CN114343635A - Variable phase-splitting amplitude coupling-based emotion recognition method and device - Google Patents
Variable phase-splitting amplitude coupling-based emotion recognition method and device Download PDFInfo
- Publication number
- CN114343635A CN114343635A CN202111475417.XA CN202111475417A CN114343635A CN 114343635 A CN114343635 A CN 114343635A CN 202111475417 A CN202111475417 A CN 202111475417A CN 114343635 A CN114343635 A CN 114343635A
- Authority
- CN
- China
- Prior art keywords
- phase
- amplitude
- amplitude coupling
- coupling
- signals
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention belongs to the cross field of cognitive neuroscience and information technology, and particularly relates to a variable phase amplitude coupling-based emotion recognition method, device, platform and computer-readable storage medium. The emotion recognition method based on variable phase-splitting amplitude coupling comprises a data acquisition step, a preprocessing step, a variable phase mode decomposition step, a phase-amplitude coupling analysis step, a significance checking step and a recognition step. The emotion recognition device based on variable phase-splitting amplitude coupling comprises a data acquisition module, a preprocessing module, a variable phase mode decomposition module, a phase-amplitude coupling analysis module, a significance inspection module and a recognition module. The invention distributes the phase amplitude coupling value which is obviously detected to the double-frequency coupling map averagely, thereby identifying the emotion of the testee. The invention can effectively extract the electroencephalogram signal characteristics under different emotion states, and improves the accuracy and reliability of emotion recognition.
Description
Technical Field
The invention belongs to the cross field of cognitive neuroscience and information technology, and particularly relates to a variable phase amplitude coupling-based emotion recognition method, device, platform and computer-readable storage medium.
Background
The emotion is attitude experience of objective objects and corresponding behavioral response, the emotion is distinguished efficiently and accurately, and the actual production and life are greatly influenced. For example, emotion recognition is performed on a patient with a psychological disease or an expression disorder, which is helpful for diagnosing the condition of a disease and guiding emotion, and helps the patient relieve pain; when teaching in class, the student can timely feed back according to the emotion of the student at that time, and different teaching means are adopted, so that the interaction in class can be increased, and the teaching efficiency is improved.
At present, there are many emotion recognition methods for recognizing and classifying emotions, and the commonly used methods include recognizing facial expressions and voice tones, and recognizing corresponding emotional states by measuring physiological signals such as electrocardio, myoelectricity, and electroencephalogram. Although facial expressions and speech signals are easily found and commonly used, they are unreliable for those who are good at masking real emotions. In contrast, electroencephalography (EEG) is a physiological signal from the central and autonomic nervous systems that is a true reflection of emotions by the nervous system. Therefore, in recent years, studies on emotion recognition based on electroencephalogram have been receiving much attention. Some studies investigated the dynamically changing factors of mood, including brain regions and/or frequency bands. However, because the electroencephalogram signals have the characteristics of non-stability, non-linearity, time variation and the like, quantification is difficult. Typically, electroencephalograms include Delta waves (0.5-4Hz), Theta waves (4-8Hz), Alpha waves (8-13Hz), Beta waves (13-30Hz), and Gamma waves (>30 Hz). At present, most emotion recognition researches based on electroencephalogram signals pay attention to frequency signals of a single wave band, and interaction among frequencies is ignored. In addition, many electroencephalogram emotion recognition studies focus on the classification accuracy based on machine learning algorithms. However, the interaction mechanism between the brain electrical rhythms under different emotional expressions has not been sufficiently explored.
Disclosure of Invention
The invention aims to provide a variable phase amplitude coupling-based emotion recognition method, device, platform and computer readable storage medium, which are used for solving the problems in the background technology and accurately and reliably recognizing emotion.
In order to achieve the above object, a first aspect of the present invention provides a method for emotion recognition based on phase-variant phase-amplitude coupling, comprising the following steps:
a data acquisition step, which is to acquire an electroencephalogram signal of a testee generating emotional stimulation;
a preprocessing step, preprocessing the electroencephalogram signals, and removing noise and interference;
a variation modal decomposition step, namely performing variation modal decomposition on the preprocessed multidimensional electroencephalogram signals one by one to obtain a plurality of intrinsic modal signals;
analyzing phase-amplitude coupling between the relatively high-frequency modal signals and the relatively low-frequency modal signals under each channel, and calculating to obtain phase-amplitude coupling values;
a significance test step, which is to test the significance of the phase amplitude coupling value;
and an identification step, namely averagely distributing the phase amplitude coupling values which are obviously detected to the dual-frequency coupling spectrum, and identifying the emotion of the tested person.
Further, in the phase-amplitude coupling analysis step, hilbert transform is performed on the modal signal to obtain a corresponding phase signal and an amplitude signal.
Further, in the phase-amplitude coupling analysis step, a phase-amplitude coupling value is calculated through a modulation index algorithm, a transfer entropy algorithm or a phase-lock value algorithm.
Further, in the identification step, positive, neutral and negative emotions are identified according to the magnitude of the phase-amplitude coupling value.
The invention provides a emotion recognition device based on phase-variable phase-amplitude coupling, which comprises:
the data acquisition module is used for acquiring electroencephalogram signals of emotional stimulation generated by the testee;
the preprocessing module is used for preprocessing the electroencephalogram signals and removing noise and interference;
the variational modal decomposition module is used for carrying out variational modal decomposition on the preprocessed multi-dimensional electroencephalogram signals one by one to obtain a plurality of intrinsic modal signals;
the phase-amplitude coupling analysis module is used for analyzing phase-amplitude coupling between the relatively high-frequency modal signals and the relatively low-frequency modal signals under each channel and calculating to obtain phase-amplitude coupling values;
the significance testing module is used for testing the significance of the phase-amplitude coupling value;
and the identification module is used for averagely distributing the phase amplitude coupling values which are obviously detected to the dual-frequency coupling spectrum and identifying the emotion of the testee.
Furthermore, the phase-amplitude coupling analysis module further performs hilbert transform on the modal signal to obtain a corresponding phase signal and an amplitude signal.
Further, in the phase-amplitude coupling analysis module, a phase-amplitude coupling value is calculated through a modulation index algorithm, a transfer entropy algorithm or a phase-lock value algorithm.
Further, in the identification module, positive, neutral and negative emotions are identified according to the magnitude of the phase-amplitude coupling value.
A third aspect of the present invention provides an emotion recognition platform, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the emotion recognition method described above.
A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the emotion recognition method described above.
Advantageous effects
The invention applies a variational modal decomposition method (VMD) to the calculation of phase-amplitude coupling (PAC), and provides a novel variational phase-amplitude coupling (VPAC) method for extracting electroencephalogram signal characteristics under different emotional states. The invention can effectively extract the electroencephalogram signal characteristics under different emotion states, and improves the accuracy and reliability of emotion recognition.
Drawings
Fig. 1 is a flow chart of a method of emotion recognition according to the present invention.
Fig. 2 is an amplitude spectrum of each mode signal according to an embodiment of the present invention.
Fig. 3 is a dual-frequency coupling diagram according to an embodiment of the present invention.
Fig. 4 is a block diagram of the emotion recognition apparatus of the present invention.
Fig. 5 is a block diagram of the emotion recognition platform of the present invention.
Detailed Description
The following describes in detail embodiments of the present invention with reference to the drawings.
Cross-frequency coupling (CFC) is widely used to characterize the oscillatory coupling between different frequency bands, with multiple modes, such As Amplitude Coupling (AAC), phase coupling (PPC), phase-frequency coupling (PFC) and phase-amplitude coupling (PAC), etc., being closely related to the cognitive and behavioral states of humans. Where Phase Amplitude Coupling (PAC) is defined as the ability of a low frequency phase to modulate its high frequency amplitude. The low frequency phase reflects the activity of local neurons, and the high frequency amplitude reflects the general state of synaptic activity in the population or the selective excitability of connected neural networks. Since the past, PAC has become a popular method of research, and has been closely related to states such as memory consolidation, attention control, and spasticity, playing an important role in neural activity.
The first step in quantifying the PAC is also the most important step in accurately extracting the phase and amplitude components of the brain electrical signal. Conventional sinusoidal models may result in loss of sensitivity and interpretability. Compared with Fourier transform, wavelet analysis has superiority in non-stationary decomposition and has good time-frequency resolution; however, the broadband nature of wavelet transforms may spread energy to a larger frequency range and therefore may not provide reliable instantaneous frequencies due to the presence of riding waves. The Empirical Mode Decomposition (EMD) algorithm has the advantages of strong adaptability and high efficiency, but lacks a theoretical basis and has the problems of end point effect and modal aliasing. Driven by the narrow-band characteristic of the intrinsic mode function, dragomirtski et al propose a variational mode decomposition method (VMD) in 2014, and obtain a plurality of mode functions with certain bandwidth by iteratively searching for the optimal solution of the variational mode and continuously updating each mode function and the central frequency. Compared with the EMD method, the signal is decomposed into non-recursive and variational modes through the VMD, and the endpoint effect and the modal aliasing phenomenon in the EMD process are effectively suppressed. VMD is essentially a generalization of Wiener filters, similar to applying a set of Wiener filters to multiple adaptive frequency bands, and thus it is more robust to noise.
As shown in fig. 1, a first embodiment of the present invention relates to a emotion recognition method based on phase-change phase amplitude coupling, including the following steps:
a data acquisition step, which is to acquire an electroencephalogram signal of a testee generating emotional stimulation;
a preprocessing step, preprocessing the electroencephalogram signals, and removing noise and interference;
a variation modal decomposition step, namely performing variation modal decomposition on the preprocessed multidimensional electroencephalogram signals one by one to obtain a plurality of intrinsic modal signals;
analyzing phase-amplitude coupling between the relatively high-frequency modal signals and the relatively low-frequency modal signals under each channel, and calculating to obtain phase-amplitude coupling values;
a significance test step, which is to test the significance of the phase amplitude coupling value;
and an identification step, namely averagely distributing the phase amplitude coupling values which are obviously detected to the dual-frequency coupling spectrum, and identifying the emotion of the tested person.
In the phase-amplitude coupling analysis step, hilbert transformation is performed on the modal signal to obtain a corresponding phase signal and an amplitude signal. And calculating the phase-amplitude coupling value through a modulation index algorithm, a transfer entropy algorithm or a phase-lock value algorithm.
In the identifying step, positive, neutral and negative emotions are identified according to the magnitude of the phase amplitude coupling value.
The following is a detailed description of a specific embodiment.
Step 1, firstly, a testee completes experiment operation according to experiment requirements, and then electroencephalogram signals of emotional stimulation generated by the testee are collected. The sampling frequency is set to fs and stored in the computer.
And 2, preprocessing the electroencephalogram signals. The method comprises the step of removing artifacts in the original electroencephalogram signals by using a notch filter with the frequency of 50Hz and a high-pass filter with the cut-off frequency of 0.5 Hz. The independent components of the electroencephalogram signals are estimated by adopting a principal component analysis method and a rapid independent component analysis method, and electroencephalogram pollution caused by eye movement, blinking, heart rhythm and power line noise is eliminated.
And 3, performing variation modal decomposition on the preprocessed multi-dimensional electroencephalogram signals one by one. The method comprises the following specific steps:
for the electroencephalogram signal f (t), the optimal solution of the constraint variation problem is searched through iteration, and the optimal solution is decomposed into K modal signals u with frequencies ranging from high to lowk(t) (K ═ 1,2, …, K), each mode signal and its center frequency are continuously updated to have a certain sparse bandwidth in the frequency domain, and the amplitude spectrum of each mode signal is calculated, the result is shown in fig. 2.
The constraint variation problem in the process of the variation modal decomposition processing is
Wherein u isk＝{u1,…,ukAnd (5) representing the decomposed K bandwidth-limited eigenmode components. In order to solve the optimal solution of the constraint variation problem, a secondary penalty parameter alpha and a Lagrangian multiplier lambda (t) are introduced, and the constraint variation problem of the formula (1) is solved. Thereby obtaining an augmented Lagrangian function of
Adopting an Alternating Direction Multiplier Method (ADMM) to obtain a saddle point of the formula (2), and iteratively updating u in a frequency domaink，ωkAnd lambda. Namely, it is
The stop conditions are as follows:
wherein F in the formula (5) is Fourier transform of the signal F (t), and n is greater than or equal to 1.
Step 4, obtaining K intrinsic mode signals u for specific electroencephalogram signals f (t) through the operation of the previous stepk(t) u ofk(t) is quasi-orthogonal and is arranged in descending frequency order. To quantify the phase-amplitude coupling of the signal, each u is further extractedk(t) the corresponding phase signal and amplitude signal. For the decomposed modal signal uk(t) Hilbert transform to obtain K phase time sequences
And K amplitude time series
And 5, quantizing the degree of phase-amplitude coupling through three algorithms of a Modulation Index (MI), a Transfer Entropy (TE) and a Phase Lock Value (PLV), wherein the three algorithms have different emphasis points and can be selected to calculate according to needs.
(1) MI aims to quantify the coupling strength between low frequency phase and high frequency amplitude, and is widely used for quantification of amplitude coupling strength, which is mainly quantified by measuring the degree to which the distribution of high frequency amplitude locked on low frequency phase deviates from a uniform distribution.
Calculated from the previous stepTo the phase component
And an amplitude component Ak(t) dividing the phase domain (0,2 pi) of the phase component into N intervals (e.g., N =20), calculating an average high frequency amplitude over each low frequency phase cell of each sample, and normalizing the average amplitude to generate a distribution P representing the proportion of high frequency amplitude over each phase cell. Calculating the distance D between the phase amplitude distribution P and the Kullback-Leibler (KL) of the uniform distribution UKL(P, U) = logN-H (P), wherein logN is uniformly distributed Shannon entropy, and H (P) is distributed P Shannon entropy defined as
Finally, MI is defined as the ratio of KL distance to logN, i.e.
The MI value is close to zero when the amplitude values on all possible phase units are very similar, approximately uniformly distributed, and is 1 only when the data obeys a bernoulli distribution.
(2) TE belongs to a time series analysis algorithm, and focuses more on quantifying causal transfer relationships between phase and amplitude in addition to obtaining the strength of phase-amplitude coupling. The phase component is obtained by the previous calculation
And an amplitude component Ak(t), defining phase-amplitude transfer entropy:
wherein { Ai(t), i is 1, …, K-1, and represents a time series of amplitude values obtained by decomposition,
representing the phase time series obtained by decomposition, since the variation modal decomposition algorithm is equivalent to a filter bank, the method has the advantages of simple structure, low cost and high efficiency
The corresponding frequency is always lower than Ai(t) the corresponding frequency;
comparison
And
the magnitude of (d) is determined by the larger of the values of the drive component and the response component of the signal. For example, if
It means that the low frequency phase has a modulating effect on the high frequency amplitude. The phase-amplitude transfer entropy defined in this way can be used for acquiring electroencephalogramThe strength and direction of the signal phase-amplitude coupling.
(3) PLV is a phase-based functional connection method, and the actual measurement is the phase difference of two signals. Is defined as
Where N is the number of time series points,
is a time-series of phases that are,
is a phase time sequence of the amplitude envelope. By definition, a value of 1 for PLV indicates that the phase sequence is locked, and a value of 0 for PLV indicates that the phase sequence is completely out of synchronization.
To test whether the MI (or TE or PLV) calculated above has a unique temporal modulation, a "block-mix" of both phase and amplitude time series at the periodic frequency is performed, generating a random arrangement of these modal signal blocks, step 6. This process is repeated 100 times for each pair of modal signals, setting the z-score (z-score) of MI (or TE or PLV) as the threshold, and values above a 0.05 level of significance will be eliminated.
And 7, obtaining a dual-frequency coupling map as shown in fig. 3, and observing MI (or TE or PLV) values of the phase frequency-amplitude frequency pairs. And repeating the steps on the multi-dimensional electroencephalogram channel signals to obtain the phase-amplitude coupling degree among the frequencies of different brain areas. And performing statistical distribution analysis on the phase amplitude coupling values obtained by multiple experiments, and identifying positive, neutral and negative emotions according to the magnitude of the phase amplitude coupling values.
As shown in fig. 4, a second embodiment of the present invention relates to an emotion recognition apparatus based on phase-change phase amplitude coupling, including:
the data acquisition module is used for acquiring electroencephalogram signals of emotional stimulation generated by the testee;
the preprocessing module is used for preprocessing the electroencephalogram signals and removing noise and interference;
the variational modal decomposition module is used for carrying out variational modal decomposition on the preprocessed multi-dimensional electroencephalogram signals one by one to obtain a plurality of intrinsic modal signals;
the phase-amplitude coupling analysis module is used for analyzing phase-amplitude coupling between the relatively high-frequency modal signals and the relatively low-frequency modal signals under each channel and calculating to obtain phase-amplitude coupling values;
the significance testing module is used for testing the significance of the phase-amplitude coupling value;
and the identification module is used for averagely distributing the phase amplitude coupling values which are obviously detected to the dual-frequency coupling spectrum and identifying the emotion of the testee.
The phase-amplitude coupling analysis module also comprises a Hilbert transform module for performing Hilbert transform on the modal signal to obtain a corresponding phase signal and an amplitude signal. And calculating the phase-amplitude coupling value through a modulation index algorithm, a transfer entropy algorithm or a phase-lock value algorithm.
In the identification module, positive, neutral and negative emotions are identified according to the magnitude of the phase amplitude coupling value.
As will be appreciated by one skilled in the art in light of the foregoing description, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
A third embodiment of the present invention relates to an emotion recognition platform, as shown in fig. 5, including:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the emotion recognition method described above.
Where the memory and processor are connected by a bus, the bus may comprise any number of interconnected buses and bridges, the buses connecting together one or more of the various circuits of the processor and the memory. The bus may also interface various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art. The interface provides an interface, e.g., a communication interface, a user interface, between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor is transmitted over a wireless medium via an antenna, which further receives the data and transmits the data to the processor.
The processor is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And the memory may be used to store data used by the processor in performing operations.
A fourth embodiment of the invention relates to a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method embodiments.
As will be understood by those skilled in the art from the foregoing description, all or part of the steps in the method according to the above embodiments may be implemented by a program, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present application. The storage medium includes, but is not limited to, various media that can store program codes, such as a usb disk, a removable hard disk, a magnetic storage, an optical storage, and the like.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalents, improvements, etc. made within the principle of the present invention are included in the scope of the present invention.
Claims (10)
1. A sentiment recognition method based on variable phase amplitude coupling is characterized by comprising the following steps:
a data acquisition step, which is to acquire an electroencephalogram signal of a testee generating emotional stimulation;
a preprocessing step, preprocessing the electroencephalogram signals, and removing noise and interference;
a variation modal decomposition step, namely performing variation modal decomposition on the preprocessed multidimensional electroencephalogram signals one by one to obtain a plurality of intrinsic modal signals;
analyzing phase-amplitude coupling between the relatively high-frequency modal signals and the relatively low-frequency modal signals under each channel, and calculating to obtain phase-amplitude coupling values;
a significance test step, which is to test the significance of the phase amplitude coupling value;
and an identification step, namely averagely distributing the phase amplitude coupling values which are obviously detected to the dual-frequency coupling spectrum, and identifying the emotion of the tested person.
2. The emotion recognition method based on phase-amplitude coupling of the variable phases, as recited in claim 1, wherein the phase-amplitude coupling analysis step further comprises hilbert transforming the modal signals to obtain corresponding phase signals and amplitude signals.
3. The emotion recognition method based on phase-amplitude-variation coupling of claim 1, wherein in the phase-amplitude coupling analysis step, the phase-amplitude coupling value is calculated by a modulation index algorithm, a transfer entropy algorithm or a phase-lock value algorithm.
4. The emotion recognition method based on phase-amplitude-variation coupling as claimed in claim 1, wherein in the recognition step, positive, neutral and negative emotions are recognized according to the magnitude of the phase-amplitude coupling value.
5. An emotion recognition device based on phase-varying phase-amplitude coupling, comprising:
the data acquisition module is used for acquiring electroencephalogram signals of emotional stimulation generated by the testee;
the preprocessing module is used for preprocessing the electroencephalogram signals and removing noise and interference;
the variational modal decomposition module is used for carrying out variational modal decomposition on the preprocessed multi-dimensional electroencephalogram signals one by one to obtain a plurality of intrinsic modal signals;
the phase-amplitude coupling analysis module is used for analyzing phase-amplitude coupling between the relatively high-frequency modal signals and the relatively low-frequency modal signals under each channel and calculating to obtain phase-amplitude coupling values;
the significance testing module is used for testing the significance of the phase-amplitude coupling value;
and the identification module is used for averagely distributing the phase amplitude coupling values which are obviously detected to the dual-frequency coupling spectrum and identifying the emotion of the testee.
6. The emotion recognition device based on phase-amplitude coupling of the variable phases, as recited in claim 5, wherein the phase-amplitude coupling analysis module further comprises a Hilbert transform for the modal signals to obtain the corresponding phase signals and amplitude signals.
7. The emotion recognition apparatus based on phase-amplitude-variation coupling, as claimed in claim 5, wherein in the phase-amplitude coupling analysis module, the phase-amplitude coupling value is calculated by a modulation index algorithm, a transmission entropy algorithm or a phase-lock value algorithm.
8. The emotion recognition apparatus based on variable phase-amplitude coupling as claimed in claim 5, wherein the recognition module recognizes the positive, neutral and negative emotions according to the magnitude of the phase-amplitude coupling value.
9. An emotion recognition platform, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the emotion recognition method as claimed in any of claims 1 to 4.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the emotion recognition method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111475417.XA CN114343635A (en) | 2021-12-06 | 2021-12-06 | Variable phase-splitting amplitude coupling-based emotion recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111475417.XA CN114343635A (en) | 2021-12-06 | 2021-12-06 | Variable phase-splitting amplitude coupling-based emotion recognition method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114343635A true CN114343635A (en) | 2022-04-15 |
Family
ID=81098142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111475417.XA Pending CN114343635A (en) | 2021-12-06 | 2021-12-06 | Variable phase-splitting amplitude coupling-based emotion recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114343635A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115500829A (en) * | 2022-11-24 | 2022-12-23 | 广东美赛尔细胞生物科技有限公司 | Depression detection and analysis system applied to neurology |
| CN115736950A (en) * | 2022-11-07 | 2023-03-07 | 北京理工大学 | Sleep dynamics analysis method based on multi-brain-area cooperative amplitude transfer |
| CN115982574A (en) * | 2023-03-20 | 2023-04-18 | 北京理工大学 | Electroencephalogram information flow direction feature extraction method based on frequency-limited mask causal decomposition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310570A (en) * | 2020-01-16 | 2020-06-19 | 山东师范大学 | Electroencephalogram signal emotion recognition method and system based on VMD and WPD |
| CN112568912A (en) * | 2019-09-12 | 2021-03-30 | 陈盛博 | Depression biomarker identification method based on non-invasive electroencephalogram signals |
| KR20210045703A (en) * | 2019-10-17 | 2021-04-27 | 광운대학교 산학협력단 | Emotion Recognition Method based on Multivariate Multiscale Fuzzy Entropy Analysis of EEG recordings |
| CN113100781A (en) * | 2021-04-09 | 2021-07-13 | 浙江象立医疗科技有限公司 | System and method for monitoring injury stimulus responsiveness in operation based on electroencephalogram coupling relation |
| CN113274033A (en) * | 2021-05-10 | 2021-08-20 | 燕山大学 | Movement function monitoring and management method based on cross frequency coupling of brain and muscle electricity |
-
2021
- 2021-12-06 CN CN202111475417.XA patent/CN114343635A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112568912A (en) * | 2019-09-12 | 2021-03-30 | 陈盛博 | Depression biomarker identification method based on non-invasive electroencephalogram signals |
| KR20210045703A (en) * | 2019-10-17 | 2021-04-27 | 광운대학교 산학협력단 | Emotion Recognition Method based on Multivariate Multiscale Fuzzy Entropy Analysis of EEG recordings |
| CN111310570A (en) * | 2020-01-16 | 2020-06-19 | 山东师范大学 | Electroencephalogram signal emotion recognition method and system based on VMD and WPD |
| CN113100781A (en) * | 2021-04-09 | 2021-07-13 | 浙江象立医疗科技有限公司 | System and method for monitoring injury stimulus responsiveness in operation based on electroencephalogram coupling relation |
| CN113274033A (en) * | 2021-05-10 | 2021-08-20 | 燕山大学 | Movement function monitoring and management method based on cross frequency coupling of brain and muscle electricity |
Non-Patent Citations (1)
| Title |
|---|
| CHUTING ZHANG 等: ""Investigating Variational Phase-Amplitude Coupling in EEG-based Emotion Recognition"", 《2021 10TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING (NER) VIRTUAL CONFERENCE》, pages 150 - 153 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115736950A (en) * | 2022-11-07 | 2023-03-07 | 北京理工大学 | Sleep dynamics analysis method based on multi-brain-area cooperative amplitude transfer |
| CN115736950B (en) * | 2022-11-07 | 2024-02-09 | 北京理工大学 | Sleep dynamics analysis method based on multi-brain-region collaborative amplitude transfer |
| CN115500829A (en) * | 2022-11-24 | 2022-12-23 | 广东美赛尔细胞生物科技有限公司 | Depression detection and analysis system applied to neurology |
| CN115982574A (en) * | 2023-03-20 | 2023-04-18 | 北京理工大学 | Electroencephalogram information flow direction feature extraction method based on frequency-limited mask causal decomposition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Detection analysis of epileptic EEG using a novel random forest model combined with grid search optimization | |
| Hussein et al. | Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals | |
| Boonyakitanont et al. | A review of feature extraction and performance evaluation in epileptic seizure detection using EEG | |
| Sharanreddy et al. | EEG signal classification for epilepsy seizure detection using improved approximate entropy | |
| Song et al. | Automatic recognition of epileptic EEG patterns via extreme learning machine and multiresolution feature extraction | |
| Guo et al. | Classification of EEG signals using relative wavelet energy and artificial neural networks | |
| Panda et al. | Classification of EEG signal using wavelet transform and support vector machine for epileptic seizure diction | |
| CN114343635A (en) | Variable phase-splitting amplitude coupling-based emotion recognition method and device | |
| Jahankhani et al. | EEG signal classification using wavelet feature extraction and neural networks | |
| Gupta et al. | FBDM based time-frequency representation for sleep stages classification using EEG signals | |
| CN111310570B (en) | Electroencephalogram signal emotion recognition method and system based on VMD and WPD | |
| Lu et al. | Classification of single-channel EEG signals for epileptic seizures detection based on hybrid features | |
| Li et al. | Multi-feature fusion method based on EEG signal and its application in stroke classification | |
| Jadhav et al. | Automated sleep stage scoring using time-frequency spectra convolution neural network | |
| Lee et al. | Automated epileptic seizure waveform detection method based on the feature of the mean slope of wavelet coefficient counts using a hidden Markov model and EEG signals | |
| Chen et al. | An automated detection of epileptic seizures EEG using CNN classifier based on feature fusion with high accuracy | |
| CN115211858A (en) | Emotion recognition method and system based on deep learning and storable medium | |
| Uyulan et al. | Entropy-based feature extraction technique in conjunction with wavelet packet transform for multi-mental task classification | |
| Cleatus et al. | Epileptic seizure detection using spectral transformation and convolutional neural networks | |
| Zhou et al. | Epileptic seizure detection via logarithmic normalized functional values of singular values | |
| Saini et al. | Discriminatory features based on wavelet energy for effective analysis of electroencephalogram during mental tasks | |
| Mehla et al. | An Efficient Classification of Focal and Non-Focal EEG Signals Using Adaptive DCT Filter Bank | |
| Mihandoost et al. | EEG signal analysis using spectral correlation function & GARCH model | |
| Wang et al. | Combining STFT and random forest algorithm for epileptic detection | |
| Fraiwan et al. | Multiclass Epilepsy Classification Using Wavelet Decomposition, Direct Quadrature, and Shannon Entropy |
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 |