CN110262658B - Brain-computer interface character input system based on enhanced attention and implementation method - Google Patents
Brain-computer interface character input system based on enhanced attention and implementation method Download PDFInfo
- Publication number
- CN110262658B CN110262658B CN201910514978.2A CN201910514978A CN110262658B CN 110262658 B CN110262658 B CN 110262658B CN 201910514978 A CN201910514978 A CN 201910514978A CN 110262658 B CN110262658 B CN 110262658B
- Authority
- CN
- China
- Prior art keywords
- brain
- signal
- character
- attention
- 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.)
- Active
Links
Images
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
Abstract
The invention relates to the technical field of brain-computer interfaces, in particular to a brain-computer interface character input system based on enhanced attention and an implementation method. The invention includes: the brain electrical stimulation brain electrical stimulation device comprises an information acquisition part, a signal processing part, a classification identification part and a feedback link, wherein the information acquisition part is used for acquiring brain electrical signals, the signal processing part removes the eye electrical interference, the electrocardio interference and the signal interference of the acquired brain electrical signals from original signals, the classification identification part is used for realizing character output, the feedback link feeds back the effect of the classification identification part to a user, and the information acquisition part is also provided with visual stimulation equipment.
Description
Technical Field
The invention relates to the technical field of brain-computer interfaces, in particular to a brain-computer interface character input system based on enhanced attention and an implementation method.
Background
Brain-Computer Interface (BCI) is a kind of artificial connection path established between the Brain of a human or animal and an external device without relying on the connection between the nerve path and the muscle tissue of the organism itself. The method relates to the interdisciplinary knowledge of multiple disciplines such as neuroscience, signal detection, signal processing, pattern recognition and the like, and is one of the hot research problems in the field of brain science research at present. The brain-computer interface system is used as a brand-new information exchange technology, can provide a new way for people to communicate with the outside, and particularly provides a new channel for the patients with language disorder or severe paralysis but normal brain function to interact with the outside.
At present, electroencephalogram signals commonly used in a brain-computer interface system are mainly classified into four types: slow-varying Cortical Potentials (SCP), steady-State Visual Evoked Potentials (SSVEP), motor imagery based Mu/Beta rhythms, event-related Potentials (ERPs). The Slow Cortical Potential (SCP) reflects the Slow voltage changes generated by the low frequency parts of the cerebral cortex, and the subject needs to be trained repeatedly to form conditioned reflex, so that the positive and negative changes of the Slow Cortical Potential can be controlled consciously when feedback information appears. In the Steady-State Visual Evoked Potential (SSVEP) system, when a subject is subjected to a Visual stimulus with a fixed frequency, a continuous response related to the stimulus frequency is generated in the Visual cortex of the brain, and the response is called Steady-State Visual Evoked Potential. And because of the electroencephalogram signal of the Mu/Beta rhythm of the motor imagery, when people imagine different limbs to move, the reduction of Mu rhythm of a sensory-motor cortical area of the corresponding limb is caused, the reduction is called as 'event-related desynchronization', and the judgment of the specific motor imagery limb is realized by identifying the reduction of Mu rhythm energy of different brain areas. The event correlation desynchronization mainly aims at the research of two motor imagery tasks, and the classification accuracy of the three or more motor imagery tasks is greatly reduced.
Relatively speaking, the brain-computer interface technology based on the event-related potential (ERP) does not need the training of the subject in advance, has concise configuration requirements and simple operation, and can achieve relatively high classification accuracy under the condition of multiple classifications. At present, the event-related potentials are basically presented in a P300 visual stimulation paradigm, and the speed of a character input system based on the P300 visual stimulation paradigm still cannot achieve the practical purpose. Researchers wish to achieve the goal of improving system performance by changing the stimulus presentation paradigm. Among them, increasing the cognitive workload or novelty of the stimulus picture can improve the system performance, but in the case of long-term gazing, the novelty is also degraded by fatigue that is more likely to cause to the user. The addition of auditory stimuli during the visual stimuli is also one of the means to improve the performance of the character spelling system, but requires more effort from the user.
Disclosure of Invention
In order to overcome the defects of the background art, the invention provides a brain-computer interface character input system based on enhanced attention, which comprises the following steps:
the technical scheme of the invention is as follows: the brain electrical stimulation brain electrical stimulation device comprises an information acquisition part, a signal processing part, a classification identification part and a feedback link, wherein the information acquisition part is used for acquiring brain electrical signals, the signal processing part removes the eye electrical interference, the electrocardio interference and the signal interference of the acquired brain electrical signals from original signals, the classification identification part is used for realizing character output, the feedback link feeds back the control effect of the classification identification part to a user, and the information acquisition part is also provided with visual stimulation equipment.
Preferably, the signal processing part consists of a preprocessing module and a feature extraction module, the preprocessing module has functions of band-pass filtering, baseline correction and threshold setting, and the feature extraction module has functions of down-sampling and feature vector combination.
Preferably, the classification and identification part has a function of identifying the electroencephalogram feature vector by using a trained classifier.
Preferably, the information acquisition part acquires original brain electrical signals of 14 electrodes of the cerebral cortex of the user, and the acquisition positions of the 14 electrodes are Fz, F3, F4, P7, P8, cz, C3, C4, pz, P3, P4, oz, O1 and O2 on the electroencephalogram distribution map of the international 10-20 system.
The invention also aims to provide an implementation method of the brain-computer interface character input system based on the attention enhancement.
The control method comprises the following control steps:
the first step is as follows: the visual stimulation equipment displays a 6 multiplied by 7 character matrix, 42 characters are divided into 13 groups according to the row and column of a virtual matrix, in the system operation process, the 13 groups of characters are covered by a semitransparent green circle in a pseudo-random manner to cause the relevant potential reaction of cerebral cortex events, the green circle is divided into an upper semicircle and a lower semicircle by a red horizontal straight line, a red solid dot is randomly presented in one of the two semicircles to form a small visual target, when a user wants to input a certain character, the user concentrates the attention on the red dot covered in the green circle on the character to achieve the purpose of enhancing the visual attention and induce the relevant potential of events with higher quality, an electroencephalogram amplifier is used for collecting, amplifying and performing analog-to-digital conversion on an original electroencephalogram signal, and the sampling frequency of the signal collecting equipment is 250Hz;
the second step is as follows: the signal processing part sequentially carries out two steps of preprocessing and feature extraction, wherein the preprocessing step carries out 0.01-30Hz band-pass filtering on an original electroencephalogram signal reflecting a target character, then 100ms before stimulation is started and 800ms after stimulation are selected for signal processing and analysis, the selected signal is used for carrying out baseline correction in-100 ms-0 ms, an electroencephalogram signal amplitude threshold value of +/-80 mu v is set to remove abnormal signals, and after a signal preprocessing stage, artifacts such as electrooculogram, electrocardio and signal interference in the original signal are removed, and effective electroencephalogram components are reserved; in the characteristic extraction step, sampling points of an original signal are reduced to facilitate characteristic classification, a time period 160-688ms which can represent the characteristics of a target signal most is determined within a signal duration of-100 ms-800 ms acquired by each channel, signal data in a selected time period is subjected to down-sampling, a data point is taken at every 4 sampling points, the sampling frequency is changed from 250Hz to 62.5Hz, and finally 34 sampling points are extracted from each channel, so that a combined characteristic vector is 14 multiplied by 34 because 14 electrode channels are used;
the third step: the classification recognition part obtains a classification model of target character recognition by training a classifier, and then performs character recognition on the feature vector of the input unknown character to obtain a recognized character;
the fourth step: and in the information feedback link, the character identified by the classifier is displayed on a screen in front of a user, if the character is a target character expected by the user, the next character is output, otherwise, the next character can be deleted, and the work flow of the whole system is completed.
Preferably, the red dots are placed on top or bottom of the green circles in the first step.
Preferably, a bayesian linear regression classification algorithm is adopted in the third step, a classification model of the target characters is firstly constructed through the feature vectors, and then classification and identification are carried out on the acquired user electroencephalogram signals after preprocessing.
The system has the advantages that the system is used by the patient with highly paralyzed limbs which has normal thinking ability but can not control muscle movement by using a new presentation paradigm, so that a user can output expected characters (namely target characters) through the system to realize normal communication with other people, express own ideas and requirements, improve the independent living ability of the patient, and can obtain higher character spelling accuracy in a shorter time to achieve the aim of improving the character output rate.
Drawings
Fig. 1 is a block diagram of a system module of the present invention.
Fig. 2 is a matrix of 6 x 7 characters displayed on the visual stimulation apparatus of the present invention.
FIG. 3 is a virtual character matrix for grouping characters according to the present invention.
Fig. 4 is an international 10-20 system electroencephalogram profile.
Detailed Description
Embodiments of the invention are further described below with reference to the accompanying drawings:
as shown in fig. 1-4, the present embodiment provides a brain-computer interface character input system based on attention enhancement, which includes four components, namely an information acquisition component, a signal processing component, a classification and identification component, and a feedback link, wherein the information acquisition component is used for acquiring electroencephalograms of a brain, the signal processing component removes the electro-oculogram, the electrocardio, and the signal interference in the original signals from the acquired electroencephalograms, the classification and identification component is used for outputting characters, the feedback link feeds back the control effect of the classification and identification component to a patient, and the information acquisition component is further provided with a visual stimulation device.
The output of the target character is realized, thereby enhancing the autonomous life ability of the patient losing the muscle control ability.
For better processing information, the signal processing part preferably consists of a preprocessing module and a feature extraction module, wherein the preprocessing module has functions of band-pass filtering, baseline correction and threshold setting, and the feature extraction module has functions of down-sampling and feature vector combination.
For better classification and identification of the electroencephalogram signals, the classification and identification section preferably has a function of identifying electroencephalogram feature vectors by using a trained classifier.
The information acquisition part acquires original electroencephalogram signals of 14 electrodes of a cerebral cortex of a user, and the acquisition positions of the 14 electric potentials are according to Fz, F3, F4, P7, P8, cz, C3, C4, pz, P3, P4, oz, O1 and O2 on an international 10-20 system electroencephalogram distribution diagram.
The invention also provides a realization method of the brain-computer interface character input system based on the attention enhancement, which comprises the following control steps:
the first step is as follows: the visual stimulation device displays a 6 multiplied by 7 character matrix, 42 characters are divided into 13 groups according to the row and column of a virtual character matrix (figure 3), in the system operation process, the 13 groups of characters are covered by a semitransparent green circle in a pseudo-random manner to cause a cerebral cortex event related potential reaction, the green circle is divided into an upper semicircle and a lower semicircle by a red horizontal straight line, a red solid dot is randomly presented in one of the two semicircles to form a small visual target, when a user wants to input a certain character, the user concentrates the attention on the red dot in the green circle covered on the character, the purpose of enhancing the visual attention is realized, the higher quality event related potential is induced, an electroencephalogram amplifier is used for collecting, amplifying and performing analog-to-digital conversion on an original electroencephalogram signal, and the sampling frequency of the signal collecting device is 250Hz;
the second step is as follows: the signal processing part sequentially carries out two steps of preprocessing and feature extraction, wherein the preprocessing step carries out 0.01-30Hz band-pass filtering on an original electroencephalogram signal reflecting a target character, then 100ms before stimulation is started and 800ms after stimulation are selected for signal processing and analysis, the selected signal is used for carrying out baseline correction in-100 ms-0 ms, an electroencephalogram signal amplitude threshold value of +/-80 mu v is set to remove abnormal signals, and after a signal preprocessing stage, artifacts such as electrooculogram, electrocardio and signal interference in the original signal are removed, and effective electroencephalogram components are reserved; in the characteristic extraction step, sampling points of an original signal are reduced to facilitate characteristic classification, a time period 160-688ms which can represent the characteristics of a target signal most is determined within a signal duration of-100 ms-800 ms acquired by each channel, signal data in a selected time period is subjected to down-sampling, a data point is taken at every 4 sampling points, the sampling frequency is changed from 250Hz to 62.5Hz, and finally 34 sampling points are extracted from each channel, so that a combined characteristic vector is 14 multiplied by 34 because 14 electrode channels are used;
the third step: the classification recognition part obtains a classification model of target character recognition by training a classifier, and then performs character recognition on the feature vector of the input unknown character to obtain a recognized character;
the fourth step: and the information feedback link displays the character identified by the classifier on a screen in front of a user, if the character is a target character expected by the user, the next character is output, otherwise, the next character can be deleted, so far, the work flow of the whole system is completed, and the brain-computer interface character input system and the implementation method based on the enhanced attention are realized.
The red color is helpful for improving attention, a small visual target can be put into more visual processing resources, the small visual target and the small visual target are combined in a presentation paradigm of a brain-computer interface character input system to form strengthened attention, preferably, in the first step, the red circular points are placed at the upper part or the lower part of the green circle, and the solid red circular points enable the frontal lobe area, the central area and the top lobe area of the cerebral cortex to have obvious electroencephalogram signal enhancement, so that the system is more favorable for capturing and extracting the electroencephalogram signals, and finally, characters which the brain wants to input are more accurately and efficiently identified.
Preferably, a bayesian linear regression classification algorithm is adopted in the third step, a classification model for target character recognition is formed by training a classifier, and then classification recognition is performed on the acquired user electroencephalogram signals after preprocessing.
Through the steps, the user can directly use the brain-computer interface to quickly output characters to express own idea, and even can directly control external equipment such as wheelchairs, mechanical arms and the like through the output characters.
By using the new presentation paradigm, the system can obtain higher spelling accuracy of the character in a shorter time, thereby achieving the purpose of improving the output speed of the character, increasing the practicability of the system, and simultaneously not increasing the burden of a user.
The present embodiment should not be construed as limiting the invention, but any modification made based on the spirit of the present invention should be within the scope of protection of the present invention.
Claims (8)
1. An implementation method of a brain-computer interface character input system based on attention enhancement is characterized in that: the control steps are as follows:
the first step is as follows: the stimulation picture displayed by the visual stimulation equipment is provided with a 6 multiplied by 7 character matrix, 42 characters are divided into 13 groups according to the row and column of a virtual character matrix, in the operation process of a system, a plurality of pseudo-random characters of the 13 groups of characters can be covered by a semitransparent green circle to cause the reaction of related potentials of cerebral cortex events, the green circle is divided into an upper semicircle and a lower semicircle by a red horizontal straight line, one red solid dot is added into the red dot so that the stimulation picture is randomly presented in one of the two semicircles to form a small visual target, when an experimental picture begins to flash, a user wants to input a certain character, the attention is focused on the red dot in the green circle of the picture covered on the character, the purpose of enhancing the visual attention is achieved, the induction of the related potentials of higher-quality cerebral electrical events is achieved, an electroencephalogram amplifier is used for collecting, amplifying and analog-to-digital conversion of original electroencephalogram signals, and the sampling frequency of the signal collection equipment is 250Hz;
the second step is as follows: the signal processing part sequentially carries out two steps of preprocessing and feature extraction, wherein the preprocessing step carries out 0.01-30Hz band-pass filtering on an original electroencephalogram signal reflecting a target character, then 100ms before stimulation starts and 800ms after stimulation are selected to be used for signal processing and analysis, the selected signal is used for carrying out baseline correction in a range of-100 ms-0 ms, an electroencephalogram signal amplitude threshold value of +/-80 mu v is set to remove abnormal electroencephalograms, and after the signal preprocessing stage, artifacts such as electro-oculogram, electrocardio and signal interference in the original signal are removed, and effective electroencephalogram components are reserved; in the characteristic extraction step, sampling points of an original signal are reduced to facilitate characteristic classification, a time period 160-688ms which can represent the characteristics of a target signal most is determined in a signal duration of-100 ms-800 ms acquired by each channel, signal data in a selected time period are subjected to down-sampling, a data point is taken at every 4 sampling points, the sampling frequency is changed from 250Hz to 62.5Hz, and finally 34 sampling points are extracted from each channel, so that a combined characteristic vector is 14 multiplied by 34 because 14 electrode channels are used;
the third step: the classification recognition part trains the input characteristic vector representing the target character through a classifier recognition algorithm to obtain a classification model representing the target character signal recognition, and then performs character recognition on the input characteristic vector representing the unknown character to obtain a recognized character;
the fourth step: and the information feedback link presents the characters identified by the classification algorithm device on a screen in front of a user, if the characters are target characters expected by the user, the next characters are output, otherwise, the next characters can be deleted, and the work flow of the whole system is completed.
2. The method for implementing a brain-computer interface character input system based on attention reinforcement according to claim 1, characterized in that: the red dots are placed on top of the green circles in the first step.
3. The method for implementing a brain-computer interface character input system based on attention reinforcement according to claim 1, characterized in that: the red dots are placed in the lower part of the green circles in the first step.
4. The method for implementing a brain-computer interface character input system based on attention reinforcement according to claim 1, characterized in that: and in the third step, a Bayesian linear regression classification algorithm is adopted, firstly, a classification model of the target character is constructed through the feature vector, and then, the acquired user electroencephalogram signal is classified and recognized after being preprocessed.
5. An attention-enhanced brain-computer interface character input system based on the implementation method of any one of claims 1 to 4, characterized in that: the brain electrical stimulation brain electrical stimulation device comprises an information acquisition part, a signal processing part, a classification identification part and a feedback link, wherein the information acquisition part is used for acquiring brain electrical signals, the signal processing part removes the eye electrical interference, the electrocardio interference and the signal interference of the acquired brain electrical signals from original signals, the classification identification part is used for controlling external equipment or realizing character output, the feedback link feeds back the effect of the classification identification part to a patient user, and the information acquisition part is also provided with visual stimulation equipment.
6. The attention-enhancing brain-computer interface character input system according to claim 5, wherein: the signal processing part comprises a preprocessing module and a feature extraction module, wherein the preprocessing module has the functions of band-pass filtering, baseline correction and threshold setting, and the feature extraction module has the functions of down-sampling and feature vector combination.
7. The attention-enhancing brain-computer interface character input system according to claim 5, wherein: the classification and identification part has the functions of obtaining a target classification model by using a trained classification algorithm and identifying input electroencephalogram feature vectors.
8. The attention-enhancing brain-computer interface character input system according to claim 5, wherein: the information acquisition part acquires original electroencephalogram signals of 14 potential electrodes of a cerebral cortex of a user, and the acquisition positions of the 14 potential electrodes are Fz, F3, F4, P7, P8, cz, C3, C4, pz, P3, P4, oz, O1 and O2 on an international 10-20 system electroencephalogram pole position recording standard distribution diagram.
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 CN110262658A (en) | 2019-09-20 |
| CN110262658B true 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) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111338482B (en) * | 2020-03-04 | 2023-04-25 | 太原理工大学 | Brain-controlled character spelling recognition method and system based on supervision self-coding |
| CN112162634A (en) * | 2020-09-24 | 2021-01-01 | 华南理工大学 | Digital input brain-computer interface system based on SEEG signal |
| CN112650386B (en) * | 2020-12-07 | 2023-05-16 | 华南师范大学 | Brain-computer interface character output system based on PCA-PCN |
Citations (3)
| 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 |
| 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) |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102282961B1 (en) * | 2012-09-28 | 2021-07-29 | 더 리젠츠 오브 더 유니버시티 오브 캘리포니아 | Systems and methods for sensory and cognitive profiling |
| CN106155329B (en) * | 2016-09-06 | 2019-01-08 | 西安交通大学 | Steady-state induced current potential brain-computer interface method based on reciprocally swinging visual perception |
-
2019
- 2019-06-14 CN CN201910514978.2A patent/CN110262658B/en active Active
Patent Citations (3)
| 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 |
| 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) |
Non-Patent Citations (1)
| Title |
|---|
| 基于P300的高速字符输入脑机接口研究;陈柱兵;《中国优秀硕士学位论文全文数据库 信息科技辑》;20180615(第2018年第6期);符输入脑机接口研究 I136-162 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110262658A (en) | 2019-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110765920B (en) | Motor imagery classification method based on convolutional neural network | |
| Takano et al. | Visual stimuli for the P300 brain–computer interface: a comparison of white/gray and green/blue flicker matrices | |
| Kaufmann et al. | Flashing characters with famous faces improves ERP-based brain–computer interface performance | |
| CN101339455B (en) | Brain machine interface system based on human face recognition specific wave N170 component | |
| CN110262658B (en) | Brain-computer interface character input system based on enhanced attention and implementation method | |
| CN113157100B (en) | Brain-computer interface method for adding Chinese character reading and motor imagery tasks | |
| CN106362287A (en) | Novel MI-SSSEP mixed brain-computer interface method and system thereof | |
| CN109521870A (en) | A kind of brain-computer interface method that the audio visual based on RSVP normal form combines | |
| CN111930238B (en) | Brain-computer interface system implementation method and device based on dynamic SSVEP (secure Shell-and-Play) paradigm | |
| CN107562191A (en) | The online brain-machine interface method of fine Imaginary Movement based on composite character | |
| CN106502404A (en) | A kind of new brain-machine interface method and system based on stable state somatosensory evoked potential | |
| CN112617863B (en) | Hybrid online computer-computer interface method for identifying lateral direction of left and right foot movement intention | |
| CN106484106A (en) | The non-attention event related potential brain-machine interface method of visual acuity automatic identification | |
| Li et al. | An adaptive P300 model for controlling a humanoid robot with mind | |
| CN108836327A (en) | Intelligent outlet terminal and EEG signal identification 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 | |
| CN107822628B (en) | Epileptic brain focus area automatic positioning device and system | |
| CN111887845A (en) | Attention regulation system based on EEG nerve feedback | |
| Pfurtscheller et al. | EEG-based brain-computer interface using subject-specific spatial filters | |
| CN106445140B (en) | The non-attention event related potential brain-computer interface method of quiet visual field automatic identification | |
| CN113807402A (en) | System for inhibiting MIs-triggering of MI-BCI system and training and testing method thereof | |
| CN113407026B (en) | Brain-computer interface system and method for enhancing hairless zone brain electric response intensity | |
| Fujisawa et al. | Extracting alpha band modulation during visual spatial attention without flickering stimuli using common spatial pattern | |
| CN107669416A (en) | Wheelchair system and control method based on persistently brisk Mental imagery nerve decoding |
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 |