CN114327061B - Method for realizing calibration-free P300 brain-computer interface - Google Patents
Method for realizing calibration-free P300 brain-computer interface Download PDFInfo
- Publication number
- CN114327061B CN114327061B CN202111616160.5A CN202111616160A CN114327061B CN 114327061 B CN114327061 B CN 114327061B CN 202111616160 A CN202111616160 A CN 202111616160A CN 114327061 B CN114327061 B CN 114327061B
- Authority
- CN
- China
- Prior art keywords
- brain
- computer interface
- current
- indicator
- component
- 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 application relates to a method for realizing a non-calibration P300 brain-computer interface, which comprises the steps of setting two indicators for each tested, wherein one indicator indicates that the current stimulus induces a P300 component, and the other indicator indicates that the current stimulus does not induce the P300 component; in the advancing process, selecting an indicator as a judgment on whether the current stimulation induces the P300 component according to a set strategy on the basis of observing the current electroencephalogram signal; meanwhile, on a P300 brain-computer interface experimental platform, a strategy is selected according to feedback optimization of the platform. The method can start the interaction of the P300 brain-computer interface on the premise of no calibration, and can quickly optimize the performance in the interaction process, thereby improving the working efficiency of the P300 brain-computer interface.
Description
Technical Field
The application belongs to the technical field of biological recognition, and particularly relates to a method for realizing a calibration-free P300 brain-computer interface.
Background
P300 is an event-related potential generated during brain cognition and is mainly related to psychological factors such as expectancy, mind, arousal, attention, and the like. The P300 brain-computer interface typically requires a process of test calibration to collect test brain-electrical data and train a test-specific classifier. However, the tested calibration process is time-consuming and laborious, affects the tested body, and is unfavorable for improving the efficiency of the P300 brain-computer interface.
Disclosure of Invention
The application aims to provide a method for realizing a P300 brain-computer interface without calibration, which can start the interaction of the P300 brain-computer interface on the premise of no calibration, quickly optimize the performance in the interaction process and improve the working efficiency of the P300 brain-computer interface.
In order to achieve the above purpose, the application adopts the following technical scheme: a method for implementing a non-calibrated P300 brain-computer interface, wherein the method comprises providing two indicators for each subject, one indicator indicating that the current stimulus induces a P300 component and the other indicator indicating that the current stimulus does not induce a P300 component; in the advancing process, selecting an indicator as a judgment on whether the current stimulation induces the P300 component according to a set strategy on the basis of observing the current electroencephalogram signal; and meanwhile, optimizing and selecting strategies according to feedback of the brain-computer interaction platform.
Further, the method sets a= { a of indicators for each tested set p ,a n Each scintillation stimulus is called a }The three, P300 brain-computer interface system according to three t The order of t=1, 2,3, … … advances; in each three, the P300 brain-computer interface system acquires the characteristic vector of the brain electrical signal of the current three:observing e according to the set strategy t Selecting an indicator a from A t The method comprises the steps of carrying out a first treatment on the surface of the If a is t ＝a p The P300 brain-computer interface system considers the current tri to elicit a P300 component, otherwise considers the current tri to not elicit a P300 component.
Further, the P300 brain-computer interface system is able to obtain feedback about the current real, called r t,p And r t,n The method comprises the steps of carrying out a first treatment on the surface of the If the current three does induce P300, r t,p ＝1,r t,n =0, otherwise r t,p ＝0,r t,n =1; the P300 brain-computer interface system updates the strategy of selecting the indicator from A every time feedback is obtained, so that the selection strategy is continuously optimized.
Further, the method for selecting the strategy of the indicator and optimizing the selection strategy by the P300 brain-computer interface system comprises the following steps:
initial settingd-dimensional identity matrix phi and d-dimensional zero vector b a a.epsilon.A, in real t During the advancement of t=1, 2,3, … …, each three performs the following steps:
step 1: extraction e t ；
Step 2: for each a.epsilon.A, calculate Φ -1 b a And assigned toThen calculate->And assign p to t,a ；
Step 3: calculation of a t ＝argmax a∈A p t,a And according to a t Output three t Judging whether to induce P300;
step 4: obtaining a three t Feedback r of (2) t,p And r t,n ；
Step 5: by usingUpdating phi;
step 6: for each a.epsilon.A, use b a +r t,aet Update b a 。
Compared with the prior art, the application has the following beneficial effects: the method allows the P300 brain-computer interface system to start P300 brain-computer interface interaction on the premise of no calibration and rapidly optimize performance in the interaction process, so that the working efficiency of the P300 brain-computer interface is improved on the premise of not affecting the tested experience.
Drawings
FIG. 1 is a schematic diagram of a method for implementing a calibration-free P300 brain-computer interface according to an embodiment of the present application.
Detailed Description
The application will be further described with reference to the accompanying drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
As shown in fig. 1, the present embodiment provides a method for implementing a calibration-free P300 brain-computer interface, in which two indicators are set for each test, one indicator indicating that the current stimulus induces a P300 component, and the other indicator indicating that the current stimulus does not induce a P300 component; in the advancing process, selecting an indicator as a judgment on whether the current stimulation induces the P300 component according to a set strategy on the basis of observing the current electroencephalogram signal; meanwhile, on a P300 brain-computer interface experimental platform, a strategy is selected according to feedback optimization of the platform.
Based on the P300 brain-computer interface system realized by the application, an indicator set A= { a is set for each tested p ,a n Each scintillation stimulus is called a trial, according to which the P300 brain-computer interface system t The order of t=1, 2,3, … … advances; in each three, after the P300 brain-computer interface system performs conventional preprocessing on the original brain-computer signal, intercepting the stimulated 800ms brain-computer signal, taking Fz, cz, pz, oz, PO7 and PO8 leads, taking an average value every 40ms on each lead, and connecting all the average values into a 120-dimensional vector, thereby obtaining corresponding feature vectors: here, d=120. Observing e according to the set strategy t Selecting an indicator a from A t The method comprises the steps of carrying out a first treatment on the surface of the If a is t ＝a p The P300 brain-computer interface system considers the current tri to elicit a P300 component, otherwise considers the current tri to not elicit a P300 component.
In the scenario of a P300 brain-computer interface replication experiment, the P300 brain-computer interface experiment platform knows whether the current three can induce the P300 component, and the P300 brain-computer interface system acquires feedback r about the current three from the experiment platform t,p And r t,n The method comprises the steps of carrying out a first treatment on the surface of the If the current three does induce P300, r t,p ＝1,r t,n =0, otherwise r t,p ＝0,r t,n =1; the P300 brain-computer interface system updates the strategy of selecting the indicator from A every time feedback is obtained, thereby enabling the selection strategySlightly optimized.
The strategy for selecting the indicator and the method for optimizing the selection strategy by the P300 brain-computer interface system are as follows.
Initial settingd-dimensional identity matrix phi and d-dimensional zero vector b a a.epsilon.A, in real t During the advancement of t=1, 2,3, … …, each three performs the following steps:
step 1: extraction e t ；
Step 2: for each a.epsilon.A, calculate Φ -1 b a And assigned toThen calculate->And assign p to t,a ；
Step 3: calculation of a t ＝argmax a∈A p t,a And according to a t Output three t Judging whether to induce P300;
step 4: obtaining a three t Feedback r of (2) t,p And r t,n ；
Step 5: by usingUpdating phi;
step 6: for each a.epsilon.A, use b a +r t,a et update b a 。
The above description is only a preferred embodiment of the present application, and is not intended to limit the application in any way, and any person skilled in the art may make modifications or alterations to the disclosed technical content to the equivalent embodiments. However, any simple modification, equivalent variation and variation of the above embodiments according to the technical substance of the present application still fall within the protection scope of the technical solution of the present application.
Claims (1)
1. A method for implementing a non-calibrated P300 brain-computer interface, wherein the method comprises providing two indicators for each subject, one indicator indicating that the current stimulus induces a P300 component and the other indicator indicating that the current stimulus does not induce a P300 component; in the advancing process, selecting an indicator as a judgment on whether the current stimulation induces the P300 component according to a set strategy on the basis of observing the current electroencephalogram signal; meanwhile, on a P300 brain-computer interface experimental platform, optimizing and selecting strategies according to feedback of the platform;
the method sets a = { a of indicators for each tested p ，a n Each scintillation stimulus is called a trial, according to which the P300 brain-computer interface system t T=1, 2,3, &..the order of the. Advances; in each three, the P300 brain-computer interface system acquires the characteristic vector of the brain electrical signal of the current three:observing e according to the set strategy t Selecting an indicator a from A t The method comprises the steps of carrying out a first treatment on the surface of the If a is t ＝a p The P300 brain-computer interface system considers that the current tri induces the P300 component, otherwise, the current tri does not induce the P300 component;
the P300 brain-computer interface system can obtain feedback about the current real, called r t，p And r t，n The method comprises the steps of carrying out a first treatment on the surface of the If the current three does induce P300, r t，p ＝1，r t，n =0, otherwise r t，p ＝0，r t，n =1; the P300 brain-computer interface system updates the strategy of selecting the indicator from the A every time feedback is obtained, so that the selection strategy is continuously optimized;
the method for selecting the strategy of the indicator and optimizing the selection strategy by the P300 brain-computer interface system comprises the following steps:
initial settingd-dimensional identity matrix phi and d-dimensional zero vector b a a.epsilon.A, in real t T=1, 2,3,. The propulsion process of the @ is, each three performs the following steps:
step 1: extraction e t ；
Step 2: for each a.epsilon.A, calculate Φ -1 b a And assigned toThen calculate->And assign p to t，a ；
Step 3: calculation of a t ＝argmax a∈A p t，a And according to a t Output three t Judging whether to induce P300;
step 4: obtaining a three t Feedback r of (2) t，p And r t，n ；
Step 5: by usingUpdating phi;
step 6: for each a.epsilon.A, use b a +r t，a e t Update b a 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111616160.5A CN114327061B (en) | 2021-12-27 | 2021-12-27 | Method for realizing calibration-free P300 brain-computer interface |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111616160.5A CN114327061B (en) | 2021-12-27 | 2021-12-27 | Method for realizing calibration-free P300 brain-computer interface |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114327061A CN114327061A (en) | 2022-04-12 |
| CN114327061B true CN114327061B (en) | 2023-09-29 |
Family
ID=81012537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111616160.5A Active CN114327061B (en) | 2021-12-27 | 2021-12-27 | Method for realizing calibration-free P300 brain-computer interface |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114327061B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104978035A (en) * | 2015-07-27 | 2015-10-14 | 中国医学科学院生物医学工程研究所 | Brain computer interface system evoking P300 based on somatosensory electrical stimulation and implementation method thereof |
| KR20150124368A (en) * | 2014-04-28 | 2015-11-05 | 삼성전자주식회사 | Apparatus and method for implementing a p300 component-based brain-computer interface |
| CN113434040A (en) * | 2021-06-07 | 2021-09-24 | 西北工业大学 | Brain-computer interface technical method based on augmented reality induction |
| CN113705732A (en) * | 2021-09-26 | 2021-11-26 | 华东理工大学 | Method and device for reducing P300 training time based on general model |
-
2021
- 2021-12-27 CN CN202111616160.5A patent/CN114327061B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150124368A (en) * | 2014-04-28 | 2015-11-05 | 삼성전자주식회사 | Apparatus and method for implementing a p300 component-based brain-computer interface |
| CN104978035A (en) * | 2015-07-27 | 2015-10-14 | 中国医学科学院生物医学工程研究所 | Brain computer interface system evoking P300 based on somatosensory electrical stimulation and implementation method thereof |
| CN113434040A (en) * | 2021-06-07 | 2021-09-24 | 西北工业大学 | Brain-computer interface technical method based on augmented reality induction |
| CN113705732A (en) * | 2021-09-26 | 2021-11-26 | 华东理工大学 | Method and device for reducing P300 training time based on general model |
Non-Patent Citations (1)
| Title |
|---|
| 脑机接口的MapReduce计算模型;黄志华;福州大学学报( 自然科学版);第41卷(第6期);981-985 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114327061A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107024987B (en) | Real-time human brain attention testing and training system based on EEG | |
| Thulasidas et al. | Robust classification of EEG signal for brain-computer interface | |
| CN106709469B (en) | Automatic sleep staging method based on electroencephalogram and myoelectricity multiple characteristics | |
| EP3181192B1 (en) | System for rapid acquisition of evoked compound action potential recordings | |
| CN111584029A (en) | Electroencephalogram self-adaptive model based on discriminant confrontation network and application of electroencephalogram self-adaptive model in rehabilitation | |
| CN108784693B (en) | P300 single extraction technology based on independent component analysis and Kalman smoothing | |
| CN117457229B (en) | Anesthesia depth monitoring system and method based on artificial intelligence | |
| CN113827865B (en) | Transcranial magnetic stimulation position determination method, transcranial magnetic stimulation position determination device, electronic equipment and storage medium | |
| CN111428601B (en) | P300 signal identification method, device and storage medium based on MS-CNN | |
| CN114327061B (en) | Method for realizing calibration-free P300 brain-computer interface | |
| CN113017645B (en) | P300 signal detection method based on void convolutional neural network | |
| CN113017650A (en) | Electroencephalogram feature extraction method and system based on power spectral density image | |
| CN111580643A (en) | Brain-computer interface method based on steady-state asymmetric visual evoked potential | |
| CN110472595B (en) | Electroencephalogram recognition model construction method and device and recognition method and device | |
| CN111616702A (en) | Lie detection analysis system based on cognitive load enhancement | |
| CN109949299A (en) | A kind of cardiologic medical image automatic segmentation method | |
| CN107822628B (en) | Epileptic brain focus area automatic positioning device and system | |
| Bayford et al. | Advances in electrical impedance tomography and bioimpedance including applications in COVID-19 diagnosis and treatment | |
| CN107374620A (en) | A kind of EEG signals preprocess method based on independent composition analysis algorithm | |
| Daǧ et al. | Leveraging deep learning techniques to improve P300-based brain computer interfaces | |
| CN115845255A (en) | Feedback intervention method and system for performing peripheral stimulation in real time in specific sleep state | |
| WO2016055979A1 (en) | Plural task fitting | |
| Liu et al. | A cross-subject SSVEP-BCI based on task related component analysis | |
| CN115474899A (en) | Basic taste perception identification method based on multi-scale convolution neural network | |
| CN114492536B (en) | Myoimpedance signal separation method |
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 |