CN103690165A - Cross-inducing-mode emotion electroencephalogram recognition and modeling method - Google Patents
Cross-inducing-mode emotion electroencephalogram recognition and modeling method Download PDFInfo
- Publication number
- CN103690165A CN103690165A CN201310689135.9A CN201310689135A CN103690165A CN 103690165 A CN103690165 A CN 103690165A CN 201310689135 A CN201310689135 A CN 201310689135A CN 103690165 A CN103690165 A CN 103690165A
- Authority
- CN
- China
- Prior art keywords
- emotion
- brain
- sample
- modeling method
- electricity
- 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
Images
Abstract
The invention discloses a cross-inducing-mode emotion electroencephalogram recognition and modeling method which comprises the following steps: designing inducing tests with different stimulation modes; collecting and preprocessing electroencephalogram data; extracting emotion electroencephalogram characteristics from the preprocessed electroencephalogram data; taking a part of video and picture inducing samples as a training set and the other part of the samples as a test set, and performing classification and recognition on emotion electroencephalogram characteristics corresponding to the training set by a support vector machine classifier based on recursive characteristic screening, wherein samples in the training set and the test set are from different material sources. According to the method, emotion electroencephalogram samples of different inducing modes are all tested, thus better conforming to practical application scenarios; the objective and moderate emotion recognition method can provide technical support for emotion detection on on-orbit astronauts, or enables a computer in a man-machine interaction field to have capabilities of sensing, recognizing and understanding human emotions so as to make a sensitive and friendly response to the emotion of a user and build a really intelligent and humanized man-machine environment.
Description
Technical field
The present invention relates to man-machine affective interaction field, space industry is for the emotion monitoring field of spaceman, particularly a kind of across bringing out pattern emotion brain electricity identification modeling method in-orbit.
Background technology
Emotion is the Premium Features of human brain, is guaranteeing organic existence and adaptation, and individual study, memory, decision-making are had to important impact.Emotion is also the source of individual variation, is the key component of many personal characteristics and mental pathology.Along with social development, each age, each field people's emotional disturbance is more and more, more and more serious, to the correct identification of emotion with regulate improving human lives's quality, ensures that physical and mental health is significant.
Researcher is identified people's emotion by expression, voice, postural cue both at home and abroad at present, use the recognition methods of various modes to obtain some effects, but due to the easy control of signal and the property pretended, recognition result cannot be got rid of the impact of tested subjective factors, sometimes cannot observe potential, real affective state.Emotion is the result of nervous process coaction under cerebral cortex and cortex, and transient behavior is strong.Brain electricity is the spontaneous discharge activities that is not subject to manual control, there is the advantage that temporal resolution is high, specific Function is strong, simple and easy to do, therefore and accuracy is relatively high aspect Emotion identification, the research of the Emotion identification based on brain electricity enjoys in recent years research to pay close attention to and becomes study hotspot.
Although the identification of emotion brain electricity reaps rich fruits, the research is also ripe far away.Current research is all to analyze single, specificly to bring out under pattern (vision, audition, audiovisual) electroresponse of emotion brain and to extract feature substantially, for example only Emotional Picture evoked brain potential is identified, training set and test set are all from the sample under same stimulus modelity.Yet there is a great limitation in this way: the disaggregated model that single emotion brings out to set up under pattern probably considered a part only with stimulus attribute response relevant and with the irrelevant feature of emotion (both brain electrical feature may be only with to bring out pattern relevant, do not comprise emotion specificity information), this disaggregated model cannot guarantee that the emotion brain electricity sample that other stimulus modelities are brought out possesses good identification ability.And people's emotion can be brought out (routine video, picture, music) by multiple different stimulus in actual life, concerning the ONLINE RECOGNITION system of practical application, in the urgent need to be one and can automatically select most important characteristics the accurate model of classification to the multiclass mood data collection obtaining under different natural conditions.
Summary of the invention
The invention provides a kind of across bringing out pattern emotion brain electricity identification modeling method, the present invention analyzes and feature extraction by the emotion brain electricity under multiple stimulus modelity, in modeling process, the feature under different stimulated pattern is merged, strengthen the learning capacity of grader, set up a kind of new, stable, reliable emotion evoked brain potential disaggregated model, described below:
Across bringing out a pattern emotion brain electricity identification modeling method, said method comprising the steps of:
(1) design the experiment of bringing out of different stimulated pattern;
(2) brain electric data collecting and pretreatment;
(3) from pretreated eeg data, extract emotion brain electrical feature;
(4) video and picture are brought out to a part in sample as training set, using another part as test set, and the sample in training set and test set comes from different material sources, by the support vector machine classifier based on recursive feature screening, the corresponding emotion brain of training set electrical feature is carried out to Classification and Identification.
Described brain electric data collecting and pretreated operation are specially:
For video, bring out experiment, use KMPlayer displaying video, subjects wears Philips earphone and watches, and for picture, brings out experiment, uses Eprime2.0 to write stimulation programs and present stimulation, uses the keyboard typing subjects reaction of marking;
The Neuroscan4.5 system of the Shi Wei Neuroscan company that brain wave acquisition instrument uses, electrode is placed in accordance with the international Nao electricity specified standard 10-20 of association standard, left and right ear two is led as reference electrode, forehead top side centre electrode grounding, gather altogether 36 and lead brain electricity, sample frequency is 1000Hz, and electrode impedance remains on below 5K ohm; Collecting 36 leads and carries out bandpass filtering after EEG data, removes eye electricity, retains 30 and lead brain electricity and intercept valid data section and process.
Described operation of extracting emotion brain electrical feature from pretreated eeg data is specially:
It to each length, is the sample of 1000 data points, calculating respectively 30 leads brain electricity each leads the power spectral density of 6 frequency ranges, the amplitude that each Frequency point in each frequency range is corresponding is added, and obtains the power spectrum energy value of each this frequency range of leading, and this intrinsic dimensionality is 30*6=180 dimension;
Calculate the Asymmetric Index of each frequency range that 12 pairs of position symmetries lead, Asymmetric Index be the power spectrum energy value that led in left side divided by the symmetrical power spectrum energy leading and.
Described 6 frequency ranges are specially: θ (4～8Hz), α (8～12Hz), β 1 (13～18Hz), β 2 (18～30Hz), γ 1 (30～36Hz), γ 2 (36～44Hz).
Described 12 pairs of position symmetries are led and are specially:
FP1-FP2，F7-F8，F3-F4，FT7-FT8，FC3-FC4，T7-T8，C3-C4，TP7-TP8，CP3-CP4，P3-P4，P7-P8，O1-O2。
The beneficial effect of technical scheme provided by the invention is: this method has considered that different emotions brings out the impact of pattern on emotion disaggregated model recognition performance (application scalability), in modeling process, merged multiple feature of bringing out the emotion brain electricity sample under pattern, and in to the test process of grader, difference is brought out to emotion brain electricity sample standard deviation corresponding to material source brand-new under pattern and test, more realistic application scenarios.The present invention has set up a kind of emotion that is independent of and has brought out more sane, the reliable disaggregated model of pattern, recognition performance.This objective, sane Emotion identification method can detect technical support is provided for spacefarer's in-orbit emotion, or helps to design hommization more, friendly interactive interface in field of human-computer interaction.
Accompanying drawing explanation
Fig. 1 is the time distribution map that video brings out task;
Fig. 2 is the appearance form that picture brings out task;
The distribution schematic diagram of Fig. 3 electrode lead;
Fig. 4 is a kind of flow chart across bringing out pattern emotion brain electricity identification modeling method.
The specific embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
Problem for current existence, this method proposes the method across pattern recognition, first for example, for different stimulated pattern (video, picture stimulation etc.) the emotion evoked brain potential under carries out feature extraction and analysis, in modeling training process, by stimulus modelity I, the feature of II hypencephalon electricity sample is all brought and is trained, in test process, use stimulus modelity I, the emotion brain electricity sample that material is corresponding that brings out brand-new under II is tested, whether the disaggregated model of setting up with check possesses identification ability to the emotion evoked brain potential sample holding in brand-new stimulation, thereby find a kind of being independent of and bring out pattern, realistic application, reliable and stable and effective Emotion identification method.
101: design the experiment of bringing out of different stimulated pattern;
1, video provocative test:
For video, bring out experiment, the present invention chooses approximately 15 vidclips, fragment glad, tranquil, nervous, sad, that detest theme respectively has 2～3, each fragment average length is about 3 minutes, these materials comprise that picture inducing materials hereinafter described all carried out emotion by more than 30 volunteers and evaluates before experiment, guarantee effectively to induce all kinds of emotions.In preliminary experiment, find, according to the order of " calmness---sadness---anxiety---happiness---detest ", bring out, emotion induced effectiveness is best, so this experiment is sequentially brought out by this.The experiment flow of every section of video is as shown in Figure 1: comprise and start prompting, video playback, self rating and 4 parts of having a rest.Starting prompt time is 2 seconds, reminds subjects to focus one's attention on, and video is about to play.Then start to play and bring out video, reproduction time is video segment duration.Each brings out after video playback finishes, and can present one section of landscape fragment (natural views) to subjects, helps subjects to calm down emotion.Allow afterwards subjects, according to real emotion impression and emotion self rating scale, the video of just having seen is carried out to subjective evaluation, feedback is watched the start-stop moment of main emotion impression, intensity, purity, joyful degree, degree of waking up and institute's induced affects fragment after video.After completing first three step, subjects has the time of having a rest of 1～3 minute, and after they return to tranquility, the prompting that starts of next film just there will be, and whole experimentation approximately needs 75 minutes.
Because the angle of personal story and experience is different, so to same experiment material, different tested impressions have certain difference with expection.For making experimental result have more science and reliability, in experiment, adopt emotion subjectiveness rating scale to do auxiliary, according to subjects's behavior performance and subjective feeling, judge the tested corresponding emotion that whether induced.
2, picture provocative test;
For reducing picture, bring out the gap of bringing out impression with video, simultaneously for fear of all kinds of Emotional Pictures switchings frequently, stimulate picture to take trifle as unit, it in trifle, is similar Emotional Picture, every trifle is containing 2～5 pictures (as shown in Figure 2), for fear of brain, grasp some with the irrelevant rule of experiment original intention, reduce the impact irrelevant with experiment purpose as far as possible, inhomogeneous trifle presents with random order.
Each experiment starts the front tranquillization data that first gather 1 minute, and between quiescent stage, experimenter, in quiet, thinking cap not, can make subjects enter tranquil state like this, is beneficial to follow-up experiment.Experiment is divided into 3 test(and is divided into 3 groups), each test comprises 12 trifles totally 49 pictures (i.e. 49 subtasks), and every pictures is 1 subtask, comprises 4 partial contents: 1) remind subjects to focus one's attention on; 2) then at center Screen, present Emotional Picture, continue 5s, picture is the current subjects of the requirement image content of concentrating one's energy to observe and experience; 3) enter the emotion self assessment phase, allow subjects according to real emotional experience, picture be carried out respectively 7 scorings of joyful degree and two dimensions of degree of waking up, mark more approaches 7, represents that enjoyment level or degree of waking up are higher.Mark more approaches 1, represents that enjoyment level or degree of waking up are lower.Scoring, by the typing of keypad numeral keys, although do not limit the scoring time, requires subjects to mark as early as possible according to sense of reality in principle; 4) prompting subjects has a rest, and the time of having a rest is 4 seconds.Each test finishes the tested rest of relief 6 minutes, then enters next group experiment.
102: brain electric data collecting and pretreatment;
12 Healthy subjects persons (6 male, 6 women, 19～24 one full year of life of age) have participated in this experiment, and all subjects's audition is normal, vision or correct defects of vision normal, the medical history that is a cup too low or psychosis family history.Have researcher to find, people's emotional activity is abundanter at night, more easily infected or induced affects.Therefore all 7 beginnings at night of experimental period, experiment subjects's mental status on the same day is good, without any anxious state of mind.
The stimulation platform of this experiment mainly divides two kinds: for video, bring out experiment, use KMPlayer displaying video, subjects wears Philips earphone and watches.For picture, bring out experiment, use Eprime2.0 to write stimulation programs and present stimulation, use the keyboard typing subjects reaction of marking.The display brightness of computer, contrast and color are all set to unified standard before experiment.In experiment, subjects is seated comfortably on the armchair at distance P C machine display screen dead ahead 1m place, and state is nature easily.
Wherein, the Neuroscan4.5 system of the Shi Wei Neuroscan company that brain wave acquisition instrument uses, electrode is placed in accordance with the international Nao electricity specified standard 10-20 of association standard, left and right ear two is led as reference electrode, forehead top side centre electrode grounding, gather altogether 36 and lead brain electricity, sample frequency is 1000Hz, and electrode impedance remains on below 5K ohm.Collect 36 and lead after EEG data, carry out data pretreatment.Data pretreatment process mainly comprises bandpass filtering, remove eye electricity, retain 30 leads brain electricity and intercepts 3 steps of valid data section.
The bandpass filtering that the present invention has carried out 1Hz～45Hz disturbs and high-frequency signal to remove direct current.In addition, because the experiment of the present invention design is by vision induced, the EEG signals therefore collecting inevitably can contain eye electricity (comprise eyeball upper and lower, move left and right nictation) and the impact that brings of electromyographic signal.Impact for the electro-ocular signal adulterating in EEG signals and electromyographic signal generation, the present invention gives filtering by the method for independent component analysis filtering, next retain and remove the data of leading of 30 outside eye electricity and reference electrode, referring to Fig. 3, according to subjects's subjective assessment result intercepting active data section, be specially: 1) for video evoked brain potential, the start-stop of bringing out according to the emotion that in emotion self rating scale, subjects provides constantly, the signal that retains corresponding time period in brain electricity (being the start-stop moment that emotion is brought out), and as active data section, for subsequent analysis, one number of seconds certificate is an emotion sample.2) for picture evoked brain potential, according to subjects's reflection, in 5 seconds of presenting at picture, conventionally the strongest their emotion impression in the 2nd second, abundant and stable, so this research is to each subjects, the 2nd number of seconds that the picture that employing is effectively brought out presents is according to as valid data section.
103: from pretreated eeg data, extract emotion brain electrical feature;
The present invention, in feature extraction step, has mainly extracted frequency domain character, and frequency domain character is by based on AR model
[1]power Spectral Estimation calculate, what model parameter computational methods adopted is Burger (Burg) algorithm
[2], model order is elected 8 rank as.It to each length, is the sample of 1000 data points, calculate respectively 30 and lead brain electricity (referring to Fig. 3) each leads the power spectral density of 6 frequency ranges, 6 frequency ranges are defined as follows: θ (4～8Hz), α (8～12Hz), β 1 (13～18Hz), β 2 (18～30Hz), γ 1 (30～36Hz), γ 2 (36～44Hz).Then amplitude corresponding to each Frequency point in each frequency range is added, obtains the power spectrum energy value E of each this frequency range of leading, this intrinsic dimensionality is 30*6=180 dimension.
Secondly, calculated the Asymmetric Index of each frequency range that 12 pairs of position symmetries lead, this 12 couple leads and is combined as FP1-FP2, F7-F8, F3-F4, FT7-FT8, FC3-FC4, T7-T8, C3-C4, TP7-TP8, CP3-CP4, P3-P4, P7-P8, the corresponding English character of O1-O2(all represents the title of leading), Asymmetric Index be the power spectrum energy value that led in left side divided by the symmetrical power spectrum energy leading and, it is defined as follows:
For example: F7-F8 lead place Asymmetric Index be: E_F7/ (E_F7+E_F8), F7 is equivalent to E
left, F8 is equivalent to E
right, this value size is between 0～1, and the intrinsic dimensionality of Asymmetric Index is 12*6=72 dimension.
By the operation of this step, obtain 252 dimension emotion brain electrical features.
104: video and picture are brought out to a part in sample as training set, using another part as test set, and the sample in training set and test set (for example: utilize sample that A, B video bring out as training set comes from different material sources, the sample that C video brings out is as test set), by the support vector machine classifier based on recursive feature screening, the corresponding emotion brain of training set electrical feature is carried out to Classification and Identification.
Innovative point of the present invention is in the division of training set and test set, in disaggregated model training process, in training set sample, not only comprise video evoked brain potential sample, also comprise picture evoked brain potential sample, this method and traditional emotion brain electricity model of cognition are (only according to specific, the single emotion brain electricity sample training of bringing out pattern) thinking is different, the different emotion brain electricity samples that bring out pattern have been merged in the present invention in grader training process, can make grader learn more fully, in test process, the present invention selects those never in training set, to occur, can induce the brand-new video evoked brain potential sample of similar emotion and picture evoked brain potential sample as test set, the test of guaranteeing grader is objective, consistent with the scene of real world applications.
Because sample set has, sample size is less than normal, intrinsic dimensionality is high, after feature extraction, uses support vector machine (Recursive feature elimination Support Vector Machine, the RFE-SVM) grader based on recursive feature screening
[3]feature is identified to (kernel function is selected linear kernel function).
In sum, this method is brought out frequency domain energy and the asymmetric feature of the emotion brain electricity sample under pattern by extracting difference, in modeling process, by difference being brought out to the training study of the emotion brain electricity sample under pattern, make grader obtain sufficient integrated learning ability, in test process, by the test of the brand-new emotion brain electricity sample under different stimulated pattern, weigh the performance of grader, this modeling method is more objective, rigorous, reliable.This invention can improve accuracy rate and the reliability of emotional state identification in application practice from now on effectively, and obtains considerable Social benefit and economic benefit.Optimum implementation intends adopting patent transfer, technological cooperation or product development.
List of references
[1] Xing Wuqiang, button gold is prosperous. the power Spectral Estimation based on AR model. and modern electronic technology, 2011,34 (7): 49-51.
[2] Yan Qinghua, Cheng Zhaogang, section Yunlong .AR model power Spectral Estimation and Matlab realize. computer and digital engineering, 2010,38 (004): 154-156.
[3] Liu Chong, Zhao Haibin, Li Chunsheng etc., the ECoG classification based on frequency band energy normalization and SVM-RFE, Chinese journal of scientific instrument, 2011,32 (3): 534～539
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
The foregoing is only preferred embodiment of the present invention, in order to limit the present invention, within the spirit and principles in the present invention not all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (5)
1. across bringing out a pattern emotion brain electricity identification modeling method, it is characterized in that, said method comprising the steps of:
(1) design the experiment of bringing out of different stimulated pattern;
(2) brain electric data collecting and pretreatment;
(3) from pretreated eeg data, extract emotion brain electrical feature;
(4) video and picture are brought out to a part in sample as training set, using another part as test set, and the sample in training set and test set comes from different material sources, by the support vector machine classifier based on recursive feature screening, the corresponding emotion brain of training set electrical feature is carried out to Classification and Identification.
2. according to claim 1 a kind ofly it is characterized in that across bringing out pattern emotion brain electricity identification modeling method, described brain electric data collecting and pretreated operation are specially:
For video, bring out experiment, use KMPlayer displaying video, subjects wears Philips earphone and watches, and for picture, brings out experiment, uses Eprime2.0 to write stimulation programs and present stimulation, uses the keyboard typing subjects reaction of marking;
The Neuroscan4.5 system of the Shi Wei Neuroscan company that brain wave acquisition instrument uses, electrode is placed in accordance with the international Nao electricity specified standard 10-20 of association standard, left and right ear two is led as reference electrode, forehead top side centre electrode grounding, gather altogether 36 and lead brain electricity, sample frequency is 1000Hz, and electrode impedance remains on below 5K ohm; Collecting 36 leads and carries out bandpass filtering after EEG data, removes eye electricity, retains 30 and lead brain electricity and intercept valid data section and process.
3. according to claim 1 a kind ofly it is characterized in that across bringing out pattern emotion brain electricity identification modeling method, described operation of extracting emotion brain electrical feature from pretreated eeg data is specially:
It to each length, is the sample of 1000 data points, calculating respectively 30 leads brain electricity each leads the power spectral density of 6 frequency ranges, the amplitude that each Frequency point in each frequency range is corresponding is added, and obtains the power spectrum energy value of each this frequency range of leading, and this intrinsic dimensionality is 30*6=180 dimension;
Calculate the Asymmetric Index of each frequency range that 12 pairs of position symmetries lead, Asymmetric Index be the power spectrum energy value that led in left side divided by the symmetrical power spectrum energy leading and.
4. according to claim 3 a kind of across bringing out pattern emotion brain electricity identification modeling method, it is characterized in that, described 6 frequency ranges are specially: θ (4～8Hz), α (8～12Hz), β 1 (13～18Hz), β 2 (18～30Hz), γ 1 (30～36Hz), γ 2 (36～44Hz).
5. according to claim 3 a kind ofly it is characterized in that across bringing out pattern emotion brain electricity identification modeling method, described 12 pairs of position symmetries are led and are specially:
FP1-FP2，F7-F8，F3-F4，FT7-FT8，FC3-FC4，T7-T8，C3-C4，TP7-TP8，CP3-CP4，P3-P4，P7-P8，O1-O2。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310689135.9A CN103690165B (en) | 2013-12-12 | 2013-12-12 | Modeling method for cross-inducing-mode emotion electroencephalogram recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310689135.9A CN103690165B (en) | 2013-12-12 | 2013-12-12 | Modeling method for cross-inducing-mode emotion electroencephalogram recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103690165A true CN103690165A (en) | 2014-04-02 |
| CN103690165B CN103690165B (en) | 2015-04-29 |
Family
ID=50351951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310689135.9A Active CN103690165B (en) | 2013-12-12 | 2013-12-12 | Modeling method for cross-inducing-mode emotion electroencephalogram recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103690165B (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303631A (en) * | 2015-09-22 | 2016-02-03 | 江西科技学院 | Method for carrying out card punching and attendance checking-in in small office by utilizing electroencephalogram signals |
| CN106778186A (en) * | 2017-02-14 | 2017-05-31 | 南方科技大学 | A kind of personal identification method and device for virtual reality interactive device |
| CN106730232A (en) * | 2016-12-09 | 2017-05-31 | 山东瀚岳智能科技股份有限公司 | A kind of intelligent awakening method and system |
| CN107016345A (en) * | 2017-03-08 | 2017-08-04 | 浙江大学 | A kind of demand model construction method applied to Product Conceptual Design |
| 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 |
| CN107080546A (en) * | 2017-04-18 | 2017-08-22 | 安徽大学 | Mood sensing system and method, the stimulation Method of Sample Selection of teenager's Environmental Psychology based on electroencephalogram |
| CN107085464A (en) * | 2016-09-13 | 2017-08-22 | 天津大学 | Emotion identification method based on P300 characters spells tasks |
| CN107157477A (en) * | 2017-05-24 | 2017-09-15 | 上海交通大学 | EEG signals Feature Recognition System and method |
| CN107485402A (en) * | 2017-08-17 | 2017-12-19 | 京东方科技集团股份有限公司 | Mood monitoring device and system |
| CN107578807A (en) * | 2017-07-17 | 2018-01-12 | 华南理工大学 | A kind of creation method of virtual reality emotion stimulating system |
| CN108056774A (en) * | 2017-12-29 | 2018-05-22 | 中国人民解放军战略支援部队信息工程大学 | Experimental paradigm mood analysis implementation method and its device based on visual transmission material |
| CN108279777A (en) * | 2018-02-11 | 2018-07-13 | 广东欧珀移动通信有限公司 | Brain wave control method and relevant device |
| CN108958486A (en) * | 2018-07-06 | 2018-12-07 | 重庆邮电大学 | Mood brain machine interface system based on recognition of face brain electricity N170 ingredient |
| CN109998570A (en) * | 2019-03-11 | 2019-07-12 | 山东大学 | Inmate's psychological condition appraisal procedure, terminal, equipment and system |
| CN109998571A (en) * | 2019-04-12 | 2019-07-12 | 清华大学深圳研究生院 | A kind of children are total to feelings experience equipment and experiential method |
| CN110037693A (en) * | 2019-04-24 | 2019-07-23 | 中央民族大学 | A kind of mood classification method based on facial expression and EEG |
| 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 |
| CN110464346A (en) * | 2019-08-29 | 2019-11-19 | 中新软件（上海）有限公司 | A kind of Psychological Evaluation method and device |
| CN110477914A (en) * | 2019-08-09 | 2019-11-22 | 南京邮电大学 | Mood excitation and EEG signals Emotion identification system based on Android |
| CN108391164B (en) * | 2018-02-24 | 2020-08-21 | Oppo广东移动通信有限公司 | Video parsing method and related product |
| CN111956219A (en) * | 2020-08-27 | 2020-11-20 | 济南大学 | Electroencephalogram signal-based emotion feature identification method and system and emotion feature identification and adjustment system |
| CN112163518A (en) * | 2020-09-28 | 2021-01-01 | 华南理工大学 | Emotion modeling method for emotion monitoring and adjusting system |
| WO2021068783A1 (en) * | 2019-10-12 | 2021-04-15 | 广东电网有限责任公司电力科学研究院 | Emotion recognition method, device and apparatus |
| CN112656427A (en) * | 2020-11-26 | 2021-04-16 | 山西大学 | Electroencephalogram emotion recognition method based on dimension model |
| CN113208635A (en) * | 2021-04-29 | 2021-08-06 | 山西大学 | Emotion electroencephalogram signal induction method based on conversation |
| CN113576478A (en) * | 2021-04-23 | 2021-11-02 | 西安交通大学 | Electroencephalogram signal-based image emotion classification method, system and device |
| CN114190944A (en) * | 2021-12-23 | 2022-03-18 | 上海交通大学 | Robust emotion recognition method based on electroencephalogram signals |
| CN114424945A (en) * | 2021-12-08 | 2022-05-03 | 中国科学院深圳先进技术研究院 | Brain wave biological feature recognition system and method based on random graphic image flash |
| CN114640699A (en) * | 2022-02-17 | 2022-06-17 | 华南理工大学 | Emotion induction monitoring system based on VR role playing game interaction |
| CN116369949A (en) * | 2023-06-06 | 2023-07-04 | 南昌航空大学 | Electroencephalogram signal grading emotion recognition method, electroencephalogram signal grading emotion recognition system, electronic equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011015788A (en) * | 2009-07-08 | 2011-01-27 | Keio Gijuku | Visual evoked potential signal detection system |
| CN102172327A (en) * | 2011-04-07 | 2011-09-07 | 中国医学科学院生物医学工程研究所 | Simultaneous stimulating and recording system of cross sensory channels of sight, sound and body sense |
| CN102715911A (en) * | 2012-06-15 | 2012-10-10 | 天津大学 | Brain electric features based emotional state recognition method |
| US20130023783A1 (en) * | 2005-12-01 | 2013-01-24 | Neba Health, Llc | S&m for analyzing and assessing depression and other mood disorders using electoencephalograhic (eeg) measurements |
-
2013
- 2013-12-12 CN CN201310689135.9A patent/CN103690165B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130023783A1 (en) * | 2005-12-01 | 2013-01-24 | Neba Health, Llc | S&m for analyzing and assessing depression and other mood disorders using electoencephalograhic (eeg) measurements |
| JP2011015788A (en) * | 2009-07-08 | 2011-01-27 | Keio Gijuku | Visual evoked potential signal detection system |
| CN102172327A (en) * | 2011-04-07 | 2011-09-07 | 中国医学科学院生物医学工程研究所 | Simultaneous stimulating and recording system of cross sensory channels of sight, sound and body sense |
| CN102715911A (en) * | 2012-06-15 | 2012-10-10 | 天津大学 | Brain electric features based emotional state recognition method |
Non-Patent Citations (1)
| Title |
|---|
| 聂聃等: "基于脑电的情绪识别研究综述", 《中国生物医学工程学报》, vol. 31, no. 4, 31 August 2012 (2012-08-31) * |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105303631A (en) * | 2015-09-22 | 2016-02-03 | 江西科技学院 | Method for carrying out card punching and attendance checking-in in small office by utilizing electroencephalogram signals |
| CN107085464A (en) * | 2016-09-13 | 2017-08-22 | 天津大学 | Emotion identification method based on P300 characters spells tasks |
| CN107085464B (en) * | 2016-09-13 | 2019-11-26 | 天津大学 | Emotion identification method based on P300 characters spells task |
| CN106730232A (en) * | 2016-12-09 | 2017-05-31 | 山东瀚岳智能科技股份有限公司 | A kind of intelligent awakening method and system |
| CN106778186A (en) * | 2017-02-14 | 2017-05-31 | 南方科技大学 | A kind of personal identification method and device for virtual reality interactive device |
| CN107016345A (en) * | 2017-03-08 | 2017-08-04 | 浙江大学 | A kind of demand model construction method applied to Product Conceptual Design |
| 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 |
| CN107080546A (en) * | 2017-04-18 | 2017-08-22 | 安徽大学 | Mood sensing system and method, the stimulation Method of Sample Selection of teenager's Environmental Psychology based on electroencephalogram |
| CN107157477A (en) * | 2017-05-24 | 2017-09-15 | 上海交通大学 | EEG signals Feature Recognition System and method |
| CN107157477B (en) * | 2017-05-24 | 2020-06-09 | 上海交通大学 | Electroencephalogram signal feature recognition system and method |
| CN107578807A (en) * | 2017-07-17 | 2018-01-12 | 华南理工大学 | A kind of creation method of virtual reality emotion stimulating system |
| CN107578807B (en) * | 2017-07-17 | 2020-12-29 | 广州博微智能科技有限公司 | Virtual reality emotional stimulation system creation method |
| CN107485402A (en) * | 2017-08-17 | 2017-12-19 | 京东方科技集团股份有限公司 | Mood monitoring device and system |
| US10881356B2 (en) | 2017-08-17 | 2021-01-05 | Boe Technology Group Co., Ltd. | Mood monitoring device, system and method |
| CN108056774A (en) * | 2017-12-29 | 2018-05-22 | 中国人民解放军战略支援部队信息工程大学 | Experimental paradigm mood analysis implementation method and its device based on visual transmission material |
| CN108279777A (en) * | 2018-02-11 | 2018-07-13 | 广东欧珀移动通信有限公司 | Brain wave control method and relevant device |
| CN108391164B (en) * | 2018-02-24 | 2020-08-21 | Oppo广东移动通信有限公司 | Video parsing method and related product |
| CN108958486A (en) * | 2018-07-06 | 2018-12-07 | 重庆邮电大学 | Mood brain machine interface system based on recognition of face brain electricity N170 ingredient |
| CN109998570A (en) * | 2019-03-11 | 2019-07-12 | 山东大学 | Inmate's psychological condition appraisal procedure, terminal, equipment and system |
| CN109998571A (en) * | 2019-04-12 | 2019-07-12 | 清华大学深圳研究生院 | A kind of children are total to feelings experience equipment and experiential method |
| CN110037693A (en) * | 2019-04-24 | 2019-07-23 | 中央民族大学 | A kind of mood classification method based on facial expression and EEG |
| 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 |
| CN110477914A (en) * | 2019-08-09 | 2019-11-22 | 南京邮电大学 | Mood excitation and EEG signals Emotion identification system based on Android |
| CN110464346B (en) * | 2019-08-29 | 2022-04-01 | 中新软件（上海）有限公司 | Psychological assessment method and device |
| CN110464346A (en) * | 2019-08-29 | 2019-11-19 | 中新软件（上海）有限公司 | A kind of Psychological Evaluation method and device |
| WO2021068783A1 (en) * | 2019-10-12 | 2021-04-15 | 广东电网有限责任公司电力科学研究院 | Emotion recognition method, device and apparatus |
| CN111956219A (en) * | 2020-08-27 | 2020-11-20 | 济南大学 | Electroencephalogram signal-based emotion feature identification method and system and emotion feature identification and adjustment system |
| CN111956219B (en) * | 2020-08-27 | 2023-04-28 | 济南大学 | Emotion characteristic recognition method, recognition and adjustment system based on electroencephalogram signals |
| CN112163518A (en) * | 2020-09-28 | 2021-01-01 | 华南理工大学 | Emotion modeling method for emotion monitoring and adjusting system |
| CN112163518B (en) * | 2020-09-28 | 2023-07-18 | 华南理工大学 | Emotion modeling method for emotion monitoring and adjusting system |
| CN112656427A (en) * | 2020-11-26 | 2021-04-16 | 山西大学 | Electroencephalogram emotion recognition method based on dimension model |
| CN113576478A (en) * | 2021-04-23 | 2021-11-02 | 西安交通大学 | Electroencephalogram signal-based image emotion classification method, system and device |
| CN113208635A (en) * | 2021-04-29 | 2021-08-06 | 山西大学 | Emotion electroencephalogram signal induction method based on conversation |
| CN114424945A (en) * | 2021-12-08 | 2022-05-03 | 中国科学院深圳先进技术研究院 | Brain wave biological feature recognition system and method based on random graphic image flash |
| CN114190944A (en) * | 2021-12-23 | 2022-03-18 | 上海交通大学 | Robust emotion recognition method based on electroencephalogram signals |
| CN114190944B (en) * | 2021-12-23 | 2023-08-22 | 上海交通大学 | Robust emotion recognition method based on electroencephalogram signals |
| CN114640699A (en) * | 2022-02-17 | 2022-06-17 | 华南理工大学 | Emotion induction monitoring system based on VR role playing game interaction |
| CN116369949A (en) * | 2023-06-06 | 2023-07-04 | 南昌航空大学 | Electroencephalogram signal grading emotion recognition method, electroencephalogram signal grading emotion recognition system, electronic equipment and medium |
| CN116369949B (en) * | 2023-06-06 | 2023-09-15 | 南昌航空大学 | Electroencephalogram signal grading emotion recognition method, electroencephalogram signal grading emotion recognition system, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103690165B (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103690165B (en) | Modeling method for cross-inducing-mode emotion electroencephalogram recognition | |
| CN107080546B (en) | Electroencephalogram-based emotion perception and stimulus sample selection method for environmental psychology of teenagers | |
| US20210012675A1 (en) | Teaching method and teaching device for improving attention, and computer readable storage medium | |
| CN102715911B (en) | Brain electric features based emotional state recognition method | |
| CN106569604B (en) | Audiovisual bimodal semantic matches and semantic mismatch collaboration stimulation brain-machine interface method | |
| CN104361356B (en) | A kind of film audient experience evaluation method based on man-machine interaction | |
| CN103412646B (en) | Based on the music mood recommend method of brain-machine interaction | |
| KR102333704B1 (en) | Method for processing contents based on biosignals, and thereof device | |
| CN106886792A (en) | A kind of brain electricity emotion identification method that Multiple Classifiers Combination Model Based is built based on layering | |
| CN101464729A (en) | Independent desire expression method based on auditory sense cognition neural signal | |
| GB2608690A (en) | Personalized mental state adjustment system and method based on brainwave music | |
| CN103631941A (en) | Electroencephalogram-based target image retrieval system | |
| Zhang et al. | The effects of probe similarity on retrieval and comparison processes in associative recognition | |
| CN110007769A (en) | A kind of AC system and method based on asynchronous brain-computer interface | |
| Conneau et al. | Assessment of new spectral features for eeg-based emotion recognition | |
| CN110141258A (en) | A kind of emotional state detection method, equipment and terminal | |
| CN110037693A (en) | A kind of mood classification method based on facial expression and EEG | |
| Kortelainen et al. | EEG-based recognition of video-induced emotions: selecting subject-independent feature set | |
| CN103019382A (en) | Brain-computer interaction method for reflecting subjective motive signals of brain through induced potentials | |
| CN105212949A (en) | A kind of method using skin pricktest signal to carry out culture experience emotion recognition | |
| CN109920498A (en) | Interpersonal relationships prediction technique based on mood brain electroresponse similitude | |
| CN106713787A (en) | Evaluation method for watching comfort level caused by rolling subtitles of different speed based on EEG | |
| Li et al. | Method of depression classification based on behavioral and physiological signals of eye movement | |
| Niu et al. | User experience evaluation in virtual reality based on subjective feelings and physiological signals | |
| CN107773254A (en) | A kind of method and device for testing Consumer's Experience |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |