Attention enhancement brain-computer interface system based on binocular color competition

Abstract

The invention discloses an attention enhancement brain-computer interface system based on binocular color competition, and belongs to the technical field of biomedical information. According to the system, electroencephalogram (EEG) data when a user watches a binocular color competition normal form is collected through an electroencephalogram cap, the collected EEG data is classified and recognized by using deep learning, man-machine interaction design is performed by using a neural feedback technology on the basis, adjustment of a neural network of the user is promoted through sound and image modes, and attention enhancement is realized. A new training mode can be provided for the attention deficit patient, and technical support is provided for application of the brain-computer interface technology in the education field.

Description

Technical Field

[0001] The present invention relates to the field of biomedical information engineering, and particularly relates to an attention-enhanced brain-computer interface system based on binocular color competition. Background Art

[0002] Existing brain-computer interface systems mainly focus on the recognition and implementation of motor intentions, while relatively few studies have been conducted on attention enhancement. Patients with neurological diseases such as attention deficit hyperactivity disorder need effective attention training methods to improve their concentration ability. Traditional attention training methods, such as drug treatment or psychological training, often have problems such as unstable curative effects or side effects. Therefore, neurofeedback training based on electroencephalogram signals has become a non-invasive physical regulation method that has received much attention.

[0003] Binocular color competition is a special visual paradigm. When the user's left and right eyes receive visual stimuli of different colors respectively, a competitive inhibition phenomenon will occur, that is, the brain can alternately perceive these two colors. Binocular color competition requires the participation of visual attention and can be used to induce brain wave patterns related to attention. By collecting and analyzing this special neural activity data, the user's attention state can be obtained, and combined with neurofeedback technology, an effective attention enhancement training system can be designed. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides an attention-enhanced brain-computer interface system based on binocular color competition.

[0005] To implement the above technical solution, specifically as follows:

[0006] An attention-enhanced brain-computer interface system based on binocular color competition, the system includes: a stimulation module, an EEG signal acquisition module, an EEG data processing module, and a human-computer interaction module.

[0007] The system usage steps are as follows:

[0008] S1. Use the stimulation module to cause a color difference between the user's left eye and right eye to induce the binocular color competition phenomenon;

[0009] The color difference formula for inducing the binocular color competition phenomenon is as follows:

[0010]

[0011] In the formula, is the LAB value of the color viewed by the left eye; is the LAB value of the color viewed by the right eye; where L is the brightness of the color, a is the axis from green to red, and b is the axis from blue to yellow; The color difference for left-eye and right-eye viewing should be greater than the binocular color competition threshold, i.e., LAB color space color difference units.

[0012] S2. Use the EEG signal acquisition module to collect the EEG signals of the user viewing the binocular color competition paradigm through a non-invasive EEG cap, and input the EEG signals into the EEG data processing module;

[0013] EEG signals, namely electroencephalogram signals, can be used to analyze brain nerve activities;

[0014] The EEG signals collected by the EEG signal acquisition module through the non-invasive EEG cap for the user viewing the binocular color competition paradigm are: the EEG signals collected by selecting an electrode cap with 128 channels, and the electrode cap signals are then transmitted to the EEG data processing module of the computer through a signal amplifier. The sampling frequency of the EEG data is 250Hz. The sampling frequency of 250Hz can not only ensure the data quality but also reduce the number of model parameters and ensure the real-time classification of the model;

[0015] The EEG signals are input into the EEG data processing module through wired transmission or wireless Bluetooth transmission.

[0016] S3. Use the EEG data processing module to classify the collected EEG data for color perception states;

[0017] Specifically, first preprocess the collected EEG data, including: filtering and removing noise and artifacts;

[0018] The filtering is: select a filtering range of 0.5Hz - 30Hz to filter the original EEG data collected by the EEG signal acquisition module;

[0019] Removing noise and artifacts is: use ICA (Independent Component Analysis) to remove noise and artifacts; the noise and artifacts include: electrooculogram, electromyogram, and electrocardiogram;

[0020] Furthermore, input the preprocessed EEG data into the EEG data processing module for color perception state classification; among them, the EEG data processing module is the preset deep learning network EEGNet. Train the preprocessed data through EEGNet, and the result of the training is the color perception state classification, including: two classifications of color fusion state and color competition state; if the user is in the binocular color competition state, it means that the attention is in a concentrated state; the color fusion state means that the attention is in a non-concentrated state.

[0021] S4. The result of the EEG data processing module is fed back to the user through the human-computer interaction module;

[0022] The human-computer interaction module includes: a visual interface, voice output, and real-time feedback function of the training progress;

[0023] The human-computer interaction module makes dynamic adjustments according to the classification results of the EEG data processing module. Specifically, when the user's state is judged to be the color competition state, it indicates that the user's attention is concentrated, and the visual interface and voice output give positive feedback; when the user's state is judged to be the color fusion state, it indicates that the user's attention is not concentrated, and negative feedback is provided to prompt the user to concentrate again, realizing the interaction between the user and the system.

[0024] Advantages of the present invention:

[0025] The present invention has the advantages of non-invasiveness and customization, providing a novel and effective training method for patients with attention deficit, and can also be applied to other scenarios that require improving attention, such as attention training in learning and work.

[0026] The technology of the present invention can also be extended and applied to other fields, such as neurorehabilitation of brain-computer interfaces, cognitive enhancement, attention control in virtual reality, etc. Description of the Drawings

[0027] Figure 1 is a schematic diagram of the binocular color competition-based attention enhancement brain-computer interface system of the present invention; in the figure: 1 represents the stimulation module, 2 represents the EEG signal acquisition module, 3 represents the EEG data processing module, and 4 represents the human-computer interaction module;

[0028] Figure 2 is a framework diagram of the binocular color competition-based attention enhancement brain-computer interface system of the present invention;

[0029] Figure 3 is the space for color selection in the stimulation module of the present invention;

[0030] Figure 4 is the EEG cap electrode diagram that can adopt 128 leads in the present invention;

[0031] Figure 5 is the data amplification schematic diagram in the EEG data processing module. Detailed Embodiments

[0032] The present invention will be further described in detail below with reference to specific embodiments.

[0033] As Figure 1 and Figure 2 shown, an attention enhancement brain-computer interface system based on binocular color competition, the system includes: a stimulation module, an EEG signal acquisition module, an EEG data processing module, and a human-computer interaction module.

[0034] The system usage steps are as follows:

[0035] S1. Use the stimulation module to cause color differences between the user's left and right eyes to induce the binocular color competition phenomenon;

[0036] The color difference formula for inducing the binocular color competition phenomenon is as follows:

[0037]

[0038] In the formula, is the LAB value of the color viewed by the left eye; is the LAB value of the color viewed by the right eye; where L is the brightness of the color, a is the axis from green to red, and b is the axis from blue to yellow; is the color difference between the colors viewed by the left and right eyes, and the color difference requirement is greater than the binocular color competition threshold, that is LAB color space color difference units, such as Figure 3 shown;

[0039] The stimulation module is used to design the binocular color competition paradigm. Specifically, when implemented, colors can be designed on a naked-eye 3D display or a display with 2D / 3D switching function that requires wearing shutter glasses, and the color values viewed by the user's left and right eyes are selected in the CIELAB color space.

[0040] S2. Use the EEG signal acquisition module to collect the EEG signal of the user viewing the binocular color competition paradigm through a non-invasive EEG cap, and input the EEG signal into the EEG data processing module;

[0041] The EEG signal, that is, the electroencephalogram signal, can be used to analyze brain nerve activities;

[0042] As Figure 4 shown, the EEG signal acquisition module collects the EEG signal of the user viewing the binocular color competition paradigm through a non-invasive EEG cap: the EEG signal collected by selecting an electrode cap containing 128 channels, and the electrode cap signal is then transmitted to the EEG data processing module of the computer through a signal amplifier. The sampling frequency of the EEG data is 250Hz. The sampling frequency of 250Hz can not only ensure the data quality, but also reduce the number of model parameters and ensure the real-time classification of the model;

[0043] Input the EEG signal into the EEG data processing module through wired transmission or wireless Bluetooth transmission;

[0044] Specifically, the stimulation module on the 3D display controls the colors viewed by the left and right eyes, thereby realizing the binocular color competition paradigm viewed by the user. When the user views the stimulation module, the generated brain electrical signal is collected by the non-invasive EEG cap and finally transmitted to the EEG data processing module through a signal amplifier either wired or wirelessly.

[0045] S3. Use the EEG data processing module to classify the collected EEG data into color perception states;

[0046] Specifically, first preprocess the collected EEG data, including: filtering and removing noise and artifacts;

[0047] The filtering is as follows: Select a filtering range of 0.5 Hz - 30 Hz to filter the original EEG data collected by the EEG signal acquisition module;

[0048] Removing noise and artifacts is as follows: Use ICA (Independent Component Analysis) to remove noise and artifacts; The noise and artifacts include: electrooculogram, electromyogram, and electrocardiogram;

[0049] Furthermore, input the preprocessed EEG data into the EEG data processing module for color perception state classification; Among them, the EEG data processing module is a preset deep learning network EEGNet, as Figure 5 shown, train the preprocessed data through EEGNet, and the result of the training is the color perception state classification, including: two classifications of color fusion state and color competition state; If the user is in the binocular color competition state, it indicates that the attention is in a concentrated state; The color fusion state indicates that the attention is in an unfocused state.

[0050] S4. The result of the EEG data processing module is fed back to the user through the human-computer interaction module;

[0051] The human-computer interaction module includes: a visual interface, sound output, and a real-time feedback function of the training progress;

[0052] The human-computer interaction module makes dynamic adjustments according to the classification result of the EEG data processing module. Specifically, when the user's state is judged to be the color competition state, it indicates that the user's attention is concentrated, and the visual interface and sound output give positive feedback; When the user's state is judged to be the color fusion state, it indicates that the user's attention is not concentrated, and negative feedback is provided to prompt the user to refocus, realizing the interaction between the user and the system.

[0053] The specific implementation manners of the present invention have been described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the above-mentioned implementation manners. Within the scope of knowledge possessed by those of ordinary skill in the art, various changes can be made without departing from the gist of the present invention.

Claims

1. An attention-enhanced brain-computer interface system based on binocular color competition, characterized in that: The system includes: a stimulation module, an EEG signal acquisition module, an EEG data processing module, and a human-computer interaction module; The steps to use the system are as follows: S1. Using the stimulation module, a color difference is generated between the user's left eye and right eye to induce binocular color competition; S2, using an EEG signal acquisition module to collect EEG signals of a user watching a binocular color competition paradigm through a non-invasive EEG cap, and inputting the EEG signals into an EEG data processing module; S3, using the EEG data processing module to classify the color perception status of the collected EEG data; S4. The results of the EEG data processing module are fed back to the user through the human-computer interaction module.

2. The attention-enhanced brain-computer interface system based on binocular color competition according to claim 1, characterized in that: The color difference formula for inducing binocular color rivalry is as follows: In the formula, LAB value of the color viewed by the left eye; is the LAB value of the color viewed by the right eye; where L is the brightness of the color, a is the axis from green to red, and b is the axis from blue to yellow; is the color difference between the left eye and the right eye, and the color difference is required to be greater than the binocular color competition threshold, that is LAB color space color difference unit.

3. The attention-enhanced brain-computer interface system based on binocular color competition according to claim 1, characterized in that: The EEG signal acquisition module is used to collect the EEG signal of the user watching the binocular color competition paradigm through a non-invasive EEG cap, and the EEG signal is input into the EEG data processing module: The EEG signal acquisition module collects the EEG signal of the user watching the binocular color rivalry paradigm through a non-invasive EEG cap: a 128-channel electrode cap is used to collect the EEG signal, and the electrode cap signal is then transmitted to the EEG data processing module of the computer through a signal amplifier; the sampling frequency of the EEG data is 250Hz.

4. The attention-enhanced brain-computer interface system based on binocular color competition according to claim 1, characterized in that: In the process of using the EEG data processing module to classify the color perception state of the collected EEG data, the collected EEG data is first preprocessed, including: filtering and removing noise and artifacts; The filtering is as follows: selecting a filter range of 0.5 Hz-30 Hz to filter the raw EEG data collected by the EEG signal acquisition module; Removing noise and artifacts: Using ICA to remove noise and artifacts; noise and artifacts include: electrooculography, electromyography and electrocardiography.

5. The attention-enhanced brain-computer interface system based on binocular color competition according to claim 1, characterized in that: The results of the EEG data processing module are fed back to the user through a human-computer interaction module, which includes: a visual interface, sound output, and real-time feedback functions of the training progress.

Images