JP7558749B2 - Determination device and program - Google Patents

Description

This disclosure relates to a determination device and a program.

Conventionally, the state of a subject has been judged using the brain waves measured from the subject. For example, an evaluation device has been proposed that evaluates a person's sensibility using brain waves obtained from the person (see, for example, Patent Document 1).

JP 2019-202031 A

However, it is common for brain waves obtained from subjects who have experienced the same event to differ from subject to subject. For this reason, it is difficult to simply determine from brain waves whether or not a particular event has been experienced. On the other hand, if it were possible to determine whether or not a particular event can be classified using brain waves, it would be useful in observing the trends in brain waves for particular events. Furthermore, if the trends in brain waves could be used, it would be possible, for example, to build an AI model that determines events using brain waves.

The present invention was made in consideration of the above-mentioned conventional situation, and aims to provide a determination device and program that can easily determine the tendency of the electroencephalogram of a subject who has experienced a specific event.

The present invention relates to a determination device that determines whether or not two events can be classified based on the electroencephalograms of a subject who has experienced two events, and that includes an electroencephalogram data acquisition unit that acquires the electroencephalogram data of the subject, a classification unit that attempts to classify the two events using the acquired electroencephalogram data, and a determination unit that determines whether or not the characteristics of the acquired electroencephalograms can be classified for each of the events based on the attempted classification results.

It is also preferable that the determination device further includes an identification unit that identifies the electroencephalographic features that contributed to the classification of the subject who can be classified.

It is also preferable that the determination unit determines whether or not there are characteristics common to the multiple subjects based on the brain wave characteristics identified for the multiple subjects.

The present invention also relates to a program for operating a computer as a determination device that determines whether or not two events can be classified based on the electroencephalograms of a subject who has experienced two events, and causes the computer to function as an electroencephalogram data acquisition unit that acquires the electroencephalogram data of the subject, a classification unit that attempts to classify the two events using the acquired electroencephalogram data, and a determination unit that determines whether or not the characteristics of the acquired electroencephalograms can be classified for each of the events based on the attempted classification results.

The present disclosure provides a determination device and program that can easily determine the electroencephalographic trends of a subject who has experienced a specific event.

1 is a schematic diagram showing an acquisition mode of electroencephalogram data determined by a determination device according to a first embodiment of the present invention. FIG. 1 is a block diagram showing a configuration of a determination device according to a first embodiment; 4 is a graph showing electroencephalogram data acquired by the electroencephalogram data acquisition section of the determination device of the first embodiment. 4 is a table showing the contents of each feature amount generated by a feature amount generating unit of the determination device of the first embodiment. 4 is a graph showing a feature amount with respect to frequency created by a feature amount creating unit of the determination device of the first embodiment. 4 is a table showing results of determination made by a determination unit of the determination device of the first embodiment. 4 is a graph showing a feature amount identified by a identifying unit of the determination device of the first embodiment. Fig. 2 is a flowchart showing the operation of the determination device according to the first embodiment Fig. 3 is a block diagram showing the configuration of a determination device according to a second embodiment of the present invention. FIG. 11 is a block diagram showing a configuration of a determination device according to a second embodiment of the present invention. 10 is a flowchart showing a flow of an operation regarding classification of a determination device according to a second embodiment.

Hereinafter, a determination device 1 and a program according to each embodiment of the present invention will be described with reference to FIGS.
First, an overview of the determination device 1 and the program according to each embodiment will be described.

The determination device 1 is a device that determines whether events experienced by subject P can be classified using electroencephalograms. For example, the determination device 1 is a device that determines whether two events experienced by subject P can be classified using electroencephalograms. In other words, the determination device 1 is a device that determines whether a difference can be detected between the electroencephalograms corresponding to the two events.

As shown in FIG. 1, the determination device 1 shows an example in which mental arithmetic is performed as the first event. In addition, in each of the following embodiments, an example in which a Stroop test is performed as the second event is shown.

[First embodiment]
Next, a determination device 1 and a program according to a first embodiment of the present invention will be described with reference to FIGS.
The determination device 1 is a device that determines whether or not two events can be classified based on electroencephalograms of each event of a subject P who experienced two events. As shown in FIG. 1 , the determination device 1 includes an electroencephalogram data acquisition unit 11, an electroencephalogram data storage unit 12, a feature amount generation unit 13, a classification unit 14, a determination unit 15, an identification unit 16, and an output unit 17.

The brainwave data acquisition unit 11 is realized, for example, by the operation of a CPU. The brainwave data acquisition unit 11 acquires brainwave data of the subject P. The brainwave data acquisition unit 11 acquires, for example, two pieces of brainwave data for each subject P. The brainwave data acquisition unit 11 acquires, for example, brainwave data as shown in FIG. 2. The brainwave data acquisition unit 11 also acquires identification information indicating the correspondence between the two brainwaves and the event. The brainwave data acquisition unit 11 acquires, for example, the time when the event was experienced as the identification information. The brainwave data acquisition unit 11 also acquires, for example, the gender of the subject P, the number of attempts of the event, age, etc. as the identification information.

The brainwave data storage unit 12 is, for example, a storage medium such as a hard disk. The brainwave data storage unit 12 stores the acquired brainwave data. The brainwave data storage unit 12 also stores the acquired identification information in association with the brainwave data.

The feature generating unit 13 is realized, for example, by the operation of a CPU. The feature generating unit 13 generates feature amounts based on the acquired brain waves. For example, as shown in FIG. 4, the feature generating unit 13 generates feature amounts for each of the items of gamma waves, high-beta waves, low-beta waves, high-alpha waves, mid-alpha waves, low-alpha waves, theta waves, PGV, Elapse, Cycle, Sex, and Gen. For each item from gamma waves to theta waves, the feature generating unit 13 generates a graph classified by frequency as shown in FIG. 5 as a feature amount. For example, the feature generating unit 13 generates multiple feature amounts at a predetermined time during the experience of an event (for example, an interval of 2 seconds with 1 second overlap). The feature generating unit 13 also generates multiple feature amounts by repeating two events multiple times.

The classification unit 14 is realized, for example, by the operation of a CPU. The classification unit 14 attempts to classify two events using the acquired electroencephalogram data. The classification unit 14 classifies the difference in the electroencephalogram data between the two events, for example, by arbitrarily weighting the generated feature amounts. The classification unit 14, for example, weights the importance of feature amounts that are thought to relatively well indicate differences in electroencephalograms. By weighting the feature amounts, the classification unit 14 makes modifications to make the difference between the two electroencephalogram data more apparent.

The determination unit 15 is realized, for example, by the operation of a CPU. The determination unit 15 determines whether the acquired electroencephalogram features can be classified for each event for the attempted classification results. For example, as shown in FIG. 6, the determination unit 15 predicts which event each of the two events is for the generated multiple feature amounts and determines whether the prediction is correct or not. For example, when the feature amount of mental arithmetic, which is the classification result, matches the mental arithmetic event, the determination unit 15 determines that the predicted value and the actual value match for mental arithmetic. On the other hand, when the feature amount of the Stroop test, which is the classification result, matches the Stroop test event, the determination unit 15 determines that the predicted value and the actual value match for the Stroop test. When the feature amount determined to match as a result of the determination of all feature amounts is greater than a predetermined threshold, the determination unit 15 determines that classification is possible. For example, the determination unit 15 may output from a comparison between the actual value and the predicted value.

The identification unit 16 is realized, for example, by the operation of a CPU. The identification unit 16 identifies the electroencephalogram features that contributed to the classification of a classifiable subject P. For example, with respect to the features shown in FIG. 4, the identification unit 16 identifies the features that were actually weighted as shown in FIG. 7.

The output unit 17 is realized, for example, by the operation of the CPU. The output unit 17 outputs the determination result to an output device such as a display or a printer. The output unit 17 also outputs the identified feature amount.

Next, the operation of the determination device 1 will be described with reference to the flowchart of FIG.
First, the electroencephalogram data acquisition section 11 acquires an electroencephalogram (step S1). Next, the feature generation section 13 generates features (step S2). Next, the classification section 14 classifies the features (step S3).

Next, the determination unit 15 determines whether classification is possible (step S4). If classification is possible (step S4: YES), the process proceeds to step S5. On the other hand, if classification is not possible (step S5: NO), the process proceeds to step S8.

In step S5, the determination unit 15 determines that classification is possible. Next, the identification unit 16 identifies the features that contributed to the classification (step S6). Next, the output unit 17 outputs the classification result and the identified features (step S7). This ends the processing according to this flow.

In step S8, the determination unit 15 determines that classification is not possible. Processing proceeds to step S7.

Next, the program will be described.
Each component included in the determination device 1 can be realized by hardware, software, or a combination of these. Here, being realized by software means being realized by a computer reading and executing a program.

The program can be stored and supplied to the computer using various types of non-transitory computer readable media. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R/Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (random access memories)). The display program may also be supplied to the computer by various types of transitory computer readable media. Examples of transitory computer readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer readable media can supply the program to the computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths.

As described above, the determination device 1 and the program according to the present embodiment provide the following advantages.
(1) A judgment device 1 that judges whether or not two events can be classified based on the electroencephalograms of a subject P who has experienced two events, and includes an electroencephalogram data acquisition unit 11 that acquires electroencephalogram data of the subject P, a classification unit 14 that attempts to classify the two events using the acquired electroencephalogram data, and a judgment unit 15 that judges whether or not the characteristics of the acquired electroencephalograms can be classified for each event based on the attempted classification results.
The program also causes a computer to operate as a judgment device 1 that judges whether or not two events can be classified based on the electroencephalograms of a subject P who has experienced two events, and causes the computer to function as an electroencephalogram data acquisition unit 11 that acquires electroencephalogram data from the subject P, a classification unit 14 that attempts to classify the two events using the acquired electroencephalogram data, and a judgment unit 15 that judges whether or not the characteristics of the acquired electroencephalograms can be classified for each event based on the attempted classification results.
This makes it easy to determine the tendency of the brain waves of a subject P who has experienced a particular event. It also makes it easy to determine a subject P who is interested in two events. For example, for a subject P who is not very interested in two events, there may not be a big difference between the experiences of the two events. In this case, it is easy to determine that no big difference appears in the brain waves and that the classification of the brain waves cannot be determined. On the other hand, if the opposite is true, it is easy to determine that the subject P is interested by determining the difference in the brain waves for each of the two events.
(2) The determination device 1 further includes an identification unit 16 that identifies electroencephalogram features that contributed to the classification of the classifiable subject P. This makes it possible to easily recognize the feature amounts that contributed to the classification of electroencephalograms that were actually classified in the classification attempted by the classification unit 14.

[Second embodiment]
Next, a determination device 1 and a program according to a second embodiment of the present invention will be described with reference to Fig. 9 and Fig. 10. In describing the second embodiment, the same components as those in the above-described embodiment are denoted by the same reference numerals, and descriptions thereof will be omitted or simplified.

The determination device 1 and the program according to the second embodiment determine whether or not a plurality of subjects P among the subjects P determined by the determination unit 15 to be classifiable can be classified.
As shown in FIG. 9, the determination device 1 according to the second embodiment differs from the first embodiment in that it further includes an extraction unit 18.

The extraction unit 18 is realized, for example, by the operation of a CPU. The extraction unit 18 extracts EEG data for the subject P who has been determined to be classifiable with respect to two events. The extraction unit 18 extracts, for example, EEG data that has been determined to be classifiable from among the EEG data stored in the EEG data storage unit 12.

The determination unit 15 determines whether or not there are common characteristics among the multiple subjects P based on the brain wave characteristics identified for the multiple subjects P. The determination unit 15 determines, for example, whether or not there are common characteristics among the characteristics identified for the multiple subjects P.

Next, the classification operation of the determination device 1 will be described with reference to the flowchart of FIG.
First, the extraction unit 18 extracts an electroencephalogram (step S11). Next, the determination unit 15 determines whether or not there is a common feature (step S12). If there is a common feature (step S12: YES), the process proceeds to step S13. On the other hand, if there is no common feature (step S12: NO), the process proceeds to step S15.

In step S13, the determination unit 15 determines that classification is possible. Next, the output unit 17 outputs the determination result (step S14). This ends the processing according to this flow.

In step S15, the determination unit 15 determines that classification is not possible. Then, the process proceeds to step S14.

As described above, the determination device 1 and the program according to the present embodiment provide the following advantages.
(3) The determination unit 15 determines whether or not there are common characteristics among the multiple subjects P based on the electroencephalogram characteristics identified for the multiple subjects P. This makes it easy to determine whether or not there are common characteristics among the multiple subjects P. For example, it becomes possible to extract characteristics that are generally seen in many subjects P for one event. On the other hand, conversely, when there are no common characteristics, it is possible to determine that although two events can be determined, there is diversity among the subjects P for one event.

Although the above describes preferred embodiments of the determination device and program of the present invention, the present disclosure is not limited to the above-described embodiments and can be modified as appropriate.

For example, in the first embodiment, the determination device 1 is described as having the identification unit 16, but this is not limited to this. The determination device 1 does not have to have the identification unit 16. The identification unit 16 may be provided separately from the determination device 1.

In addition, in each of the above embodiments, the determination device 1 can be used as a taste classification device, an olfactory classification device, etc. The determination device 1 can be used, for example, as an evaluation device for food, beverages, etc.

In addition, in the above embodiment, the brainwave data is not limited to time series data, and may be acquired as data converted into frequency data.

In addition, in the above embodiment, the determination device, for example, treats two types of sweets as two events and determines the brain waves. If subject P likes sweets, it is expected that he or she will be able to distinguish the difference in taste between the two types of sweets, and a difference will appear in the brain waves. On the other hand, if subject P does not like sweets, he or she may not be able to distinguish the difference in taste between the two types of sweets. The determination device 1 determines whether or not such differences in brain waves according to the preferences of subject P can be classified. This makes it possible to determine subject P's preferences.

In the above embodiment, the classification unit 14 may also attempt classification based on past classification. The classification unit 14 may also be executed by a device separate from the device operating as the determination unit. The classification unit 14 may create a classification method as separate data as a so-called prospective test. In addition, when the tendency of appearance of the characteristics of the EEG data relating to each of the two events is known in advance, the classification unit 14 may obtain information on the tendency of appearance and attempt to classify the EEG data based on the obtained tendency of appearance.

REFERENCE SIGNS LIST 1 Determination device 11 Electroencephalogram data acquisition unit 14 Classification unit 15 Determination unit 16 Identification unit P Subject

Claims (3)

A determination device that determines whether or not two events can be classified with respect to electroencephalograms for each event of a subject who has experienced two events, comprising:
an electroencephalogram data acquisition unit for acquiring electroencephalogram data of the subject;
A classification unit that attempts to classify the two events using the acquired electroencephalogram data;
a determination unit that determines whether the acquired electroencephalogram features are classifiable or unclassifiable for each of the events based on the attempted classification results;
An identification unit that identifies electroencephalogram features that contributed to the classification of the subject who can be classified,
When the determination unit determines that the acquired electroencephalogram features are classifiable, the identification unit identifies the electroencephalogram features that contributed to the classification, and when the determination unit determines that the acquired electroencephalogram features are unclassifiable, the determination unit outputs a message that the features are unclassifiable. The determination device according to claim 1 , wherein the determination unit determines whether or not the plurality of subjects have a common characteristic based on the electroencephalogram characteristics identified for the plurality of subjects. A program for operating a computer as a determination device for determining whether two events can be classified or not for an electroencephalogram of a subject who has experienced two events, the program comprising:
The computer,
an electroencephalogram data acquisition unit for acquiring electroencephalogram data of the subject;
a classification unit that attempts to classify the two events using the acquired electroencephalogram data;
a determination unit for determining whether the characteristics of the acquired electroencephalogram are classifiable or unclassifiable for each of the events based on the attempted classification results;
an identification unit that identifies electroencephalogram features that contributed to the classification of the subject that can be classified;
When the determination unit determines that the acquired electroencephalogram features are classifiable, the identification unit identifies the electroencephalogram features that contributed to the classification, and when the determination unit determines that the acquired electroencephalogram features are unclassifiable, the determination unit outputs a message that the features are unclassifiable.

Images