CN107080546A - Electroencephalogram-based emotion perception system and method for environmental psychology of teenagers and stimulation sample selection method - Google Patents
Electroencephalogram-based emotion perception system and method for environmental psychology of teenagers and stimulation sample selection method Download PDFInfo
- Publication number
- CN107080546A CN107080546A CN201710252127.6A CN201710252127A CN107080546A CN 107080546 A CN107080546 A CN 107080546A CN 201710252127 A CN201710252127 A CN 201710252127A CN 107080546 A CN107080546 A CN 107080546A
- Authority
- CN
- China
- Prior art keywords
- mrow
- potency
- score
- subject
- eeg signals
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000008451 emotion Effects 0.000 title claims abstract description 30
- 230000007613 environmental effect Effects 0.000 title claims abstract description 21
- 230000000638 stimulation Effects 0.000 title abstract description 21
- 230000008447 perception Effects 0.000 title abstract description 8
- 238000010187 selection method Methods 0.000 title abstract description 4
- 238000012549 training Methods 0.000 claims abstract description 23
- 230000000007 visual effect Effects 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 230000036651 mood Effects 0.000 claims description 52
- 230000002996 emotional effect Effects 0.000 claims description 21
- 238000001228 spectrum Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 16
- 210000004556 brain Anatomy 0.000 claims description 13
- 238000009432 framing Methods 0.000 claims description 13
- 238000002474 experimental method Methods 0.000 claims description 9
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012880 independent component analysis Methods 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 5
- 239000012634 fragment Substances 0.000 claims description 4
- 238000002203 pretreatment Methods 0.000 claims description 4
- 238000000205 computational method Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 abstract description 7
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 206010062519 Poor quality sleep Diseases 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 10
- 238000013461 design Methods 0.000 description 8
- 230000005611 electricity Effects 0.000 description 8
- 230000036541 health Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 210000001061 forehead Anatomy 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000008909 emotion recognition Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 208000027534 Emotional disease Diseases 0.000 description 1
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000007630 basic procedure Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000007177 brain activity Effects 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 210000004720 cerebrum Anatomy 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002964 excitative effect Effects 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000000366 juvenile effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003557 neuropsychological effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Classifications
-
- 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
- A61B5/72—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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Psychiatry (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Psychology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Social Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an electroencephalogram-based emotion sensing system and method for environmental psychology of teenagers and a stimulation sample selection method, wherein the system comprises an electroencephalogram signal acquisition module, an electroencephalogram signal preprocessing module, an electroencephalogram signal feature extraction module, an emotion sensing module and the like; the established environment that teenagers often contact, participate or are keen is taken as a visual stimulus source. The emotion perception method comprises the steps of visual stimulus source selection, electroencephalogram signal collection, electroencephalogram signal preprocessing, electroencephalogram signal feature extraction, model training, emotion intensity determination and the like. The method for selecting the stimulation sample comprises the steps of dividing 5 emotion intensities in the wakefulness dimension and the valence dimension respectively, and determining a rectangular selection frame in a non-equidistant mode according to the actual selection condition of the sample and the distribution state of the sample in a two-dimensional space. The emotion sensing system and method and the stimulation sample selection method have the advantages of strong emotion sensing capability, strong object expansion capability and the like, and have high application value in environmental psychology research.
Description
Technical field
The present invention relates to a kind of mood sensing system and method for teenager's Environmental Psychology based on electroencephalogram, stimulate sample
System of selection.
Background technology
According to statistics, minor's quantity of China's under-18s is up to 3.67 hundred million.According to conservative estimation, there are various study, feelings
Thread and behavior disorder person are up to 30,000,000.In recent years, the incidence of adolescents in China psychological problems becomes in substantially rising in recent years
Gesture, infantile psychology rate of behavior problems is up to 14%~17%.Wherein, emotional problem (such as anxiety, depression) is the common heart
One of reason problem, and incidence is high, involve wide, and influence behavior and the psychosocial function of individual.The World Health Organization
(WHO) predict, the children of neuropsychological problem and teenager occur in the year two thousand twenty world wide will increase by more than 50%, and these are asked
Inscribe as one of first five reason for causing children and juvenile disease, deformity and death.
Built environment refers to the artificial environment provided for the mankind's activity including the environment of large size city.Correlative study
Show, built environment is used as a kind of artificial visual environment, thus it is possible to vary the mood of people, influence their healthy and behaviors.Similarly,
Built environment around teenager can be different with mental health generation to teen-age mood influence.If for example, teenager
It is in lively audio visual environment, they understand feeling excited, higher emotionality degree occurs, and long-term high wake-up degree is then
Fatigue can be brought, it is unhelpful to health;, can be with conversely, green environment, landscape, the static interior space then reduce emotionality degree
Relieving mood, loosen mood.
At present, in environmental psychology and landscape design field, the mood sensing based on EEG signals has become new
Study hotspot.For example:Ulrich detects the indexs such as heart rate, blood pressure, brain activity, compared for artificial nature by questionnaire, interview
Environment and people's industry and commerce, industrial environment, it is found that alpha ripples are more notable under artificial nature environment;Nakamura et al. allow by
Examination person watches hedge and enclosure of concrete, analyze they alpha ripples and the beta rhythm and pace of moving things quantity, it is found that subject is look at hedge
Alpha ratios (a/ (a+b)) are higher during concrete walls than watching attentively during basketry wall;Aspinall et al. passes through wearable brain wave acquisition
Equipment, records and analyzes when subject runs in the guide commercial street and vert space two dimensions, the emotional change of five channels;Roe
Et al. also by wearable brain electric equipment, record and analyze the brain induced by two groups of photos of viewing landscape and urban environment
Electric signal, and show that vert space has relatively low wake-up degree and the conclusion of higher meditation degree compared to City scenarios.
The studies above is concerned with carrying out satisfaction and health evaluating, emphasis to a certain specific environment using electroencephalogram method
What is analyzed is the relation of specific environment and general groups, and then more rare for general environment and the relation of special group, especially
It is in terms of description built environment is on adolescents ' emotional influence.In addition, for mood is described in accuracy, in psychology
With computer affection computation field, although existing emotion recognition and the correlation technique basis for calculating bio signal, including brain electricity, the heart
The single or multi-modal emotion recognition model such as electricity, respiratory rate, blood oxygen saturation, shell temperature, but above-mentioned model is mainly used in
Some typical type of emotion are recognized, such as:Sad, happy, disappointed, angry etc., these affective states are generally by including plot
Stimulus swash and produce, it is clear that natural emotion state of the above-mentioned typical affective style under the different built environment of description teenager
It is insufficient.
In addition, in the selection of stimulus, existing method is more single, it is that the stimulus comprising plot swashs mostly;
And stimulation object and the content of source in itself are not differentiated between, there is larger contingency in practical operation, effect of stimulation is also not to the utmost such as
People's will.It would therefore be desirable to set up a kind of mood sensing system and method for teenager's Environmental Psychology based on electroencephalogram, stimulation
Method of Sample Selection, for it is true, objectively respond teen-age psychological activity situation.
The content of the invention
The present invention is that there is provided a kind of mood sensing ability, object to avoid weak point present in above-mentioned prior art
Mood sensing system and method, the stimulation Method of Sample Selection for teenager's Environmental Psychology that extended capability is strong, application value is high.
The present invention uses following technical scheme to solve technical problem.
The mood sensing system of teenager's Environmental Psychology based on electroencephalogram, it is structurally characterized in that, including EEG signals are adopted
Collect module, EEG signals pretreatment module, EEG feature extraction module and mood sensing module;Often connect with teenager
The built environment touched, participate in or be keen to is visual stimulus source, and subject is teenager;
The electroencephalogramsignal signal acquisition module, original 32 for gathering subject by recording electrode and reference electrode lead
Join EEG signals, and the original EEG signals of collection are sent to the EEG signals pretreatment module;The EEG signals are pre-
Processing module, for the original EEG signals that are sent to the electroencephalogramsignal signal acquisition module carry out framing, adding window, bandpass filtering and
The operations such as the dynamic artefact removal of eye, to reduce noise jamming, improve model perception performance;
The EEG feature extraction module, for respectively from the electric frequency range of different brains of pretreated EEG signals
The middle power spectrum difference for extracting power spectrum, energy and symmetry electrode is as characteristic parameter, to characterize primary signal and reduce number
According to redundancy;
The mood sensing module, for passing through the instruction to SVMs (Support Vector Machine, SVM)
Practice with identification, in wake-ups degree dimension with realize teenager to the emotional intensity of residing visual environment in potency dimension respectively
Perceive.
Present invention also offers a kind of mood sensing method of teenager's Environmental Psychology.
A kind of mood sensing method of teenager's Environmental Psychology based on electroencephalogram, including following steps:
Step 1:Visual stimulus source selects step;Using teenager often in contact with, the built environment that participates in or be keen to as vision
Stimulus, subject is used as using teenager;
Step 2:Eeg signal acquisition step;Subject's viewing visual stimulus source, then gathers the original brain electricity of subject
Signal;
Step 3:EEG signals pre-treatment step;Original EEG signals are carried out with the dynamic puppet of framing, adding window, bandpass filtering and eye
The operations such as mark removal;
Step 4:EEG feature extraction step;Pretreated EEG signals are divided into training data and test number
According to;For training data and test data, the power spectrum difference for extracting power spectrum, energy and symmetry electrode is used as characteristic parameter;
Step 5:Model training step;It is respectively trained using the characteristic parameter corresponding to training data and emotion intensity label
Wake-up degree SVM submodels and potency SVM submodels;
Step 6:Emotional intensity determines step;Two that the characteristic parameter of test data is inputted in above-mentioned steps 5 respectively
The wake-up degree SVM submodels and potency SVM submodels trained, realizes that the emotion in two dimensions of wake-up degree and potency is strong
The perception of degree.
In the step 3, framing length is 2 seconds, and it is 1 second that frame, which is moved, and window is carried out to original EEG signals using Hamming window;
The cut-off frequency of bandpass filter is set to 0.1-45Hz;The removal that eye moves artefact is carried out using independent component analysis method.
In the step 4, the characteristic parameter includes the power spectrum and energy, 12 pairs of electricity of 6 frequency ranges on 32 electrodes
5 frequency band power spectral difference values on extremely in addition to Alpha wave frequencies section at a slow speed.
A kind of stimulus choosing during being set up present invention also offers adolescents ' emotional sensor model based on electroencephalogram
Selection method.
Stimulus system of selection during adolescents ' emotional sensor model foundation based on electroencephalogram, including following step
Suddenly,
Step 01:According to subject's subjective feeling from all primitive stimulus videos, 55 seconds highlighted videos of manual extraction;
Step 02:Ensure that at least 20 subjects are participated in experiment, and every subject viewing step 01 as much as possible
Highlighted video segment, every subject after each video is watched according to 5 grades, wake-ups degree with two dimensions of potency
Given a mark respectively;
Step 03:According to the marking numerical value of step 02, calculate respectively each video segment with the wake-up scale in potency
Standardization score score (xa) and potency on standardized score score (xv), computational methods are:
In above formula, x represents to stimulate the call number of video, i.e. video segment x, xaIt is that subject's viewing is stimulated after video x
The marking value of wake-up degree, xvIt is that subject's viewing stimulates the marking value of the potency after video segment x.μ represents score averages, is
The average value of one video segment x multiple subjects marking;σ represents score variance, is a video segment x multiple subjects
The variance of person's marking.Standardized score score (xs of one video segment x in wake-up degreea) dimension is being waken up by the video segment
On score averages μxaDivided by scoring variances sigmaxaObtain;Similarly, standardized score of the video segment in potency dimension
score(xv) score averages μ by the video in potency dimensionxvDivided by scoring variances sigmaxvObtain;
Step 04:First, by the score (x acquired in step 03a) and score (xv) be mapped in two-dimensional coordinate system.So
Afterwards, non-equidistant divides 5 rectangle frames on wake-up degree and two dimensions of potency, and the video of correspondence different emotions intensity is selected to frame
Fragment;
Step 05:8 video segments are selected to be used as visual stimulus source out of step 04 rectangle frame.
Compared with the prior art, the present invention has the beneficial effect that:
The mood sensing system and method for teenager's Environmental Psychology based on electroencephalogram of the present invention, stimulation samples selection side
Method, mood sensing system mainly includes collection, pretreatment, feature extraction and the mood sensing module of EEG signals.The step of method
Suddenly include:First, using teenager as research object, the stimulation sample of varying environment scene is in optimized selection;Then, in quilt
The EEG signals that synchronous acquisition is induced by the video when examination person's viewing stimulates video, and it is dynamic to carry out framing, adding window and removal eye
The pretreatment operations such as artefact;Then, after being pre-processed to the EEG signals of all collections, training data and test are divided into
Two parts of data;SVMs (SVM) is carried out on wake-up degree and two emotion dimensions of potency respectively using training data
Model training;Finally, the characteristic parameter of test data is inputted into the SVM models that above-mentioned two has been trained respectively, realizes mood
The perception of intensity.
The mood sensing system and method for teenager's Environmental Psychology based on electroencephalogram of the present invention, stimulation samples selection side
Method, with following 3 aspect the characteristics of.
1st, the present invention has stronger mood sensing ability.
The present invention carries out mood sensing on wake-up degree and two dimensions of potency respectively using two independent classification policys,
In theory, the mood that the present invention is perceived can be any emotion of wake-up degree-potency two-dimensional model (as shown in Figure 2).Meanwhile,
We have carried out the division of 5 emotion intensity respectively to each dimension again, and situation is chosen and two-dimentional empty according to the reality of sample
Between distribution, non-equidistant determines that rectangle selects frame, makes the selection of training sample more scientific and reasonable, so as to realize to mood shape
State is more accurately perceived, and efficiently solves the existing emotion recognition model shortcoming poor to enriching affective state descriptive power.Experiment
Lower 10 subjects of room environmental are tested using the stimulation source video after optimization, and it is wake-up degree and potency in two dimensions
Recognition correct rate be respectively 70.9% and 64.1%, the result verification validity of above-mentioned way.
2nd, the present invention has very strong object extension ability.
The main application of the present invention is teenager, and the purpose of invention is the feelings to teenager under different built environments
Thread is perceived.Younger population possesses preferable experiment condition, for example:They come from this school student, and experiment fitness is high, body
Body acuity is high, and stability is preferable, it is ensured that the science and the accuracy of result tested in the present invention, at the same have using pair
The extended capability of elephant.It is all social specific group, the mood of the weak population such as children, the elderly, patient is as health status
Need concern.In Environment Design field, the positive research of the concepts such as landscape is cured around medical garden, rehabilitation garden, treatment, is emphasized
In terms of physiology, psychology and spirit three from people, overall health is regained, these mostly researchs are based on observation, interview and questionnaire
Completed etc. method.And during factual survey, in them, some people can not accurately describe subjective emotion impression, or be willing to
Meaning coordinates the self-evaluation of word.The present invention is carried out to improve and migrate, optimum choice, man-machine interaction such as to stimulus on a small quantity
The amount body design at interface etc., passes through multi-disciplinary cooperation and collaborative design, it is possible to be applied to the mood sensing model set up
There is very big extending space in more crowd particularly disadvantaged group, future.By the recognition result of the model, for special people
The health and environmental psychology feature of group, treats more for emotion and health reparation provides possibility.
3rd, the present invention has stronger application value.
Teenager is the specific group of society, that they are lived, study, also or their preferences, dislike is built up
Environment can produce Different Effects to its mood, and then involve their health status.The mood sensing model that the present invention is set up
System and method, stimulate Method of Sample Selection, applied to the abundant emotional change research of teenager in different environments, be pair
Its health problem carries out science prevention and the basis effectively controlled.Test result shows that institute's established model of the present invention can be to teenager
Natural emotion state is preferably described, can for it is true, objectively reflect teen-age psychological activity situation, be environment
The positive research of psychology and Environment Design provides new methods and techniques means;Meanwhile, the present invention can also avoided
Emotional state of the different crowd in all kinds of scenes is objectively detected in the case of many manual interventions, for example, different outdoor rings
Border, such as different open levels, different color level, difference enclose influence and reparation of the form condition to mood;It can also answer
For perceiving the emotional state in a certain specific environment, such as crowd is visiting the old space of exhibition of a sequence, experience interaction scenarios
During anxious state of mind etc., help designer and policymaker to understand the effect assessment after built environment use, judge different
Constitution element, abundant design syntax and Spatial ambience are to the influence degree of emotional state, so as to be that Environment Design and landscape are advised
Draw the foundation that evidence-based design is provided.
The mood sensing system and method for teenager's Environmental Psychology based on electroencephalogram of the present invention, stimulation samples selection side
Method, has the advantages that stronger mood sensing ability and object extension ability, has higher answer in Study on environmental psychology
With value.
Brief description of the drawings
EEG signals generations and collection schematic diagram of the Fig. 1 for the present invention.
Fig. 2 for the present invention wake-up degree and potency two-dimensional mood dimension definition.
Fig. 3 is the basic flow sheet of the mood sensing of the present invention.
Fig. 4 is the schematic diagram of the potency and two dimensions of wake-up degree of the stimulation Method of Sample Selection of the present invention.
Fig. 5 is the electric single experiment normal form schematic diagram of mood brain of the invention.
The self-evaluation software interface that Fig. 6 uses for the electric single experiment of mood brain of the present invention.
Fig. 7 is 32 electrode schematic view of the mounting position of the invention.
Fig. 8 is original EEG signals framing schematic diagram (EEG signals pre-treatment step) of the invention.
Below by way of embodiment, and with reference to accompanying drawing, the invention will be further described.
Embodiment
Referring to Fig. 1~8, the mood sensing system of teenager's Environmental Psychology based on electroencephalogram, including eeg signal acquisition
Module, EEG signals pretreatment module, EEG feature extraction module and mood sensing module;With teenager often in contact with,
The built environment for participating in or being keen to is visual stimulus source, and subject is teenager;
The electroencephalogramsignal signal acquisition module, original 32 for gathering subject by recording electrode and reference electrode lead
Join EEG signals, and the original EEG signals of collection are sent to the EEG signals pretreatment module;Original 32 lead brain electricity
Signal employs international 10-20 system electrodes placement methods to gather acquisition, and each electrode pair answers 1 EEG signals.This hair
Bright used international 10-20 system electrodes place tagmeme:Place 30 recording electrodes and 2 reference electrodes, 32 electrodes
Arrangement is as shown in Figure 7;
The EEG signals pretreatment module, for entering to the original EEG signals that the electroencephalogramsignal signal acquisition module is sent
Row framing, adding window, bandpass filtering and eye move the operations such as artefact removal, to reduce noise jamming, improve model perception performance;
The EEG feature extraction module, for respectively from the electric frequency range of different brains of pretreated EEG signals
It is middle extract power spectrum, energy and symmetry electrode power spectrum difference as characteristic parameter (, to characterize primary signal and reduce number
According to redundancy);
The mood sensing module, for passing through the instruction to SVMs (Support Vector Machine, SVM)
Practice with identification, in wake-ups degree dimension with realize teenager to the emotional intensity of residing visual environment in potency dimension respectively
Perceive.Wake-up degree and potency the two dimensions, are divided into 5 grades, 5 grades are level 1- respectively successively from low to high
level 5.Wherein, wake-up degree the lowest class level 1 is tranquility, and highest ranking level 5 is excitatory state;Potency is most
Inferior grade level 1 is does not please, and highest ranking level 5 is pleasure.It is blue or green due to stimulate source video selection in the present invention
Visual environment residing for teenager rather than the feature film comprising plot, are not likely to produce some extreme emotions, therefore, in two dimensions
Training sample is selected in 5 grades, non-isometric division methods are employed, to obtain optimal perceived effect.
A kind of mood sensing method of teenager's Environmental Psychology based on electroencephalogram, including following steps:
Step 1:Visual stimulus source selects step;Using teenager often in contact with, the built environment that participates in or be keen to as vision
Stimulus, subject is used as using teenager;
Step 2:Eeg signal acquisition step;Subject's viewing visual stimulus source, then gathers the original brain electricity of subject
Signal;There is the blank screen of 5 seconds first in display, and then computer sends the warning tones of a 20ms " serge ";0.5 second
Afterwards, video random display is stimulated, now, the EEG signals of subject are by synchronous recording, and its acquisition rate is set to 250Hz;Video
After fragment broadcasting terminates, subject clicks on respective selection on self-evaluation software and completes emotional intensity assessment table.Complete above-mentioned
Step, after the subject slightly loosens, system continues to play next video, and gathers corresponding EEG signals, until all
Video playback is finished.
Then, subject is changed.For the next subject being replaced, " there is the blank of 5 seconds first in display for repetition
Screen ... until all video playbacks finish " above-mentioned steps.
Step 3:EEG signals pre-treatment step;Original EEG signals are carried out with the dynamic puppet of framing, adding window, bandpass filtering and eye
The operations such as mark removal;
Step 4:EEG feature extraction step;Pretreated EEG signals are divided into training data and test number
According to;For training data and test data, the power spectrum difference for extracting power spectrum, energy and symmetry electrode is used as characteristic parameter;
By training data and test data, power spectrum, energy are extracted respectively on 6 typical EEG signals frequency ranges, 32 electrodes, and
5 typical EEG signals frequency ranges, the power spectrum differences of 12 pairs of symmetry electrodes amount to 444 dimension datas as characteristic parameter.
Step 5:Model training step;It is respectively trained using the characteristic parameter corresponding to training data and emotion intensity label
Wake-up degree SVM submodels and potency SVM submodels;
Step 6:Emotional intensity determines step;Two that the characteristic parameter of test data is inputted in above-mentioned steps 5 respectively
The wake-up degree SVM submodels and potency SVM submodels trained, realizes that the emotion in two dimensions of wake-up degree and potency is strong
The perception of degree.
In the step 3, framing length is 2 seconds, and it is 1 second that frame, which is moved, and window is carried out to original EEG signals using Hamming window;
The cut-off frequency of bandpass filter is set to 0.1-45Hz;The removal that eye moves artefact is carried out using independent component analysis method.Eye
The removal step of dynamic artefact is:First, statistical iteration point is carried out to original 32 lead EEG signal using independent component analysis ICA
Analysis, to obtain different " sources ";Then, by calculating the kurtosis of all output channels to determine that eye is dynamic independent " source ";Finally, will
Observation signal is reconstructed after output channel zero setting corresponding to the dynamic artefact of eye, so as to realize the removal that artefact is moved to eye.
In the step 4, the characteristic parameter includes the power spectrum and energy, 12 pairs of electricity of 6 frequency ranges on 32 electrodes
5 frequency band power spectral difference values on extremely in addition to Alpha wave frequencies section at a slow speed.Characteristic parameter includes Delta (0.5-4Hz), Theta
In (4-8Hz), Alpha (8-12Hz), at a slow speed Alpha (8-10Hz), Beta (12-30Hz), 6 frequency ranges of Gamma (30-40Hz)
Power spectrum and energy;Extraction FP1-FP2, F7-F8, F3-F4, FT7-FT8, FC3-FC4, T3-T4, C3- are further comprises simultaneously
On 12 pairs of electrodes such as C4, TP7-TP8, CP3-CP4, T5-T6, P3-P4, O1-O2 in addition to Alpha (8-10Hz) wave frequency section at a slow speed
5 frequency band power spectral difference values be complementary features parameter, the distribution of 12 pairs of electrodes is as illustrated in figures 1 and 7.Characteristic parameter is 444 dimensions
Parameter;444 dimension parameters include:Power spectrum:Tie up 32 lead × 6 frequency ranges=192;Energy:32 lead × 6 frequency range=192;Work(
Rate spectral difference value:12 lead × 5 frequency range=60;In this way, accumulative 192+192+60=444 dimensional features.
Stimulus system of selection during adolescents ' emotional sensor model foundation based on electroencephalogram, including it is following
Step,
Step 01:According to subject's subjective feeling from all primitive stimulus videos, 55 seconds highlighted videos of manual extraction, i.e.,
The most possible video segment for inducing emotion;
Step 02:Ensure that at least 20 subjects are participated in experiment, and every subject viewing step 01 as much as possible
Highlighted video segment, every subject after each video is watched according to 5 grades, wake-ups degree with two dimensions of potency
Given a mark respectively;
Step 03:According to the marking numerical value of step 02, calculate respectively each video segment with the wake-up scale in potency
Standardization score score (xa) and potency on standardized score score (xv), computational methods are:
In above formula, x represents to stimulate the call number of video, i.e. video segment x, xaIt is that subject's viewing is stimulated after video x
The marking value of wake-up degree, xvIt is that subject's viewing stimulates the marking value of the potency after video segment x.μ represents score averages, is
The average value of one video segment x multiple subjects marking;σ represents score variance, is a video segment x multiple subjects
The variance of person's marking.Standardized score score (xs of one video segment x in wake-up degreea) dimension is being waken up by the video segment
On score averages μxaDivided by scoring variances sigmaxaObtain;Similarly, standardized score of the video segment in potency dimension
score(xv) score averages μ by the video in potency dimensionxvDivided by scoring variances sigmaxvObtain;
Step 04:First, by the score (x acquired in step 03a) and score (xv) be mapped in two-dimensional coordinate system.So
Afterwards, non-equidistant divides 5 rectangle frames on wake-up degree and two dimensions of potency, and the video of correspondence different emotions intensity is selected to frame
Fragment;Rectangle frame sets such as Fig. 4:Waken up in the longitudinal axis in dimension:(neutrality) rectangle frames of level 3 are chosen using 0 transverse axis as center line
8 videos closest to center line are used as stimulus;According to the distribution situation of video, level 1 (calmness) and level 5 (excitement)
Be closest to respectively ± 2.5 transverse axis cover 8 videos select frame;Level 2 and the rectangle frames of level 4 are horizontal with ± 0.7 respectively
Axle is center line, and 8 videos chosen closest to center line are used as stimulus;
In transverse axis potency dimension:(neutrality) rectangle frames of level 3 are chosen closest to the 8 of center line using 0 longitudinal axis as center line
Individual video is used as stimulus;According to the distribution situation of video, level 1 (not pleasing) and level 5 (pleasure) are most to lean on respectively
Closely -1.5 and+3 longitudinal axis cover 8 videos select frame;Level 2 and the rectangle frames of level 4 respectively using -0.4 and+1 longitudinal axis as
Center line, 8 videos chosen closest to center line are used as stimulus;)
Step 05:8 video segments are selected out of step 04 rectangle frame as visual stimulus source, i.e., from above-mentioned rectangle frame
Interior selector closes 8 video segments of above-mentioned condition as the stimulation video after preferably.
Fig. 1 is that EEG signals generate schematic diagram.When subject is watching stimulus scene, a large amount of nerve cell products
Tired activity will produce current potential on cerebral hemisphere surface, this current potential can by be placed on cerebral cortex some are biological
Electrode is got, and forms electroencephalogram.
Referring to Fig. 2, wake-up degree and the definition of two dimensions of potency in the present embodiment are illustrated.Transverse axis is one and preference journey
Spend related mood potency, the dimension never pleasure, the positive and negative emotional state to weigh a people;The longitudinal axis be with it is emerging
The related emotionality degree of degree of putting forth energy, from calmness to excitement, the degree that performance mood is waken up.The mankind are trickle, complexity, pole
The emotional state at end is (such as:Sadness, satisfaction, indignation etc.), it can be found in this two dimensional model.
Referring to Fig. 3, the basic procedure of mood sensing in the present embodiment is illustrated.First, it is right using teenager as research object
The stimulus sample of varying environment scene is in optimized selection.When subject's viewing stimulates video, synchronous acquisition is by the video institute
The EEG signals of induction, and framing, adding window are carried out with removing the pretreatment operations such as the dynamic artefact of eye.Secondly, by the feelings of all collections
After sense eeg data is pre-processed, it is divided into two parts of training and test, in 6 typical EEG signals frequency ranges, 32 electricity
The power spectrum difference for extracting power spectrum, energy and symmetry electrode on extremely respectively amounts to 444 dimension datas as characteristic parameter.Then,
Wake-up degree SVM submodels and potency SVM is respectively trained using the characteristic parameter corresponding to training data and emotion intensity label
Model.Finally, the characteristic parameter of test data is inputted into the SVM submodels that above-mentioned two has been trained respectively, realizes and waking up
Degree and the perception of the emotion intensity in two dimensions of potency.
Referring to Fig. 4, the present embodiment moderate stimulation Method of Sample Selection is illustrated.Round dot in figure is corresponding to 100 videos
Score value, it can be seen that selected overall distribution is uneven.Some extreme emotional states are seldom generated, for example, place
Less with the sample point of high wake-ups degree intersection (position corresponding type of emotion be indignation) in low liter, this is due to stimulation
Source video from the built environment rather than plot feature film residing for teenager, will not produce above-mentioned mood mostly.According to distribution feelings
Condition, 5 typical case intervals have respectively been divided in order to improve in mood sensing model performance, two dimensions of the invention, to select to have representative
The training sample of property.Rectangle frame sets as shown in Figure 4.
Waken up in the longitudinal axis in dimension:Level3 (neutrality) rectangle frames are chosen closest to the 8 of center line using 0 transverse axis as center line
Individual video is used as stimulus;According to the distribution situation of video, level 1 (calmness) and level 5 (excitement) are closest to respectively
The rectangle frame for covering 8 videos of ± 2.5 transverse axis, the sideline of the bottom of level 1 rectangle frame be numerical value for -2.5 it is flat
Row is in the horizontal line of transverse axis, and the sideline of the top of level 5 rectangle frame is the horizontal line parallel to transverse axis that numerical value is+2.5;
Level 2 and the rectangle frames of level 4 are respectively using ± 0.7 transverse axis as center line, and 8 videos chosen closest to center line are used as stimulation
Source;
In transverse axis potency dimension:(neutrality) rectangle frames of level 3 are chosen closest to the 8 of center line using 0 longitudinal axis as center line
Individual video is used as stimulus;According to the distribution situation of video, level 1 (not pleasing) and level 5 (pleasure) are most to lean on respectively
Closely -1.5 and the frame that selects for covering 8 videos of+3 longitudinal axis, the sideline of the leftmost of level 1 rectangle frame is that numerical value is -1.5
Parallel to the vertical curve of the longitudinal axis, the sideline of the rightmost of level 1 rectangle frame be numerical value for+3 parallel to the vertical of the longitudinal axis
Line;Level 2 and the rectangle frames of level 4 choose 8 video conducts closest to center line respectively using -0.4 and+1 longitudinal axis as center line
Stimulus;
Referring to Fig. 5, the detailed process of mood sensing single experiment normal form in the present embodiment is illustrated.First, display is first
First there is the blank screen of 5 seconds, then computer sends 20ms warning tones (" serge ");After 0.5 second, stimulate video random
It has been shown that, now, the EEG signals of subject are by synchronous recording, and its acquisition rate is set to 250Hz;After video segment broadcasting terminates,
Subject clicks on respective selection on self-evaluation software and completes emotional intensity assessment table.Complete after above-mentioned steps, subject is slightly
Work loosens, and continues lower battery of tests.In order to ensure effect of stimulation, we stimulate in each two and will played with colour band in the middle of video
For the neutral video of homophony.The broadcasting of neutral video, enables to effect of stimulation to become apparent.
Referring to Fig. 6, self-evaluation software interface in the present embodiment is illustrated.The major function of software is video playback and feelings
The mark of thread intensity, traditional questionnaire to substitute, with efficiency high, intelligence, using it is simple the features such as.In experimentation
In, subject is clicked in different dimensions using mouse after one section of viewing stimulates video and to experience identical radio box with it
.
Referring to Fig. 7, the installation site of 32 electrodes in the present embodiment is illustrated.Placed using international 10-20 system electrodes
Method, be specially:It is defined by the median line that the nasion to occipital tuberosity is linked to be, left and right is made in the equidistant corresponding site of this line or so
Forehead point (FP1, FP2), volume point (FC3, FC4), central point (C3, C4), summit (CP3, CP4) and pillow point (O1, O2), forehead point
Position on the nasion equivalent to the 10% of the nasion to occipital tuberosity at, volume point is after forehead point equivalent to the nasion to forehead point
Two times of distance are that at nasion median line distance 20%, center, the interval pushed up, rest the head on all points are 20% backward.
Referring to Fig. 8, framing method in the present embodiment is illustrated.It is x to make the n-th frame signal after framingn(m), its adding window mistake
Journey is represented by:
In above formula,The signal after window is represented, ω (m) represents in window function, the present embodiment that we use Hamming
Window, it is defined as:
Wherein, N represents frame length, and M represents that frame is moved, and M=(1/2) N, n, N and M is positive integer, and N takes 128 as needed
A certain integral multiple, such as:128,256,512 etc..
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit is required rather than described above is limited, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the claim involved by limitation.
Moreover, it will be appreciated that although the present specification is described in terms of embodiments, not each embodiment is only wrapped
Containing an independent technical scheme, this narrating mode of specification is only that for clarity, those skilled in the art should
Using specification as an entirety, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
It may be appreciated other embodiment.
Claims (5)
1. the mood sensing system of teenager's Environmental Psychology based on electroencephalogram, it is characterized in that, including electroencephalogramsignal signal acquisition module,
EEG signals pretreatment module, EEG feature extraction module and mood sensing module;With teenager often in contact with, participate in or
The built environment being keen to is visual stimulus source, and subject is teenager;
The electroencephalogramsignal signal acquisition module, the original 32 lead brain for gathering subject by recording electrode and reference electrode
Electric signal, and the original EEG signals of collection are sent to the EEG signals pretreatment module;
The EEG signals pretreatment module, for being divided the original EEG signals that the electroencephalogramsignal signal acquisition module is sent
Frame, adding window, bandpass filtering and eye move the operations such as artefact removal;
The EEG feature extraction module, for being carried respectively from the electric frequency range of the different brains of pretreated EEG signals
The power spectrum difference of power spectrum, energy and symmetry electrode is taken as characteristic parameter;
The mood sensing module, for by the training to SVMs (Support Vector Machine, SVM) with
Identification, realizes in wake-up degree dimension and respectively sense of the teenager to the emotional intensity of residing visual environment in potency dimension
Know.
2. a kind of mood sensing method of teenager's Environmental Psychology based on electroencephalogram, it is characterized in that, comprise the following steps:
Step 1:Visual stimulus source selects step;Using teenager often in contact with, the built environment that participates in or be keen to as visual stimulus
Source, subject is used as using teenager;
Step 2:Eeg signal acquisition step;Subject's viewing visual stimulus source, then gathers the original EEG signals of subject;
Step 3:EEG signals pre-treatment step;Original EEG signals are carried out with the dynamic artefact of framing, adding window, bandpass filtering and eye to go
Operated except waiting;
Step 4:EEG feature extraction step;Pretreated EEG signals are divided into training data and test data;It is right
In training data and test data, the power spectrum difference for extracting power spectrum, energy and symmetry electrode is used as characteristic parameter;
Step 5:Model training step;Wake-up is respectively trained using the characteristic parameter corresponding to training data and emotion intensity label
Spend SVM submodels and potency SVM submodels;
Step 6:Emotional intensity determines step;Two that the characteristic parameter of test data is inputted in above-mentioned steps 5 respectively have instructed
The wake-up degree SVM submodels and potency SVM submodels perfected, are realized in wake-up degree and the emotion intensity in two dimensions of potency
Perceive.
3. mood sensing method according to claim 2, it is characterized in that, in the step 3, framing length is 2 seconds, and frame is moved
For 1 second, window is carried out to original EEG signals using Hamming window;The cut-off frequency of bandpass filter is set to 0.1-45Hz;Adopt
The removal that eye moves artefact is carried out with independent component analysis method.
4. mood sensing method according to claim 2, it is characterized in that, in the step 4, the characteristic parameter includes 32
The power spectrum of 6 frequency ranges on individual electrode and 5 frequency band powers on energy, 12 pairs of electrodes in addition to Alpha wave frequencies section at a slow speed
Spectral difference value.
5. the stimulus system of selection during the adolescents ' emotional sensor model foundation based on electroencephalogram, it is characterized in that, including
Following steps:
Step 01:According to subject's subjective feeling from all primitive stimulus videos, 55 seconds highlighted videos of manual extraction;
Step 02:Ensure that at least 20 subjects participate in the height in experiment, and every subject viewing step 01 as much as possible
Bright video segment, every subject, according to 5 grades, distinguishes after each video is watched on wake-up degree and two dimensions of potency
Given a mark;
Step 03:According to the marking numerical value of step 02, each video segment is calculated respectively and is standardized with the wake-up degree in potency
Score score (xa) and potency on standardized score score (xv), computational methods are:
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>s</mi>
<mi>c</mi>
<mi>o</mi>
<mi>r</mi>
<mi>e</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>a</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>x</mi>
<mi>a</mi>
</mrow>
</msub>
<msub>
<mi>&sigma;</mi>
<mrow>
<mi>x</mi>
<mi>a</mi>
</mrow>
</msub>
</mfrac>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>s</mi>
<mi>c</mi>
<mi>o</mi>
<mi>r</mi>
<mi>e</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>v</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<msub>
<mi>&mu;</mi>
<mrow>
<mi>x</mi>
<mi>v</mi>
</mrow>
</msub>
<msub>
<mi>&sigma;</mi>
<mrow>
<mi>x</mi>
<mi>v</mi>
</mrow>
</msub>
</mfrac>
<mo>,</mo>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
In above formula, x represents to stimulate the call number of video, i.e. video segment x, xaIt is that subject's viewing stimulates the wake-up degree after video x
Marking value, xvIt is that subject's viewing stimulates the marking value of the potency after video segment x.μ represents score averages, is one and regards
The average value of frequency fragment x multiple subjects marking;σ represents score variance, is a video segment x multiple subjects marking
Variance.Standardized score score (xs of one video segment x in wake-up degreea) obtaining in dimension is being waken up by the video segment
Divide average value muxaDivided by scoring variances sigmaxaObtain;Similarly, standardized score score (x of the video segment in potency dimensionv) by
Score averages μ of the video in potency dimensionxvDivided by scoring variances sigmaxvObtain;
Step 04:First, by the score (x acquired in step 03a) and score (xv) be mapped in two-dimensional coordinate system.Then, exist
Wake-up degree divides 5 rectangle frames with non-equidistant in two dimensions of potency, and the video segment of correspondence different emotions intensity is selected to frame;
Step 05:8 video segments are selected to be used as visual stimulus source out of step 04 rectangle frame.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710252127.6A CN107080546B (en) | 2017-04-18 | 2017-04-18 | Electroencephalogram-based emotion perception and stimulus sample selection method for environmental psychology of teenagers |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710252127.6A CN107080546B (en) | 2017-04-18 | 2017-04-18 | Electroencephalogram-based emotion perception and stimulus sample selection method for environmental psychology of teenagers |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107080546A true CN107080546A (en) | 2017-08-22 |
CN107080546B CN107080546B (en) | 2020-08-21 |
Family
ID=59611578
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710252127.6A Active CN107080546B (en) | 2017-04-18 | 2017-04-18 | Electroencephalogram-based emotion perception and stimulus sample selection method for environmental psychology of teenagers |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107080546B (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108143412A (en) * | 2017-12-22 | 2018-06-12 | 苏州创捷传媒展览股份有限公司 | A kind of control method of children's brain electricity mood analysis, apparatus and system |
CN108294739A (en) * | 2017-12-27 | 2018-07-20 | 苏州创捷传媒展览股份有限公司 | A kind of method and its device of test user experience |
CN108881985A (en) * | 2018-07-18 | 2018-11-23 | 南京邮电大学 | Program points-scoring system based on brain electricity Emotion identification |
CN108937968A (en) * | 2018-06-04 | 2018-12-07 | 安徽大学 | lead selection method of emotion electroencephalogram signal based on independent component analysis |
CN109157231A (en) * | 2018-10-24 | 2019-01-08 | 阿呆科技(北京)有限公司 | Portable multi-channel Depression trend assessment system based on emotional distress task |
CN109190658A (en) * | 2018-07-19 | 2019-01-11 | 中国电子科技集团公司电子科学研究院 | Video degree of awakening classification method, device and computer equipment |
CN109276243A (en) * | 2018-08-31 | 2019-01-29 | 易念科技(深圳)有限公司 | Brain electricity psychological test method and terminal device |
CN109567830A (en) * | 2018-10-30 | 2019-04-05 | 清华大学 | A kind of measurement of personality method and system based on neural response |
CN109620260A (en) * | 2018-12-05 | 2019-04-16 | 广州杰赛科技股份有限公司 | Psychological condition recognition methods, equipment and storage medium |
CN109697413A (en) * | 2018-12-13 | 2019-04-30 | 合肥工业大学 | Personality analysis method, system and storage medium based on head pose |
CN110141258A (en) * | 2019-05-16 | 2019-08-20 | 深兰科技(上海)有限公司 | A kind of emotional state detection method, equipment and terminal |
WO2019184031A1 (en) * | 2018-03-27 | 2019-10-03 | 中育苑(北京)文化传媒股份有限公司 | Psychological measurement and persuasion method and system based on image information |
CN111104815A (en) * | 2018-10-25 | 2020-05-05 | 北京入思技术有限公司 | Psychological assessment method and device based on emotion energy perception |
CN111413874A (en) * | 2019-01-08 | 2020-07-14 | 北京京东尚科信息技术有限公司 | Method, device and system for controlling intelligent equipment |
CN111466931A (en) * | 2020-04-24 | 2020-07-31 | 云南大学 | Emotion recognition method based on EEG and food picture data set |
CN112401886A (en) * | 2020-10-22 | 2021-02-26 | 北京大学 | Processing method, device and equipment for emotion recognition and storage medium |
CN112638256A (en) * | 2018-09-04 | 2021-04-09 | 强生消费者公司 | Device and method for assessing emotions of infants and young children |
CN113349778A (en) * | 2021-06-03 | 2021-09-07 | 杭州回车电子科技有限公司 | Emotion analysis method and device based on transcranial direct current stimulation and electronic device |
CN113490456A (en) * | 2019-03-29 | 2021-10-08 | 松下知识产权经营株式会社 | Psychological condition estimation system, psychological condition estimation method, program, and estimation model generation method |
CN113576478A (en) * | 2021-04-23 | 2021-11-02 | 西安交通大学 | Electroencephalogram signal-based image emotion classification method, system and device |
CN114027840A (en) * | 2021-11-12 | 2022-02-11 | 江苏科技大学 | Emotional electroencephalogram recognition method based on variational modal decomposition |
CN114638263A (en) * | 2022-03-15 | 2022-06-17 | 华南理工大学 | Building space satisfaction evaluation method based on electroencephalogram signals |
CN114870195A (en) * | 2022-05-09 | 2022-08-09 | 北京航空航天大学 | Method for regulating emotion of personnel by using vegetable green wall |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
RU2743876C1 (en) * | 2020-05-19 | 2021-03-01 | Татьяна Евгеньевна Ефремова | Method for rehabilitation of children and adolescents with behavioral and emotional disorders suffering from mental disorders |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103690165A (en) * | 2013-12-12 | 2014-04-02 | 天津大学 | Cross-inducing-mode emotion electroencephalogram recognition and modeling method |
CN105894039A (en) * | 2016-04-25 | 2016-08-24 | 京东方科技集团股份有限公司 | Emotion recognition modeling method, emotion recognition method and apparatus, and intelligent device |
CN106267514A (en) * | 2016-10-19 | 2017-01-04 | 上海大学 | Feeling control system based on brain electricity feedback |
-
2017
- 2017-04-18 CN CN201710252127.6A patent/CN107080546B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103690165A (en) * | 2013-12-12 | 2014-04-02 | 天津大学 | Cross-inducing-mode emotion electroencephalogram recognition and modeling method |
CN105894039A (en) * | 2016-04-25 | 2016-08-24 | 京东方科技集团股份有限公司 | Emotion recognition modeling method, emotion recognition method and apparatus, and intelligent device |
CN106267514A (en) * | 2016-10-19 | 2017-01-04 | 上海大学 | Feeling control system based on brain electricity feedback |
Non-Patent Citations (2)
Title |
---|
MOHSEN NAJI ET AL: "Emotion Classification Based on Forehead Biosignals using Support Vector Machines in Music Listening", 《PROCEEDINGS OF THE 2012 IEEE 12TH INTERNATIONAL CONFERENCE ON BIOINFORMATICS & BIOENGINEERING(BIBE)》 * |
王海宁: "《基于多通道生理信号的情绪识别技术研究》", 31 August 2016, 湖南大学出版社 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108143412A (en) * | 2017-12-22 | 2018-06-12 | 苏州创捷传媒展览股份有限公司 | A kind of control method of children's brain electricity mood analysis, apparatus and system |
CN108294739A (en) * | 2017-12-27 | 2018-07-20 | 苏州创捷传媒展览股份有限公司 | A kind of method and its device of test user experience |
WO2019184031A1 (en) * | 2018-03-27 | 2019-10-03 | 中育苑(北京)文化传媒股份有限公司 | Psychological measurement and persuasion method and system based on image information |
CN108937968A (en) * | 2018-06-04 | 2018-12-07 | 安徽大学 | lead selection method of emotion electroencephalogram signal based on independent component analysis |
CN108881985A (en) * | 2018-07-18 | 2018-11-23 | 南京邮电大学 | Program points-scoring system based on brain electricity Emotion identification |
CN109190658A (en) * | 2018-07-19 | 2019-01-11 | 中国电子科技集团公司电子科学研究院 | Video degree of awakening classification method, device and computer equipment |
CN109276243A (en) * | 2018-08-31 | 2019-01-29 | 易念科技(深圳)有限公司 | Brain electricity psychological test method and terminal device |
CN112638256A (en) * | 2018-09-04 | 2021-04-09 | 强生消费者公司 | Device and method for assessing emotions of infants and young children |
CN109157231A (en) * | 2018-10-24 | 2019-01-08 | 阿呆科技(北京)有限公司 | Portable multi-channel Depression trend assessment system based on emotional distress task |
CN111104815A (en) * | 2018-10-25 | 2020-05-05 | 北京入思技术有限公司 | Psychological assessment method and device based on emotion energy perception |
CN109567830A (en) * | 2018-10-30 | 2019-04-05 | 清华大学 | A kind of measurement of personality method and system based on neural response |
CN109620260A (en) * | 2018-12-05 | 2019-04-16 | 广州杰赛科技股份有限公司 | Psychological condition recognition methods, equipment and storage medium |
CN109697413B (en) * | 2018-12-13 | 2021-04-06 | 合肥工业大学 | Personality analysis method, system and storage medium based on head gesture |
CN109697413A (en) * | 2018-12-13 | 2019-04-30 | 合肥工业大学 | Personality analysis method, system and storage medium based on head pose |
CN111413874A (en) * | 2019-01-08 | 2020-07-14 | 北京京东尚科信息技术有限公司 | Method, device and system for controlling intelligent equipment |
CN111413874B (en) * | 2019-01-08 | 2021-02-26 | 北京京东尚科信息技术有限公司 | Method, device and system for controlling intelligent equipment |
CN113490456A (en) * | 2019-03-29 | 2021-10-08 | 松下知识产权经营株式会社 | Psychological condition estimation system, psychological condition estimation method, program, and estimation model generation method |
CN110141258A (en) * | 2019-05-16 | 2019-08-20 | 深兰科技(上海)有限公司 | A kind of emotional state detection method, equipment and terminal |
CN111466931A (en) * | 2020-04-24 | 2020-07-31 | 云南大学 | Emotion recognition method based on EEG and food picture data set |
CN112401886A (en) * | 2020-10-22 | 2021-02-26 | 北京大学 | Processing method, device and equipment for emotion recognition and storage medium |
CN112401886B (en) * | 2020-10-22 | 2023-01-31 | 北京大学 | Processing method, device and equipment for emotion recognition and storage medium |
CN113576478A (en) * | 2021-04-23 | 2021-11-02 | 西安交通大学 | Electroencephalogram signal-based image emotion classification method, system and device |
CN113349778A (en) * | 2021-06-03 | 2021-09-07 | 杭州回车电子科技有限公司 | Emotion analysis method and device based on transcranial direct current stimulation and electronic device |
CN113349778B (en) * | 2021-06-03 | 2023-02-17 | 杭州回车电子科技有限公司 | Emotion analysis method and device based on transcranial direct current stimulation and electronic device |
CN114027840A (en) * | 2021-11-12 | 2022-02-11 | 江苏科技大学 | Emotional electroencephalogram recognition method based on variational modal decomposition |
CN114638263A (en) * | 2022-03-15 | 2022-06-17 | 华南理工大学 | Building space satisfaction evaluation method based on electroencephalogram signals |
CN114870195A (en) * | 2022-05-09 | 2022-08-09 | 北京航空航天大学 | Method for regulating emotion of personnel by using vegetable green wall |
Also Published As
Publication number | Publication date |
---|---|
CN107080546B (en) | 2020-08-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107080546A (en) | Electroencephalogram-based emotion perception system and method for environmental psychology of teenagers and stimulation sample selection method | |
CN109298779B (en) | Virtual training system and method based on virtual agent interaction | |
CN106569604B (en) | Audiovisual bimodal semantic matches and semantic mismatch collaboration stimulation brain-machine interface method | |
Ulrich | Natural versus urban scenes: Some psychophysiological effects | |
CN110680314B (en) | Virtual reality situation task attention training system based on brain electricity multi-parameter | |
CN109224242B (en) | Psychological relaxation system and method based on VR interaction | |
CN102319067B (en) | Nerve feedback training instrument used for brain memory function improvement on basis of electroencephalogram | |
Li et al. | Research on environmental comfort and cognitive performance based on EEG+ VR+ LEC evaluation method in underground space | |
CN112641450B (en) | Time-varying brain network reconstruction method for dynamic video target detection | |
CN107402635B (en) | Mental health adjusting method and system combining brain waves and virtual reality | |
CN108324292A (en) | Indoor visual environment satisfaction degree analysis method based on electroencephalogram signals | |
CN109247917A (en) | A kind of spatial hearing induces P300 EEG signal identification method and device | |
CN113425297A (en) | Electroencephalogram signal-based children attention concentration training method and system | |
CN105919556A (en) | Near-infrared brain imager map collecting method based on cognitive tasks | |
CN106372729A (en) | Depth learning method and device for mental analysis | |
CN106447042A (en) | Psychoanalysis method and apparatus based on drawing projection | |
Qin et al. | Quantitative evaluation of attraction intensity of highway landscape visual elements based on dynamic perception | |
Su et al. | Adolescents environmental emotion perception by integrating EEG and eye movements | |
Rad et al. | Cognitive and perceptual influences of architectural and urban environments with an emphasis on the experimental procedures and techniques | |
Wang et al. | EEG-based research on brain functional networks in cognition | |
KR20170047099A (en) | Reasoning System of Group Emotion Based on Amount of Movements in Video Frame | |
Ma et al. | Effects of green walls on thermal perception and cognitive performance: An indoor study | |
CN115335102B (en) | Method, system and brain keyboard for generating feedback in brain | |
Zhang et al. | Affective computing using clustering method for mapping human's emotion | |
Zheng et al. | Psychological display of color VISION IN flash animation making course |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200720 Address after: 234000 building 7, electronic industrial park, high tech Zone, Suzhou City, Anhui Province Applicant after: Anhui Zhiqu Angel Information Technology Co., Ltd Address before: 230601 No. 111 Jiulong Road, Hefei economic and Technological Development Zone, Anhui, China Applicant before: ANHUI University |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |