | 2012-12-18 | A kind of Steady State Visual Evoked Potential brain-machine interface signal recognition methods |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103019383A CN103019383A (en) | 2013-04-03 |
| CN103019383B true CN103019383B (en) | 2016-01-13 |
Family
ID=47968067
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210551943.4A Active CN103019383B (en) | 2012-12-18 | 2012-12-18 | A kind of Steady State Visual Evoked Potential brain-machine interface signal recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103019383B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| IL239191A0 (en) * | 2015-06-03 | 2015-11-30 | Amir B Geva | Image classification system |
| CN105022486B (en) * | 2015-07-17 | 2018-01-19 | 西安交通大学 | EEG signals discrimination method based on the driving of different expressions |
| CN105942975B (en) * | 2016-04-20 | 2018-07-06 | 西安电子科技大学 | Brain-electrical signal processing method based on stable state vision inducting |
| CN106155323B (en) * | 2016-07-05 | 2018-10-19 | 西安交通大学 | Based on etc. brightness and colors strengthen stable state of motion Evoked ptential brain-computer interface method |
| CN107220599A (en) * | 2017-05-16 | 2017-09-29 | 北京信息科技大学 | Image quality evaluating method based on EEG signal |
| CN107811735B (en) * | 2017-10-23 | 2020-01-07 | 广东工业大学 | Auxiliary eating method, system, equipment and computer storage medium |
| CN108181995A (en) * | 2018-01-31 | 2018-06-19 | 京东方科技集团股份有限公司 | interactive system, method and device |
| CN108600508B (en) * | 2018-03-14 | 2020-08-18 | Oppo广东移动通信有限公司 | Electronic device, screen locking control method and related product |
| CN109582131B (en) * | 2018-10-29 | 2021-09-07 | 中国航天员科研训练中心 | Asynchronous hybrid brain-computer interface method |
| CN113520409B (en) * | 2021-05-31 | 2024-03-26 | 杭州回车电子科技有限公司 | SSVEP signal identification method, device, electronic device and storage medium |
| CN113419537A (en) * | 2021-07-08 | 2021-09-21 | 西安理工大学 | Brain-computer fusion control method and system for autonomous movement of mobile robot |
| CN113907757B (en) * | 2021-10-18 | 2022-09-30 | 中国民航大学 | Alertness testing method based on attention system theory |
| CN116584957B (en) * | 2023-06-14 | 2024-07-09 | 中国医学科学院生物医学工程研究所 | Data processing method, device, equipment and storage medium of hybrid brain-computer interface |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4493539A (en) * | 1982-06-30 | 1985-01-15 | The United States Of America As Represented By The Secretary Of The Air Force | Method and apparatus for objective determination of visual contrast sensitivity functions |
| US4651145A (en) * | 1984-05-31 | 1987-03-17 | Medical Research Institute | Communication system for the disabled in which a display target is selected by encephalogram response |
| US4832480A (en) * | 1986-06-24 | 1989-05-23 | Quintron, Inc. | Differential diagnosis of sensory abnormalities using a normalized, ratiometric analysis of steady state evoked potentials |
| CN1556450A (en) * | 2003-12-31 | 2004-12-22 | 中国人民解放军第三军医大学野战外科 | Method of extracting brain machine interface control signa based on instantaneous vision sense induced electric potential |
| CN101339455A (en) * | 2008-08-07 | 2009-01-07 | 北京师范大学 | Brain machine interface system based on human face recognition specific wave N170 component |
| CN101887307A (en) * | 2010-06-03 | 2010-11-17 | 西安交通大学 | Multi-frequency time sequence combined steady-stage visual evoked potential brain-computer interface method |
-
2012
- 2012-12-18 CN CN201210551943.4A patent/CN103019383B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4493539A (en) * | 1982-06-30 | 1985-01-15 | The United States Of America As Represented By The Secretary Of The Air Force | Method and apparatus for objective determination of visual contrast sensitivity functions |
| US4651145A (en) * | 1984-05-31 | 1987-03-17 | Medical Research Institute | Communication system for the disabled in which a display target is selected by encephalogram response |
| US4832480A (en) * | 1986-06-24 | 1989-05-23 | Quintron, Inc. | Differential diagnosis of sensory abnormalities using a normalized, ratiometric analysis of steady state evoked potentials |
| CN1556450A (en) * | 2003-12-31 | 2004-12-22 | 中国人民解放军第三军医大学野战外科 | Method of extracting brain machine interface control signa based on instantaneous vision sense induced electric potential |
| CN101339455A (en) * | 2008-08-07 | 2009-01-07 | 北京师范大学 | Brain machine interface system based on human face recognition specific wave N170 component |
| CN101887307A (en) * | 2010-06-03 | 2010-11-17 | 西安交通大学 | Multi-frequency time sequence combined steady-stage visual evoked potential brain-computer interface method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103019383A (en) | 2013-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103019383B (en) | A kind of Steady State Visual Evoked Potential brain-machine interface signal recognition methods | |
| CN103092340B (en) | A kind of brain-computer interface method of visual activation and signal recognition method | |
| Chen et al. | A novel EEMD-CCA approach to removing muscle artifacts for pervasive EEG | |
| CN108236464B (en) | Feature extraction method based on electroencephalogram signals and detection extraction system thereof | |
| Lee et al. | A brain-wave-actuated small robot car using ensemble empirical mode decomposition-based approach | |
| US20070179396A1 (en) | Method and System for Detecting and Classifying Facial Muscle Movements | |
| CN111920408B (en) | Signal analysis method and component of electroencephalogram nerve feedback system combined with virtual reality | |
| CN103699226B (en) | A kind of three mode serial brain-computer interface methods based on Multi-information acquisition | |
| CN106691474A (en) | Brain electrical signal and physiological signal fused fatigue detection system | |
| CN107361765B (en) | Brain wave analysis method and device | |
| CN103019382B (en) | A kind of brain-machine interface method utilizing Evoked ptential to reflect brain subjective motivation signal | |
| CN104536573B (en) | A kind of brain-machine interface method stimulated based on high frequency flicker emotion | |
| CN106527732A (en) | Method for selecting and optimizing feature signals in somatosensory electric stimulation brain computer interface | |
| EP3932303A1 (en) | Method and system for detecting attention | |
| CN115067971B (en) | Nerve feedback system for controlling virtual object based on brain electrical signal feedback | |
| CN108209909A (en) | Bimodulus spy's nerve signal feature selection approach based on action intention task | |
| CN106484106A (en) | The non-attention event related potential brain-machine interface method of visual acuity automatic identification | |
| CN113208634A (en) | Attention detection method and system based on EEG brain waves | |
| CN112426162A (en) | Fatigue detection method based on electroencephalogram signal rhythm entropy | |
| CN117064409A (en) | Method, device and terminal for evaluating transcranial direct current intervention stimulation effect in real time | |
| CN111144450A (en) | Method for constructing ERP paradigm based on name stimulation with different lengths | |
| CN204759349U (en) | Aircraft controlling means based on stable state vision evoked potential | |
| CN103816007A (en) | Equipment and method for tinnitus treatment based on electroencephalogram frequency-domain characteristic indexation algorithm | |
| KR101034875B1 (en) | Intention reasoning method using pattern of brain waves | |
| CN114366101B (en) | Motor imagery electroencephalogram signal classification method, device, equipment and storage medium |
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 |