REAL-TIME EVALUATION METHOD AND EVALUATION SYSTEM FOR GROUP EMOTION HOMOGENEITY

Abstract

The present invention discloses a real-time evaluation method and evaluation system for group emotion homogeneity. The method comprises the steps as follows: enabling testees to be in the same emotion induction environment, and collecting the original electroencephalograph (EEG) signals of multiple persons at the same time through online multichannel EEG equipment; and based on the average instantaneous phase per second of the beta frequency band and the energy value per second of the alpha frequency band obtained after wavelet transformation, calculating the time synchronization degree and the valence consistency degree in real time, and finally obtaining a group emotion homogeneity index for the objective evaluation of group emotion homogeneity.

Claims

1. A real-time evaluation method for group emotion homogeneity, wherein the method comprises steps as follows: S1: Wearing multichannel electroencephalograph (EEG) measurement equipment for multiple testees at the same time; S2: Enabling the testees to be in a same emotion induction environment, and synchronously collecting original EEG signals of the multiple testees; S3: Performing real-time preprocessing and wavelet transformation for the original EEG signals from forehead and anterior temporal channels to obtain an average instantaneous phase per second of a beta frequency band, and calculating an energy value per second of an alpha frequency band in real time; S4: Calculating a time synchronization degree in real time based on the average instantaneous phase, and calculating a valence consistency degree in real time based on the energy value; S5: Calculating a group emotion homogeneity index in real time based on the time synchronization degree and the valence consistency degree; S6: Conducting evaluation and grading for the group emotion homogeneity based on a curve of the group emotion homogeneity index changing along with time; the valence consistency degree in S4 is calculated by formulae as follows: $$\begin{gathered} V=\frac{1}{k}\max \left\{{.Math.Y_{M_{+}}.Math.}_1,{.Math.Y_{M_{-}}.Math.}_1\right\}{Y}_{M_{+}}=\max \left\{Y_M,0\right\}{Y}_{M-}=\min \left\{Y_M,0\right\}{Y}_M\left(i\right)=\{\begin{array}{cc}1& M_i>0\\ 0& M_i=0\\ -1& M_i<0\end{array} \\ M=\left(M_1,M_2,M_3,.Math.M_k\right) \\ M\in R^k \\ {M}_i=\log \left(P{L}_i\right)-\log \left(P{R}_i\right) \end{gathered}$$ where, V is the valence consistency degree, Y.sub.M is a sign function, M is a k-dimensional vector, PL is an average value of energy of the alpha frequency band collected from a left forehead channel and a left anterior temporal channel of the testee, PR is an average value of energy of the alpha frequency band collected from a right forehead channel and a right anterior temporal channel of the testee, i represents the i.sup.th testee in sequence, and k is a total number of the testees.

2. The real-time evaluation method for group emotion homogeneity according to claim 1, wherein the time synchronization degree in S4 is calculated by formulae as follows: $$\begin{gathered} T=\frac{2}{k\left(k-1\right)}\underset{i=1}{\overset{k}{.Math.}}\underset{j=1}{\overset{k}{.Math.}}\exp \left(S_{ij}\right)S_{ij}=\{\begin{array}{cc}.Math.x_i-x_j.Math.& i<j\\ 0& i\ge j\end{array} \\ S=\left[\begin{array}{ccc}{S}_{11}& .Math.& S_{k1}\\ .Math.& \ddots & .Math.\\ S_{1k}& .Math.& S_{\mathrm{kk}}\end{array}\right] \\ S\in R^{k\times k} \end{gathered}$$ where, T is the time synchronization degree, S is a real matrix for Row k and Line k, S.sub.ij is a value of phase difference, x represents an average instantaneous phase of the beta frequency band of the testee, i represents i.sup.th testee in sequence, j represents j.sup.th testee in sequence, and k is the total number of the testees.

3. The real-time evaluation method for group emotion homogeneity according to claim 1, wherein the group emotion homogeneity index per second in S4 is calculated by a formula as follows:
E=V*T where, E is the group emotion homogeneity index per second.

4. The real-time evaluation method for group emotion homogeneity according to claim 1, wherein the forehead and anterior temporal channels in S3 are selected by a method that: electrode points are configured according to an international 10-20 system and a distribution of related brain areas, and the electrode points of FP1, FPz, FP2, F7 and F8 are selected for calculating an emotion time synchronization degree, whereas the electrode points of FP1, FPz, FP2, Fz, F3, F4, F7 and F8 are selected for calculating the valence consistency degree.

5. The real-time evaluation method for group emotion homogeneity according to claim 1, wherein standards for the evaluation and grading for homogeneity are as follows: the group emotion homogeneity index E≥0.6 is deemed as strong group emotion homogeneity, 0.4≤E<0.6 is deemed as convergent group emotion homogeneity, and E<0.4 is deemed as insufficient group emotion homogeneity.

6. The real-time evaluation method for group emotion homogeneity according to claim 1, wherein the multichannel EEG measurement equipment in S1 adopts 32-channel electrode caps and uses saline or gel electrodes, and an impedance of each electrode point is less than 5 kΩ.

7. A real-time evaluation system for group emotion homogeneity, comprising an emotion induction device, an EEG measurement equipment group and a group emotion homogeneity calculation unit connected in order; wherein the group emotion homogeneity calculation unit comprises a group EEG signal preprocessing module, a group emotion homogeneity calculation module and a data visualization module connected in order; the emotion induction device is used as a stimulus to induce emotion of testees; the EEG measurement equipment group is used for synchronously collecting an EEG signals of the multiple testees and transmitting the EEG signals to the group EEG signal preprocessing module; the group EEG signal preprocessing module is used for preprocessing the collected EEG signals by amplification, noise reduction and filtering; the group emotion homogeneity calculation module is used for performing wavelet transformation for the EEG signals after preprocessing to obtain an average instantaneous phase per second of a beta frequency band, calculating an energy value per second of an alpha frequency band in real time, then calculating a time synchronization degree and a valence consistency degree in real time, and generating a group emotion homogeneity index; the data visualization module is used for displaying a curve of the group emotion homogeneity index changing along with time.

8. The real-time evaluation system for group emotion homogeneity according to claim 7, wherein the preprocessing refers to the amplification, capturing analysis segments, noise reduction, artifacts removal and band-pass filtering for the collected EEG signals; the artifacts removal comprises removing an interference from electrooculogram, electromyogram, electrocardiogram and power frequency.

9. The real-time evaluation system for group emotion homogeneity according to claim 7, wherein the emotion induction device comprises an image displaying device and an image processing and storage device, and the emotion induction device is used for displaying emotion stimulating materials as a visual stimulus, as well as used for processing and storing the emotion stimulating materials.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0035] FIG. 1 is the structural chart of the system of the present invention.

[0036] FIG. 2 is the flow chart of the system of the present invention.

DESCRIPTION OF THE EMBODIMENTS

[0037] The embodiment of the present invention will be described in detail below in combination with the drawings. It shall be understood that the embodiment described is used only for stating and explaining the present invention, rather than limiting the present invention.

[0038] Emotional experience is mainly triggered by environmental stimuli to cause the changes in brain functional activities, the response of the peripheral autonomic nervous system, and the changes in neurochemical substances in the body. An electroencephalograph (EEG) signal, as the overall reflection of the electrophysiological activities of brain nerve cells on the cerebral cortex or scalp surface, contains a large amount of physiological and psychological information related to emotions, and has the features of being direct and objective, difficult to disguise, easy to quantify, diversified characteristics, and it is the cognitive physiological index with the most significant effect in the field of emotion recognition. Through monitoring multi-person EEG signals at the same time, based on the correlation of intercerebral emotion related nervous activities, the group emotion homogeneity can be effectively monitored. A real-time evaluation method and evaluation system for group emotion homogeneity collect the EEG signal data of multiple persons using an online multichannel EEG equipment to perform the real-time dynamic analysis of group emotion, realizing the processing and displaying of agile data.

[0039] As shown in FIG. 1, the real-time evaluation system for group emotion homogeneity comprises:

[0040] An emotion induction device comprising an image displaying device and an image processing and storage device, used for displaying emotion stimulating materials, and employing a screen as a visual stimulus according to the usual browsing habit. As an optional embodiment, a group of testees face a film screen for emotion induction by playing movie clips.

[0041] An EEG measurement equipment group, used for synchronously collecting the EEG signals of multiple testees and transmitting the signals to a group emotion homogeneity calculation unit. As an optional embodiment, the EMOTIV EPOC Flex Saline Sensor Kit EEG collection system (including a control box, a signal receiver, an EPOC Flex Cap and an EPOC Flex saline sensor) can be used, with a single ADC and a bandwidth of 0.16-43 Hz, containing 32-channel data, configuring 2 reference electrodes for ears, and realizing synchronous sequential sampling on multiple machines. The EMOTIV EPOC Flex series, with a high cost performance, suitable for the cost control of group measurement, was applied in clinical studies by relevant scholars. By comparing its data with those of expensive BP and Neuroscan equipments, it was found that there were quite small differences in the quality of the collected data. The configurations of the host for the system are: CPU: Intel Core i7-9700 or higher; GPU: NVIDIA GeForce GTX 2080 Ti or higher; memory: 64 GB RAM; 1 TB of free disk space.

[0042] A group emotion homogeneity calculation unit, comprising a group EEG signal preprocessing module, a group emotion homogeneity calculation module and a data visualization module. The group EEG signal preprocessing module is used for preprocessing the collected EEG signals by amplification, analysis segment capturing, noise reduction, artifacts removal (removing the interference from electrooculogram, electromyogram, electrocardiogram and power frequency) and band-pass filtering; the group emotion homogeneity calculation module is used for performing wavelet transformation for the EEG signals after preprocessing to obtain the average instantaneous phase per second of the beta frequency band, calculating the energy value per second of the alpha frequency band in real time, then calculating the time synchronization degree and the valence consistency degree in real time, and generating the group emotion homogeneity index; the data visualization module is used for displaying the profile of the group emotion homogeneity index over time, which helps users monitor the group emotion homogeneity and provides scientific evidence for decision-making.

[0043] As shown in FIG. 2, a real-time evaluation method for group emotion homogeneity, which is achieved based on the above real-time evaluation system, specifically comprises the steps as follows:

[0044] S1: Wearing multichannel EEG measurement equipment for multiple testees at the same time, adopting 32-channel electrode caps, and keeping the impedance of each electrode point at less than 5 kΩ by using saline or gel electrodes. An international uniform standard 10-20 system is used for the configuration for electrode positions.

[0045] S2: Placing the testees in the same emotion induction environment, and synchronously collecting the original EEG signals of multiple testees. The testees should minimize head movements or other body movements, avoid language communications among the testees, and reduce the interference of irrelevant visual or audio stimulus.

[0046] S3: Performing real-time preprocessing and wavelet transformation for the original EEG signals from forehead and anterior temporal channels to obtain the average instantaneous phase per second of the beta frequency band, and calculating the energy value per second of the alpha frequency band in real time. The forehead and anterior temporal channels are selected by the method that: electrode points are configured according to the international 10-20 system and the distribution of related brain areas, and the electrode points FP1, FPz, FP2, F7 and F8 are selected for calculating the emotion time synchronization degree, and the electrode points FP1, FPz, FP2, Fz, F3, F4, F7 and F8 are selected for calculating the valence consistency degree.

[0047] S4: Calculating the time synchronization degree in real time based on the average instantaneous phase obtained in S3, and calculating the valence consistency degree in real time based on the energy value obtained in S3;

[0048] The time synchronization degree T is calculated by the formulae as follows:

[00003]$$\begin{gathered} T=\frac{2}{k\left(k-1\right)}\underset{i=1}{\overset{k}{.Math.}}\underset{j=1}{\overset{k}{.Math.}}\exp \left(S_{ij}\right)S_{ij}=\{\begin{array}{cc}.Math.x_i-x_j.Math.& i<j\\ 0& i\ge j\end{array} \\ S=\left[\begin{array}{ccc}{S}_{11}& .Math.& S_{k1}\\ .Math.& \ddots & .Math.\\ S_{1k}& .Math.& S_{\mathrm{kk}}\end{array}\right] \\ S\in R^{k\times k} \end{gathered}$$

[0049] where, S is the real matrix for Row k and Line k, S.sub.ij is the value of phase difference, x represents the average instantaneous phase of the beta frequency band of a testee, i represented the i.sup.th testee in sequence, j represents the j.sup.th testee in sequence, and k is the total number of testees.

[0050] The valence consistency degree V is calculated by the formulae as follows:

[00004]$$\begin{gathered} V=\frac{1}{k}\max \left\{{.Math.Y_{M_{+}}.Math.}_1,{.Math.Y_{M_{-}}.Math.}_1\right\}{Y}_{M_{+}}=\max \left\{Y_M,0\right\}{Y}_{M-}=\min \left\{Y_M,0\right\}{Y}_M\left(i\right)=\{\begin{array}{cc}1& M_i>0\\ 0& M_i=0\\ -1& M_i<0\end{array} \\ M=\left(M_1,M_2,M_3,.Math.M_k\right) \\ M\in R^k \\ {M}_i=\log \left(P{L}_i\right)-\log \left(P{R}_i\right) \end{gathered}$$

[0051] where, Y.sub.M is a sign function, M is a k-dimensional vector, PL is the average value of energy of the alpha frequency band collected from the left forehead channel and the left anterior temporal channel of a testee, PR is the average value of energy of the alpha frequency band collected from the right forehead channel and the right anterior temporal channel of the testee, i represents the i.sup.th testee in sequence, and k is the total number of testees.

[0052] S5: Calculating the group emotion homogeneity index in real time based on the time synchronization degree and the valence consistency degree in S4. The group emotion homogeneity index per second E is calculated by the formula as follows:

E=V*T

[0053] S6: Evaluating and grading the group emotion homogeneity based on the profile of the group emotion homogeneity index over time. The standards for evaluating and grading the homogeneity are as follows: the group emotion homogeneity index E≥0.6 is deemed as strong group emotion homogeneity, 0.4≤E<0.6 is deemed as convergent group emotion homogeneity, and E<0.4 is deemed as insufficient group emotion homogeneity.

[0054] According to the invention, multi-person synchronous real-time measurement and analysis are realized, the group emotion homogeneity can be dynamically monitored in a proceduring manner, the problems of after-event sampling, strong subjectivity, social desirability bias and the like of a traditional measurement means are effectively avoided, and the method has a wide market application prospect.

[0055] The embodiments above are only used for explaining, rather than limiting, the technical solutions of the present invention; although the present invention is explained in detail by reference to the above embodiments, those of ordinary skill in the art should understand that, they may modify the technical solutions recorded in the above embodiments, or equivalently replace a part or all of the technical features, whereas such modifications or replacements will not make the nature of the modified technical solutions deviate from the scope of the technical solution of the embodiment of the present invention.