KR101518575B1 - Analysis method of user intention recognition for brain computer interface - Google Patents

Abstract

A user intent awareness analysis method for BCI is disclosed. The user's intentional cognitive analysis method comprises the steps of: converting user's brain wave data into a frequency signal and classifying a frequency region related to a kinesthetic sensation according to a band of the converted frequency signal; And detecting intention recognition of the user by analyzing characteristics of the user in the frequency domain based on the motor imagery of the user.

Description

METHOD OF USER INTENTION RECOGNITION FOR BRAIN COMPUTER INTERFACE < RTI ID = 0.0 >

Embodiments of the present invention relate to techniques for controlling electronic devices using human brain waves.

The brain is a control center that oversees the whole area of human activity. It recognizes that cerebral information function is expressed by neurons in the cerebral cortex, and it is composed of dynamic knowledge activities such as cognition and thinking, various senses, It is also known to be responsible for even.

Electroencephalogram (EEG) was recorded through an electrode attached to the scalp. Electroencephalogram (EEG) was recorded through an electrode attached to the scalp. The EEG had a frequency of 1 to 50 Hz and an amplitude of about 10 to 200 μV. The physiologist Hansberger Hans Berger). This electrical activity was later referred to as EEG and showed that the EEG changes with the mental state of the experimenter.

The factors that cause changes in EEG include individual differences, age, changes in conscious state, mental activity and perception stimulation, and physiological changes in the body. The brain is subdivided by its functions and has a specific pattern due to changes in brain waves from time to time depending on the state of consciousness and mental activity. For example, when a large number of alpha (alpha) waves occur, it is in a comfortable state, when eyes are closed, when concentrating or when thinking creatively, and when a large number of beta (beta) waves occur, When you are in a state, a conscious lifestyle, anxiety and tension, you are doing a normal job. In addition, when θ (Theta) waves occur, it is said to occur when sleepiness or deep meditation occurs. In addition, it is known that δ (Delta) waves occur in a state of arousal when they are normal persons, and it is known that there are pathological factors such as brain tumor and encephalitis.

It is based on the fact that the changes in the brain waves that appear when moving a part of the body are similar to those of imagining movement, and it is also called Sensorimotor Rhythms (SMR) or Motor Imagery. Use the imaginary movement of the relatively far left hand, right hand, foot or tongue.

On the other hand, in recent years, studies on human brain waves have been actively carried out in order to understand human judgment and emotion. Specifically, the brain waves reflect not only the motion of the muscles around the user's eyes but also human judgment and emotion. Thus, when the brain waves are measured, the measured brain waves are digitized, and then the human brain waves are measured again, the measured brain waves can be used to determine human judgment and emotion. In recent years, an experiment has been successful in inputting characters using only human brain waves. In another example, Korean Patent Laid-Open No. 10-2013-0005753 discloses a technique for generating a control signal corresponding to user's brain wave information and controlling the display device accordingly Lt; / RTI >

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to control an electronic device based on an intention of a user by using an EEG (Electroencephalogram) obtained by converting a user's brain wave into an electrical signal.

According to an embodiment of the present invention, a user's intent perception analysis method includes: obtaining user's brain wave data measured from an EEG (electroencephalogram) measurement device; And detecting a frequency region indicated by an event-related synchronization (ERS) which is a signal pattern increasing according to a user's motor imagery to determine intention recognition of the user .

According to an embodiment of the present invention, a user's intent perception analysis method includes: converting a user's brain wave data into a frequency signal and classifying a frequency region related to a kinesthetic sensation according to a band of the converted frequency signal; And detecting intention recognition of the user by analyzing characteristics of the user in the frequency domain based on the motor imagery of the user.

According to an aspect, the EEG data may be an EEG signal measured through electrodes of 14 channels attached to the user.

According to another aspect, the brain wave data may be an EEG signal measured by applying a sampling rate of 128SPS (2048 Hz).

According to another aspect, the electrode may be attached to 14 sites of the scalp according to the international standard 10-20 method.

According to another aspect, the step of classifying the frequency region related to the kinesthetic sensation may classify the 8-12 Hz region, which is the mu rhythm (μ) region of EEG.

According to another aspect of the present invention, the step of classifying the frequency region related to the kinesthetic sensation includes a step of classifying the frequency region of 8-12 Hz, which is a mu rhythm (μ) region of EEG using a digital notch filter (DNF) or a band pass filter Can be classified.

According to another aspect of the present invention, the step of detecting the intention of the user includes detecting an event-related synchronization (ERS), which is a pattern of signals increasing in a mu rhythm (mu) region occurring in a kinematic sensory cortex region of the brain, It is possible to confirm whether or not the user is intent.

According to another aspect of the present invention, the step of detecting the intention of the user includes the steps of: detecting EEG data in a mu rhythm area occurring in a kinetic sensory cortex region of the brain among the EEG data through STFT (Short-Time Fourier Transform) Performing a Fourier transform on the time domain; And using a Particle Swarm Optimization (PSO) algorithm to find a frequency of an optimal point having a maximum amplitude at an average amplitude of the mu rhythm ([mu]) region.

According to another aspect, performing the Fourier transform on the time domain comprises: detecting an event-related synchronization (ERS), which is a pattern of signals increasing in the mu rhythm area, The power spectrum of the ERS can be obtained using Equation (1).

Equation 1:

는 f_k 주파수에서의 r₀에서 r₀+m 시간의 평균 파워를 나타낸다.)(Wherein, P represents the power, j denotes the amount of time, f _k denotes a frequency,

Represents the average power of r ₀ to r ₀ + m times at frequency f _k ).

According to another aspect, the user's intention recognition analysis method may further include displaying the detection result of the intention recognition so that the user can confirm the intention recognition result.

According to another aspect, the user's intent awareness analysis method may further include the step of classifying the frequency region related to the kinesthetic sense and the step of detecting the intent of the user.

According to an embodiment of the present invention, the user's intent perception analyzing apparatus includes an identification unit for converting user's brain wave data into a frequency signal and classifying a frequency region related to a kinesthetic sensation according to a band of the converted frequency signal; And a detection unit for detecting intention recognition of the user by analyzing characteristics of the user in the frequency domain based on the motor imagery of the user.

According to the embodiments of the present invention, it is easy to classify and analyze the acquired EEG, and it is possible to increase the accuracy of the signal by quantifying the EEG.

According to the embodiments of the present invention, it is possible to apply the present invention to contents in the educational field including games in combination with other software based on the intention of the user.

FIG. 1 is a flowchart illustrating a user's intent perception analysis method using an STFT and a PSO in an embodiment of the present invention.
2 is a view for explaining an electrode attaching position of an EEG measuring apparatus according to an embodiment of the present invention.
Fig. 3 is a diagram showing the power spectrum results of FC5 and FC6 in one embodiment of the present invention. Fig.
FIG. 4 shows the results of the ERS phenomenon according to the results of FC5 and FC6 with respect to the motion image of the right hand and the left hand, according to an embodiment of the present invention.
Figure 5 shows the results of a PSO in one embodiment of the present invention.
6 illustrates a BCI system structure based on a motion imaginary EEG signal in an embodiment of the present invention.
7 is a block diagram illustrating an internal configuration of a user's intent perception analysis apparatus using STFT and PSO in an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between . Also, when a part is referred to as "including " an element, it does not exclude other elements unless specifically stated otherwise.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

The present invention relates to a user's intention recognition method for BCI (Brain Computer Interface), which includes an accurate intent cognition classification technique in measured brain waves and an Event-Related Synchronization (ERS) The present invention provides a method and a solution for defining a frequency region in which a characteristic of a frequency band is most expressed.

An object of the present invention is to control an electronic device using an EEG in which a human brain wave is converted into an electrical signal. To do this, a classification technique is needed to classify the user's exact intention in the measured EEG. In addition, it is necessary to define the frequency region in which the characteristics of the ERS appearing in different frequency regions are expressed most individually. Therefore, the present invention provides a method and solution for defining the frequency domain and the intention recognition classification technique described above.

BCI is defined as an interface technology that directly connects a human brain with a computer to control the computer through brain waves. It is widely known as HCI (Human Computer Interface) technology. In addition, BCI technology is sometimes referred to as BMI (Brain Machine Interface) because brain waves can manipulate machines such as wheelchairs and robots. The implementation of BCI technology involves measuring brain waves through a device that recognizes EEG stimuli, analyzing EEG through signal processing, and then issuing commands to input / output devices.

In visual rhythm, while imagining left-handed or right-handed movements, activity in the rhythm area of the subject is weakened or blocked, or suppressed, and this phenomenon is referred to as event-related desynchronization (ERD). Mainly occurs in β in the μ rhythm and β rhythm region. ERS is a phenomenon that is opposite to that of ERD and increases the amplitude of the EEG.

STFT (Short-Time Fourier Transform) is the simplest method for time-frequency analysis. It performs Fourier transform on a desired part in a short time domain and shows the frequency distribution based on the time axis. STFT can be used to express frequency domain analysis and time domain analysis.

PSO (Particle Swarm Optimization) is a probabilistic optimization technique that performs optimization based on the sociability of groups of components. Here, the particles are moved to the optimal location in the search space, and the position of each entity is based on the updating of the two optimal values to obtain the value of the new location. It begins with a group of initial irregular solutions, but differs in that each potential solution consists of a combination of random velocity and previous potential solutions. An object with optimal location information is called pbest, and the most optimal Is an object representing the position information of the object.

FIG. 1 is a flowchart illustrating a process of selecting a maximum amplitude and a time in a frequency band using a STFT and a PSO in order to analyze a user's intention recognition according to an exemplary embodiment of the present invention. Referring to FIG.

Referring to FIG. 1, a user's intent perception analysis method according to an exemplary embodiment includes an EEG acquisition step 110, a filtering application step 120, an STFT application step 130, a stimulus presentation step 140, a PSO application step 150 , And a user's intent recognition categorization step 160. The user intent perception analysis method according to one embodiment can be performed by each step of the user intent perception analysis apparatus to be described below.

First, in the EEG acquisition step 110, the user's intent awareness analyzing apparatus can acquire an actually measured raw EEG signal from an EEG measurement apparatus (e.g., Emotiv's EPOC apparatus). Then, the user's intent perception analyzing apparatus can perform a preprocessing process on EEG data by removing noise from the acquired EEG data or amplifying weak EEG data.

In this embodiment, 14-channel electrodes having a sampling rate of 128SPS (2048 Hz) can be attached to a user in accordance with the 10-20 electrode position method to acquire real brain wave data of a user. A sampling rate higher than necessary causes an increase in the data to be processed, resulting in a problem of lowering the processing speed and can be a limitation in real time driving. In this embodiment, 128SPS, which is the minimum necessary sampling number required for EEG analysis, is preferable. However, it is not limited to 128SPS, and it can be changed within a certain range (128 +?

2 is a view for explaining an electrode attaching position of an EEG measuring apparatus according to an embodiment of the present invention. The electrodes are attached to the user's brain to measure EEG data. At this time, as shown in FIG. 2, the positions of the electrodes for measuring the EEG are determined based on 14-20 parts of the scalp (AF3 , F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, F8, AF4.

Referring again to FIG. 1, in the filtering application step 120, the user's intention recognition analyzing apparatus can classify the 8-12 Hz region, which is a mu rhythm (μ) region, in the obtained EEG data. At this time, the user's intentional cognitive analysis apparatus can classify a necessary area using a DNF (digital notch filter) or a BPF (band pass filter). The characteristics according to kinesthetic sensation in EEG appear mainly in the frequency range of 8-30 Hz. The reason for using the 8-12 Hz region in the present invention is that when PSO is applied to a wide frequency region, the probability of falling into a local maximum is high and mu rhythms (μ, 8-12 ㎐), it is possible to classify motion imagery.

In the STFT application step 130, the user's intent perception apparatus can perform Fourier transform on the time domain in which the EEG data in the 8-12 Hz region is briefly cleaved.

That is, the user's intent perception analyzing apparatus inputs the preprocessed EEG data into a preset algorithm, converts the EEG data into frequency signals, and classifies the desired EEG according to the converted frequency domain.

Then, in the stimulus presenting step 140, the user's intent perception apparatus can perform time-frequency analysis on the converted EEG data through STFT. In this case, the STFT can use a hamming window, and the power spectrum of the ERS can be obtained using Equation 1 to detect ERS in each frequency region.

는 f_k 주파수에서의 r₀에서 r₀+m 시간의 평균 파워를 나타낸다.Here, P represents the power, j denotes the amount of time, f _k denotes a frequency,

Represents the average power of r ₀ to r ₀ + m time at f _k frequency.

3 is a diagram showing the power spectrum results of FC5 and FC6.

In short, ERS can be obtained in the following order.

1. Collect the low EEG signal (Sampling rate 2048 Hz).

2. Extract the data of the frequency component of μ field using BPF (band pass filter) (8-12 Hz).

3. Calculate averages for all trials (perform a 4-second motion imagination starting with the cue, and 1-2 seconds have a rest).

4. Substitute the average value into the equation (2) to obtain the power P _j of the time _j , and then substitute the solution into the equation (3) to calculate the final ERS value

FIG. 4 shows the results of the ERS phenomenon according to the results of FC5 and FC6 with respect to the motion image of the right hand and the left hand.

로 최대 파워와 시간 주파수이다. 도 5는 PSO 적용 단계(150)에서 얻어진 PSO의 결과를 도시한 것이다.Referring again to FIG. 1, in the PSO applying step 150, the user's intent perception apparatus searches for an optimal point in which a particle and a swarm are combined using a PSO algorithm in a rhythm region corresponding to the ERS . In this case, the optimal point is the amplitude that is increased when the motion is imagined, and the fitness value

As is the maximum power and time frequency. FIG. 5 shows the result of the PSO obtained in the PSO application step 150. FIG.

Therefore, in this embodiment, an analysis method in the frequency domain using the STFT for the analysis of brain wave data can be presented, and the optimization can be performed by the probabilistic optimization technique.

Finally, in FIG. 1, the user's intent recognition categorization apparatus 160 can determine whether the user's intention is through the feature point by analyzing EEG data. At this time, the user's intent awareness analyzing apparatus finds the maximum amplitude at the average amplitude in the 8-12 Hz frequency region and can identify the frequency at which the ERS is most generated. At this time, when the particle position and the velocity are the same, an update is made using Equation (4).

The result of the intention recognition detected in the user's intention recognition step 160 may be displayed through the display means so that the user can confirm the result.

Since the result of the intention recognition is changed in real time, the process is repeated from the step 110 of acquiring the user's brain wave data again after the user's intention recognition classification step 160. [

The user's intention cognitive analyzer can detect the ERS, which is a pattern of signals increasing in the mu rhythm (μ) region occurring in the kinesthetic sensory cortex region of the brain, using STFT and PSO. In other words, the user's intention cognitive analyzer uses the PSO in the EEG average of 8-12 Hz to detect the frequency with the largest amplitude and detects the frequency with the highest frequency, It is possible to find the characteristics of ERS which appear in motion imagination in each channel by using PSO. By analyzing the characteristics of ERS appearing in different frequency regions for each individual by fixing it to the most frequently expressed frequency region, can do.

The basic structure of the BCI system to which the above-described user's intention recognition analysis method is applied is shown in FIG.

As shown in FIG. 6, in the calibration phase, a signal processing preprocessing process for removing noise from the collected EEG or amplifying a weak EEG, and a preprocessing process for enhancing the recognition rate when classifying the EEG And feature extraction and classifier training to classify the processed data as important or unimportant parts. Finally, in the feedback phase, various electromagnetic devices can be controlled using data classified through a classifier to classify which group the features obtained in the feature extraction step belong to.

The user's intent perception analysis method according to the present invention may include at least two operations based on the details described with reference to FIG. 1 through FIG. At this time, two or more operations can be combined, and the order or position of operations can be changed.

The methods according to embodiments of the present invention may be implemented in the form of a program instruction that can be executed through various computer systems and recorded in a computer-readable medium. Particularly, in this embodiment, the EEG data measured in the cerebral cortex of the user is purified through a preprocessing step; Classifying the frequency domain related to the kinesthetic sensation according to the band of the converted frequency signal after converting the purified brain wave data into a frequency signal; And analyzing characteristics of the user's motor imagery in the frequency domain EEG data to detect the intention of the user.

FIG. 7 is a block diagram illustrating an internal configuration of a user's intent perception analysis apparatus using an STFT and a PSO in an embodiment of the present invention. Referring to FIG. 7, the user's intent awareness analyzing apparatus according to an embodiment may include a pre-processing unit 710, an identification unit 720, a detection unit 730, and a display unit 740. The user's intent awareness analyzing apparatus according to an embodiment may further shorten the elements or further include additional elements based on the details of the user's intent perception analysis method described with reference to FIG. 1 through FIG.

The preprocessing unit 710 may perform preprocessing on EEG data by removing noise from the EEG data acquired after acquiring the measured EEG data from the EEG measuring apparatus or amplifying weak EEG data. At this time, the positions of the electrodes for measuring the EEG were determined based on the 14-20 regions (AF3, F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, F8, AF4) can be selectively determined.

The identification unit 720 inputs the pre-processed EEG data into a predetermined algorithm, converts EEG data into frequency signals, and performs classification of EEG according to the converted frequency domain. The identification unit 720 can classify the 8-12 Hz region, which is the mu rhythm (mu) region, in the obtained EEG data. At this time, the identifying unit 720 can classify the required area using a digital notch filter (DNF) or a band pass filter (BPF).

로 최대 파워와 시간 주파수이다. 다시 말해, 검출부(730)는 8-12㎐ 주파수 영역의 평균 진폭에서 최대 진폭을 찾아 ERS가 가장 많이 발생하는 주파수를 확인할 수 있다.The detection unit 730 determines the intention through the feature points through analysis of the classified EEG data. First, the detection unit 730 may perform a time-frequency analysis on the converted EEG data through STFT. In this case, the STFT can use a hamming window, and the power spectrum of the ERS can be obtained using Equation (1) to detect ERS in each frequency region. The detector 730 may use the PSO algorithm in the rhythm region corresponding to the ERS to find an optimal point in which particles and swarms are combined. In this case, the optimal point is the amplitude that is increased when the motion is imagined, and the fitness value

As is the maximum power and time frequency. In other words, the detector 730 finds the maximum amplitude at the average amplitude in the 8-12 Hz frequency region and can identify the frequency at which the ERS is most generated.

The display unit 740 can display the intention of the user detected through the detection unit 730. Since the result of detection of the intention is changed in real time, the process of repeating the above processes is repeated from the process of acquiring the user's brain wave data again after the user's intention recognition classification, so that the user can confirm the result of real- 740).

According to the above configuration, the user's intent perception analyzing apparatus can detect the ERS, which is a pattern of signals increasing in the mu rhythm (mu) region occurring in the kinesthetic sensory cortex region of the brain, using STFT and PSO. In other words, the user's intention cognitive analyzer uses the PSO in the EEG average of 8-12 Hz to detect the frequency with the largest amplitude and detects the frequency with the highest frequency, It is possible to find the characteristics of ERS which appear in motion imagination in each channel by using PSO. By analyzing the characteristics of ERS appearing in different frequency regions for each individual by fixing it to the most frequently expressed frequency region, can do.

As described above, according to the embodiments of the present invention, it is easy to classify and analyze the obtained EEG, and it is possible to increase the accuracy of the signal through quantification of brain waves. In addition, according to embodiments of the present invention, it is possible to apply the present invention to contents in the education field including games in combination with other software based on the intention of the user.

The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the apparatus and components described in the embodiments may be implemented within a computer system, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA) , A programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For ease of understanding, the processing apparatus may be described as being used singly, but those skilled in the art will recognize that the processing apparatus may have a plurality of processing elements and / As shown in FIG. For example, the processing unit may comprise a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of the foregoing, and may be configured to configure the processing device to operate as desired or to process it collectively or collectively Device can be commanded. The software and / or data may be in the form of any type of machine, component, physical device, virtual equipment, computer storage media, or device , Or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed over a networked computer system and stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.

The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical 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 produced 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 devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

710:
720:
730:
740:

Claims (25)

delete In a user's intention recognition method,
The user's intention recognition analysis method is executed by a user's intention recognition analysis apparatus including a pre-processing unit, an identification unit, a detection unit, and a display unit,
Acquiring brain wave data of a user measured by an EEG (electroencephalogram) measuring device in the preprocessing unit;
Converting the brain wave data into a frequency signal and classifying a frequency region related to a kinesthetic sensation according to a band of the converted frequency signal;
Detecting intention recognition of the user by analyzing a feature appearing in the frequency domain based on motor imagery of the user in the detection unit; And
Displaying on the display unit a result of detection of the intention that the user can confirm
Lt; / RTI >
The brain wave data is an EEG signal measured by attaching 14 channels of electrodes having a sampling rate of 128SPS (2048 Hz) to the user,
F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, and F4 of the scalp according to an international standard 10-20 method. F8, AF4,
Wherein classifying the frequency domain associated with the kinesthetic sensation comprises:
We classify the mu rhythm (μ) region of EEG using DNF (digital notch filter)
The method comprising the steps of: acquiring brain wave data of the user; classifying the frequency region related to the kinesthetic sensation; detecting the intention of the user; and displaying the detection result of the intention recognition that
And a user's intention recognition method. delete delete delete delete delete delete 3. The method of claim 2,
Wherein the step of detecting the intention of the user comprises:
Checking the user's intention by detecting an event-related synchronization (ERS) which is a pattern of signals increasing in a mu rhythm (mu) region occurring in the kinesthetic sensory cortex region of the brain
And a user's intention recognition method. 3. The method of claim 2,
Wherein the step of detecting the intention of the user comprises:
Performing Fourier transform on time-domain through short-time Fourier transform (STFT) of brain wave data of a mu rhythm (mu) region occurring in a kinetic sensory cortex region of the brain among the brain wave data; And
A step of finding a frequency of an optimal point having a maximum amplitude in an average amplitude of the mu rhythm area using a PSO (Particle Swarm Optimization) algorithm
A user's intention recognition method. 11. The method of claim 10,
Wherein performing the Fourier transform on the time domain comprises:
(1) to obtain the power spectrum of the ERS in order to detect event-related synchronization (ERS) which is a pattern of signals increasing in the mu rhythm
And a user's intention recognition method.
Equation 1:

(Wherein, P represents the power, j denotes the amount of time, f _k denotes a frequency,

Represents the average power of r ₀ to r ₀ + m times at frequency f _k ). delete delete A computer readable medium comprising instructions that control a computer system to analyze a user's intention recognition for a brain computer interface (BCI)
The command includes:
Acquiring brain wave data of a user measured from an EEG (electroencephalogram) measuring device;
Transforming brain wave data of the user into a frequency signal and classifying a frequency region related to a kinesthetic sensation according to a band of the converted frequency signal;
Analyzing features appearing in the user's motional imagery in the EEG brain wave data to detect the intention of the user; And
Displaying the detection result of the intention recognition so that the user can confirm
The method comprising: controlling the computer system by a method comprising:
The brain wave data is an EEG signal measured by attaching 14 channels of electrodes having a sampling rate of 128SPS (2048 Hz) to the user,
F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, and F4 of the scalp according to an international standard 10-20 method. F8, AF4,
Wherein classifying the frequency domain associated with the kinesthetic sensation comprises:
We classify the mu rhythm (μ) region of EEG using DNF (digital notch filter)
The method comprising the steps of: acquiring brain wave data of the user; classifying the frequency region related to the kinesthetic sensation; detecting the intention of the user; and displaying the detection result of the intention recognition that
Gt; computer-readable < / RTI > A preprocessor for acquiring EEG data measured by an EEG (electroencephalogram) measuring device;
An identification unit for converting the brain wave data into a frequency signal and classifying a frequency region related to a kinesthetic sensation according to a band of the converted frequency signal;
A detector for detecting an intention recognition of the user by analyzing a feature appearing in the frequency domain based on motor imagery of the user; And
A display unit for displaying the detection result of the intention recognition so that the user can confirm the detection result;
Lt; / RTI >
The brain wave data is an EEG signal measured by attaching 14 channels of electrodes having a sampling rate of 128SPS (2048 Hz) to the user,
F7, F3, FC5, T7, P7, O1, O2, P8, T8, FC6, F4, and F4 of the scalp according to an international standard 10-20 method. F8, AF4,
Wherein,
We classify the mu rhythm (μ) region of EEG using DNF (digital notch filter)
A step of classifying frequency regions related to the kinesthetic sense; a step of detecting intent perception of the user; and a step of displaying a result of detection of intent perception that
The user's intention recognition device comprising: delete delete delete delete delete delete 16. The method of claim 15,
Wherein:
Checking the user's intention by detecting an event-related synchronization (ERS) which is a pattern of signals increasing in a mu rhythm (mu) region occurring in the kinesthetic sensory cortex region of the brain
The user's intention recognition device comprising: 16. The method of claim 15,
Wherein:
The brain wave data of the mu rhythm area occurring in the kinetic sensory cortex region of the brain are subjected to Fourier transform for the time domain through STFT (Short Time Fourier Transform), then PSO (Particle Swarm Optimization) Algorithm to find the frequency of the optimal point with the maximum amplitude in the average amplitude of the mu rhythm (μ) region
The user's intention recognition device comprising: 24. The method of claim 23,
Wherein:
(1) to obtain the power spectrum of the ERS in order to detect event-related synchronization (ERS) which is a pattern of signals increasing in the mu rhythm
The user's intention recognition device comprising:
Equation 1:

(Wherein, P represents the power, j denotes the amount of time, f _k denotes a frequency,

Represents the average power of r ₀ to r ₀ + m times at frequency f _k ). delete

Images