CN110262658A - A kind of brain-computer interface character input system and implementation method based on reinforcing attention - Google Patents
A kind of brain-computer interface character input system and implementation method based on reinforcing attention Download PDFInfo
- Publication number
- CN110262658A CN110262658A CN201910514978.2A CN201910514978A CN110262658A CN 110262658 A CN110262658 A CN 110262658A CN 201910514978 A CN201910514978 A CN 201910514978A CN 110262658 A CN110262658 A CN 110262658A
- Authority
- CN
- China
- Prior art keywords
- character
- brain
- signal
- computer interface
- classification
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Dermatology (AREA)
- Health & Medical Sciences (AREA)
- Neurosurgery (AREA)
- General Health & Medical Sciences (AREA)
- Neurology (AREA)
- Human Computer Interaction (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The present invention relates to brain-computer interface technical fields, and in particular to a kind of based on the brain-computer interface character input system and implementation method of strengthening attention.The present invention includes: including four information collection part, signal processing, Classification and Identification part and feedback element component parts, the information collection part is used to acquire the EEG signals of brain, the signal processing electric, electrocardio and signal interference by collected EEG signals removal original signal eye therein, the Classification and Identification part is for realizing character output, the staining effect of Classification and Identification part to user, is additionally provided with visual stimulus equipment on the information collection part by the feedback element.
Description
Technical field
The present invention relates to brain-computer interface technical fields, and in particular to a kind of based on the brain-computer interface character input for strengthening attention
System and implementation method.
Background technique
Brain-computer interface (Brain-Computer Interface, BCI) is one kind independent of biological self neural access
With the connection of musculature, the artificial connection access of equipment is established between the brain and external equipment of human or animal.It is related to
It is current brain science research field to the knowledge of the multi-crossed disciplines such as Neuscience, signal detection, signal processing, pattern-recognition
One of hot research problem.Brain-computer interface can provide a kind of and outer as a kind of completely new message-switching technique for people
The new way that boundary is exchanged, especially for there is brain machine for aphasis or severe paralysis but the normal patient of brain function to connect
Port system is the new tunnel interacted they provide one with the external world.
The EEG signals for being usually used in brain machine interface system at present are broadly divided into four classes: becoming cortical potential (Slow slowly
Cortical Potential, SCP), Steady State Visual Evoked Potential (Steady-State Visual Evoked
Potential, SSVEP), be based on the Mental imagery Mu/Beta rhythm and pace of moving things, event related potential (Event-related
Potentials, ERPs).Slow cortical potential (Slow Cortical Potential, SCP) reflection is in cerebral cortex
The slow voltage change that low frequency part generates, subject need by training formation condition reflection repeatedly, in feedback information
It is capable of the positive negative sense variation of the conscious slow cortical potential of control when appearance.In Steady State Visual Evoked Potential (Steady-State
Visual Evoked Potential, SSVEP) in system, when subject by a fixed frequency visual stimulus when
It waits, a continuously response related with frequency of stimulation can be generated in brain visual cortex, this response is referred to as stable state vision
Evoked ptential, although the system have can class object number is more, single discrimination is high and the training time is short advantage, long-time
Observation be easy to allow people to generate fatigue even to cause epilepsy.And the EEG signals based on the Mental imagery Mu/Beta rhythm and pace of moving things, when people exists
When imagining that different limbs are moved, the reduction of the corresponding limbs sensorimotor cortex region mu rhythm and pace of moving things, this reduction can be caused
It is called " Event-related desynchronization ", by identifying the decline of Different brain region mu rhythm and pace of moving things energy, realizes to specific Mental imagery limb
The judgement of body.Event-related desynchronization appoints three kinds and the above Mental imagery mainly for the research of two kinds of Mental imagery tasks
The classification accuracy of business will have a greatly reduced quality.
Comparatively, it is based on the brain-computer interface technology of event related potential (ERP), subject is not needed and trains in advance, match
It is succinct to set requirement, it is easy to operate, it also can achieve relatively high classification accuracy in polytypic situation.Event phase at present
Powered-down position, which is substantially, is presented normal form using P300 visual stimulus, and the character input system of normal form is presented based on P300 visual stimulus
Its rate of uniting still is unable to reach practical purpose.Researcher wishes to stimulate presentation normal form to reach raising system by changing
The purpose of performance.Wherein, system performance can be improved in the cognition workload or novelty for increasing stimulation picture, but long-term
In the case of watching attentively, it is easier to which causing the fatigue of user can also be such that novelty drops.It is added and listens during carrying out visual stimulus
Feel stimulation, and improve one of the means of characters spells system performance, but it is more also to require that user needs to put into simultaneously
Energy.
Summary of the invention
In order to overcome the shortcomings of that background technique, the present invention provide a kind of based on the brain-computer interface character input system for strengthening attention
System:
The technical scheme is that including information collection part, signal processing, Classification and Identification part and feedback element four
A component part, the information collection part are used to acquire the EEG signals of brain, and the signal processing will be collected
EEG signals remove original signal eye electricity, electrocardio and signal interference therein, and the Classification and Identification part is for realizing character
The control effect of Classification and Identification part is fed back to user, also set on the information collection part by output, the feedback element
There is visual stimulus equipment.
Preferably, the signal processing is made of preprocessing module, characteristic extracting module, the preprocessing module tool
There are bandpass filtering, baseline correction, setting threshold function, the characteristic extracting module has down-sampled, assemblage characteristic vector functionality.
Preferably, the Classification and Identification part, which has, identifies brain electrical feature vector functionality using trained classifier.
Preferably, the original EEG signals of described information collection part acquisition 14 electrodes of user's cerebral cortex, described 14
The acquisition position of a electrode presses Fz, F3, F4, P7, P8, Cz, C3, C4, Pz, the P3 on world 10-20 system brain electrode distribution map,
P4, Oz, O1, O2.
The object of the invention is also to provide a kind of based on the realization side for strengthening the brain-computer interface character input system paid attention to
Method.
The rate-determining steps of control method of the present invention are as follows:
1) the visual stimulus equipment shows 6 × 7 character matrix, and 42 characters are divided into 13 according to the ranks of virtual matrix
Group, in system operation, 13 groups of characters are pseudorandom to be covered by translucent green circle, cause cerebral cortex event related
Potentiometric response, by a red horizontal line segmentation at upper and lower two semicircles, a red black circle is in the green circle at random
In one of present two semicircles, a small sensation target is formd, when user wants to input some character, will just be paid attention to
Power concentrates on the red spots in the green circle being covered on the character, realizes the purpose of enhancing vision attention, reaches induction
Higher-quality event related potential is acquired original EEG signals using eeg amplifier, amplifies and analog-to-digital conversion, letter
Number acquisition equipment sample frequency be 250Hz；
2) signal processing successively pre-processed, two steps of feature extraction, the pre-treatment step to reaction mesh
The original EEG signals of marking-up symbol carry out 0.01-30Hz bandpass filtering, after then selection stimulation starts preceding 100ms and stimulation
800ms is used as signal processing and analyzing, and carries out baseline correction using selected signal -100ms~0ms, ± 80 μ v's of setting
EEG signals amplitude threshold removes abnormal signal, and by the Signal Pretreatment stage, we will remove the electricity of the eye in original signal, the heart
The artefacts such as electricity and signal interference, retain effective brain electricity ingredient；The characteristic extraction step will reduce the sampling of original signal
Point is in order to tagsort, and in the collected -100ms in each channel~800ms signal duration, determination can most represent target
The period 160-688ms of signal characteristic, down-sampled to the signal data progress in the selected period, every 4 sampled points take one
Data point, then sample frequency becomes 62.5Hz from 250Hz, 34 sampled points of extraction in final each channel, since we use
14 electrode channels, therefore assemblage characteristic vector is 14 × 34；
3) the Classification and Identification part obtains the disaggregated model of target character identification by being trained to classifier, then right
The feature vector of the unknown character of input carries out character recognition, the character identified；
4) on the screen that the character that the information feedback loop section identifies classifier is presented in face of user, if the character is
The desired target character of user then carries out the output of character late, otherwise can be deleted, so far, the work of whole system
Process is completed, accomplished based on the brain-computer interface character input system and implementation method for strengthening attention.
Preferably, red spots are placed on the top or lower part of green circle in the first step.
Preferably, Bayes's linear regression sorting algorithm is used in the third step, is constructed first by feature vector
Then the disaggregated model of target character carries out Classification and Identification after pretreatment to collected user's EEG signals.
The invention has the advantages that, to possess normal thinking ability, can not but be controlled by using new presentation normal form
The limbs height paralysed patient of muscular movement processed uses, and allows user that can export expectation character (i.e. target by the system
Character) with other people realize it is normal exchange, express oneself idea and demand, improve the autonomous viability of patient, system can be with
Higher characters spells accuracy rate is obtained within the shorter time, achievees the purpose that improve character output speed.
Detailed description of the invention
Fig. 1 is system module structure chart of the invention.
Fig. 2 is 6 × 7 character matrixes shown in visual stimulus equipment of the present invention.
Fig. 3 is virtual character matrix of the present invention for character grouping.
The world Tu4Shi 10-20 system brain electrode distribution map
Specific embodiment
The embodiment of the present invention is described further below for attached drawing:
As Figure 1-Figure 4, the present embodiment provides a kind of based on the brain-computer interface character input system for strengthening attention, including information
Four collecting part, signal processing, Classification and Identification part and feedback element component parts, the information collection part is used for
Acquire the EEG signals of brain, the signal processing by collected EEG signals removal original signal eye therein electricity,
Electrocardio and signal interference, the Classification and Identification part is for realizing character output, and the feedback element is by Classification and Identification part
Control effect feed back to patient, be additionally provided with visual stimulus equipment on the information collection part.
The output of target character is realized, to enhance the autonomous viability lost to muscle control ability patient.
In order to preferably handle information, it is preferable that the signal processing is by preprocessing module, characteristic extracting module group
At the preprocessing module has bandpass filtering, baseline correction, setting threshold function, and there is the characteristic extracting module drop to adopt
Sample, assemblage characteristic vector functionality.
For better Classification and Identification EEG signals, it is preferable that the Classification and Identification part has by using training
Classifier identify brain electrical feature vector functionality.
The original EEG signals of described information collection part acquisition 14 electrodes of user's cerebral cortex, 14 current potentials
Acquisition position presses Fz, F3, F4, P7, P8, Cz, C3, C4, Pz, P3, P4, the Oz on world 10-20 system brain electrode distribution map,
O1, O2.
The present invention also provides a kind of based on the implementation method for strengthening the brain-computer interface character input system paid attention to, control step
It is rapid as follows:
1) character matrix for having 6 × 7 that the visual stimulus equipment is shown, 42 characters are according to virtual character matrix (Fig. 3)
Ranks are divided into 13 groups, and in system operation, 13 groups of characters are pseudorandom to be covered by translucent green circle, cause brain skin
Layer event related potential reaction, for the green circle by a red horizontal line segmentation at upper and lower two semicircles, a red is solid
Dot is presented at random in one of two semicircles, forms a small sensation target, and user wants to input some character
When, just concentrate our efforts for being covered on the mesh that enhancing vision attention is realized on the red spots in the green circle on the character
, reach and induce higher-quality event related potential, original EEG signals are acquired using eeg amplifier, amplify and
Analog-to-digital conversion, the sample frequency of signal collecting device are 250Hz；
2) signal processing successively pre-processed, two steps of feature extraction, the pre-treatment step to reaction mesh
The original EEG signals of marking-up symbol carry out 0.01-30Hz bandpass filtering, after then selection stimulation starts preceding 100ms and stimulation
800ms is used as signal processing and analyzing, and carries out baseline correction using selected signal -100ms~0ms, ± 80 μ v's of setting
EEG signals amplitude threshold removes abnormal signal, and by the Signal Pretreatment stage, we will remove the electricity of the eye in original signal, the heart
The artefacts such as electricity and signal interference, retain effective brain electricity ingredient；The characteristic extraction step will reduce the sampling of original signal
Point is in order to tagsort, and in the collected -100ms in each channel~800ms signal duration, determination can most represent target
The period 160-688ms of signal characteristic, down-sampled to the signal data progress in the selected period, every 4 sampled points take one
Data point, then sample frequency becomes 62.5Hz from 250Hz, 34 sampled points of extraction in final each channel, since we use
14 electrode channels, therefore assemblage characteristic vector is 14 × 34；
3) the Classification and Identification part obtains the disaggregated model of target character identification by being trained to classifier, then right
The feature vector of the unknown character of input carries out character recognition, the character identified；
4) on the screen that the character that the information feedback loop section identifies classifier is presented in face of user, if the character is
The desired target character of user then carries out the output of character late, otherwise can be deleted, so far, the work of whole system
Process is completed, accomplished based on the brain-computer interface character input system and implementation method for strengthening attention.
Red helps to improve attention, and small sensation target can be put into more visual processes resources, the two is tied
It closes to be formed to strengthen in the presentation normal form of brain-computer interface character input system and pay attention to, it is preferable that red circle in the first step
Point is placed on the top or lower part of green circle, and solid red spots will appear corticocerebral frontal lobe area, center and top area
Apparent EEG signals enhancing, is more conducive to system and captures and extract EEG signals, finally more accurately and efficiently identify
Brain wants the character of input out.
Preferably, Bayes's linear regression sorting algorithm is used in the third step, first by carrying out to classifier
Training forms the disaggregated model of target character identification, then classifies after pretreatment to collected user's EEG signals
Identification.
User can be allowed directly to express the idea of oneself using the quick output character of brain-computer interface through the above steps,
The external devices such as wheelchair, mechanical arm can be even directly controlled by the character of output.
Substantially by using new presentation normal form, system can obtain higher character within the shorter time and spell the present invention
Accuracy rate is write, achievees the purpose that improve character output speed, increases system availability, while not increasing user's burden again, it should
Equipment and method use cost are cheap.
The present embodiment is not construed as the limitation to invention, but any based on spiritual improvements introduced of the invention, all should be
Within protection scope of the present invention.
Claims (8)
1. a kind of based on the brain-computer interface character input system for strengthening attention, it is characterised in that: including information collection part, signal
Four processing part, Classification and Identification part and feedback element component parts, the information collection part are used to acquire the brain of brain
Electric signal, the signal processing electric, electrocardio and signal by collected EEG signals removal original signal eye therein
Interference, the Classification and Identification part is for controlling external equipment or realizing character output, and the feedback element is by Classification and Identification portion
Point staining effect to patient user, be additionally provided with visual stimulus equipment on the information collection part.
2. a kind of based on the brain-computer interface character input system for strengthening attention according to claim 1, it is characterised in that: described
Signal processing is made of preprocessing module, characteristic extracting module, and the preprocessing module has bandpass filtering, baseline school
Just, threshold function is set, and the characteristic extracting module has down-sampled, assemblage characteristic vector functionality.
3. a kind of based on the brain-computer interface character input system for strengthening attention according to claim 1, it is characterised in that: described
Classification and Identification part, which has, obtains object-class model device, identification input brain electrical feature vector function using trained sorting algorithm
Energy.
4. a kind of based on the brain-computer interface character input system for strengthening attention according to claim 1, it is characterised in that: described
Information collection part acquires the original EEG signals of 14 potential electrodes of user's cerebral cortex, the acquisition of 14 potential electrodes
Fz, F3, F4, P7, P8, Cz, C3, C4, Pz, the P3 on the record standard distribution map of world 10-20 system brain electrode position are pressed in position,
P4, Oz, O1, O2.
5. according to described a kind of based on strengthening the brain-computer interface character input system paid attention to using any one of Claims 1-4 4
Implementation method, it is characterised in that: its rate-determining steps is as follows:
1) there is 6 × 7 character matrix in the stimulation picture that the visual stimulus equipment is shown, 42 characters are according to virtual character square
The ranks of battle array are divided into 13 groups, and in system operation, the pseudorandom several characters of 13 groups of characters can be by translucent green circle
Covering causes cerebral cortex event related potential to react, and the green circle circle is by a red horizontal line segmentation at upper and lower two
Semicircle, in a red black circle red spots are added in one that stimulation picture is presented on two semicircles at random,
In form a small sensation target, when test picture start flashing when, when user wants to input some character, will just infuse
Meaning power concentrates on the red spots in the green circle of the picture being covered on the character, realizes the purpose of enhancing vision attention,
Reach and induce higher-quality event related potential, original EEG signals are acquired using eeg amplifier, are amplified and mould
Number conversion, the sample frequency of signal collecting device are 250Hz；
2) signal processing is successively pre-processed, two steps of feature extraction form, and the pre-treatment step is to anti-
The original EEG signals of target character are answered to carry out 0.01-30Hz bandpass filtering, after then selection stimulation starts preceding 100ms and stimulation
800ms is used as signal processing and analyzing, and carries out baseline correction using selected signal -100ms~0ms, ± 80 μ v's of setting
EEG signals amplitude threshold is gone unless except abnormal EEG signals, and by the Signal Pretreatment stage, we will be removed in original signal
Eye electricity, the artefacts such as electrocardio and signal interference, retain effective brain electricity ingredient；The characteristic extraction step will reduce original letter
Number sampled point in order to tagsort, in the collected -100ms in each channel~800ms signal duration, determination most can
The period 160-688ms for representing echo signal feature carries out down-sampled, every 4 samplings to the signal data in the selected period
Point takes a data point, then sample frequency becomes 62.5Hz from 250Hz, 34 sampled points of extraction in final each channel, due to
We used 14 electrode channels, therefore assemblage characteristic vector is 14 × 34；
3) the Classification and Identification part is by carrying out feature vector of the classifier recognizer to the representative target character of input
Training, obtain the disaggregated model for representing target character signal identification, then to the feature vector of the representative unknown character of input into
Line character identification, the character identified；
4) character that sorting algorithm device identifies is presented on the screen in face of user by the information feedback loop section, if the word
Symbol is the output that the desired target character of user then carries out character late, otherwise can be deleted, so far, whole system
Workflow is completed, accomplished based on the brain-computer interface character input system and implementation method for strengthening attention.
6. implementation method according to claim 5, it is characterised in that: red spots are placed on green circle in the first step
Top.
7. implementation method according to claim 5, it is characterised in that: red spots are placed on green circle in the first step
Lower part.
8. implementation method according to claim 5, it is characterised in that: use Bayes's linear regression in the third step
Sorting algorithm constructs the disaggregated model of target character by feature vector first, then passes through to collected user's EEG signals
Classification and Identification is carried out after crossing pretreatment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910514978.2A CN110262658B (en) | 2019-06-14 | 2019-06-14 | Brain-computer interface character input system based on enhanced attention and implementation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910514978.2A CN110262658B (en) | 2019-06-14 | 2019-06-14 | Brain-computer interface character input system based on enhanced attention and implementation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110262658A true CN110262658A (en) | 2019-09-20 |
| CN110262658B CN110262658B (en) | 2023-02-03 |
Family
ID=67918296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910514978.2A Active CN110262658B (en) | 2019-06-14 | 2019-06-14 | Brain-computer interface character input system based on enhanced attention and implementation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110262658B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111338482A (en) * | 2020-03-04 | 2020-06-26 | 太原理工大学 | Brain-controlled character spelling recognition method and system based on supervised self-encoding |
| CN112162634A (en) * | 2020-09-24 | 2021-01-01 | 华南理工大学 | Digital input brain-computer interface system based on SEEG signal |
| CN112650386A (en) * | 2020-12-07 | 2021-04-13 | 华南师范大学 | PCA-PCN-based brain-computer interface character output system |
| CN113421141A (en) * | 2020-07-29 | 2021-09-21 | 阿里巴巴集团控股有限公司 | Shopping processing method and device based on brain-computer and brain nerve signals and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103399639A (en) * | 2013-08-14 | 2013-11-20 | 天津医科大学 | Combined brain-computer interface method and device based on SSVEP (Steady-State Visually Evoked Potentials) and P300 |
| WO2014052938A1 (en) * | 2012-09-28 | 2014-04-03 | The Regents Of The University Of California | Systems and methods for sensory and cognitive profiling |
| CN103955270A (en) * | 2014-04-14 | 2014-07-30 | 华南理工大学 | Character high-speed input method of brain-computer interface system based on P300 |
| CN103995582A (en) * | 2014-04-25 | 2014-08-20 | 南昌大学 | Brain-computer interface character input method and system based on steady-state visual evoked potential (SSVEP) |
| CN106155329A (en) * | 2016-09-06 | 2016-11-23 | 西安交通大学 | Steady-state induced current potential brain-machine interface method based on reciprocally swinging visually-perceptible |
-
2019
- 2019-06-14 CN CN201910514978.2A patent/CN110262658B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014052938A1 (en) * | 2012-09-28 | 2014-04-03 | The Regents Of The University Of California | Systems and methods for sensory and cognitive profiling |
| CN103399639A (en) * | 2013-08-14 | 2013-11-20 | 天津医科大学 | Combined brain-computer interface method and device based on SSVEP (Steady-State Visually Evoked Potentials) and P300 |
| CN103955270A (en) * | 2014-04-14 | 2014-07-30 | 华南理工大学 | Character high-speed input method of brain-computer interface system based on P300 |
| CN103995582A (en) * | 2014-04-25 | 2014-08-20 | 南昌大学 | Brain-computer interface character input method and system based on steady-state visual evoked potential (SSVEP) |
| CN106155329A (en) * | 2016-09-06 | 2016-11-23 | 西安交通大学 | Steady-state induced current potential brain-machine interface method based on reciprocally swinging visually-perceptible |
Non-Patent Citations (5)
| Title |
|---|
| HANHAN ZHANG等: "Concentrate your mind by counting the flashing point: A new P300 pattern in BCI", 《2016 SIXTH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND TECHNOLOGY》 * |
| 俞建成等: "基于事件相关电位的水下机械手脑电波控制", 《机器人》 * |
| 李佳宁等: "基于体感电刺激诱发P300的脑机接口", 《仪器仪表学报》 * |
| 李奇等: "基于P300脑机接口系统实验范式的研究现状", 《电子科技》 * |
| 陈柱兵: "基于P300的高速字符输入脑机接口研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111338482A (en) * | 2020-03-04 | 2020-06-26 | 太原理工大学 | Brain-controlled character spelling recognition method and system based on supervised self-encoding |
| CN113421141A (en) * | 2020-07-29 | 2021-09-21 | 阿里巴巴集团控股有限公司 | Shopping processing method and device based on brain-computer and brain nerve signals and electronic equipment |
| CN112162634A (en) * | 2020-09-24 | 2021-01-01 | 华南理工大学 | Digital input brain-computer interface system based on SEEG signal |
| CN112650386A (en) * | 2020-12-07 | 2021-04-13 | 华南师范大学 | PCA-PCN-based brain-computer interface character output system |
| CN112650386B (en) * | 2020-12-07 | 2023-05-16 | 华南师范大学 | Brain-computer interface character output system based on PCA-PCN |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110262658B (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262658A (en) | A kind of brain-computer interface character input system and implementation method based on reinforcing attention | |
| Kamousi et al. | Classification of motor imagery tasks for brain-computer interface applications by means of two equivalent dipoles analysis | |
| Rao et al. | Brain-computer interfacing [in the spotlight] | |
| Krepki et al. | The Berlin Brain-Computer Interface (BBCI)–towards a new communication channel for online control in gaming applications | |
| Thulasidas et al. | Robust classification of EEG signal for brain-computer interface | |
| McFarland et al. | Brain-computer interfaces for communication and control | |
| CN106362287A (en) | Novel MI-SSSEP mixed brain-computer interface method and system thereof | |
| CN101339455B (en) | Brain machine interface system based on human face recognition specific wave N170 component | |
| CN104978035B (en) | Brain machine interface system and its implementation based on body-sensing electric stimulus inducing P300 | |
| Lehtonen et al. | Online classification of single EEG trials during finger movements | |
| CN106502405A (en) | Based on the compound limbs Imaginary Movement multi-mode brain-computer interface method and system of synchronicity | |
| CN102184415A (en) | Electroencephalographic-signal-based fatigue state recognizing method | |
| CN107463250B (en) | The method for improving P300 spelling device using effect under Mental Workload state | |
| CN113157100A (en) | Brain-computer interface method for adding Chinese character reading and motor imagery tasks | |
| CN107562191A (en) | The online brain-machine interface method of fine Imaginary Movement based on composite character | |
| CN106502410A (en) | Improve the transcranial electrical stimulation device of Mental imagery ability and method in brain-computer interface | |
| Naveen et al. | Brain computing interface for wheel chair control | |
| CN102306303A (en) | Electroencephalography signal characteristic extraction method based on small training samples | |
| CN113208593A (en) | Multi-modal physiological signal emotion classification method based on correlation dynamic fusion | |
| Li et al. | An adaptive P300 model for controlling a humanoid robot with mind | |
| CN106774851A (en) | Sense of touch finger motion rehabilitation system and method based on brain-computer interface | |
| CN112162634A (en) | Digital input brain-computer interface system based on SEEG signal | |
| CN101339413B (en) | Switching control method based on brain electric activity human face recognition specific wave | |
| CN106897656A (en) | Brain-computer interface training method and device based on Mental imagery | |
| Pfurtscheller et al. | EEG-based brain-computer interface using subject-specific spatial filters |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |