JP6859622B2 - EEG signal processing system, EEG signal processing method and program - Google Patents

Description

The present invention relates to an electroencephalogram signal processing system, an electroencephalogram signal processing method and a program suitable for use in knowing the psychological state or physiological state of the user by observing the electroencephalogram of the user.

By analyzing the distribution and changes in brain activity, the psychological and physiological states of the user can be estimated. For example, the Brain-Machine Interface estimates the user's intention by analyzing the user's brain activity and uses it as an operation input of the device (Non-Patent Document 1). Various attempts have been made to estimate the user's emotions from the activity in the brain (Non-Patent Document 2).

One of the widely used measuring means for estimating the state of intracerebral activity is the electroencephalograph side. By mounting a plurality of electroencephalogram electrodes on the scalp and using an electroencephalogram amplifier capable of amplifying a plurality of channels, an electroencephalogram signal reflecting the distribution of intracerebral activity can be obtained. The method of using the change in the power spectrum of the brain wave obtained by using frequency analysis such as Fourier transform and the difference in the power spectrum between the electrodes as an index showing the behavior of the signal source in the brain for estimating the user's state is widespread. It is used. There is also a method of estimating the user's state from the interrelationship of the electroencephalogram signals of a plurality of channels observed at different electrode positions corresponding to the activities of different parts of the brain (Non-Patent Document 3). The interrelationship of signal sources in the brain can be quantified by the mutual correlation coefficient between EEG channels.

However, the electroencephalogram signal (hereinafter referred to as the observation signal) measured using the electrodes mounted on the scalp is a mixture of electrical signals from a plurality of signal sources scattered in and out of the brain. , It does not directly reflect the behavior of a specific part in the brain. Independent component analysis assuming statistical independence of the original signal emitted by the signal source as a method of separating and analyzing the signal sources related to a specific event when it is assumed that there are a plurality of signal sources (Patent Documents). 1. A signal source separation method using an algorithm such as Non-Patent Document 4) is known.

An external stimulus with a known physiological and psychological effect is given to the user, the brain wave of the user receiving this external stimulus is measured, and the feature amount obtained by analyzing the measured brain wave (hereinafter referred to as the brain wave feature amount) is described. Ask. Then, since the external stimulus given to the user causes a change in the physiological and psychological state of the user, the user is asked to search for an electroencephalogram feature amount that changes in conjunction with the change in the physiological and psychological state of the user. It is possible to determine the interrelationship between the EEG features and changes in the physiological and psychological state of the given external stimulus.
Furthermore, by using this interrelationship as known information, it becomes possible to estimate the physiological and psychological state of the user based on the electroencephalogram feature amount obtained from the electroencephalogram of the user in an unknown state.

In addition, when the user is instructed to recall situations such as emotions, scenes, and movements, and the recall of this situation is used as an internal stimulus, the user is induced to have a physiological and psychological state, and when this internal stimulus is given. Measure brain waves. Then, from this measurement result, it is possible to obtain an electroencephalogram feature amount that changes in conjunction with a change in the user's physiological and psychological state.

Japanese Patent No. 4876988

"Using the Brain" Study Group, Brain Machine Interface-Connecting the Brain and Machine, Ohmsha 2007/9 Daisuke Seki, Koichi Yokozawa, Evaluation of the relationship between the impression given by just intonation chords and magnetoencephalographic activity, IEICE Technical Report. NC, Neurocomputing 111 (483), 371-376, 2012-03-07 Yuji Takeda, Interest and Favorability Measured by Gamma Band EEG, AIST TODAY Vol. 9, pp. 20, 2009 Noriaki Kanayama, Hideki Ohira, Kazuo Hiraki, Separation of brain activity during visual-tactile integrated processing using independent component analysis, IEICE Technical Report, HIP, Human Information Processing 109 (345), 119-123, 2009

By the way, an electroencephalogram is an electrical signal obtained by observing an impulse flowing through a neuron network from the outside. Therefore, brain waves can be classified into 0.4 to 4 Hz delta waves, 4 to 8 Hz theta waves, 8 to 14 Hz alpha waves, and 14 to 26 Hz beta waves, depending on the frequency of the main vibration signal.

When the electroencephalogram feature amount which is an electric signal is the amplitude of the signal component in each frequency band, the number of electroencephalogram feature amount to be acquired is calculated as follows. That is, if the number of electrodes attached to the user's head for measuring brain waves is N and the number of frequency bands for extracting amplitude is M, the number of brain wave features is N × M. ..
Furthermore, when the interrelationship between the electrodes attached to the head, for example, the phase difference or the correlation coefficient, is added as the electroencephalogram feature amount, the number of electrodes is N, and the number of frequency bands is M, the electroencephalogram feature amount. The number of is N × (N-1) / 2 × M.

In addition to the above-mentioned phase difference or correlation coefficient, the phase difference, time-series amplitude value, and waveform change can be used as the electroencephalogram feature amount.
Furthermore, secondary EEG features can be derived by performing the functions obtained from the signals of each frequency band of the EEG and the four arithmetic operations of the obtained EEG features.
As a result, the number of electroencephalogram features becomes enormous, and from the obtained electroencephalogram features, the electroencephalogram features corresponding to changes in the user's physiological and psychological state, such as "comfort" and "enjoyment", are physiological psychology. In order to search for EEG features related to changes in the target state, a large computational load is required for the analysis in the search.

The present invention has been made in view of such a situation, and among many electroencephalogram features, the electroencephalogram features related to the change in the physiological and psychological state of the user are given to the experimenter (analyst). An object of the present invention is to provide an electroencephalogram signal processing system, an electroencephalogram signal processing method, and a program that can be easily searched without applying a load.

In order to solve the above-mentioned problems, the electroencephalogram signal processing system of the present invention has an electroencephalogram feature amount which is a feature amount of an electroencephalogram signal generated in response to a given stimulus and a stimulus feature amount which is a feature amount of the stimulus. a brain wave signal processing system for determining the relevance, the feature amount calculating unit for obtaining a plurality of the EEG feature value of the brain wave signal corresponding to the stimulus, and each of the one or more of the stimulation characteristic quantity of the stimulation, a plurality For each combination with each of the electroencephalogram feature amounts of the above, an interrelationship degree calculation unit that calculates the degree of interrelationship indicating the degree of association of the combination, and the stimulus feature amount that the degree of interrelationship exceeds a predetermined threshold. A feature amount selection unit that extracts a combination of the electroencephalogram feature amount and the electroencephalogram feature amount and selects the electroencephalogram feature amount that is highly related to the stimulus feature amount, and a component having the electroencephalogram signal having a plurality of series of electroencephalogram features. A signal separation unit for separating into signals is provided, and the feature amount calculation unit calculates the electroencephalogram feature amount from the component signal.
The electroencephalogram signal processing system of the present invention is an electroencephalogram signal processing system that obtains the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus. Therefore, a feature amount calculation unit for obtaining a plurality of the electroencephalogram feature amounts based on the frequency of the electroencephalogram signal emitted by each of the signal sources in the brain corresponding to each of the stimuli, and one or more of the stimulus features of the stimulus. For each combination of each amount and each of the plurality of electroencephalogram feature amounts, a degree of interrelationship calculation unit that calculates the degree of interrelationship indicating the degree of association of the combination, and the degree of interrelationship set a predetermined threshold value. It is characterized by including a feature amount selection unit that extracts a combination of the stimulus feature amount and the brain wave feature amount that exceeds the stimulus feature amount and selects the brain wave feature amount that is highly related to the stimulus feature amount.
The electroencephalogram signal processing system of the present invention is related to each of the stimulus feature quantities, which is the feature quantity of the stimulus, among the electroencephalogram feature quantities, which are the feature quantities of the brain wave signals generated in response to the given stimulus. An electroencephalogram signal processing system that selects a high electroencephalogram feature amount, which comprises a feature amount calculation unit for obtaining a plurality of the electroencephalogram feature amounts of the electroencephalogram signal corresponding to the stimulus, and one or more of the stimulus feature amounts of the stimulus. For each combination of each and the plurality of electroencephalogram feature amounts, a degree of interrelationship calculation unit that calculates the degree of relevance indicating the degree of relevance of the combination, and the degree of interrelationship exceeding a predetermined threshold. A combination of the stimulus feature amount and the brain wave feature amount is extracted, and the feature amount selection unit for selecting the brain wave feature amount having a high relevance to the stimulus feature amount is provided, and the plurality of the brain wave feature amounts are provided. of, characterized in that at least two or more of the EEG feature amount Ru different types of unit der each other.

The electroencephalogram signal processing system of the present invention is characterized by using a mutual information amount as the degree of interrelationship.

The electroencephalogram signal processing system of the present invention is characterized in that a correlation coefficient is used as the degree of interrelationship.

The electroencephalogram signal processing system of the present invention further includes a stimulus presenting unit that presents the stimulus to the user, and the stimulus presenting unit presents the stimulus having a different type of stimulus feature amount to the user. It is characterized by that.

The electroencephalogram signal processing system of the present invention further includes an electroencephalogram estimation database, and the electroencephalogram feature amount that is highly related to the stimulus feature amount selected by the feature amount selection unit for the stimulus feature amount. It is characterized in that it is written and stored in the electroencephalogram estimation database as a set with the stimulus feature amount.

In the electroencephalogram signal processing system of the present invention, when the electroencephalogram feature amount of the electroencephalogram signal is supplied, the stimulus feature amount corresponding to the electroencephalogram feature amount is extracted from the electroencephalogram estimation database, and the stimulus feature amount of the stimulus is extracted. It is characterized by further including a user state estimation unit for estimating.

The electroencephalogram signal processing method of the present invention is an electroencephalogram signal processing method for obtaining the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus. Therefore, it is an electroencephalogram signal processing method for obtaining the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus, and the feature amount is calculated. The feature amount calculation process for obtaining the brain wave feature amount of the plurality of electroencephalogram signals corresponding to the stimulus, and the interrelationship degree calculation unit are each of one or more of the stimulus feature amounts of the stimulus and a plurality of the above. For each combination with each electroencephalogram feature amount, the interrelationship degree calculation process for calculating the degree of interrelationship indicating the degree of association of the combination and the feature amount selection unit indicate that the degree of interrelationship exceeds a predetermined threshold. The feature amount selection process of extracting the combination of the stimulus feature amount and the brain wave feature amount and selecting the brain wave feature amount having a high relevance to the stimulus feature amount, and the signal separation unit generate the brain wave signal. It includes a signal separation process of separating into component signals having a plurality of series of electroencephalogram features, and the feature amount calculation unit calculates the brain wave feature amount from the component signals.
EEG signal processing method of the present invention, EEG feature quantity is a feature quantity of EEG signal generated in response to a given stimulus, the stimulus of the feature at which stimulation characteristic of relevance determined electroencephalogram signal processing method Therefore, the feature amount calculation unit obtains a plurality of the electroencephalogram feature amounts based on the frequencies of the electroencephalogram signals emitted by each of the signal sources in the brain in response to each of the stimuli, and the degree of interrelationship with the feature amount calculation process. The calculation unit calculates the degree of interrelationship indicating the degree of association of the combination for each combination of one or more of the stimulus feature amounts of the stimulus and each of the plurality of the electroencephalogram feature amounts. The calculation process and the feature amount selection unit extract a combination of the stimulus feature amount and the electroencephalogram feature amount in which the degree of interrelationship exceeds a predetermined threshold, and the feature amount is highly related to the stimulus feature amount. It is characterized by including a feature amount selection process for selecting an electroencephalogram feature amount.
The brain wave signal processing method of the present invention is related to each of the stimulus features, which are the stimulus features, among the brain wave features, which are the features of the brain wave signals generated in response to the given stimulus. A brain wave signal processing method for selecting a high brain wave feature amount, wherein the feature amount calculation unit obtains a plurality of the brain wave feature amounts of the brain wave signal corresponding to the stimulus, and the interrelationship degree calculation unit. However, for each combination of one or more of the stimulus features of the stimulus and each of the plurality of brain wave features, a process of calculating the degree of interrelationship indicating the degree of relevance of the combination is calculated. The feature amount selection unit extracts a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold, and the brain wave feature having a high relevance to the stimulus feature amount. The feature amount selection process of selecting the amount is included, and at least two or more of the brain wave feature amounts among the plurality of the brain wave feature amounts are units of different types from each other.

Program of the present invention is a program for determining a characteristic quantity of EEG signal generated in response to a given stimulus EEG feature amount, the relevant stimulus feature quantity is a feature quantity of the stimulation, the computer A feature amount calculating means for obtaining a plurality of the brain wave feature amounts of the brain wave signal corresponding to the stimulus, each combination of one or more of the stimulus feature amounts of the stimulus and each of the plurality of the brain wave feature amounts. In addition, a means for calculating the degree of interrelationship, which indicates the degree of relevance of the combination, and a combination of the stimulus feature amount and the electroencephalogram feature amount in which the degree of interrelationship exceeds a predetermined threshold are extracted. , The feature amount selection means for selecting the electroencephalogram feature amount having a high relevance to the stimulus feature amount, and the signal separation means for separating the electroencephalogram signal into component signals having a plurality of series of electroencephalogram features. The separation means is a program that separates the electroencephalogram signal into component signals having the characteristics of a plurality of series of electroencephalograms.
Program of the present invention is a program for determining a characteristic quantity of EEG signal generated in response to a given stimulus EEG feature amount, the relevant stimulus feature quantity is a feature quantity of the stimulation, the computer A feature amount calculating means for obtaining a plurality of the electroencephalogram feature amounts based on the frequencies of the electroencephalogram signals emitted by each of the signal sources in the brain corresponding to each of the stimuli, and one or more of the stimulus feature amounts of the stimulus. Correlation degree calculation means for calculating the degree of interrelationship indicating the degree of association of the combination for each combination of each of the plurality of electroencephalogram feature amounts, and the degree of interrelationship exceeds a predetermined threshold. This is a program for extracting a combination of a stimulus feature amount and the electroencephalogram feature amount and operating it as a feature amount selection means for selecting the brain wave feature amount having a high relevance to the stimulus feature amount.
In the program of the present invention, among the brain wave features which are the features of the brain wave signal generated in response to a given stimulus, the brain waves which are highly related to each of the stimulus features which are the features of the stimulus. It is a program for selecting a feature amount, and a computer is used with a feature amount calculation means for obtaining a plurality of the brain wave feature amounts of the brain wave signal corresponding to the stimulus, and one or more of the stimulus feature amounts of the stimulus. , The interrelationship degree calculation means for calculating the degree of interrelationship indicating the degree of association of the combination for each combination with each of the plurality of the brain wave features, and the stimulus feature in which the degree of interrelationship exceeds a predetermined threshold. A combination of the amount and the brain wave feature amount is extracted and operated as a feature amount selection means for selecting the brain wave feature amount having a high relevance to the stimulus feature amount, and among the plurality of the brain wave feature amounts. At least two or more of the brain wave features are programs that are different types of units.

As described above, according to the present invention, the EEG feature amount related to the change in the physiological and psychological state of the user is given a load to the experimenter (analyst) from among many EEG feature amounts. It is possible to provide an electroencephalogram signal processing system, an electroencephalogram signal processing method, and a program that can be easily searched without.

It is a block diagram which shows the schematic structure of the user state estimation apparatus which is one Embodiment of the electroencephalogram signal processing system of this invention. It is a figure which shows the schematic structure of the electroencephalogram measuring unit 19 shown in FIG. It is a figure which shows the structural example of the questionnaire for finding the correspondence relationship between the stimulus stored in the stimulus feature amount storage part 14 and the stimulus feature amount. It is a conceptual diagram which shows the processing of each part in FIG. 1 and the flow of the signal output of each part. It is a figure of the table which shows the structural example of the stimulus feature amount stored in the stimulus feature amount storage part 14. It is a figure which shows an example of the data of the independent component 1 (IC1) and the independent component 2 (IC2) in the independent component 42. It is a figure which shows an example of the data of the component signal 43 obtained by separating the independent component 42 by a frequency filter. It is a figure which shows the structural example of the electroencephalogram feature 44 obtained from each of IC1 alpha wave, IC1 beta wave, IC2 alpha wave and IC2 beta wave. It is a figure which shows the mutual information amount obtained by associating each time interval of a stimulus feature amount 45 and an electroencephalogram feature amount 44. It is a figure of the graph which shows the correspondence relationship between a stimulus feature amount and an electroencephalogram feature amount (alpha wave amplitude). It is a graph which shows the correspondence with the amplitude of the beta wave in the independent component of a music and an electroencephalogram signal. It is a figure which shows the table of the excitement degree for each music obtained in advance using the questionnaire of FIG. It is a figure which shows the table of the mutual information amount obtained from the amplitude and excitement degree of each beta wave of 19 independent components shown in FIG. It is a figure which showed the amplitude of the beta wave of the independent component "9" which has the largest mutual information amount in FIG. 13 extracted from FIG. It is a figure which showed the amplitude of the beta wave of the independent component "3" which has the smallest mutual information in FIG. 13 extracted from FIG.

Hereinafter, embodiments of the electroencephalogram signal processing system of the present invention will be described with reference to the drawings. In this embodiment, as an example, the signal source in the brain is estimated by separating the signal source in the brain by independent component analysis, and the amplitude and the specific frequency component of the signal of the specific frequency component emitted by the signal source in the brain are estimated. It has a configuration for estimating the user state using the change of each phase difference of.
FIG. 1 is a block diagram showing a schematic configuration of a user state estimation device according to an embodiment of the electroencephalogram signal processing system of the present invention. The user state estimation device 1 includes a computer 10, an electroencephalogram measuring unit 19, a display device 18a, and a speaker 11a. The computer 10 is, for example, an information processing device such as a personal computer, a smartphone, or a tablet terminal. In the example shown in FIG. 1, the display device 18a and the speaker 11a are provided outside the computer 10, but the computer 10 may include the display device 18a and the speaker 11a.
Further, in the example shown in FIG. 1, sound is used as a stimulus from the auditory sense, but a visual stimulus such as a still image, a moving image, or a sentence, or a stimulus by the sense of touch, smell, or taste, etc. Stimuli other than sound may be used.
In addition, instead of using external stimuli such as sounds, images, and odors, the user is instructed to recall a predetermined emotion or imagine a predetermined scene, and induces an internal stimulus state in the brain. May be good.
In the example shown in FIG. 1, the mutual information amount is used as an index of the degree of interrelationship between the EEG feature amount and the stimulus feature amount, but the relationship (relationship) between two variables such as the correlation coefficient is high. Other indicators indicating the above may be used.

The computer 10 shown in FIG. 1 includes a stimulus presentation unit 11, a signal separation unit 12, a feature amount calculation unit 13, a stimulus feature amount storage unit 14, a mutual information amount calculation unit 15, and a feature amount selection unit 16. A user state estimation unit 17 and a display unit 18 are provided. The stimulus presentation unit 11, the signal separation unit 12, the feature amount calculation unit 13, the stimulus feature amount storage unit 14, the mutual information amount calculation unit 15, the feature amount selection unit 16, and the user state estimation unit 17 are CPUs that make up the computer 10. It is composed of hardware such as a central processing unit) and a storage device, and software executed by a CPU.

In the configuration example shown in FIG. 1, the stimulus presenting unit 11 changes the user's emotions (emotions, likes and dislikes, etc.) in chronological order when measuring the brain waves that change due to emotions. Present changing stimuli to users. In the present embodiment, for example, a musical piece having a different musical tone and a different musical composition is switched and presented to the user via the speaker 11a at regular time intervals so that the user's emotions change significantly.

Next, FIG. 2 shows a schematic configuration of the electroencephalogram measuring unit 19 shown in FIG. The electroencephalogram measuring unit 19 includes a ground electrode 21 and an electroencephalogram electrode 22 having the same number or more as the number of measurement channels. Further, the electroencephalogram measuring unit 19 includes an amplifier 24 and an AD (analog / digital) converter 25. The ground electrode 21 and the electroencephalogram electrode 22 are attached to the user's head 7 by using a band 22a, a cap, a gel agent, or the like. The amplifier 24 amplifies the brain wave, which is a weak electric signal, and uses it as an input of the AD converter 25. The AD converter 25 digitally converts the analog electroencephalogram signal amplified by the amplifier 24 to generate a digitized observation signal as an input of the computer 10. Here, the observed signal includes a plurality of channels of digital electroencephalogram signals. The digital electroencephalogram signal is a signal obtained by digitizing an analog electroencephalogram signal including brain waves and noise.

The AD converter 25 samples the analog electroencephalogram signal of each channel at a rate of, for example, 4000 times / second, and converts the sampled sample into 16-bit digital data per channel. In this case, the electroencephalogram signal up to 2 kHz can be measured.

Returning to FIG. 1, the signal separation unit 12 separates the observed signal into a plurality of series of component signals by frequency division or independent component analysis. That is, the signal separation unit 12 executes an independent component analysis on the observed signals of a plurality of channels and separates them into independent components which are mutually independent signals presumed to correspond to the signal source in the brain. Further, the signal separation unit 12 separates the separated independent components into an alpha wave component and a beta wave component through a frequency filter provided inside, and obtains a component signal. This frequency filter extracts the frequency components used for analysis from the signal including all the separated frequency components. That is, in the frequency filter, the alpha wave signal component (hereinafter referred to as the alpha wave component) and the beta wave signal component (hereinafter referred to as the beta wave component) in the frequency band are referred to as the target signal used for the analysis from each separated signal component. ) And each are extracted and output. As a result, the signal separation unit 12 separates the electroencephalogram signal, which is an observation signal, into component signals having the characteristics of a plurality of series of electroencephalograms.

The feature amount calculation unit 13 obtains the average value of the brain wave feature amounts of the component signals separated by the signal separation unit 12 for each time interval. In the present embodiment, as the electroencephalogram feature amount, the amplitude of each of the alpha wave component and the beta wave component extracted for each independent component, and the phase difference of each of the alpha wave component and the beta wave component between the independent components are combined. I am using it. Here, the time interval uses, for example, the switching of the stimulus presented by the stimulus presenting unit 11 as a delimiter. Further, this time interval may be set as an arbitrary time interval, or the time intervals may overlap each other.

Unique stimulus features such as comfort, uplifting, likability, and volume, which will be described later, are written and held in the stimulus feature storage unit 14 in response to each stimulus presented by the stimulus presentation unit 11. There is. This stimulus feature amount is a unique feature amount such as comfort level and volume as an evaluation value felt by the user who received each stimulus for each stimulus presented by the stimulus presenting unit 11.

FIG. 3 is a diagram showing a configuration example of a questionnaire for obtaining a correspondence relationship between a stimulus stored in the stimulus feature amount storage unit 14 and a stimulus feature amount. For example, by using this questionnaire, the psychological amount obtained by the subjective evaluation that allows the user to evaluate the degree of impression that the user feels for each stimulus presented by the stimulus presenting unit 11 is obtained as the stimulus feature amount. .. The evaluation results are, for example, a 5-point evaluation from 0 points for "unpleasant" to 4 points for "comfort", a 5-point evaluation from 0 points for "boring" to 4 points for "fun", and 0 points for "dislike". The evaluation is made on a 5-point scale from to 4 points of "like", and each evaluation value is "comfort", "elevation", and "favorability" as the stimulus feature amount of the stimulus.

The subjective evaluation of the stimulus feature amount may be performed at the same time as the EEG measurement, or the process of presenting the stimulus and obtaining the answer (subjective) is performed before or after the EEG measurement without performing the EEG measurement at the same time. Is also good.
The evaluation values of each of the target users of a plurality of electroencephalogram measurements for the same stimulus may be averaged, and the average evaluation value may be used as the stimulus feature amount. Further, the evaluation value for the stimulus by a user other than the target user of the electroencephalogram measurement may be used as the stimulus feature amount.

Moreover, not only the subjective evaluation felt by the user due to the stimulus of the music as described above, but also the physical quantity such as the volume of the auditory stimulus and the brightness of the visual stimulus, and the physical quantity such as the loudness level which is an evaluation index of the volume feeling felt by the person. A psychological quantity derived from intensity or the like may be used as a stimulus feature quantity. Here, the stimulus feature quantity does not have to have a linear correspondence with the physical quantity and the psychological quantity of the stimulus, and the psychological quantity may change according to the intensity of the physical quantity of the stimulus.
For example, an arbitrary number may be assigned to each of the stimuli given to the user to identify the stimulus. At this time, the stimuli are classified into groups according to some criteria such as the genre of music and the type of the subject of the image, and a number for identifying each group is assigned to each of the classified groups, and the stimulus features of the stimuli of the same group are assigned. The amounts may be the same value.

The mutual information amount calculation unit 15 has the brain wave feature amount in each time interval of each component signal obtained by the feature amount calculation unit 13 and the stimulus feature amount corresponding to the time interval stored in the stimulus feature amount storage unit 14. Find the mutual information that indicates the degree of association of the combination with and. Instead of mutual information, other indicators of the degree of relationship between variables, such as the correlation coefficient, can be used. This mutual information amount is an index showing the strength of the interdependence of the two random variables, and the mutual information amount between the two random variables X and Y can be obtained by the following equation (1). In the following equation (1), each of p (x) and p (y) is a peripheral probability function of X and Y, respectively. Further, p (x, y) is a simultaneous probability function of X and Y, respectively.

The feature amount selection unit 16 has a strong relationship with each of the stimulus feature amounts from the brain wave feature amounts calculated by the feature amount calculation unit 13 based on the mutual information amount obtained by the mutual information amount calculation unit 15. Identify and select each EEG feature.
When a linear relationship is obtained between the stimulus feature and the EEG feature, the correlation coefficient between the stimulus feature and the EEG feature is used instead of the mutual information, and this correlation coefficient is used. Depending on the size, each of the brain wave features having a strong relationship with each of the stimulus features may be specified and selected.

The user state estimation unit 17 obtains the relationship between the brain wave feature amount selected by the feature amount selection unit 16 and the stimulus feature amount. That is, the user state estimation unit 17 determines the relationship between the brain wave features selected by the feature selection unit 16 corresponding to each of the stimulus features, and the brain wave features when the emotions indicated by the stimulus features are estimated. Used as.
As a result, the user state estimation unit 17 can estimate the user's psychological state caused by the stimulus from the user's electroencephalogram feature amount when the stimulus is received.

The display unit 18 generates an image that displays information on the user's physiological psychological state estimated by the user state estimation unit 17 in a format that can be recognized by the user and other experimenters, such as numerical values, graphs, and maps, and is displayed on a liquid crystal display. Is displayed on the display device 18a such as. For example, the display unit 18 displays the “comfort”, “elevation”, “favorability”, etc. in the stimulus feature amount as a graph on the display device 18a, so that the estimated psychology corresponding to the received stimulus is displayed. Shows a typical state.
Further, the display unit 18 is an electroencephalogram waveform measured by the electroencephalogram measurement unit 19, a signal separation result, an electroencephalogram feature amount calculated by the feature amount calculation unit 13, a mutual information amount calculated by the mutual information amount calculation unit 15, and a feature amount selection unit. Original data or intermediate information such as information on the electroencephalogram feature amount selected by 16 may be displayed.

Next, the flow of the signal separation process in the present embodiment will be described with reference to FIG. FIG. 4 is a conceptual diagram showing the processing of each part in FIG. 1 and the flow of signals output by each part. In addition, supplementary explanations will be given to the configuration examples of the present embodiment described with reference to FIG. The observation signal 41 is, for example, a digital brain wave signal obtained by digitally converting the brain waves of Ch1 and Ch2, which are two channels, measured by the brain wave electrodes 22 at three locations on the frontal region of the user. As shown in FIG. 4, the observation signal 41 is illustrated as a waveform of an electroencephalogram signal having time on the horizontal axis and voltage on the vertical axis.

For example, the stimulus presenting unit 11 automatically reproduces the music according to the order preset by the measurer, gives (presents) the presentation sound corresponding to the music to the user via the speaker 11a, and hears by the sound information. Gives a stimulus to.
In the present embodiment, an example will be described in which three types of music, which are considered to give different impressions when heard by a human being, for example, have different musical tunes and tunes, are presented three times, for a total of nine times. However, as already described, a configuration in which a stimulus other than sound, that is, a stimulus other than hearing may be used as the stimulus may be used. In addition to external stimuli such as hearing, the user may be instructed to evoke a specific scene or emotion to give an internal stimulus.
In the stimulus feature amount storage unit 14, the stimulus feature amount 45 of the stimulus (auditory stimulus in the present embodiment) presented to the user is written and stored in advance.

FIG. 5 is a diagram of a table showing a configuration example of the stimulus feature amount stored in the stimulus feature amount storage unit 14. As shown in FIG. 5, in the present embodiment, the stimulus feature amount 45 is the sound source number, comfort level, tempo, volume feeling, and genre of the music, and is a value corresponding to each section indicating the time of nine stimulus presentations. Holds. The sound source number is identification information for identifying which of the three types of music is used. The comfort level indicates a psychological amount obtained by quantifying the psychological state based on the subjective evaluation of the user's stimulus obtained from the questionnaire shown in FIG. The tempo is a physical quantity that is physically measured from the audio signal of a musical piece and indicates how fast the beat is beaten in the musical piece. The sense of volume is a psychological quantity extracted from the amplitude of each frequency band of the audio signal of the music using the loudness curve. The genre indicates, for example, the classification of music with classical music as "1" and pop music as "2".

For example, in the section "1" in the first row of the table, it is shown that the sound source number is "1". The music that is the sound source of the sound source number "1" has a comfort level of "4.2", a tempo of "60", a volume feeling of "2.9", and a genre of "1 (classical)". ) ”. Similarly, in the section "2" in the second row of the table, it is shown that the sound source number is "2". The music that is the sound source of the sound source number "2" has a comfort level of "2.1", a tempo of "80", a volume feeling of "4.1", and a genre of "1 (pops)". ) ”.

Returning to FIG. 4, when the stimulus presentation unit 11 presents the stimulus to the user, the electroencephalogram measurement unit 19 acquires the observation signal 41 of the electroencephalogram signal via the electroencephalogram electrode 22 attached to the user's head, and signals. Output to the separation unit 12. In the present embodiment, the electroencephalogram measuring unit 19 acquires the observation signals 41 of each of the channel Ch1 and the channel Ch2 corresponding to each of the electroencephalogram electrodes 22. Here, as already described, the brain wave measuring unit 19 samples the observation signals of each of the channel Ch1 and the channel Ch2 at a predetermined cycle by the AD converter 25, and signals the observation signal 41 as a digital signal obtained by digitally converting the analog signal. Output to the separation unit 12. Further, in general, the electroencephalogram signals detected from the electroencephalogram electrodes adjacent to each other in the head have a strong correlation with their characteristics (signal waveform, power spectrum, etc.). Furthermore, by increasing the number of electroencephalogram electrodes and arranging the observation points of the electroencephalogram signal so as to cover a wide area of the head, the independent components by the independent component analysis are extracted in finer units, which is obtained. The amount of information will also increase.

The signal separation unit 12 separates the observation signal 41 into the component signal 43 by using independent component analysis in order to use it for deriving the electroencephalogram feature amount. In the present embodiment, the observation signals 41 of a plurality of channels (channels Ch1 and Ch2) are separated into independent components 42, which are mutually independent signals presumed to correspond to a signal source in the brain, by independent component analysis. The independent component 42 is an independent component 1 (IC1) and an independent component 2 (IC2), respectively. In general, since the correlation between the independent components is low, the correlation between the obtained independent component 1 (IC1) and the independent component 2 (IC2) is also low.

FIG. 6 is a diagram showing an example of data of the independent component 1 (IC1) and the independent component 2 (IC2) in the independent component 42. In each of the graph of the independent component 1 (IC1) and the graph of the independent component 2 (IC2) shown in FIG. 6, the vertical axis represents the voltage of the independent component and the horizontal axis represents the time. The signal waveforms of the independent component 1 (IC1) and the independent component 2 (IC2) are the waveforms of the electroencephalogram signals generated by each of the user's brain signal sources, that is, the characteristics of the electroencephalogram signals in each of the brain signal sources. Is shown.
In the present embodiment, the independent component analysis and the frequency filter are used as the signal separation method of the independent component, but the present invention is not limited to these, and the principal component analysis or the like is used instead of the independent component analysis to obtain the frequency filter. Alternatively, a configuration using a Fourier transform or the like may be used.

Returning to FIG. 4, the signal separation unit 12 separates each of the independent component 1 (IC1) and the independent component 2 (IC2) of the obtained independent component 42 into an alpha component and a beta component by a frequency filter (digital filter), respectively. The component signal 43 is calculated.

FIG. 7 is a diagram showing an example of data of the component signal 43 obtained by separating the independent component 42 by a frequency filter. Each of the IC1 alpha wave and the IC1 beta wave shown in FIG. 6 is a waveform of a signal obtained by separating the independent component 1 (IC1) by a frequency filter. Further, each of the IC2 alpha wave and the IC2 beta wave is a waveform of a signal obtained by separating the independent component 2 (IC2) by a frequency filter. In each of the IC1 alpha wave, IC1 beta wave, IC2 alpha wave and IC2 beta wave, the vertical axis represents the voltage of the component signal and the horizontal axis represents time. Each of the IC1 alpha wave, IC1 beta wave, IC2 alpha wave, and IC2 beta wave signals adds a parameter called frequency to the signal of the independent component 42 indicating the brain wave signal in each of the user's brain signal sources. This is a feature subdivided from the independent component 42.

Returning to FIG. 4, the feature amount calculation unit 13 is a brain wave showing the characteristics of the brain wave signal from each of the IC1 alpha wave, IC1 beta wave, IC2 alpha wave and IC2 beta wave in the component signal 43 separated by the signal separation unit 12. Find the feature amount 44.

FIG. 8 is a diagram showing a configuration example of an electroencephalogram feature amount 44 obtained from each of the IC1 alpha wave, IC1 beta wave, IC2 alpha wave, and IC2 beta wave.
FIG. 8A shows a graph of each EEG feature amount of the IC1 alpha wave and the IC1 beta wave. In this graph of electroencephalogram features, the horizontal axis indicates time (from the time interval "1" to the interval "9" shown in FIG. 5), and the vertical axis is the average of the amplitudes of the signal waveforms in the time interval. It shows the amplitude.

FIG. 8B shows a graph of each electroencephalogram feature amount of the IC2 alpha wave and the IC2 beta wave. In this graph of electroencephalogram features, the horizontal axis indicates time (from the time interval "1" to the interval "9" shown in FIG. 5), and the vertical axis is the amplitude obtained by averaging the amplitudes of the signal waveforms in the time interval. Is shown.

FIG. 8C is a graph showing the phase difference between the independent components, that is, the phase difference in the waveforms of the ICI alpha wave and the IC2 alpha wave, and the phase difference in the waveforms of the ICI beta wave and the IC2 beta wave. In this EEG feature graph, the horizontal axis indicates time (from the time interval "1" to the interval "9" shown in FIG. 5), and the vertical axis averages the phase differences of the signal waveforms in the time interval. It shows the phase difference.

Returning to FIG. 4, as shown in FIG. 8, the feature amount calculation unit 13 has the amplitudes of the IC1 alpha wave, the IC1 beta wave, the IC2 alpha wave, and the IC2 beta wave for each time interval, and the ICI for each time interval. The brain wave feature 44 of the brain wave signal including the phase difference of the alpha wave and the IC2 alpha wave and the phase difference of the ICI beta wave and the IC2 beta wave is obtained.

The mutual information amount calculation unit 15 calculates the mutual information amount 46 between each of the brain wave feature amounts 44 of the electroencephalogram signal obtained by the feature amount calculation unit 13 and the stimulus feature amount 45 stored in the stimulus feature amount storage unit 14. Ask. Here, the mutual information amount calculation unit 15 calculates the mutual information amount 46 by the above equation (1) by associating each time section of the stimulus feature amount 45 and the brain wave feature amount 44 with each other.
In the present embodiment, when the mutual information amount calculation unit 15 specifies, for example, a feature amount whose value fluctuates according to a sound source number, a comfort level, a tempo, a feeling of volume, and a genre from an electroencephalogram feature amount 44, there are five types. For each combination of the stimulus feature amount 45 and the six types of brain wave feature amount 44, the mutual information amount 46 is calculated by the equation (1), where the brain wave feature amount 44 is X and the stimulus feature amount 45 is Y.

FIG. 9 is a diagram showing a mutual information amount obtained by associating each time interval between the stimulus feature amount 45 and the electroencephalogram feature amount 44. The table shown in FIG. 9A shows the amount of mutual information between the sound source number and the electroencephalogram feature amount 44. In column 101 of the table, the mutual information amount "0.411" between the sound source number and the amplitude of the IC1 alpha wave in the electroencephalogram feature amount 44 (the graph on the left side of FIG. 8A) is shown. In column 102 of the table, the mutual information amount "0.351" between the sound source number and the amplitude of the IC1 beta wave in the electroencephalogram feature amount 44 (the graph on the right side of FIG. 8A) is shown. In column 103 of the table, the mutual information amount "0.211" between the sound source number and the amplitude of the IC2 alpha wave in the electroencephalogram feature amount 44 (the graph on the left side of FIG. 8B) is shown. In column 104 of the table, the mutual information amount "0.292" between the sound source number and the amplitude of the IC2 beta wave in the electroencephalogram feature amount 44 (the graph on the right side of FIG. 8B) is shown. In column 105 of the table, the mutual information "0.177" between the sound source number and the phase difference between the IC1 alpha wave and the IC2 alpha wave in the electroencephalogram feature 44 (graph on the left side of FIG. 8C) is shown. Has been done. In column 106 of the table, the mutual information "0.225" between the sound source number and the phase difference between the IC1 beta wave and the IC2 beta wave in the electroencephalogram feature 44 (graph on the right side of FIG. 8C) is shown. Has been done.

The table shown in FIG. 9B shows the amount of mutual information between the comfort level and the electroencephalogram feature amount 44. The table shown in FIG. 9C shows the mutual information between the tempo and the electroencephalogram feature 44. The table shown in FIG. 9D shows the amount of mutual information between the feeling of volume and the electroencephalogram feature amount 44. The table shown in FIG. 9E shows the amount of mutual information between the genre (genre 1) and the electroencephalogram feature amount 44. Each of these, FIG. 9 (b), FIG. 9 (c), FIG. 9 (d), and FIG. 9 (e), also has each of the stimulus feature amount 45 and the brain wave feature amount 44, as in FIG. 1 (a). The amount of mutual information with each is shown in each column of the table.

Returning to FIG. 4, the feature amount selection unit 16 has a mutual information amount among the mutual information amounts for each combination of the five types of stimulation feature amounts 45 and the six types of electroencephalogram feature amounts 44 shown in FIG. Extract combinations that exceed a preset determination threshold. This determination threshold is the threshold of the mutual information amount for determining the presence or absence of the relationship between the stimulus feature amount and the brain wave feature amount. In the embodiment, this determination threshold is set to, for example, 0.5. Therefore, the feature amount selection unit 16 has a mutual information amount of "0" among the mutual information amounts for each combination of the five types of stimulation feature amounts 45 and the six types of electroencephalogram feature amounts 44 shown in FIG. The mutual information amount exceeds the judgment threshold for the combination of the comfort level of ".624" and the IC1 alpha wave amplitude and the combination of the genre and the IC1 alpha wave amplitude of which the mutual information amount is "0.656". Because it is extracted. Then, the feature amount selection unit 16 selects the IC1 alpha wave amplitude in the independent component as the brain wave feature amount 47 used for estimating the user's comfort level and the genre of the music.

The feature amount selection unit 16 sets the stimulus feature amount obtained as an index and the brain wave feature amount related to the stimulus feature amount as a set with respect to the electroencephalogram estimation database 20 with respect to the electroencephalogram estimation database 20. Write and memorize.
The user state estimation unit 17 uses the brain wave feature amount 47 selected by the feature amount selection unit 16, that is, the IC1 alpha wave amplitude in the independent component of the brain wave signal, as an index for estimating the user's comfort level and the genre of the music.

FIG. 10 is a graph showing the correspondence between the stimulus feature amount and the electroencephalogram feature amount (IC1 alpha wave amplitude). FIG. 10A shows the correspondence between the comfort level of the stimulus feature and the alpha wave amplitude of the EEG feature. From the graph of FIG. 10A, it can be seen that the larger the alpha wave amplitude (IC1 alpha wave amplitude), the more comfortable the user is.
Similarly, FIG. 10B shows the correspondence between the genre of stimulus features and the alpha wave amplitude of EEG features. From the graph of FIG. 10B, it can be seen that when the alpha wave amplitude (IC1 alpha wave amplitude) is large, it can be estimated that the genre of the song being viewed by the user is genre 2. From the relationship of FIG. 10, it is estimated that the larger the alpha wave amplitude (IC1 alpha wave amplitude) is, the more comfortable the user is, and when the alpha wave amplitude exceeds the preset estimation threshold, the user is in the genre. It can be presumed that you are listening to 2 songs. This estimated threshold value is obtained from, for example, the IC1 alpha wave amplitudes of a plurality of users with respect to the genre of the music and the variance of the IC1 alpha wave amplitudes.

From the above, according to the present embodiment, the IC1 alpha wave amplitude of the independent component is an electroencephalogram feature amount useful for estimating the comfort level of the user and the genre of the music being listened to, and the IC1 alpha wave of the independent component. The relationship between the amplitude, the comfort level of the user, and the genre of the music being listened to is required.
Further, according to the present embodiment, by referring to the above-mentioned electroencephalogram estimation database 20, even when the user is listening to a music whose stimulus feature amount is unknown, the user state estimation unit 17 is the feature amount calculation unit 13. It is possible to estimate the user's comfort level and the genre of the music being listened to from the EEG features obtained in. That is, in the present embodiment, the brain wave estimation database 20 is provided, and by accumulating the relationship between the user's stimulus feature amount and the brain wave feature amount, the stimulus feature amount storage unit 14, the mutual information amount calculation unit 15, and the feature amount are accumulated. By omitting each process with the selection unit 16, it is possible to estimate the user's comfort level with respect to the unknown music and the genre of the music being listened to.

As described above, the user state estimation device 1 (electroencephalogram signal processing system) of the present embodiment uses the stimulus presentation unit 11 that presents sensory stimuli to the user in chronological order and the electroencephalogram electrode 22 attached to the head. The electroencephalogram measuring unit 19 that acquires the observation signal 41, the signal separation unit 12 that divides the observation signal 41 into component signals 43 by frequency division, multivariate analysis, etc., and the feature amount calculation for obtaining the electroencephalogram feature amount 44 of the component signal 43. Part 13, the mutual information amount calculation unit 15 that obtains the mutual information amount of the electroencephalogram feature amount 44 and the stimulus feature amount 45, and the feature that identifies and selects the brain wave feature amount that is strongly related to the stimulus feature amount based on the mutual information amount. The amount selection unit 16 and the user state estimation unit 17, which estimates the user's state from the relationship between the selected brain wave feature amount and the stimulus feature amount, accumulates the relationship between the user's stimulus feature amount and the brain wave feature amount. , Each of the electroencephalogram estimation database 20 is provided.

FIG. 11 is a graph showing the correspondence between the amplitude of the beta wave in the independent component of the music and the electroencephalogram signal. In FIG. 11, the horizontal axis represents time and the vertical axis represents the amplitude of beta waves.
Here, the electroencephalogram signals when the signal separation unit 12 repeatedly listens to four types of music are measured by the 19 electroencephalogram electrodes 22, and the measured electroencephalogram signals are separated from the 19 electroencephalogram signals by using independent component analysis. The amplitude change of each beta wave of the independent components of is shown in FIG.

FIG. 12 is a table showing the degree of excitement for each song obtained in advance using the questionnaire sheet of FIG. The excitement of the song "1" is "0.8", the excitement of the song "2" is "3.2", the excitement of the song "3" is "3.7", and the song "2". It is shown that the degree of excitement of "4" is "0.5".

FIG. 13 is a diagram showing a table of mutual information obtained from the amplitude and excitement of the beta waves of each of the 19 independent components shown in FIG. The items in the table are each of rank, component and mutual information. The components show the distinction of each of the 19 independent components from 0 to 18. The mutual information indicates the mutual information between the degree of excitement and the amplitude of the beta wave of each independent component. The ranking indicates the order from the one with the largest amount of mutual information between the degree of excitement and the independent component to the one with the smallest amount of mutual information. That is, the rank of the independent component "9" having the largest mutual information (0.4) is "1", and the rank of the independent component "3" having the smallest mutual information (0.09) is "19". is there.

FIG. 14 is a diagram showing the amplitude of the beta wave of the independent component “9” having the largest mutual information in FIG. 13 extracted from FIG. In FIG. 14, the horizontal axis represents time and the vertical axis represents the amplitude of beta waves.
From the results of FIG. 14, it can be seen that the greater the degree of excitement of the acquired music shown in FIG. 12, the greater the amplitude of the user's beta wave, and the smaller the degree of excitement, the smaller the amplitude of the beta wave. It can be seen that the amplitude of the beta wave, which is "", can be used to estimate the degree of excitement.

FIG. 15 is a diagram showing the amplitude of the beta wave of the independent component “3” having the smallest mutual information in FIG. 13 extracted from FIG. In FIG. 15, the horizontal axis represents time and the vertical axis represents the amplitude of beta waves.
From the result of FIG. 15, since the relation (correlated change) between the excitement degree by the acquired music shown in FIG. 12 and the amplitude of the beta wave is not observed, the amplitude of the beta wave which is the independent component “3” is It turns out that it cannot be used to estimate the degree of excitement.

The program for realizing the function of the brain wave signal processing system of FIG. 1 in the present invention is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into the computer system and executed. You may perform the process of obtaining the information for estimating the stimulus received from the brain wave signal. The term "computer system" as used herein includes hardware such as an OS and peripheral devices.
Further, the "computer system" shall also include a WWW system provided with a homepage providing environment (or display environment). Further, the "computer-readable recording medium" refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, or a CD-ROM, or a storage device such as a hard disk built in a computer system. Furthermore, a "computer-readable recording medium" is a volatile memory (RAM) inside a computer system that serves as a server or client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. In addition, it shall include those that hold the program for a certain period of time.

Further, the program may be transmitted from a computer system in which this program is stored in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the "transmission medium" for transmitting a program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. Further, the above program may be for realizing a part of the above-mentioned functions. Further, a so-called difference file (difference program) may be used, which can realize the above-mentioned functions in combination with a program already recorded in the computer system.

Although the embodiments of the present invention have been described so far, the above-described embodiments are merely examples, and the present invention is not limited to the above-described embodiments, and is implemented in various different forms within the scope of the technical idea. Needless to say, it's good.
Also, the scope of the present invention is not limited to the exemplary embodiments illustrated and described, but also includes all embodiments that provide an effect equal to that intended by the present invention. Furthermore, the scope of the present invention is not limited to the combination of the features of the invention defined by each claim, but includes any desired combination of the specific features of all the disclosed features.

10 ... Computer 11 ... Stimulation presentation unit 12 ... Signal separation unit 13 ... Feature amount calculation unit 14 ... Stimulation feature amount storage unit 15 ... Mutual information amount calculation unit 16 ... Feature amount selection unit 17 ... User state estimation unit 18 ... Display unit 19 ... EEG measurement unit 20 ... EEG estimation database 21 ... Ground electrode 22 ... EEG electrode 24 ... Amplifier 25 ... AD converter

Claims (14)

It is an electroencephalogram signal processing system that obtains the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus.
A feature amount calculation unit for obtaining a plurality of the brain wave feature amounts of the brain wave signal corresponding to the stimulus, and a feature amount calculation unit.
For each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features, a degree of interrelationship calculation unit for calculating the degree of interrelationship indicating the degree of relevance of the combination, and
A feature amount selection unit that extracts a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold value and selects the brain wave feature amount having a high relevance to the stimulus feature amount. When,
It is provided with a signal separation unit that separates the electroencephalogram signal into component signals having the characteristics of a plurality of series of electroencephalograms.
An electroencephalogram signal processing system characterized in that the feature amount calculation unit calculates the brain wave feature amount from the component signal. It is an electroencephalogram signal processing system that obtains the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus.
A feature amount calculation unit that obtains a plurality of the electroencephalogram feature amounts based on the frequencies of the electroencephalogram signals emitted by each of the signal sources in the brain in response to each of the stimuli.
For each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features, a degree of interrelationship calculation unit for calculating the degree of interrelationship indicating the degree of relevance of the combination, and
A feature amount selection unit that extracts a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold value and selects the brain wave feature amount having a high relevance to the stimulus feature amount. An electroencephalogram signal processing system characterized by being equipped with. Among the EEG features, which are the features of the EEG signal generated in response to a given stimulus, the EEG that selects the EEG features that are highly relevant to each of the Stimulus features, which are the features of the stimulus. It ’s a signal processing system,
A feature amount calculation unit for obtaining a plurality of the brain wave feature amounts of the brain wave signal corresponding to the stimulus, and a feature amount calculation unit.
For each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features, a degree of interrelationship calculation unit for calculating the degree of interrelationship indicating the degree of relevance of the combination, and
A feature amount selection unit that extracts a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold value and selects the brain wave feature amount having a high relevance to the stimulus feature amount. With and
Of the plurality of electroencephalogram features, at least two or more of the electroencephalogram features are units of different types from each other.
EEG signal processing system comprising a call. The electroencephalogram signal processing system according to any one of claims 1 to 3, wherein a mutual information amount is used as the degree of interrelationship. The electroencephalogram signal processing system according to any one of claims 1 to 3, wherein a correlation coefficient is used as the degree of interrelationship. It also has a stimulus presentation unit that presents the stimulus to the user.
The electroencephalogram signal processing system according to any one of claims 1 to 5, wherein the stimulus presenting unit presents the stimulus having a different type of stimulus feature amount to the user. With an additional EEG estimation database
The electroencephalogram feature amount selected by the feature amount selection unit with respect to the stimulus feature amount and having a high relevance to the stimulus feature amount is written and stored in the electroencephalogram estimation database as a set with the stimulus feature amount. The electroencephalogram signal processing system according to any one of claims 1 to 6, wherein the electroencephalogram signal processing system is characterized. When the brain wave feature amount of the brain wave signal is supplied, the stimulus feature amount corresponding to the brain wave feature amount is extracted from the brain wave estimation database, and a user state estimation unit that estimates the stimulus feature amount of the stimulus is further added. The electroencephalogram signal processing system according to claim 7, further comprising. It is an electroencephalogram signal processing method for obtaining the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus.
It is an electroencephalogram signal processing method for obtaining the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus.
A feature amount calculation process in which the feature amount calculation unit obtains a plurality of the brain wave feature amounts of the brain wave signal corresponding to the stimulus, and a feature amount calculation process.
The interrelationship calculation unit calculates the degree of interrelationship indicating the degree of association of the combination for each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features. Interrelationship calculation process and
The feature amount selection unit extracts a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold value, and obtains the brain wave feature amount which is highly related to the stimulus feature amount. Feature selection process to be selected and
The signal separation unit includes a signal separation process of separating the brain wave signal into component signals having the characteristics of a plurality of series of brain waves.
An electroencephalogram signal processing method characterized in that the feature amount calculation unit calculates the brain wave feature amount from the component signal. It is an electroencephalogram signal processing method for obtaining the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus.
A feature amount calculation process in which the feature amount calculation unit obtains a plurality of the brain wave feature amounts based on the frequencies of the brain wave signals emitted by each of the signal sources in the brain in response to each of the stimuli.
The interrelationship calculation unit calculates the degree of interrelationship indicating the degree of association of the combination for each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features. Interrelationship calculation process and
The feature amount selection unit extracts a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold, and obtains the brain wave feature amount having a high relevance to the stimulus feature amount. An electroencephalogram signal processing method characterized by including a feature selection process to be selected. Among the EEG features, which are the features of the EEG signal generated in response to a given stimulus, the EEG that selects the EEG features that are highly relevant to each of the Stimulus features, which are the features of the stimulus. It is a signal processing method
A feature amount calculation process in which the feature amount calculation unit obtains a plurality of the brain wave feature amounts of the brain wave signal corresponding to the stimulus, and a feature amount calculation process.
The interrelationship calculation unit calculates the degree of interrelationship indicating the degree of association of the combination for each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features. Interrelationship calculation process and
The feature amount selection unit extracts a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold value, and obtains the brain wave feature amount which is highly related to the stimulus feature amount. Including the feature selection process to be selected
Of the plurality of electroencephalogram features, at least two or more of the electroencephalogram features are units of different types from each other.
Electroencephalogram signal processing method characterized by and this. It is a program for finding the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus.
Computer,
A feature amount calculation means for obtaining a plurality of the electroencephalogram feature amounts of the electroencephalogram signal corresponding to the stimulus,
A means for calculating the degree of interrelationship, which calculates the degree of interrelationship indicating the degree of relevance of the combination for each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features.
A feature amount selection means for extracting a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold value and selecting the brain wave feature amount having a high relevance to the stimulus feature amount. ,
It is operated as a signal separation means for separating the electroencephalogram signal into component signals having the characteristics of a plurality of series of electroencephalograms.
A program in which the signal separation means separates the electroencephalogram signal into component signals having the characteristics of a plurality of series of electroencephalograms. It is a program for finding the relationship between the electroencephalogram feature amount, which is the feature amount of the electroencephalogram signal generated in response to a given stimulus, and the stimulus feature amount, which is the feature amount of the stimulus.
Computer,
A feature amount calculation means for obtaining a plurality of the electroencephalogram feature amounts based on the frequencies of the electroencephalogram signals emitted by each of the intracerebral signal sources in response to each of the stimuli.
A means for calculating the degree of interrelationship, which calculates the degree of interrelationship indicating the degree of relevance of the combination for each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features.
A feature amount selection means for extracting a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold value and selecting the brain wave feature amount having a high relevance to the stimulus feature amount. A program to operate as. To select the electroencephalogram feature that is highly relevant to each of the stimulus features that are the stimulus features, among the electroencephalogram features that are the features of the electroencephalogram signal generated in response to the given stimulus. Program
Computer,
A feature amount calculation means for obtaining a plurality of the electroencephalogram feature amounts of the electroencephalogram signal corresponding to the stimulus,
A means for calculating the degree of interrelationship, which calculates the degree of interrelationship indicating the degree of relevance of the combination for each combination of one or more of the stimulus features of the stimulus and each of the plurality of electroencephalogram features.
A feature amount selection means for extracting a combination of the stimulus feature amount and the brain wave feature amount whose degree of interrelationship exceeds a predetermined threshold value and selecting the brain wave feature amount having a high relevance to the stimulus feature amount. To operate as
A program in which at least two or more of the plurality of electroencephalogram features are units of different types.

Images