CN113208594A - Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram - Google Patents
Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram Download PDFInfo
- Publication number
- CN113208594A CN113208594A CN202110518743.8A CN202110518743A CN113208594A CN 113208594 A CN113208594 A CN 113208594A CN 202110518743 A CN202110518743 A CN 202110518743A CN 113208594 A CN113208594 A CN 113208594A
- Authority
- CN
- China
- Prior art keywords
- electroencephalogram signal
- time
- spectral density
- electroencephalogram
- power
- 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
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
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Psychiatry (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (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 emotion feature representation method based on an electroencephalogram signal space-time power spectrogram, which comprises the following steps of: obtaining an electrode position image according to a 10-20 system electrode placement method, and carrying out gray processing on the electrode position image to obtain an electrode position gray image; acquiring electroencephalogram signals collected by each electrode, and filtering; dividing the electroencephalogram signal after filtering processing according to time periods to obtain time domain characteristic data of the electroencephalogram signal; calculating the power spectral density of a corresponding frequency band in the electroencephalogram signal of each time period, extracting the logarithm of the power spectral density as a characteristic value, and normalizing the characteristic value to 0-255 color values; assigning the normalized characteristic values to the positions of corresponding electrodes in the electrode position gray level graph in a one-to-one correspondence manner; and performing pseudo-color processing on the assigned electrode position gray-scale image to obtain an electroencephalogram signal space-time power spectrogram. The invention can represent the change difference of each channel of the electroencephalogram signal through the color change, and has more intuition.
Description
Technical Field
The invention relates to the technical field of human emotion recognition, in particular to an emotion feature representation method based on an electroencephalogram signal space-time power spectrogram.
Background
The electroencephalogram signals can be changed due to human emotion changes, the feature extraction plays a crucial role in the research of emotion recognition by the electroencephalogram signals, and the extracted features are not appropriate, so that the direct influence on whether the subsequent accurate recognition can be carried out is realized.
The earliest electroencephalogram analysis method was time domain feature analysis, which has wide application because of its low signal information loss, clear physical significance and convenient extraction. However, the electroencephalogram signal has small amplitude, randomness and no obvious rule, so that the characteristic extraction only carried out in the time domain is not enough to analyze the electroencephalogram signal in all aspects.
Since electroencephalogram signals contain rich frequency information, in recent years, frequency domain features are the choice of many researchers for feature extraction of electroencephalogram signals.
Because the left and right brain areas have asymmetric reactions to different emotional states, when electroencephalogram signals are collected, multi-channel information is collected at the same time, and multi-channel data cannot be analyzed at the same time no matter time domain analysis or frequency domain analysis is carried out, so that the spatial domain characteristics of the electroencephalogram signals are ignored.
Therefore, how to provide an emotion feature representation method capable of representing the difference condition of a plurality of access electroencephalograms by color difference in consideration of the spatial domain features of the electroencephalograms is a problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides an emotion feature representation method based on a brain electrical signal space-time power spectrogram, which can represent the change difference of each channel of the brain electrical signal through color change and is more intuitive.
In order to achieve the purpose, the invention adopts the following technical scheme:
an emotion feature representation method based on an electroencephalogram signal space-time power spectrogram comprises the following steps:
obtaining an electrode position image according to a 10-20 system electrode placement method, and carrying out gray processing on the electrode position image to obtain an electrode position gray image;
acquiring electroencephalogram signals collected by each electrode, and filtering;
dividing the electroencephalogram signal after filtering processing according to time periods to obtain time domain characteristic data of the electroencephalogram signal;
calculating the power spectral density of a corresponding frequency band in the electroencephalogram signal of each time period, extracting the logarithm of the power spectral density as a characteristic value, and normalizing the characteristic value to 0-255 color values;
assigning the normalized characteristic values to the positions of corresponding electrodes in the electrode position gray level graph in a one-to-one correspondence manner;
and performing pseudo-color processing on the assigned electrode position gray-scale image to obtain an electroencephalogram signal space-time power spectrogram.
Preferably, in the above method for representing emotional characteristics based on the electroencephalogram signal space-time power spectrogram, the extraction process of the power spectral density is as follows:
and performing Fourier transform on the time domain characteristic data of the electroencephalogram signal to obtain the power spectral density of the frequency band corresponding to each time period.
Preferably, in the above method for representing emotional characteristics based on a time-space power spectrogram of an electroencephalogram signal, the power spectral density is calculated according to the following formula:
wherein, XT(ω) represents the Fourier transform of the brain electrical signal, P (ω) represents the power spectral density, and 2T represents a duration of 2T for the brain electrical signal.
Preferably, in the above method for representing emotional characteristics based on a time-space power spectrogram of an electroencephalogram signal, the characteristic value is normalized to a color value of 0 to 255 by using the following formula:
wherein X represents the original characteristic value, Y represents the characteristic value after normalization, XMax、XMinRespectively represent the originalMaximum and minimum values of the characteristic values, Ymax、YminRepresenting the maximum and minimum values of the normalized power spectral density, respectively.
Preferably, in the method for representing emotional characteristics based on the electroencephalogram signal space-time power spectrogram, a low-pass filter, a band-pass filter, a high-pass filter or an 8-order butterworth filter is adopted to filter the electroencephalogram signals acquired by each electrode.
Preferably, in the method for representing emotional characteristics based on the electroencephalogram signal space-time power spectrogram, the electroencephalogram signal after filtering is divided according to the length of 3s-12 s.
According to the technical scheme, compared with the prior art, the emotion feature representation method based on the electroencephalogram signal space-time power spectrogram can be used for simultaneously collecting electroencephalograms collected by a plurality of electrode channels, performing time domain analysis and frequency domain information on the electroencephalograms of the channels respectively in sequence to obtain the power spectral density of the electroencephalograms of the channels, normalizing the logarithm of the power spectral density to 0-255 color values, and assigning the values to corresponding positions of an electrode position map correspondingly, so that the extraction of the spatial domain features of the electroencephalograms is realized, the visualization of the electroencephalograms is realized by adopting different colors to represent the change difference of the electroencephalograms of different channels, the electroencephalograms of left and right brain areas can be simultaneously visualized and analyzed, and the change condition of the emotion feature can be more intuitively reflected.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of an emotion feature representation method based on an electroencephalogram signal space-time power spectrogram, provided by the invention;
FIG. 2 is a comparison graph of an electroencephalogram signal before and after filtering provided by the present invention;
FIG. 3 is a diagram of a time-space power spectrogram of an electroencephalogram signal generated without normalization of feature values in a DEAP database according to the present invention;
FIG. 4 is a diagram of a time-space power spectrogram of an electroencephalogram signal generated in a DEAP database under the condition of normalization processing of characteristic values according to the present invention;
FIG. 5 is a time-space power spectrogram of an electroencephalogram signal generated without normalization of feature values in an SEED database according to the present invention;
FIG. 6 is a time-space power spectrogram of an electroencephalogram signal generated in a SEED database under the condition of normalization processing of characteristic values according to the present invention;
FIG. 7 is a time-space power spectrogram of an electroencephalogram signal in a positive emotional state of two channels Fp1 and Fp2 selected from a frontal lobe area on a DEAP database, provided by the invention;
fig. 8 is a time-space power spectrogram of an electroencephalogram signal in a passive emotional state of two channels Fp1 and Fp2 provided by the invention and selecting a frontal lobe area on a DEAP database.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in FIG. 1, the embodiment of the invention discloses an emotion feature representation method based on an electroencephalogram signal space-time power spectrogram, which comprises the following steps:
and S1, obtaining an electrode position image according to the 10-20 system electrode placement method, and performing gray processing on the electrode position image to obtain an electrode position gray image.
And S2, acquiring the electroencephalogram signals collected by the electrodes, and filtering.
The butterworth filter is selected in the embodiment because the frequency response of the butterworth filter is relatively flat in both the pass band and the stop band, wherein the pass band frequency response curve is particularly flat, and for the butterworth filter, the amplitude-frequency characteristic of the butterworth filter is better and better along with the increase of the order. To avoid the distortion problem of the transition band, an 8-order butterworth filter is selected in this embodiment, and the effects before and after filtering are shown in fig. 2.
In other embodiments, if the electrical signal needs to be processed by frequency division, the signal can be filtered to the corresponding frequency band by different filters such as low-pass, band-pass, high-pass, etc.
And S3, dividing the electroencephalogram signal after the filtering processing according to time periods to obtain time domain characteristic data of the electroencephalogram signal.
The time division is carried out on the signals by considering the reusability and the intermediate state of the data, the data are divided by taking 3-12s as the length on the DEAP data set, and the effect obtained by classification in the dimensions of arousal degree and valence is the best. In order to increase the number of samples, the present embodiment divides the electroencephalogram signal data by a length of 3 s. In this embodiment, 3S data is used as a time segment, the electroencephalogram data is divided, and then the power spectral density is calculated for the data in each time segment.
S4, calculating the power spectral density of the corresponding frequency band in the electroencephalogram signal of each time period, extracting the logarithm of the power spectral density as a characteristic value, and normalizing the characteristic value to 0-255 color values.
The method specifically comprises the following steps:
performing Fourier transform on time domain characteristic data of the electroencephalogram signals, transforming the electroencephalogram signals from a time domain to a frequency domain to obtain power spectral density of a frequency band corresponding to each time period, taking logarithm of the power spectral density as a characteristic value, and normalizing the characteristic value to 0-255 to enable the characteristic value to correspond to a pixel value.
Wherein, the power spectral density refers to the distribution of power in unit frequency, and the average power spectral density is one of the most common linear dynamic parameters for visualization. Assuming that x (t) represents an electroencephalogram signal and can be directly subjected to Fourier transform, the following formula can be obtained according to Parseval's theorem:
where X (ω) is the Fourier transform of X (t). Many signals with limited power cannot be directly subjected to Fourier transform, and a common solution is to intercept a part of power signals and perform Fourier transform on the power signals within a limited time. For electroencephalogram signals, the electroencephalogram signals are power signals and are limited in time, so that Fourier transform can be performed. Assuming a power signal x of duration 2TT(t), performing a fourier transform to obtain the following equation:
it also satisfies the Barcelavan theorem:
both ends of the above formula are simultaneously divided by 2T, and when T → ∞ the following formula can be obtained:
the power spectral density is then expressed as:
the power spectral density reflects the variation of the signal power with frequency, and its physical meaning is the energy characteristics contained in the corresponding signal.
Meanwhile, normalization is essentially linear transformation, normalization of power spectral density is an indispensable step, and whether characteristics are normalized or not is also a factor influencing the classification effect when emotion states are identified subsequently.
In the embodiment, the normalization mainly comprises two steps:
1. taking logarithm of power spectral density as a characteristic value; the reason for taking the logarithm is that the power spectral density values of different channels obtained have too large difference and reach the power of 10, so that the power spectral density values need to be logarithmized before the characteristic values are normalized, and the situation that the power spectral density values of different channels have too large difference can be avoided.
2. The extracted eigenvalues of the power spectral density are normalized to 0-255 color values by the following equation.
Wherein X represents the original feature, Y is the normalized feature, XMax、XMinRespectively represent the maximum value and the minimum value of the original characteristic, Ymax、YminRespectively representing the maximum and minimum values of the normalized power spectral density.
And S5, assigning the characteristic values after the normalization processing to the positions of corresponding electrodes in the electrode position gray scale map in a one-to-one correspondence manner. The step ensures the accurate positioning of the electroencephalogram signal data and retains the spatial information of the electroencephalogram signal.
And S6, performing pseudo-color processing on the assigned electrode position gray-scale image to obtain an electroencephalogram signal space-time power spectrogram.
Pseudo-color processing (pseudo-color) refers to the processing of a signal according to some mapping of given gray-values to RGB-values. Color images may highlight certain features compared to grayscale images, resulting in better visualization.
And S7, inputting the electroencephalogram signal space-time power spectrogram into a pre-constructed neural network, and obtaining the emotional characteristic change condition by the neural network according to the color difference change of different electrode positions in the electroencephalogram signal space-time power spectrogram.
In another embodiment, the invention adopts another visualization method to realize quick judgment of the frequency band of the brain wave of each channel in the current time period. The method specifically comprises the following steps:
when the original electroencephalogram signals are filtered, the electroencephalogram signals are divided into five frequency bands of delta rhythm, theta rhythm, alpha rhythm, beta rhythm and gamma rhythm, then the characteristic value corresponding to which frequency of the same channel is the largest at the same moment is compared, the characteristic value of the frequency band is assigned to the corresponding channel, in order to visually display electroencephalograms of different frequency bands appearing in different channels at the moment, the characteristic values of the five frequency bands are corresponding to five different colors, the delta wave corresponds to deep blue, the theta wave corresponds to light blue, the alpha wave corresponds to green, the beta wave corresponds to orange, and the gamma wave corresponds to red, so that electroencephalogram frequency bands appearing in different channels at the moment can be displayed in real time.
Experimental analysis:
1. and (3) analyzing a normalized result:
before assigning the calculated characteristic value of the power spectral density to the corresponding electroencephalogram signal channel, the characteristic value needs to be normalized to 0-255 so as to be displayed by pictures. Because the magnitude order difference of the power spectral density values is large, if normalization is not carried out and the values directly correspond to 0-255, a plurality of 0 values exist, and the formed pictures are not very different. The pair of time-space power spectrograms of the brain electrical signals before and after normalization on the DEAP database is shown in figures 3 and 4. The comparison of the time-space power spectrogram of the brain electrical signals before and after normalization on the SEED database is shown in fig. 5 and fig. 6. The numbers 9, 10, 11, 17, 18 and 19 in fig. 3-6 respectively represent the electroencephalogram signal space-time power spectrograms of the 9 th, 10 th, 11 th, 17 th, 18 th and 19 th time periods.
As can be seen from fig. 3 and 5, the pixel values of most channels before normalization are the same and are all the minimum values, and because the magnitude difference of the power spectral density values is large, fine distinction cannot be made; after normalization to 0-255, the power spectra are shown in fig. 4 and 6, and the difference between the channels is more obvious.
2. Analyzing the effectiveness of a time-space power spectrogram of an electroencephalogram signal:
and (3) carrying out effectiveness analysis on the time-space power spectrogram of the electroencephalogram signal according to the difference of the reactions of the frontal lobe area of the electroencephalogram signal to the negative emotional state and the positive emotional state, namely the asymmetry of the left and right brain areas. Many studies show that the frontal lobe area is more related to emotional states, so that the experiment selects two channels Fp1 and Fp2 of the frontal lobe area on a DEAP database, and the obtained electroencephalogram space-time power spectrogram is shown in fig. 7 and 8.
The time periods 6 and 7 in fig. 7 correspond to the power spectrogram of positive emotion, and the time periods 8 and 9 in fig. 8 correspond to the power spectrogram of negative emotion, so that it can be seen that the activities of the left and right brain regions of the brain have asymmetric characteristics in different emotional states, generally, when a person is in positive emotion, the electroencephalogram signal corresponding to the left brain region is relatively frequent, and when the person is in negative emotion, the electroencephalogram signal corresponding to the right brain region is relatively strong.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. An emotion feature representation method based on an electroencephalogram signal space-time power spectrogram is characterized by comprising the following steps:
obtaining an electrode position image according to a 10-20 system electrode placement method, and carrying out gray processing on the electrode position image to obtain an electrode position gray image;
acquiring electroencephalogram signals collected by each electrode, and filtering;
dividing the electroencephalogram signal after filtering processing according to time periods to obtain time domain characteristic data of the electroencephalogram signal;
calculating the power spectral density of a corresponding frequency band in the electroencephalogram signal of each time period, extracting the logarithm of the power spectral density as a characteristic value, and normalizing the characteristic value to 0-255 color values;
assigning the normalized characteristic values to the positions of corresponding electrodes in the electrode position gray level graph in a one-to-one correspondence manner;
and performing pseudo-color processing on the assigned electrode position gray-scale image to obtain an electroencephalogram signal space-time power spectrogram.
2. The method for representing emotional characteristics based on the electroencephalogram signal space-time power spectrogram as claimed in claim 1, wherein the extraction process of the power spectral density is as follows:
and performing Fourier transform on the time domain characteristic data of the electroencephalogram signal to obtain the power spectral density of the frequency band corresponding to each time period.
3. The method for representing emotional characteristics based on the electroencephalogram signal space-time power spectrogram according to claim 1, wherein the power spectral density is calculated by the following formula:
wherein, XT(ω) represents the Fourier transform of the brain electrical signal, P (ω) represents the power spectral density, and 2T represents a duration of 2T for the brain electrical signal.
4. The method for representing emotional characteristics based on the electroencephalogram signal space-time power spectrogram according to claim 1, wherein the characteristic values are normalized to 0-255 color values by using the following formula:
wherein X represents the original characteristic value, Y represents the characteristic value after normalization, XMax、XMinRespectively representing the maximum and minimum values of the original characteristic values, Ymax、YminRepresenting the maximum and minimum values of the normalized power spectral density, respectively.
5. The method for representing emotional characteristics of the electroencephalogram signal based on the time-space power spectrogram of claim 1, wherein a low-pass filter, a band-pass filter, a high-pass filter or an 8-order Butterworth filter is adopted to filter the electroencephalogram signal acquired by each electrode.
6. The method for representing emotional characteristics of the brain electrical signal based on the time-space power spectrogram of claim 1, wherein the brain electrical signal after the filtering process is divided according to a length of 3s-12 s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518743.8A CN113208594A (en) | 2021-05-12 | 2021-05-12 | Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110518743.8A CN113208594A (en) | 2021-05-12 | 2021-05-12 | Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113208594A true CN113208594A (en) | 2021-08-06 |
Family
ID=77095310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110518743.8A Pending CN113208594A (en) | 2021-05-12 | 2021-05-12 | Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113208594A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114224363A (en) * | 2022-01-25 | 2022-03-25 | 杭州电子科技大学 | Child epilepsy syndrome auxiliary analysis method based on double-flow 3D deep neural network |
| CN116392149A (en) * | 2023-03-03 | 2023-07-07 | 南京左右脑医疗科技集团有限公司 | Brain cognitive state recognition method, device and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5323241A (en) * | 1992-10-30 | 1994-06-21 | Dainippon Screen Mfg. Co., Ltd. | Method of and an apparatus for generating a normalizing curve |
| CN102499677A (en) * | 2011-12-16 | 2012-06-20 | 天津大学 | Emotional state identification method based on electroencephalogram nonlinear features |
| CN103006211A (en) * | 2013-01-17 | 2013-04-03 | 西安电子科技大学 | Map mapping device based on brain electrical activity network analysis |
| CN103394161A (en) * | 2013-07-16 | 2013-11-20 | 山西大学 | Cerebral alpha wave feedback regulation acupoint magnetic stimulation system |
| CN107714035A (en) * | 2017-09-14 | 2018-02-23 | 中国人民解放军第四军医大学 | A kind of wearable digitlization eeg monitoring helmet |
| CN108831485A (en) * | 2018-06-11 | 2018-11-16 | 东北师范大学 | Method for distinguishing speek person based on sound spectrograph statistical nature |
| CN109924990A (en) * | 2019-03-27 | 2019-06-25 | 兰州大学 | A kind of EEG signals depression identifying system based on EMD algorithm |
| CN109984759A (en) * | 2019-03-15 | 2019-07-09 | 北京数字新思科技有限公司 | The acquisition methods and device of individual emotional information |
| CN110169770A (en) * | 2019-05-24 | 2019-08-27 | 西安电子科技大学 | The fine granularity visualization system and method for mood brain electricity |
| CN111134692A (en) * | 2019-11-15 | 2020-05-12 | 北方工业大学 | Method for generating electroencephalogram signal multi-dimensional characteristic picture sequence |
| CN111477299A (en) * | 2020-04-08 | 2020-07-31 | 广州艾博润医疗科技有限公司 | Method and device for regulating and controlling sound-electricity stimulation nerves by combining electroencephalogram detection and analysis control |
| CN112641449A (en) * | 2020-12-18 | 2021-04-13 | 浙江大学 | EEG signal-based rapid evaluation method for cranial nerve functional state detection |
| CN112773378A (en) * | 2021-01-20 | 2021-05-11 | 杭州电子科技大学 | Electroencephalogram emotion recognition method for feature weight adaptive learning |
-
2021
- 2021-05-12 CN CN202110518743.8A patent/CN113208594A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5323241A (en) * | 1992-10-30 | 1994-06-21 | Dainippon Screen Mfg. Co., Ltd. | Method of and an apparatus for generating a normalizing curve |
| CN102499677A (en) * | 2011-12-16 | 2012-06-20 | 天津大学 | Emotional state identification method based on electroencephalogram nonlinear features |
| CN103006211A (en) * | 2013-01-17 | 2013-04-03 | 西安电子科技大学 | Map mapping device based on brain electrical activity network analysis |
| CN103394161A (en) * | 2013-07-16 | 2013-11-20 | 山西大学 | Cerebral alpha wave feedback regulation acupoint magnetic stimulation system |
| CN107714035A (en) * | 2017-09-14 | 2018-02-23 | 中国人民解放军第四军医大学 | A kind of wearable digitlization eeg monitoring helmet |
| CN108831485A (en) * | 2018-06-11 | 2018-11-16 | 东北师范大学 | Method for distinguishing speek person based on sound spectrograph statistical nature |
| CN109984759A (en) * | 2019-03-15 | 2019-07-09 | 北京数字新思科技有限公司 | The acquisition methods and device of individual emotional information |
| CN109924990A (en) * | 2019-03-27 | 2019-06-25 | 兰州大学 | A kind of EEG signals depression identifying system based on EMD algorithm |
| CN110169770A (en) * | 2019-05-24 | 2019-08-27 | 西安电子科技大学 | The fine granularity visualization system and method for mood brain electricity |
| CN111134692A (en) * | 2019-11-15 | 2020-05-12 | 北方工业大学 | Method for generating electroencephalogram signal multi-dimensional characteristic picture sequence |
| CN111477299A (en) * | 2020-04-08 | 2020-07-31 | 广州艾博润医疗科技有限公司 | Method and device for regulating and controlling sound-electricity stimulation nerves by combining electroencephalogram detection and analysis control |
| CN112641449A (en) * | 2020-12-18 | 2021-04-13 | 浙江大学 | EEG signal-based rapid evaluation method for cranial nerve functional state detection |
| CN112773378A (en) * | 2021-01-20 | 2021-05-11 | 杭州电子科技大学 | Electroencephalogram emotion recognition method for feature weight adaptive learning |
Non-Patent Citations (1)
| Title |
|---|
| 王雪娇阳,王连明: "基于脑机接口竞赛脑电数据集的运动想象识别影响因素分析", 《科学技术与工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114224363A (en) * | 2022-01-25 | 2022-03-25 | 杭州电子科技大学 | Child epilepsy syndrome auxiliary analysis method based on double-flow 3D deep neural network |
| CN114224363B (en) * | 2022-01-25 | 2024-04-30 | 杭州电子科技大学 | Child epileptic syndrome auxiliary analysis method based on double-current 3D deep neural network |
| CN116392149A (en) * | 2023-03-03 | 2023-07-07 | 南京左右脑医疗科技集团有限公司 | Brain cognitive state recognition method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Patil et al. | Feature extraction of EEG for emotion recognition using Hjorth features and higher order crossings | |
| CN105496363B (en) | The method classified based on detection sleep cerebral electricity signal to sleep stage | |
| Vrbancic et al. | Automatic classification of motor impairment neural disorders from EEG signals using deep convolutional neural networks | |
| CN109770900B (en) | Method, system and device for issuing brain-computer interface instruction based on convolutional neural network | |
| CN113208594A (en) | Emotional characteristic representation method based on electroencephalogram signal space-time power spectrogram | |
| CN111184509A (en) | Emotion-induced electroencephalogram signal classification method based on transfer entropy | |
| CN112084879B (en) | Block selection common space mode feature extraction method for motor imagery electroencephalogram | |
| Taqi et al. | Classification and discrimination of focal and non-focal EEG signals based on deep neural network | |
| CN107411739A (en) | EEG signals Emotion identification feature extracting method based on dual-tree complex wavelet | |
| Al-Qazzaz et al. | Effective EEG channels for emotion identification over the brain regions using differential evolution algorithm | |
| CN113180659A (en) | Electroencephalogram emotion recognition system based on three-dimensional features and cavity full convolution network | |
| CN113331845A (en) | Electroencephalogram signal feature extraction and accuracy discrimination method based on continuous coherence | |
| Bigirimana et al. | A hybrid ICA-wavelet transform for automated artefact removal in EEG-based emotion recognition | |
| CN107704881A (en) | A kind of data visualization processing method and processing device based on animal electroencephalogramrecognition recognition | |
| Ladekar et al. | EEG based visual cognitive workload analysis using multirate IIR filters | |
| CN114098765A (en) | Method and device for extracting parameters and features of multi-channel high-frequency brain wave coupled brain network | |
| KR102298709B1 (en) | Device and method for learning connectivity | |
| CN110403602B (en) | Improved public spatial mode feature extraction method for electroencephalogram signal emotion analysis | |
| CN115192040B (en) | Electroencephalogram emotion recognition method and device based on poincare graph and second-order difference graph | |
| WO2021143538A1 (en) | Wearable workload measurement method, system and apparatus, and storage medium | |
| CN114218986A (en) | State classification method based on EEG electroencephalogram data | |
| CN113208633A (en) | Emotion recognition method and system based on EEG brain waves | |
| CN115886841A (en) | Steady-state vision-evoked electroencephalogram dynamic initial classification method based on brain region linkage | |
| CN113017648A (en) | Electroencephalogram signal identification method and system | |
| CN114580464A (en) | Human heart rate variability and respiratory rate measurement method based on variational modal decomposition and constraint independent component analysis |
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 |