CN113778228A - Brain-computer interface system based on multifunctional emotion recognition and self-adaptive adjustment - Google Patents
Brain-computer interface system based on multifunctional emotion recognition and self-adaptive adjustment Download PDFInfo
- Publication number
- CN113778228A CN113778228A CN202111062641.6A CN202111062641A CN113778228A CN 113778228 A CN113778228 A CN 113778228A CN 202111062641 A CN202111062641 A CN 202111062641A CN 113778228 A CN113778228 A CN 113778228A
- Authority
- CN
- China
- Prior art keywords
- emotion
- pressure
- brain
- computer interface
- emotions
- 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.)
- Pending
Links
- 230000008909 emotion recognition Effects 0.000 title claims abstract description 23
- 230000008451 emotion Effects 0.000 claims abstract description 180
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 230000010482 emotional regulation Effects 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 10
- 239000000463 material Substances 0.000 claims description 32
- 230000001939 inductive effect Effects 0.000 claims description 29
- 230000007935 neutral effect Effects 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 9
- 230000002996 emotional effect Effects 0.000 claims description 7
- 230000006698 induction Effects 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000036651 mood Effects 0.000 claims description 6
- 208000019901 Anxiety disease Diseases 0.000 claims description 5
- 230000036506 anxiety Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 230000033228 biological regulation Effects 0.000 claims description 3
- 230000035568 catharsis Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000000638 stimulation Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 6
- 238000000605 extraction Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 239000003550 marker Substances 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 210000004556 brain Anatomy 0.000 description 6
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000001652 frontal lobe Anatomy 0.000 description 2
- 230000006996 mental state Effects 0.000 description 2
- 210000000869 occipital lobe Anatomy 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000001914 calming effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000994 depressogenic effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000005037 parasympathetic nerve Anatomy 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002889 sympathetic effect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
- A61B5/378—Visual stimuli
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
- A61B5/38—Acoustic or auditory stimuli
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/01—Indexing scheme relating to G06F3/01
- G06F2203/011—Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention provides a brain-computer interface system based on multifunctional emotion recognition and self-adaptive adjustment. The method has the beneficial effects that (1) the extraction of the electroencephalogram characteristics under different emotions is realized by using a space frequency optimization method, and the accuracy of emotion recognition is improved by combining the extraction of the electroencephalogram characteristics with the characteristic fusion of the pressure signals. (2) The emotion marker is changed into a pressure sensor type, and a pressure emotion signal is increased under the condition that the test is not increased, so that the emotion recognition rate is improved. Meanwhile, the pressure sensor can be used as an emotion releasing tool in measurement to achieve various effects of emotion regulation, emotion calibration, emotion measurement and the like.
Description
Technical Field
The invention relates to human-computer interaction, emotion recognition and emotion regulation technologies, in particular to a brain-computer interface system based on multifunctional emotion recognition and self-adaptive regulation.
Background
Emotion recognition refers to recognition of emotional changes of a person under external stimulation, and is widely applied to the fields of mental state detection, crime prevention, disease treatment and the like. The EEG electroencephalogram signals are gradually paid attention to emotion recognition in recent years, and especially have important practical application value in the aspects of psychological state detection and emotion regulation.
Because the electroencephalogram signal is a direct reaction of the brain electric signal, the electroencephalogram signal has more intuitive expression relative to other signals which depend on sympathetic parasympathetic nerve regulation, such as electrocardio, electrodermal and the like, for example, the electroencephalogram signal has wide space-frequency domain distribution difference under different emotions, and therefore, the electroencephalogram signal has better emotion classification and identification effects. The study of Fumikazu et al shows that the activity intensity of theta wave of frontal lobe is increased in mental state, while the activity of a wave of occipital lobe is inhibited in resting state, and the study of WL Zheng et al shows that the active emotion is higher in beta and gamma wave energy than the passive emotion, and the active emotion is stronger in the frontal lobe and the active energy of delta wave of the apical lobe and occipital lobe is enhanced in the negative emotion. Based on the method, the extraction of the electroencephalogram characteristics under different emotions can be realized by using a space frequency optimization method, so that the classification of different emotions can be realized.
The Brain generates signals with certain characteristics to realize communication and control with electronic devices (such as computers and the like), which is called Brain Computer Interface (BCI), and the key of the BCI is to recognize the characteristics of the Brain signals so as to convert the Brain signals into correct commands for controlling the devices. The brain-computer interface system based on emotion recognition can be realized by performing emotion recognition on the electroencephalogram and applying the emotion recognition result to the reverse emotion regulation of a computer. However, the accuracy of emotion recognition of a single electroencephalogram is not high enough, and the information of emotion calibration is not sufficiently utilized.
Disclosure of Invention
The invention provides a brain-computer interface system based on multifunctional emotion recognition and adaptive adjustment, which is characterized by comprising an emotion induction unit, an electroencephalogram signal acquisition module, a pressure signal emotion calibration module, an emotion decoding unit and an emotion adjusting unit,
the emotion inducing unit is used for playing emotion inducing materials of audio and/or video and inducing different emotions of the tester;
the electroencephalogram signal acquisition module is used for acquiring electroencephalogram signals under different emotional states;
the pressure signal emotion calibration module comprises a first pressure sensor, a second pressure sensor and a third pressure sensor, wherein the first pressure sensor, the second pressure sensor and the third pressure sensor are used for recording the pressure of the pressure sensors under different emotions in the training stage when a tester watches/listens to emotion inducing materials, and the pressure is used as a basis for emotion auxiliary judgment;
the emotion decoding unit is used for emotion decoding;
the emotion adjusting unit is used for adjusting extreme emotions and restoring excited emotions.
As a further improvement of the present invention, the stress signal emotion calibration module further includes a fourth stress sensor, the fourth stress sensor is used as a detector for knocking in the discrimination stage, and the fourth stress sensor is used as an emotion signal collector and also as a catharser for anxiety and excited emotion to counteract emotion regulation.
As a further improvement of the invention, the emotion inducing materials comprise active, neutral and negative emotion materials in a Chinese emotion stimulating material library, the active, neutral and negative emotions of the tester are induced by playing the active, neutral and negative emotion materials, and electroencephalogram signals corresponding to the emotions are acquired by an electroencephalogram signal acquisition module.
As a further improvement of the present invention, the first to third pressure sensors are labeled "positive", "neutral" and "negative", respectively, and the first to third pressure sensors record the pressure under the corresponding emotion-inducing material, and since the pressures of the pressure sensors are differentiated under different emotions, the first to third pressure sensors serve as emotion markers and also serve as emotion discrimination markers.
As a further improvement of the invention, the emotion decoding unit carries out emotion decoding through scale weighted space-frequency optimization algorithm and pressure signal emotion judgment and then carries out feature fusion.
As a further improvement of the invention, the emotion adjusting unit enables the brain-computer interface system to have a self-adaptive learning function, and parameters can be adjusted according to different environments, time and individuals.
As a further improvement of the invention, the method for emotion decoding by the space-frequency optimization algorithm is as follows:
step 1: performing band-pass filtering on the electroencephalogram signals by 1-45hz, and reserving the electroencephalogram signals from delta waves to gamma wave frequency bands;
step 2: dividing the pass band, and then calculating a projection matrix of each sub-band by performing a common space mode on each sub-band;
and step 3: optimizing the subspace projection matrix in combination with the scale score of the training set, and performing weighted average to form a new projection matrix; classifying the test data to find an optimal projection matrix and an optimal classification sub-band;
and 4, step 4: and classifying the electroencephalogram signals by the optimal sub-band and the trained optimal projection matrix to obtain the characteristics generated by the electroencephalogram signals.
As a further improvement of the present invention, in the emotion decoding unit, feature fusion is performed by a feature fusion model, which is as follows:
where d is the decoding dimension of the system, fd×1For outputting, namely a result of fusion of the space-frequency optimization algorithm and the emotion distinguishing characteristic of the stress signal, M is the number of system signals,
a feature vector representing the ith signal, the number of features being Ni，
Is that
Is a weight of d × NiMatrix of bd×1Is a vector of dX 1, which is a bias coefficient;
task decision is implemented using softmax:
wherein f isk,1Is a vector fd×1The subscript is the value of (k, 1).
As a further improvement of the invention, the current emotion state is obtained through feature fusion and judgment, and the emotion adjusting unit realizes the emotion adjustment in the following way: for negative emotions in multiple tests, positive emotion materials are played through an emotion induction unit to induce positive emotions; for positive emotions in multiple tests, neutral emotion materials are played through an emotion induction unit to achieve emotion smoothing;
in the emotion recognition link, a tester can press the fourth pressure sensor at will, and the pressure sensor serves as an emotion signal collector and also serves as a catharsis device for anxiety and excited emotion to counteract emotion regulation.
The invention has the beneficial effects that: (1) the method of space frequency optimization is used for extracting electroencephalogram features and combining with pressure signals to perform feature fusion under different emotions, so that the emotion recognition accuracy is improved. (2) The emotion marker is changed into a pressure sensor type, and a pressure emotion signal is increased under the condition that the test is not increased, so that the emotion recognition rate is improved. Meanwhile, the pressure sensor can be used as an emotion releasing tool in measurement to achieve various effects of emotion regulation, emotion calibration, emotion measurement and the like.
Drawings
FIG. 1 is a functional block diagram of a brain-computer interface system of the present invention;
FIG. 2 is a schematic diagram of a stress signal mood calibration module;
FIG. 3 is a schematic diagram of an emotion space frequency optimization discrimination algorithm;
FIG. 4 is a schematic diagram of a stress signal emotion determination method;
FIG. 5 is a block diagram of an adaptive learning structure based on softmax regression;
fig. 6 is a schematic diagram of the mood-adjusting unit implementing mood adjustment.
Detailed Description
As shown in figure 1, the invention discloses a brain-computer interface system based on multifunctional emotion recognition and adaptive adjustment, which comprises an electroencephalogram signal acquisition module, a pressure signal emotion calibration module, an emotion induction unit, an emotion decoding unit, an emotion adjustment unit and an adaptive learning module. The electroencephalogram signal acquisition module acquires electroencephalogram signals under different emotional states; the pressure signal emotion calibration module comprises four pressure sensors, the first three pressure sensors are used for recording the pressure of the pressing sensor under different emotions when the induced video is watched in the training stage and used as the basis of emotion auxiliary judgment, and the fourth pressure sensor is used as a detector for knocking in the judgment stage; the emotion inducing unit plays emotion inducing materials such as audio and video; the emotion decoding unit performs emotion decoding through a time-space-frequency optimization algorithm; the functions of adjusting extreme emotions, calming excited emotions and the like are realized through the emotion adjusting unit; the self-adaptive learning module is used for learning before a user uses the system for the first time, executing a set behavior task according to an operation guide, collecting physiological activity signals in the process of executing the task, and calculating to obtain optimal parameters of feature extraction and task classification.
As shown in fig. 2, the emotion calibration module of the stress signal excites the corresponding emotion of the tester, the stress signal emotion calibration module includes four pressure sensors that can be depressed, three of the pressure sensors are labeled "positive", "neutral" and "negative", the fourth label "please press after measurement", in the emotion training phase, after watching the inducing material played by the emotion inducing unit, the tester presses the pressure sensor with the "positive" label after watching the positive inducing material, presses the pressure sensor with the "neutral" label after watching the neutral inducing material, presses the pressure sensor with the "negative" label after watching the negative inducing material, and the force is performed according to the corresponding emotion. The pressure sensors record the pressure under the corresponding inducing material, and the pressure sensors are used as emotion marks and also as emotion distinguishing marks when the pressure sensors are used for emotion calibration because the pressure of the pressure sensors under different emotions is distinguished.
The testers need to fill in a titer-arousal degree scale in the emotion training stage to carry out detailed annotation of emotions.
The emotion adjusting unit enables the brain-computer interface system to have a self-adaptive learning function, parameters can be adjusted according to different environments, time and used individuals, and accuracy of system control is guaranteed to the maximum extent.
The schematic diagram of the space-frequency optimization algorithm is shown in fig. 3, and the electroencephalogram signals are subjected to band-pass filtering of 1-45hz, and brain wave signals from delta waves to gamma wave frequency bands are reserved. The pass band is divided and then the projection matrix is calculated for each sub-band in a co-spatial mode. And optimizing the subspace projection matrix by combining the scale scores of the training set, and performing weighted average to form a new projection matrix. The test data is classified to find an optimal projection matrix and an optimal classification subband. And classifying the electroencephalogram signals by the optimal sub-band and the trained optimal projection matrix to obtain the characteristics generated by the electroencephalogram signals.
As shown in fig. 4, in the emotion training stage, after watching the inducing material played by the emotion inducing unit, the tester presses the pressure sensor with the "positive" label after watching the positive inducing material, presses the pressure sensor with the "neutral" label after watching the neutral inducing material, presses the pressure sensor with the "negative" label after watching the negative inducing material, and performs the stress according to the corresponding emotion.
FIG. 5 shows a simplified learning model of softmax regression.
The emotion adjusting unit achieves emotion adjustment as shown in fig. 6, current emotion states (positive, neutral and negative) are obtained through feature fusion judgment, negative emotions are obtained for multiple tests, and positive emotion materials are played through the emotion inducing unit to induce the positive emotions. And (4) playing neutral emotion materials through an emotion inducing unit to perform emotion smoothing for positive emotions in multiple tests. In the emotion recognition link, a tester can press the fourth pressure sensor at will, and the pressure sensor acts as an emotion signal collector and also can act as a catharsis device under anxiety and excited emotion to counteract emotion regulation.
Aiming at the defects in the prior art, the emotion calibration module is designed into a pressure signal emotion calibration module, and the pressure for pressing under different emotions and the label of the emotion at the moment are collected; meanwhile, an emotion space-frequency optimization algorithm is designed for emotion decoding, and the judgment of emotion is optimized by fusing a pressure characteristic and an electroencephalogram space-frequency characteristic through a characteristic fusion model. The emotion is reversely adjusted by combining the brain-computer interface technology, negative emotions are obtained for multiple tests, positive emotion materials are played through the emotion inducing unit to induce positive emotions, positive emotions are obtained for multiple tests, and neutral emotion materials are played through the emotion inducing unit to achieve emotion restoration.
The invention has the beneficial effects that:
(1) the method of space frequency optimization is used for extracting electroencephalogram features and combining with pressure signals to perform feature fusion under different emotions, so that the emotion recognition accuracy is improved.
(2) The emotion marker is changed into a pressure sensor type, and a pressure emotion signal is increased under the condition that the test is not increased, so that the emotion recognition rate is improved. Meanwhile, the pressure sensor can be used as an emotion releasing tool in measurement to achieve various effects of emotion regulation, emotion calibration, emotion measurement and the like.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (9)
1. A brain-computer interface system based on multifunctional emotion recognition and adaptive adjustment is characterized by comprising an emotion induction unit, an electroencephalogram signal acquisition module, a pressure signal emotion calibration module, an emotion decoding unit and an emotion adjustment unit,
the emotion inducing unit is used for playing emotion inducing materials of audio and/or video and inducing different emotions of the tester;
the electroencephalogram signal acquisition module is used for acquiring electroencephalogram signals under different emotional states;
the pressure signal emotion calibration module comprises a first pressure sensor, a second pressure sensor and a third pressure sensor, wherein the first pressure sensor, the second pressure sensor and the third pressure sensor are used for recording the pressure of the pressure sensors under different emotions in the training stage when a tester watches/listens to emotion inducing materials, and the pressure is used as a basis for emotion auxiliary judgment;
the emotion decoding unit is used for emotion decoding;
the emotion adjusting unit is used for adjusting extreme emotions and restoring excited emotions.
2. The brain-computer interface system according to claim 1, wherein the stress signal mood calibration module further comprises a fourth stress sensor, wherein the fourth stress sensor is used as a detector for the stroke during the discrimination phase, and the fourth stress sensor is used as a mood signal collector and a catharser for anxiety and excited mood to counteract the mood regulation.
3. The brain-computer interface system according to claim 1, wherein the emotion-inducing materials comprise positive, neutral and negative emotion materials in a Chinese emotional stimulation material library, positive, neutral and negative emotions of the tester are induced by playing the positive, neutral and negative emotion materials, and electroencephalogram signals corresponding to the emotions are acquired by the electroencephalogram signal acquisition module.
4. The brain-computer interface system according to claim 1, wherein the first to third pressure sensors are labeled "positive", "neutral" and "negative", respectively, and the first to third pressure sensors record the pressure under the corresponding emotional inducing material, and since the pressure of the pressure sensors is differentiated under different emotions, the first to third pressure sensors are used as the emotion markers and also as the emotion judgment markers.
5. The brain-computer interface system according to claim 1, wherein the emotion decoding unit performs emotion decoding by a scale weighted space-frequency optimization algorithm and pressure signal emotion judgment, and then performs feature fusion.
6. The brain-computer interface system according to claim 5, wherein the emotion adjusting unit enables the brain-computer interface system to have an adaptive learning function, and parameters can be adjusted according to different environments, time and individuals.
7. The brain-computer interface system according to claim 5, wherein the method of emotion decoding by the space-frequency optimization algorithm is as follows:
step 1: performing band-pass filtering on the electroencephalogram signals by 1-45hz, and reserving the electroencephalogram signals from delta waves to gamma wave frequency bands;
step 2: dividing the pass band, and then calculating a projection matrix of each sub-band by performing a common space mode on each sub-band;
and step 3: optimizing the subspace projection matrix in combination with the scale score of the training set, and performing weighted average to form a new projection matrix; classifying the test data to find an optimal projection matrix and an optimal classification sub-band;
and 4, step 4: and classifying the electroencephalogram signals by the optimal sub-band and the trained optimal projection matrix to obtain the characteristics generated by the electroencephalogram signals.
8. The brain-computer interface system according to claim 5, wherein in the emotion decoding unit, feature fusion is performed by a feature fusion model as follows:
where d is the decoding dimension of the system, fd×1For outputting, namely a result of fusion of the space-frequency optimization algorithm and the emotion distinguishing characteristic of the stress signal, M is the number of system signals,
a feature vector representing the ith signal, the number of features being Ni，
Is that
Is a weight of d × NiMatrix of bd×1Is a vector of dX 1, which is a bias coefficient;
task decision is implemented using softmax:
wherein f isk,1Is a vector fd×1The subscript is the value of (k, 1).
9. The brain-computer interface system according to claim 5, wherein the current emotional state is determined through feature fusion, and the emotion adjusting unit implements emotion adjustment in the following manner: for negative emotions in multiple tests, positive emotion materials are played through an emotion induction unit to induce positive emotions; for positive emotions in multiple tests, neutral emotion materials are played through an emotion induction unit to achieve emotion smoothing;
in the emotion recognition link, a tester can press the fourth pressure sensor at will, and the pressure sensor serves as an emotion signal collector and also serves as a catharsis device for anxiety and excited emotion to counteract emotion regulation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111062641.6A CN113778228A (en) | 2021-09-10 | 2021-09-10 | Brain-computer interface system based on multifunctional emotion recognition and self-adaptive adjustment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111062641.6A CN113778228A (en) | 2021-09-10 | 2021-09-10 | Brain-computer interface system based on multifunctional emotion recognition and self-adaptive adjustment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113778228A true CN113778228A (en) | 2021-12-10 |
Family
ID=78842487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111062641.6A Pending CN113778228A (en) | 2021-09-10 | 2021-09-10 | Brain-computer interface system based on multifunctional emotion recognition and self-adaptive adjustment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113778228A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102512160A (en) * | 2011-12-16 | 2012-06-27 | 天津大学 | Electroencephalogram emotional state feature extraction method based on adaptive tracking in different frequency bands |
| CN102715911A (en) * | 2012-06-15 | 2012-10-10 | 天津大学 | Brain electric features based emotional state recognition method |
| CN103654798A (en) * | 2013-12-11 | 2014-03-26 | 四川大学华西医院 | Method and device for monitoring and recording emotion |
| CN107007291A (en) * | 2017-04-05 | 2017-08-04 | 天津大学 | Intense strain intensity identifying system and information processing method based on multi-physiological-parameter |
| CN108509040A (en) * | 2018-03-28 | 2018-09-07 | 哈尔滨工业大学深圳研究生院 | Mixing brain machine interface system based on multidimensional processiug and adaptive learning |
| CN110576443A (en) * | 2018-08-03 | 2019-12-17 | 重庆市武义赏网络科技有限公司 | robot system for psychological catharsis and data acquisition and analysis method thereof |
| CN112669882A (en) * | 2021-01-07 | 2021-04-16 | 上海龙旗科技股份有限公司 | Media playing method and device based on pressure detection |
| CN112987917A (en) * | 2021-02-08 | 2021-06-18 | 中国科学院自动化研究所 | Motion imagery enhancement method, device, electronic equipment and storage medium |
| CH717003A2 (en) * | 2019-12-27 | 2021-06-30 | Univ Lanzhou | System for regulating a depressed mood through music feedback based on an electroencephalogram signal. |
-
2021
- 2021-09-10 CN CN202111062641.6A patent/CN113778228A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102512160A (en) * | 2011-12-16 | 2012-06-27 | 天津大学 | Electroencephalogram emotional state feature extraction method based on adaptive tracking in different frequency bands |
| CN102715911A (en) * | 2012-06-15 | 2012-10-10 | 天津大学 | Brain electric features based emotional state recognition method |
| CN103654798A (en) * | 2013-12-11 | 2014-03-26 | 四川大学华西医院 | Method and device for monitoring and recording emotion |
| CN107007291A (en) * | 2017-04-05 | 2017-08-04 | 天津大学 | Intense strain intensity identifying system and information processing method based on multi-physiological-parameter |
| CN108509040A (en) * | 2018-03-28 | 2018-09-07 | 哈尔滨工业大学深圳研究生院 | Mixing brain machine interface system based on multidimensional processiug and adaptive learning |
| CN110576443A (en) * | 2018-08-03 | 2019-12-17 | 重庆市武义赏网络科技有限公司 | robot system for psychological catharsis and data acquisition and analysis method thereof |
| CH717003A2 (en) * | 2019-12-27 | 2021-06-30 | Univ Lanzhou | System for regulating a depressed mood through music feedback based on an electroencephalogram signal. |
| CN112669882A (en) * | 2021-01-07 | 2021-04-16 | 上海龙旗科技股份有限公司 | Media playing method and device based on pressure detection |
| CN112987917A (en) * | 2021-02-08 | 2021-06-18 | 中国科学院自动化研究所 | Motion imagery enhancement method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108629313B (en) | Emotion adjusting method, device and system and computer storage medium | |
| Phinyomark et al. | A feature extraction issue for myoelectric control based on wearable EMG sensors | |
| CN110353702A (en) | A kind of emotion identification method and system based on shallow-layer convolutional neural networks | |
| CN108304917A (en) | A kind of P300 signal detecting methods based on LSTM networks | |
| CN111091074B (en) | Motor imagery electroencephalogram signal classification method of optimal region co-space mode | |
| CN103690165A (en) | Cross-inducing-mode emotion electroencephalogram recognition and modeling method | |
| CN101464729A (en) | Independent desire expression method based on auditory sense cognition neural signal | |
| CN113017645B (en) | P300 signal detection method based on void convolutional neural network | |
| CN116400800B (en) | ALS patient human-computer interaction system and method based on brain-computer interface and artificial intelligence algorithm | |
| US20220051039A1 (en) | Biometric identification using electroencephalogram (eeg) signals | |
| CN108491792B (en) | Office scene human-computer interaction behavior recognition method based on electro-oculogram signals | |
| CN114557708A (en) | Device and method for detecting somatosensory stimulation consciousness based on electroencephalogram dual-feature fusion | |
| CN111067513A (en) | Sleep quality detection key brain area judgment method based on characteristic weight self-learning | |
| CN104793743B (en) | A kind of virtual social system and its control method | |
| Yoon et al. | Spatial and time domain feature of ERP speller system extracted via convolutional neural network | |
| CN113778228A (en) | Brain-computer interface system based on multifunctional emotion recognition and self-adaptive adjustment | |
| KR20150076932A (en) | apparatus for analyzing brain wave signal and analyzing method thereof, and user terminal device for using the analyzation result | |
| CN101571747A (en) | Method for realizing multi-mode EEG-control intelligent typewriting | |
| WO2023027578A1 (en) | Nose-operated head-mounted device | |
| CN111905229A (en) | Piano music hypnosis treatment control system and method based on 5G | |
| CN108764008B (en) | Method for detecting movement intention based on combination of dynamic stopping strategy and integrated learning | |
| CN114201041A (en) | Human-computer interaction command method and device based on brain-computer interface | |
| Sanggarini et al. | Hjorth descriptor as feature extraction for classification of familiarity in EEG signal | |
| CN113070875A (en) | Manipulator control method and device based on brain wave recognition | |
| Deepajothi et al. | Performance evaluation of SVM–RBF kernel for classifying ECoG motor imagery |
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 |