CN111134692A - Method for generating electroencephalogram signal multi-dimensional characteristic picture sequence - Google Patents
Method for generating electroencephalogram signal multi-dimensional characteristic picture sequence Download PDFInfo
- Publication number
- CN111134692A CN111134692A CN201911116301.XA CN201911116301A CN111134692A CN 111134692 A CN111134692 A CN 111134692A CN 201911116301 A CN201911116301 A CN 201911116301A CN 111134692 A CN111134692 A CN 111134692A
- Authority
- CN
- China
- Prior art keywords
- electroencephalogram
- characteristic
- matrix
- seconds
- electroencephalogram signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims abstract description 36
- 238000001228 spectrum Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 4
- 230000003595 spectral effect Effects 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 12
- 210000004556 brain Anatomy 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 8
- 238000002474 experimental method Methods 0.000 claims description 8
- PIZHFBODNLEQBL-UHFFFAOYSA-N 2,2-diethoxy-1-phenylethanone Chemical compound CCOC(OCC)C(=O)C1=CC=CC=C1 PIZHFBODNLEQBL-UHFFFAOYSA-N 0.000 claims description 7
- 230000005611 electricity Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008451 emotion Effects 0.000 abstract description 11
- 238000000605 extraction Methods 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000011161 development Methods 0.000 abstract description 3
- 230000001737 promoting effect Effects 0.000 abstract 1
- 238000012360 testing method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
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]
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Psychiatry (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Psychology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (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)
Abstract
The invention discloses a method for generating an electroencephalogram signal multi-dimensional characteristic picture sequence, which comprises the following steps: s1, generating a square matrix; s2, extracting the power spectrum of the electroencephalogram signal in the unit time length window as the frequency domain characteristic of the electroencephalogram signal; s3, making an electroencephalogram characteristic frame in a time-length window by the method; s4, with the forward movement of the window, making other electroencephalogram multi-dimensional feature frames corresponding to the corresponding time periods by the same method; s5, forming an electroencephalogram characteristic matrix from the original signals, and then forming an electroencephalogram characteristic sequence; s6, carrying out standardization processing on the characteristic values of the electroencephalogram, and uniformly classifying the power spectral density of the electroencephalogram into a real number range of [0,1 ]; s7, constructing an electroencephalogram multi-dimensional characteristic frame sequence, laying a foundation for next step of image extraction and emotion classification and identification, and effectively promoting the combination and development and application of electroencephalogram signal detection and emotion identification.
Description
Technical Field
The invention relates to the technical field of electroencephalogram signals, in particular to a method for generating an electroencephalogram signal multi-dimensional characteristic picture sequence.
Background
Emotion is an important sign of human intelligence, and therefore, one of important signs of artificial intelligence is that a machine can understand human emotion. Emotion recognition by human behavior, facial expression, or physiological signals is becoming a focus of research. However, in some social scenes, people often intentionally mask real emotion of their own centers by changing sounds or masking expressions, and for this reason, researchers tend to recognize real emotional states of people more by physiological signals such as electroencephalogram signals, eye movement signals, body temperature signals, blood pressure signals, and electromyogram signals. The electroencephalogram signal directly reflects the activity state of the brain of people, so that the electroencephalogram signal is more emphasized by researchers, and therefore a method for generating an electroencephalogram signal characteristic frame needs to be provided.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides a method for generating an electroencephalogram signal multi-dimensional characteristic picture sequence.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for generating an electroencephalogram signal multi-dimensional characteristic picture sequence comprises the following steps:
s1, mapping the spatial distribution condition of the brain electricity electrode involved in the DEAP experiment to a 10-20 system plane diagram to form a standard brain electricity electrode distribution diagram, and generalizing to generate a square matrix;
s2, decomposing the electroencephalogram signal through a Hilbert-Huang transform method, dividing the electroencephalogram signal according to a unit time length window, and extracting a power spectrum of the electroencephalogram signal in the unit time length window as the frequency domain characteristic of the electroencephalogram signal;
s3, making an electroencephalogram characteristic frame in a time-length window by the method;
s4, with the forward movement of the window, making other electroencephalogram multi-dimensional feature frames corresponding to the corresponding time periods by the same method;
s5, acquiring 60-second electroencephalogram signal oscillograms corresponding to 32 tested electroencephalogram electrodes in DEAP, marking a time window from 1 to N on the oscillograms, forming an electroencephalogram characteristic matrix from original signals, and then forming an electroencephalogram characteristic sequence;
s6, carrying out standardization processing on the characteristic values of the electroencephalogram, and uniformly classifying the power spectral density of the electroencephalogram into a real number range of [0,1 ];
and S7, constructing the electroencephalogram multi-dimensional characteristic frame sequence.
Preferably, the square matrix of the step S1 is a 9 × 9 electroencephalogram feature square matrix.
Preferably, the value of the electroencephalogram electrode to be tested in the step S2 is directly a frequency domain characteristic value of the electroencephalogram, and the value of the electroencephalogram electrode not to be tested is calculated from the values of the peripheral points in the graph.
Preferably, the electroencephalogram feature frame of step S3 further includes a vertical matrix expressed as one dimension: p(electrode,sequence,trial,subject)Where P is a matrix of (32 × 60 × 40 × 32).
Preferably, the constructing of the electroencephalogram multidimensional characteristic frame sequence in the step S7 includes the following steps:
p1, extracting electroencephalogram signals from the original data set, preprocessing the electroencephalogram signals, and constructing an initialized electroencephalogram characteristic matrix structure according to the electrode number and the spatial distribution position of the electroencephalogram signals acquired by the experiment;
p2, extracting characteristic values from the electroencephalogram signals, wherein the frequency domain characteristic value power spectrum density [52,56,72,90,92] of the electroencephalogram signals is extracted in the chapter, the calculation method of the power spectrum density is to use a Welch method for calculation, then, the characteristics of the original electroencephalogram are extracted through different time length windows (the length of the time length windows comprises 1 second, 2 seconds, 3 seconds, 4 seconds, 5 seconds, 6 seconds, 10 seconds, 15 seconds, 20 seconds, 30 seconds and 60 seconds), no overlapping exists among the time length windows, and finally, an electroencephalogram characteristic value matrix is obtained;
p3, normalizing the eigenvalue in the electroencephalogram eigenvalue matrix, and limiting the eigenvalue to be in the range of [0,1 ];
and P4, directly filling the positions of the red color points in the electroencephalogram characteristic matrix into the normalized electroencephalogram characteristic values.
Preferably, the calculation formula of the step P3 is as follows:
wherein, FiIs the characteristic value corresponding to the ith time length window before normalization, Fi ’For its normalized characteristic value, FmaxMaximum eigenvalue, F, in the sequence of eigenvalues calculated for one electroencephalogram electrode corresponding to the electroencephalogram signal through a fixed duration windowminIs the minimum eigenvalue.
Preferably, the calculation formula in the step P3 is:
wherein V(m,n)Is the characteristic value of the gray point corresponding to the m row and n column in the EEG characteristic value matrix, V’ (m,n)Are characteristic values of four points, upper, lower, left, and right, around the gray point.
Preferably, the subscript is out of the range of 0 or 8, and thus has a value of 0, K is the number of elements in the molecule other than 0, and is set to 1 by default.
According to the method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence, provided by the invention, through extraction of the electroencephalogram signal and generation of the characteristic frame, the electroencephalogram multi-dimensional characteristic frame sequence can be generated by the energy characteristic of the electroencephalogram signal according to the time sequence and the spatial arrangement characteristic of the electroencephalogram electrode. The electroencephalogram multi-dimensional characteristic frame sequences reflect the change rule of electroencephalogram signals in emotion test experiments, lay a foundation for next image extraction and emotion classification and identification, and effectively promote the combination and development and application of electroencephalogram signal detection and emotion identification.
Drawings
FIG. 1 is a DEAP data set test brain electrical electrode layout and generalized brain electrical characteristic matrix diagram of the present invention;
FIG. 2 is a flow chart of a sequence of frames for constructing a multi-dimensional feature of brain electricity according to the present invention;
FIG. 3 is an enlarged electroencephalogram feature frame picture, an electroencephalogram electrode label and an interpolation contour map of the present invention;
FIG. 4 is a diagram of a sequence of electroencephalogram features generated by windows of different durations according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
A method for generating an electroencephalogram signal multi-dimensional characteristic picture sequence comprises the following steps:
s1, mapping the spatial distribution condition of the brain electricity electrode involved in the DEAP experiment to a 10-20 system plane diagram to form a standard brain electricity electrode distribution diagram, and generalizing to generate a square matrix;
s2, decomposing the electroencephalogram signal through a Hilbert-Huang transform method, dividing the electroencephalogram signal according to a unit time length window, and extracting a power spectrum of the electroencephalogram signal in the unit time length window as the frequency domain characteristic of the electroencephalogram signal;
s3, making an electroencephalogram characteristic frame in a time-length window by the method;
s4, with the forward movement of the window, making other electroencephalogram multi-dimensional feature frames corresponding to the corresponding time periods by the same method;
s5, acquiring 60-second electroencephalogram signal oscillograms corresponding to 32 tested electroencephalogram electrodes in DEAP, marking a time window from 1 to N on the oscillograms, forming an electroencephalogram characteristic matrix from original signals, and then forming an electroencephalogram characteristic sequence;
s6, carrying out standardization processing on the characteristic values of the electroencephalogram, and uniformly classifying the power spectral density of the electroencephalogram into a real number range of [0,1 ];
and S7, constructing the electroencephalogram multi-dimensional characteristic frame sequence.
Preferably, the square matrix of the step S1 is a 9 × 9 electroencephalogram feature square matrix.
Preferably, the value of the electroencephalogram electrode to be tested in the step S2 is directly a frequency domain characteristic value of the electroencephalogram, and the value of the electroencephalogram electrode not to be tested is calculated from the values of the peripheral points in the graph.
Preferably, the electroencephalogram feature frame of step S3 further includes a vertical matrix expressed as one dimension:
P(electrode,sequence,trial,subject)where P is a matrix of (32 × 60 × 40 × 32).
Preferably, the constructing of the electroencephalogram multidimensional characteristic frame sequence in the step S7 includes the following steps:
p1, extracting electroencephalogram signals from the original data set, preprocessing the electroencephalogram signals, and constructing an initialized electroencephalogram characteristic matrix structure according to the electrode number and the spatial distribution position of the electroencephalogram signals acquired by the experiment;
p2, extracting characteristic values from the electroencephalogram signals, wherein the frequency domain characteristic value power spectrum density [52,56,72,90,92] of the electroencephalogram signals is extracted in the chapter, the calculation method of the power spectrum density is to use a Welch method for calculation, then, the characteristics of the original electroencephalogram are extracted through different time length windows (the length of the time length windows comprises 1 second, 2 seconds, 3 seconds, 4 seconds, 5 seconds, 6 seconds, 10 seconds, 15 seconds, 20 seconds, 30 seconds and 60 seconds), no overlapping exists among the time length windows, and finally, an electroencephalogram characteristic value matrix is obtained;
p3, normalizing the eigenvalue in the electroencephalogram eigenvalue matrix, and limiting the eigenvalue to be in the range of [0,1 ];
and P4, directly filling the positions of the red color points in the electroencephalogram characteristic matrix into the normalized electroencephalogram characteristic values.
Preferably, the calculation formula of the step P3 is as follows:
wherein, FiIs the characteristic value corresponding to the ith time length window before normalization, Fi ’For its normalized characteristic value, FmaxMaximum eigenvalue, F, in the sequence of eigenvalues calculated for one electroencephalogram electrode corresponding to the electroencephalogram signal through a fixed duration windowminIs the minimum eigenvalue.
Preferably, the calculation formula in the step P3 is:
wherein V(m,n)Is the characteristic value of the gray point corresponding to the m row and n column in the EEG characteristic value matrix, V’ (m,n)Are characteristic values of four points, upper, lower, left, and right, around the gray point.
Preferably, the subscript is out of the range of 0 or 8, and thus has a value of 0, K is the number of elements in the molecule other than 0, and is set to 1 by default.
According to the method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence, provided by the invention, through extraction of the electroencephalogram signal and generation of the characteristic frame, the electroencephalogram multi-dimensional characteristic frame sequence can be generated by the energy characteristic of the electroencephalogram signal according to the time sequence and the spatial arrangement characteristic of the electroencephalogram electrode. The electroencephalogram multi-dimensional characteristic frame sequences reflect the change rule of electroencephalogram signals in emotion test experiments, lay a foundation for next image extraction and emotion classification and identification, and effectively promote the combination and development and application of electroencephalogram signal detection and emotion identification.
Examples
From fig. 4, electroencephalogram multidimensional characteristic frame sequences formed by different time windows are shown, and because the number of frames included in the sequences corresponding to the smaller time windows is large, in the figure, only the first five characteristic frames of each sequence are shown, in the figure, each row represents electroencephalogram characteristic frame pictures corresponding to the same time window, and each column represents electroencephalogram characteristic frame pictures corresponding to different time windows and having the same sequence number. Taking the electroencephalogram feature frames of the first two rows in the figure as an example, the electroencephalogram multi-dimensional feature frame sequence of the first row shows the energy change feature of the electroencephalogram signal within the first 5 seconds by using pictures of 5 frames, and the electroencephalogram signal within the second 6 seconds by using the first three frames of the second row. Assuming use of MFI（m,n）(MFI is short for MultiFeatures Images) represent different frames in a sequence of EEG multidimensional feature frames, and we can clearly see that MFI is shown in FIG. 4(1,5)And MFI(2,3)The two characteristic frames are very similar, and can be intuitively deduced from the picture, the electroencephalogram multi-dimensional characteristic frame sequence generated by the short duration window can show more details for the change of the electroencephalogram signal, and each frame image of the electroencephalogram multi-dimensional characteristic frame sequence generated by the longer duration window has more generalization.
Claims (8)
1. A method for generating an electroencephalogram signal multi-dimensional characteristic picture sequence is characterized by comprising the following steps: the generation method comprises the following steps:
s1, mapping the spatial distribution condition of the brain electricity electrode involved in the DEAP experiment to a 10-20 system plane diagram to form a standard brain electricity electrode distribution diagram, and generalizing to generate a square matrix;
s2, decomposing the electroencephalogram signal through a Hilbert-Huang transform method, dividing the electroencephalogram signal according to a unit time length window, and extracting a power spectrum of the electroencephalogram signal in the unit time length window as the frequency domain characteristic of the electroencephalogram signal;
s3, making an electroencephalogram characteristic frame in a time-length window by the method;
s4, with the forward movement of the window, making other electroencephalogram multi-dimensional feature frames corresponding to the corresponding time periods by the same method;
s5, acquiring 60-second electroencephalogram signal oscillograms corresponding to 32 tested electroencephalogram electrodes in DEAP, marking a time window from 1 to N on the oscillograms, forming an electroencephalogram characteristic matrix from original signals, and then forming an electroencephalogram characteristic sequence;
s6, carrying out standardization processing on the characteristic values of the electroencephalogram, and uniformly classifying the power spectral density of the electroencephalogram into a real number range of [0,1 ];
and S7, constructing the electroencephalogram multi-dimensional characteristic frame sequence.
2. The method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence according to claim 1, which is characterized in that: the square matrix of the step S1 is a 9 multiplied by 9 electroencephalogram characteristic square matrix.
3. The method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence according to claim 1, which is characterized in that: and in the step S2, the value of the tested electroencephalogram electrode is directly the frequency domain characteristic value of the electroencephalogram, and the value of the untested electroencephalogram electrode is obtained by calculating the values of the peripheral points in the graph.
4. The method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence according to claim 1, which is characterized in that: the electroencephalogram feature frame of the step S3 further includes a vertical matrix expressed as one dimension:
P(electrode,sequence,trail,subject)where P is a matrix of (32 × 60 × 40 × 32).
5. The method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence according to claim 1, which is characterized in that: the step of S7, constructing the electroencephalogram multi-dimensional feature frame sequence, comprises the following steps:
p1, extracting electroencephalogram signals from the original data set, preprocessing the electroencephalogram signals, and constructing an initialized electroencephalogram characteristic matrix structure according to the electrode number and the spatial distribution position of the electroencephalogram signals acquired by the experiment;
p2, extracting characteristic values from the electroencephalogram signals, wherein the frequency domain characteristic value power spectrum density [52,56,72,90,92] of the electroencephalogram signals is extracted in the chapter, the calculation method of the power spectrum density is to use a Welch method for calculation, then, the characteristics of the original electroencephalogram are extracted through different time length windows (the length of the time length windows comprises 1 second, 2 seconds, 3 seconds, 4 seconds, 5 seconds, 6 seconds, 10 seconds, 15 seconds, 20 seconds, 30 seconds and 60 seconds), no overlapping exists among the time length windows, and finally, an electroencephalogram characteristic value matrix is obtained;
p3, normalizing the eigenvalue in the electroencephalogram eigenvalue matrix, and limiting the eigenvalue to be in the range of [0,1 ];
and P4, directly filling the positions of the red color points in the electroencephalogram characteristic matrix into the normalized electroencephalogram characteristic values.
6. The method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence according to claim 5, which is characterized in that: the calculation formula of the step P3 is:
wherein, FiIs the characteristic value corresponding to the ith time length window before normalization，F’iFor its normalized characteristic value, FmaxMaximum eigenvalue, F, in the sequence of eigenvalues calculated for one electroencephalogram electrode corresponding to the electroencephalogram signal through a fixed duration windowminIs the minimum eigenvalue.
7. The method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence according to claim 5, which is characterized in that: the calculation formula in the step P3 is:
wherein m, n is a natural number ranging from 0 to 8, V(m,n)Is the eigenvalue of the gray point corresponding to the m-th row and n-th column in the electroencephalogram eigenvalue matrix, and V' (m, n) is the eigenvalue of four points, upper, lower, left and right, surrounding the gray point.
8. The method for generating the electroencephalogram signal multi-dimensional characteristic picture sequence according to claim 7, which is characterized in that: v'(m,n)Is outside the range of 0 or 8, then the value is 0. K is the number of non-0 elements in the numerator and the default value is set to 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911116301.XA CN111134692A (en) | 2019-11-15 | 2019-11-15 | Method for generating electroencephalogram signal multi-dimensional characteristic picture sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911116301.XA CN111134692A (en) | 2019-11-15 | 2019-11-15 | Method for generating electroencephalogram signal multi-dimensional characteristic picture sequence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111134692A true CN111134692A (en) | 2020-05-12 |
Family
ID=70517138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911116301.XA Pending CN111134692A (en) | 2019-11-15 | 2019-11-15 | Method for generating electroencephalogram signal multi-dimensional characteristic picture sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111134692A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113208594A (en) * | 2021-05-12 | 2021-08-06 | 海南热带海洋学院 | Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram |
| CN113509190A (en) * | 2021-03-18 | 2021-10-19 | 上海交通大学 | Product design evaluation method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150029969A (en) * | 2013-09-11 | 2015-03-19 | 세종대학교산학협력단 | Sensibility classification method using brain wave |
| CN108888264A (en) * | 2018-05-03 | 2018-11-27 | 南京邮电大学 | EMD and CSP merges power spectral density brain electrical feature extracting method |
| CN109924990A (en) * | 2019-03-27 | 2019-06-25 | 兰州大学 | A kind of EEG signals depression identifying system based on EMD algorithm |
| KR20200071807A (en) * | 2018-11-30 | 2020-06-22 | 인하대학교 산학협력단 | Human emotion state recognition method and system using fusion of image and eeg signals |
-
2019
- 2019-11-15 CN CN201911116301.XA patent/CN111134692A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150029969A (en) * | 2013-09-11 | 2015-03-19 | 세종대학교산학협력단 | Sensibility classification method using brain wave |
| CN108888264A (en) * | 2018-05-03 | 2018-11-27 | 南京邮电大学 | EMD and CSP merges power spectral density brain electrical feature extracting method |
| KR20200071807A (en) * | 2018-11-30 | 2020-06-22 | 인하대학교 산학협력단 | Human emotion state recognition method and system using fusion of image and eeg signals |
| CN109924990A (en) * | 2019-03-27 | 2019-06-25 | 兰州大学 | A kind of EEG signals depression identifying system based on EMD algorithm |
Non-Patent Citations (2)
| Title |
|---|
| MOHAMMAD ZAVID PARVEZ; MANORANJAN PAUL: "NOVEL APPROACHES OF EEG SIGNAL CLASSIFICATION USING IMF BANDWIDTH AND DCT FREQUENCY", 《BIOMEDICAL ENGINEERING: APPLICATIONS, BASIS AND COMMUNICATIONS》 * |
| 李幼军: "生理信号的情感计算研究及其应用", 《中国优秀博硕士学位论文全文数据库》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113509190A (en) * | 2021-03-18 | 2021-10-19 | 上海交通大学 | Product design evaluation method and system |
| CN113208594A (en) * | 2021-05-12 | 2021-08-06 | 海南热带海洋学院 | Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Phase-locking value based graph convolutional neural networks for emotion recognition | |
| Song et al. | Graph-embedded convolutional neural network for image-based EEG emotion recognition | |
| CN111329474B (en) | Electroencephalogram identity recognition method and system based on deep learning and information updating method | |
| Niu et al. | Robust remote heart rate estimation from face utilizing spatial-temporal attention | |
| Gao et al. | EEG-based spatio–temporal convolutional neural network for driver fatigue evaluation | |
| Niu et al. | Synrhythm: Learning a deep heart rate estimator from general to specific | |
| CN110287805B (en) | Micro-expression identification method and system based on three-stream convolutional neural network | |
| CN109299751B (en) | EMD data enhancement-based SSVEP electroencephalogram classification method of convolutional neural model | |
| Zhao et al. | A 3D convolutional neural network for emotion recognition based on EEG signals | |
| CN107122050B (en) | Stable state of motion visual evoked potential brain-computer interface method based on CSFL-GDBN | |
| CN109784023A (en) | Stable state vision inducting brain electricity personal identification method and system based on deep learning | |
| Pan et al. | Emotion recognition based on EEG using generative adversarial nets and convolutional neural network | |
| CN111184509A (en) | Emotion-induced electroencephalogram signal classification method based on transfer entropy | |
| CN111134692A (en) | Method for generating electroencephalogram signal multi-dimensional characteristic picture sequence | |
| Anwar et al. | EEG signal classification using convolutional neural networks on combined spatial and temporal dimensions for BCI systems | |
| Jinliang et al. | EEG emotion recognition based on granger causality and capsnet neural network | |
| US20230101539A1 (en) | Physiological electric signal classification processing method and apparatus, computer device and storage medium | |
| CN114631831A (en) | Cross-individual emotion electroencephalogram recognition method and system based on semi-supervised field self-adaption | |
| CN111797747A (en) | Potential emotion recognition method based on EEG, BVP and micro-expression | |
| Jiang et al. | Analytical comparison of two emotion classification models based on convolutional neural networks | |
| CN114145744B (en) | Cross-equipment forehead electroencephalogram emotion recognition based method and system | |
| CN113128353B (en) | Emotion perception method and system oriented to natural man-machine interaction | |
| CN114145745A (en) | Multi-task self-supervision emotion recognition method based on graph | |
| Li et al. | A mild cognitive impairment diagnostic model based on IAAFT and BiLSTM | |
| CN112200221B (en) | Epilepsy prediction system and method based on electrical impedance imaging and electroencephalogram signals |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200512 |
|
| WD01 | Invention patent application deemed withdrawn after publication |