KR20160001081A - Group emotion analysis platform and method based on electroencephalogram, and recording medium for performing the method - Google Patents

Abstract

A group emotion analysis apparatus based on a brain wave comprises: a brain wave data collecting unit which receives brain wave data from multiple brain wave measuring devices; a data processing unit which processes the brain wave data; an analysis unit which classifies the processed brain wave data by each emotion by using a group emotion classification algorithm; and an interface unit which utilizes the classification result of the analysis unit and provides an interface for controlling the brain wave data collecting unit, the brain wave data processing unit, and the analysis unit. Accordingly, it is possible to accurately analyze emotion of a group by using brain waves.

Description

TECHNICAL FIELD [0001] The present invention relates to a group emotion analysis apparatus, a method, and a recording medium for performing the same. [0002] The present invention relates to a group emotion analyzing apparatus,

The present invention relates to an apparatus and method for analyzing a cluster emotion based on EEG, and a recording medium for performing the method. More particularly, the present invention relates to a cluster emotion analyzing apparatus and method for analyzing common emotions An analysis apparatus, a method, and a recording medium for performing the same.

Electroencephalogram (EEG) is an electrical signal that can be measured on a person's scalp and classified into delta wave, set wave, alpha wave, beta wave, and gamma wave depending on the frequency band and the amplitude of the voltage. Electroencephalogram (EEG) technology is currently being used for medical, academic, and commercial purposes as a technique for analyzing brain waves. EEG is a technology for recording electrical signals generated by the action of neurons in the human brain. From a medical point of view, EEG means recording the spontaneous electrical activity of the brain in a short time. Such an EEG detects electrical signals from a plurality of electrodes that normally contact the human head.

EEG can be measured in real time and is generated from the brain without any action, so research is being conducted to use it as a computer interface. These research fields are called BCI (Brain Computer Interface). In addition, each EEG exhibits different wavelengths depending on the state of the body and mental state, so it is used for medical or research purposes.

There are two methods of measuring brain waves: invasive and noninvasive. In the invasive method, the microchip is applied to the scalp and the EEG is measured. Although accurate measurement is possible, the procedure is necessary and there may be a surgical side effect. The noninvasive method is a method of measuring EEG with a helmet or a headset type device. However, it is simple but has a low accuracy because it is measured with noise.

In general, non-invasive methods, which do not require surgical procedures, are being used to utilize EEG, and studies are in progress to remove the inevitable noise from noninvasive methods.

There are two types of EEG using EEG and EEG according to the characteristics of EEG. The brain wave induction method induces the appearance of a specific EEG, and training is necessary to generate a specific EEG because the user's actual intention and the appearance of EEG do not coincide with each other. Research is underway to utilize this EEG as an input interface for games, computers, or robots.

EEG is a way of analyzing human brain waves as it is and transferring them to computers or machines. Anesthesia depth meter is an example of this method that confirms the state of anesthesia by comparing EEG differences before and after anesthesia. Research is also underway to analyze the interaction between people and people at the brain level, to measure concentration, attention, sleep level, and emotion using human brain waves.

However, studies on individuals and research on 1: 1 interaction between humans and humans have been conducted, such as using brain waves or analyzing brain waves to identify human conditions. However, 1: n or n: n No studies have been conducted to collect a large number of brain waves and to measure a common response to a specific object or environment or compare them to a large number of subjects.

KR 2002-0015547 A KR 10-1345216 B1

SUMMARY OF THE INVENTION Accordingly, the present invention has been made in view of the above problems, and it is an object of the present invention to provide a cluster emotion analyzing apparatus for analyzing common emotions due to environments or objects by measuring EEG for a cluster.

Another object of the present invention is to provide a cluster emotion analysis method for analyzing EEG on a cluster to analyze common emotions due to the environment or object.

It is still another object of the present invention to provide a recording medium for performing the cluster emotion analysis method.

According to an embodiment of the present invention, there is provided an apparatus for analyzing a cluster emotion based on brain waves, comprising: an EEG data collecting unit for receiving EEG data from a plurality of EEG analyzers; An EEG data processing unit for processing the EEG data; An analyzer for classifying the processed EEG data for each emotion using a cluster emotion classification algorithm; And an interface unit for providing the interface for controlling the brain wave data collecting unit, the brain wave data processing unit, and the analyzing unit, utilizing the results classified by the analyzing unit.

In the embodiment of the present invention, the cluster sensory classification algorithm can provide a classification function for brain wave data input through the learned algorithm after machine learning using the collected brain wave data as training data.

In an embodiment of the present invention, the apparatus may further include a storage unit for storing the brain wave data in a database.

In an embodiment of the present invention, the EEG data may further include a privacy protection unit for protecting personal information from being exposed to a third party or an unauthorized person.

In an embodiment of the present invention, the EEG data processing unit may include: a filtering unit that removes noise of the EEG data; And an effective EEG detecting unit for detecting an effective EEG region necessary for emotional classification of the EEG data.

According to another aspect of the present invention, there is provided a method for analyzing cluster emotion based on brain waves, comprising the steps of: collecting EEG data from a plurality of EEGs; Processing the EEG data; Classifying the processed EEG data by each emotion using a cluster emotion classification algorithm; And providing an interface for utilizing and controlling the classified results of the EEG data.

According to an embodiment of the present invention, classifying the processed EEG data by each emotion using a cluster emotion classification algorithm comprises: performing machine learning using collected EEG data as training data; And classifying the EEG data inputted through the learned algorithm.

In an embodiment of the present invention, the cluster emotion analysis method based on the EEG may further include protecting personal information so that the EEG data is not exposed to a third party or an unauthorized person.

In an embodiment of the present invention, the step of processing the brain wave data includes filtering the brain wave data to remove noise; And detecting an effective EEG region necessary for emotional classification in the EEG data.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing a computer program for performing a cluster emotion analysis method based on the brain waves described above.

According to the present invention, a plurality of brain wave data can be collected to analyze and compare brain wave data of 1: n or n: n, and it is possible to confirm general emotions appearing in a situation facing a specific group or a focused object have. In addition, it is possible to identify a more subtle emotion than observing facial expressions in a group of people with limited expressive power or difficulty in expressing their opinions, such as elderly people, preschoolers, and people with physical disabilities. Furthermore, it can help identify and solve social problems related to such groups, and can be applied to the brain computer interface (BCI) field.

1 is a block diagram of a cluster emotion analyzing apparatus based on EEG according to an embodiment of the present invention.
2 is a block diagram of a cluster emotion analyzing apparatus based on EEG according to another embodiment of the present invention.
3 is a block diagram of an EEG data processing unit.
4 is a block diagram of an apparatus for analyzing a cluster emotion based on EEG according to another embodiment of the present invention.
5 is a conceptual view of the platform of the cluster emotion analysis software.
Figure 6 is an internal data flow diagram of the platform of Figure 5;
7 is a flowchart illustrating a method of analyzing cluster emotion based on EEG according to another embodiment of the present invention.
8 is a flowchart of steps of processing brain wave data of FIG.
9 is a flowchart of a step of analyzing brain wave data using the cluster sensibility classification algorithm of FIG.

The following detailed description of the invention refers to the accompanying drawings, which illustrate, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different, but need not be mutually exclusive. For example, certain features, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in connection with an embodiment. It is also to be understood that the position or arrangement of the individual components within each disclosed embodiment may be varied without departing from the spirit and scope of the invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is to be limited only by the appended claims, along with the full scope of equivalents to which such claims are entitled, if properly explained. In the drawings, like reference numerals refer to the same or similar functions throughout the several views.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings.

1 is a block diagram of a cluster emotion analyzing apparatus based on EEG according to an embodiment of the present invention. 2 is a block diagram of a cluster emotion analyzing apparatus based on EEG according to another embodiment of the present invention. 3 is a block diagram of an EEG data processing unit. 4 is a block diagram of an apparatus for analyzing a cluster emotion based on EEG according to another embodiment of the present invention.

Referring to FIG. 1, a cluster emotion analyzing apparatus 10 (hereinafter referred to as a device) based on EEG according to the present embodiment includes an EEG data collecting unit 110, an EEG data processing unit 130, an analyzing unit 150, (170).

In the present invention, crowd refers to a large number of people having a common point. Also, the term "cluster emotion" means the emotion such as sadness, joy, anger, etc. commonly felt by a group obtained from the community.

The device 10 of the present invention may be a platform configured to perform cluster emotion analysis based on brain waves, and may be a computer system on which hardware or software or an application program on which a computer system is based may be executed. For example, the device 10 may comprise an operating system, an auxiliary program for a computer system, and a microprocessor, a microchip (IC) that performs logic operations and directs data movement within the computer.

Alternatively, software (application) for performing cluster emotion analysis based on brain waves may be installed and executed. The configuration of the brain wave data collection unit 110 and the like may be controlled by software executed in the apparatus 10 .

The device 10 may be a separate device or some module of the terminal. The device 10 may be fixed or mobile and may be in the form of a server or an engine and may be a device, an apparatus, a terminal, a user equipment (UE) a mobile station, an MT, a user terminal (UT), a subscriber station (SS), a wireless device, a personal digital assistant (PDA), a wireless modem, a handheld device, And so on.

The EEG data collecting unit 110 collects a large number of EEGs in the form of 1: n or n: n, measures a common reaction to a specific object or environment, compares EEG data from a plurality of EEG data, . The EEG data collecting unit 110 performs data communication with the plurality of brain wave measuring devices by wire or wirelessly.

For example, the plurality of electroencephalographs may measure a specific group of electroencephalograms in a non-invasive manner, and may transmit the measured electroencephalogram data to the electroencephalogram data collection unit 110 in real time.

Referring to FIG. 2, the apparatus 10 may further include a storage unit 120 for managing the brain wave data received from the brain wave data collection unit 110.

The storage unit 120 may store the brain wave data in a database and transmit the brain wave data to the brain wave data processor 130. The storage unit 120 stores and manages the brain wave data processed by the brain wave data processor 130 and the analysis result of the analysis unit 150 in a database.

The brain wave data processor 130 processes the brain wave data into valid data before analyzing the brain wave data. 3, the EEG data processing unit 130 may include a filtering unit 131 and a EEG detecting unit 133.

The filtering unit 131 may include a noise canceling filter for improving the interoperability of brain wave data and cluster emotion classification. For example, the filtering unit 131 may include a full-wave rectification filter or a low-pass filter to remove noise of the EEG data. The effective EEG detector 133 detects an effective EEG area required for emotional classification of the EEG data.

The analyzer 150 classifies the brain wave data processed in the brain wave data processor 130 by each emotion using a cluster emotion classification algorithm. The cluster sensibility classification algorithm provides a classification function for brain wave data input through the learned algorithm after machine learning using collected EEG data as training data.

For example, the algorithm may be an analytical model having specific parameters and weights. In this case, the analysis unit 150 may generate the analysis model through repeated experiments.

The interface unit 170 utilizes the result output from the analysis unit 150 and provides an interface for overall platform control. Specifically, the interface unit 170 includes an API (Application Program Interface) for utilizing results classified by the analysis unit 150 and an API (Application Program Interface) for using the results of the brain wave data collection unit 110, the brain wave data processing unit 130, An API for controlling the analysis unit 150 may be provided.

The user can monitor the EEG data currently collected through the interface unit 170 and control the EEG data collecting unit 110, the EEG data processing unit 130 and the analysis unit 150 .

Referring to FIG. 4, the apparatus 10 may further include a privacy protection unit 140. FIG. The privacy protection unit 140 may protect personal information such that the brain wave data is not exposed to a third party or an unauthorized person during transmission and reception of brain wave data. In particular, the privacy protection unit 140 may function when a user accesses brain wave data through the interface.

5 is a conceptual view of the platform of the cluster emotion analysis software. Figure 6 is an internal data flow diagram of the platform of Figure 5;

Referring to FIG. 5, an example of the configuration of the platform 12 of the cluster emotion analysis software includes a module 210 for data communication with a plurality of brain wave measuring instruments, a module 220 for storing and utilizing database and EEG data, A module 240 for providing a personal information protection function between the transmission and reception, a valid EEP region detection module 233 for sensing the community in EEG data, a noise cancellation filter module 231 for improving the interoperability of EEG data and cluster emotion classification, A cluster sensibility classification algorithm module 250, and an interface 270 for utilization of analysis results and platform control.

Referring to FIG. 6, EEG data are received from a plurality of external EEPGs through the module 210, and the EEPROM is output to the module 220. The module 220 stores and manages brain wave data through the database 20, removes noise of brain wave data through the module 231, and detects the effective EEG region through the module 233. [ The detected effective brain wave data is subjected to a cluster emotion classification algorithm in the module 250 and can be utilized through the interface 270. [

Thus, it is possible to analyze and compare EEG data of 1: n or n: n by collecting a large number of brain wave data beyond the use of brain waves for an individual, You can see general emotions.

For example, it is possible to identify more subtle emotions than observing facial expressions in groups such as elderly people, preschoolers, and people with physical disabilities who lack expressive power or difficulty in expressing their opinions. Furthermore, it can help identify and solve social problems related to such groups. The more research subjects or analysis about EEG, the more accurate the accuracy of EEG will be, so the accumulated EEG can be used for various research or new services.

7 is a flowchart illustrating a method of analyzing cluster emotion based on EEG according to another embodiment of the present invention. 8 is a flowchart of steps of processing brain wave data of FIG. 9 is a flowchart of a step of analyzing brain wave data using the cluster sensibility classification algorithm of FIG.

The cluster sensibility analysis method based on the EEG according to the present embodiment can be performed in substantially the same configuration as the apparatus 10 of FIG. Therefore, the same constituent elements as those of the apparatus 10 of FIG. 1 are denoted by the same reference numerals, and repeated description is omitted.

Referring to FIG. 7, the cluster emotion analysis method based on the EEG according to the present embodiment collects brain wave data from a plurality of brain wave measuring devices (step S10). The plurality of brain wave measuring devices can transmit measured EEG data in real time. The brain wave data can be stored and managed in a database and utilized.

The brain wave data is processed for analysis (step S30).

Referring to FIG. 8, the step of processing the brain wave data (step S30) includes filtering the brain wave data to remove noises (step S31) and detecting the effective EEG area necessary for emotion classification in the brain wave data (Step S33). The brain wave data processed through the step S31 or the step S33 can also be stored and managed and utilized in the database.

The processed EEG data is classified by each emotion using a cluster emotion classification algorithm (step S50).

Referring to FIG. 9, the step of classifying the processed EEG data by each emotion using a cluster emotion classification algorithm (step S50) includes a step of performing machine learning using collected EEG data as training data (step S51) And classifying the EEG data inputted through the learned algorithm (step S53).

In addition, an interface for utilizing and controlling the classified result of the brain wave data can be provided (step S70). The user can monitor the currently collected EEG data through the interface unit, utilize the analyzed result, and control the respective steps.

The cluster emotion analysis method based on EEG according to the present invention can protect personal information so that the EEG data is not exposed to a third party or unauthorized person between the transmission and reception of EEG data.

The cluster emotion analysis method based on the EEG described above according to the present invention can be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, and the like, alone or in combination.

The program instructions recorded on the computer-readable recording medium may be ones that are specially designed and configured for the present invention and are known and available to those skilled in the art of computer software.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

Examples of program instructions include machine language code such as those generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules for performing the processing according to the present invention, and vice versa.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the present invention as defined by the following claims. You will understand.

The apparatus and method for analyzing cluster emotion based on EEG according to the present invention can analyze and compare brain wave data of 1: n or n: n by collecting a plurality of brain wave data, You can identify the general emotions that are presented by the situation you are facing or the person you are concentrating on.

For example, it is possible to identify more subtle emotions than observing facial expressions in groups such as elderly people, preschoolers, and people with physical disabilities who lack expressive power or difficulty in expressing their opinions. Furthermore, it can help identify and solve social problems related to such groups.

Since the accuracy of the study or analysis of brain waves increases with the number of subjects, the accumulated brain waves can be used for various studies or new services.

10: Cluster sensibility analyzer 110: EEG data collecting unit
120: storage unit 130: brain wave data processing unit
140: Privacy Protection Unit 150: Analysis Unit
170: interface unit 131: filtering unit
133: EEG detecting unit
12: Platform of cluster emotion analysis software

Claims (10)

An EEG data collection unit for receiving EEG data from a plurality of EEG meters;
An EEG data processing unit for processing the EEG data;
An analyzer for classifying the processed EEG data for each emotion using a cluster emotion classification algorithm; And
And an interface unit for providing an interface for controlling the brain wave data collecting unit, the brain wave data processing unit, and the analyzing unit using the results classified by the analyzing unit.
2. The method of claim 1,
A cluster emotion analyzing device based on EEG, which provides machine learning function using collected EEG data as training data and classifying function of EEG data inputted through learned algorithm.
The method according to claim 1,
And a storage unit for storing the brain wave data in a database.
The method according to claim 1,
And a privacy protection unit for protecting personal information so that the brain wave data is not exposed to a third party or an unauthorized person.
The apparatus according to claim 1, wherein the brain-
A filtering unit for removing noise of the brain wave data; And
And an effective EEG detecting unit for detecting an EEG region necessary for emotional classification of the brain wave data.
Collecting brain wave data from a plurality of brain wave measuring devices;
Processing the EEG data;
Classifying the processed EEG data by each emotion using a cluster emotion classification algorithm; And
And providing an interface for utilizing and controlling the classified result of the brain wave data.
The method of claim 6, wherein classifying the processed EEG data by each emotion using a cluster emotion classification algorithm comprises:
Performing machine learning using collected EEG data as training data; And
And classifying the EEG data inputted through the learned algorithm.
The method according to claim 6,
And protecting personal information so that the brain wave data is not exposed to a third party or an unauthorized person.
7. The method of claim 6, wherein the step of processing the brain wave data comprises:
Filtering the EEG data to remove noise; And
And detecting an effective EEG region necessary for emotional classification of the brain wave data.
A computer-readable recording medium on which a computer program is recorded, for performing a cluster emotion analysis method based on brain waves according to any one of claims 6 to 9.

Images