KR102533054B1 - Apparatus for diagnosis and prediction of tinnitus based on electroencephalography, method for processing electroencephalography signal and computer program for the same - Google Patents

Abstract

An apparatus for diagnosing and predicting tinnitus based on brain waves includes a stimulus presentation unit configured to output an auditory stimulus signal including a standard stimulus and a target stimulus; a measurement unit configured to measure an EEG signal of a subject in a resting state or in an information processing state listening to the auditory stimulation signal; and an analyzer configured to extract one or more features of the measured EEG signal and determine the presence or absence of tinnitus symptoms in the subject by classifying the EEG signal by multivariate pattern analysis (MVPA) using the one or more features. can do. Using the brain wave-based tinnitus diagnosis and prediction device, depending on the cause of tinnitus, an approach due to abnormal processing of top-down information in the auditory center of the patient and bottom-up information of the patient's auditory peripheral nerve Accurate diagnosis and/or prediction of tinnitus is possible only by measuring EEG in a short period of time, either through an approach due to processing abnormality or in a resting state, and MVPA technology is used in the time domain, frequency domain, and event-related potential (Event-Related Potential; By applying various methods such as ERP), time-frequency map, or cross-frequency coupling (CFC) to identify tinnitus patients, a quick and accurate diagnosis can be made without the need for an experienced experimenter to read the EEG signal. possible.

Description

EEG-based tinnitus diagnosis and prediction device, EEG signal processing method and computer program therefor

Embodiments relate to an EEG-based tinnitus diagnosis and prediction device, an EEG signal processing method, and a computer program therefor. More specifically, the embodiments measure EEG signals in a resting state or while performing bottom-up information processing or top-down information processing paradigm tasks, and multivariate pattern recognition (MVVA). ) technology to analyze the EEG characteristics of tinnitus patients compared to normal people by discriminating the activation patterns and timings of EEGs with state differences.

Tinnitus refers to a symptom of hearing sound in the ears or in the head even when there is no external sound stimulus. In the case of the United States, 25.3% of adults have experienced tinnitus, and 7.9% of them are known to experience tinnitus frequently. Tinnitus is a disease with a high frequency of occurrence. In particular, it is predicted that the proportion of the population suffering from tinnitus disease due to high-frequency auditory signals will increase worldwide as the environment in which people live wearing earphones increases.

Meanwhile, with the development of EEG signal processing technology, technologies for diagnosing and predicting various types of diseases using EEG are being developed. Among them, as an example of applying brain wave signal processing to tinnitus, International Publication No. WO2012/121450 discloses a tinnitus test device using brain waves and a tinnitus test method using the same.

However, the prior art disclosed in International Publication No. WO2012/121450 acquires the subject's Auditory Evoked Potential (AEP) brain wave according to the stimulus sound and analyzes only the time axis analysis components of the brain wave to diagnose tinnitus. ) method, it has a disadvantage that it is very vulnerable to EEG noise. In addition, the prior art has a limitation in not being able to predict tinnitus before it occurs, only diagnosing tinnitus that has already occurred.

International Publication No. WO2012/121450

According to one aspect of the present invention, it is possible to diagnose a tinnitus patient with a high recognition rate using only EEG measurement, and by using Multivariate Pattern Analysis (MVPA) technology to determine the activation pattern and timing of EEG with state differences, It is possible to provide an EEG-based tinnitus diagnosis and prediction device capable of extracting EEG signal characteristics of a tinnitus patient that can be discriminated against a normal person and effectively predicting the occurrence of tinnitus, an EEG signal processing method, and a computer program therefor.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

An apparatus for diagnosing and predicting tinnitus based on brain waves according to an aspect of the present invention includes a stimulus presentation unit configured to output an auditory stimulus signal including a standard stimulus and a target stimulus; a measuring unit configured to measure an EEG signal of a subject in a resting state or in an information processing state listening to the auditory stimulation signal; and an analyzer configured to extract one or more features of the measured EEG signal, and classify the EEG signal by multivariate pattern recognition using the one or more features, thereby determining the presence or absence of tinnitus symptoms in the subject.

In one embodiment, the stimulus presentation unit is further configured to randomly mix a standard stimulus having a first frequency and a target stimulus having a second frequency different from the first frequency to generate the auditory stimulus signal.

In one embodiment, the analysis unit may include a feature extraction unit configured to generate a pattern vector corresponding to the one or more features using the EEG signal; a pattern generator configured to generate a pattern signal including a training set and a testing set by using the plurality of pattern vectors corresponding to the subject's symptoms; and a classifier configured to determine a symptom of the subject by performing learning using the learning set of the pattern signals and evaluating a learning result using the evaluation set.

In one embodiment, the pattern vector is a time domain analysis method, a frequency domain analysis method, a time-frequency map analysis method, an event-related potential (ERP) analysis method, or a cross-frequency tuning method. It includes feature values extracted by one or more of the (Cross-Frequency Coupling; CFC) analysis methods.

In one embodiment, the pattern generating unit is further configured to generate the pattern signal using an average value of the pattern vectors generated from a plurality of the EEG signals.

An apparatus for diagnosing and predicting tinnitus based on brain waves according to an embodiment further includes an input unit configured to receive an input signal input as a response to the stimulation signal by a subject listening to the auditory stimulation signal.

An EEG signal processing method according to an aspect of the present invention includes measuring, by a signal processing device, an EEG signal of a subject in a resting state or in an information processing state of listening to an auditory stimulus signal including a standard stimulus and a target stimulus; extracting, by the signal processing device, one or more characteristics of the measured EEG signal; and classifying, by the signal processing device, the EEG signal by multivariate pattern recognition using the at least one feature to determine whether or not there is a tinnitus symptom in the subject.

The brain wave signal processing method according to an embodiment further includes, before the step of measuring the brain wave signal, the signal processing device outputting the auditory stimulation signal.

In one embodiment, the outputting of the auditory stimulus signal may include the signal processing device randomly mixing a standard stimulus having a first frequency and a target stimulus having a second frequency different from the first frequency to obtain the auditory stimulus. generating a signal.

In an embodiment, the classifying of the EEG signal may include generating, by the signal processing device, a pattern vector corresponding to the at least one feature using the EEG signal; generating, by the signal processing apparatus, a pattern signal including a training set and an evaluation set using the plurality of pattern vectors corresponding to symptoms of the subject; performing, by the signal processing device, learning of a classifier using the learning set of the pattern signal; and determining, by the signal processing device, a symptom of the subject by using a learning result of the classifier.

In an embodiment, the generating of the pattern signal includes generating, by the signal processing device, the pattern signal by using an average value of the pattern vectors generated from the plurality of EEG signals.

The EEG signal processing method according to an embodiment further includes receiving, by the signal processing device, an input signal input as a response to the stimulus signal by a subject listening to the auditory stimulus signal.

A computer program according to an aspect of the present invention is combined with hardware to execute the EEG signal processing method according to the above-described embodiments, and may be stored in a computer-readable recording medium.

According to an EEG-based tinnitus diagnosis and prediction device and an EEG signal processing method according to an aspect of the present invention, according to the cause of tinnitus, an approach due to top-down information processing abnormality in the patient's auditory center and a patient's hearing There is an advantage in that accurate diagnosis and prediction of tinnitus can be made only by measuring EEG in a short time through either an approach due to peripheral nerve bottom-up information processing abnormality or a resting state.

An EEG-based tinnitus diagnosis and prediction device and an EEG signal processing method according to an aspect of the present invention use a technology that combines cognitive neuroscience and brain engineering, and uses Multivariate Pattern Analysis (MVVA) technology in the time axis, frequency axis, By applying various methods such as Time-Frequency Map, Event-Related Potential (ERP), and Cross-Frequency Coupling (CFC) to discriminate tinnitus patients, a skilled experimenter can use EEG. There is an advantage in that accurate diagnosis can be made even without reading the signal.

Using the EEG-based tinnitus diagnosis and prediction device and the EEG signal processing method according to one aspect of the present invention, the treatment success rate is increased before the onset of patients through tinnitus diagnosis and prediction, and the proportion of the population suffering from tinnitus disease due to the use of earphones is reduced. It is expected to contribute to increasing social productivity and reducing medical costs in an environment that is expected to increase.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a schematic block diagram of an apparatus for diagnosing and predicting tinnitus based on brain waves according to an embodiment.
2 is a conceptual diagram illustrating an examination environment using an apparatus for diagnosing and predicting tinnitus based on brain waves according to an embodiment.
3 is a flowchart illustrating each step of an EEG signal processing method according to an embodiment.
4 is a conceptual diagram illustrating an auditory stimulation signal applied by an EEG signal processing method according to an embodiment.
5 is a conceptual diagram illustrating an analysis process of an EEG signal by an EEG signal processing method according to an embodiment.
6A and 6B are results of analyzing the subject's responses to an oddball task for a top-down information processing test and a passive task for a bottom-up information processing test, respectively, by the EEG signal processing method according to an embodiment; is a graph that represents
7A and 7B are graphs showing results of analyzing subjects' responses to a target stimulus and a standard stimulus, respectively, by an EEG signal processing method according to an embodiment.

Hereinafter, with reference to the drawings, look at the embodiments of the present invention in detail.

1 is a schematic block diagram of an apparatus for diagnosing and predicting tinnitus based on brain waves according to an embodiment.

Referring to FIG. 1 , the apparatus 1 for diagnosing and predicting tinnitus based on brain waves includes a stimulus presentation unit 10 , a measurement unit 20 and an analysis unit 40 . In one embodiment, the apparatus 1 for diagnosing and predicting tinnitus based on brain waves includes an input unit 30 for receiving an input of a subject. Also, in one embodiment, the analyzer 40 includes a feature extractor 401, a pattern generator 402, and a classifier 403.

The devices described herein may be entirely hardware, or may have aspects that are part hardware and part software. For example, the apparatus for diagnosing and predicting tinnitus based on brain waves 1 of the present specification and each unit 10, 20, 30, 40 included therein processes data in a specific format and content or/or uses an electronic communication method. Hardware for exchanging and receiving may be collectively referred to as software related thereto. In this specification, terms such as "unit", "module", "device", "terminal", "server" or "system" are intended to refer to a combination of hardware and software driven by the hardware. For example, the hardware may be a data processing device including a CPU or other processor. Also, software driven by hardware may refer to a running process, an object, an executable file, a thread of execution, a program, and the like.

In addition, each element constituting the apparatus 1 for diagnosing and predicting tinnitus based on brain waves according to the present embodiment is not intended to refer to a separate device that is necessarily physically separated from each other. That is, the stimulus presenting unit 10, the measuring unit 20, the input unit 30, and the analyzing unit 40 of FIG. 1 are performed by the hardware constituting the EEG-based tinnitus diagnosis and prediction device 1. It is only functionally divided according to operation, and each part does not necessarily have to be provided independently of each other. Of course, depending on embodiments, one or more of the parts of the apparatus 1 for diagnosing and predicting tinnitus based on brain waves may be implemented as separate devices that are physically separated from each other.

The stimulus presentation unit 10 is configured to output an auditory stimulus signal including a standard stimulus and a target stimulus. To this end, the stimulus presentation unit 10 may include a device such as a speaker for reproducing sound. The standard stimulus and the target stimulus may have different frequencies, which will be described later in detail. In addition, the stimulus presentation unit 10 may include a display device for reproducing an image or video provided along with the auditory stimulus.

The measuring unit 20 is configured to measure an EEG signal of a subject listening to an auditory stimulus signal reproduced by the stimulus presenting unit 10 . To this end, the measurement unit 20 may include one or more sensors disposed so as to be worn on the subject's head or fixed adjacent to the head. In the present specification, the EEG signal includes information measured from the brain by any neuroimaging method. As an example, the brain wave signal may refer to an electroencephalogram (EEG) signal that is invasively identified using a device attached to the surface of the subject's head.

The analyzer 40 may extract one or more features from the EEG signal measured by the measurer 20 and analyze the EEG signal through multivariate pattern analysis (MVPA) using the one or more features. To this end, the analyzer 40 may include a feature extractor 401 for extracting a pattern vector from an EEG signal and a pattern generator 402 for generating a pattern signal using the pattern vectors. In addition, the analysis unit 40 analyzes the EEG signal by using some of the pattern vectors of the pattern signal as a training set and other parts as a testing set to train the classifier 403. can

The analyzer 40 may determine whether the subject has tinnitus symptoms based on a classification result of the classifier 403 for the EEG signal. For example, the analysis unit 40 may classify the pattern vector corresponding to the evaluation set using the learning result using the pattern vectors corresponding to the learning set, which is used to determine the presence or absence of tinnitus symptoms of the subject corresponding to the evaluation set. it means. A process of analyzing the EEG signal by the analyzer 40 will be described later in detail with reference to FIG. 5 .

2 is a conceptual diagram illustrating an examination environment using an apparatus for diagnosing and predicting tinnitus based on brain waves according to an embodiment.

Referring to FIG. 2 , the subject 2 may hear an auditory stimulus signal reproduced through the stimulus presentation unit 10 while wearing the measurement unit 20 including the sensor device for measuring the brain waves on the head. Alternatively, the stimulus presentation unit 10 may include sound reproducing means such as earphones worn on both ears of the examinee 2 . While the subject 2 listens to the auditory stimulation signal, the EEG signal of the subject 2 is measured by the measuring unit 20 . However, it will be easily understood that the shape of each device shown in FIG. 2 is an example for convenience of description and does not limit the configuration of the device for diagnosing and predicting tinnitus based on EEG according to the embodiments.

In embodiments, the auditory stimulation signal provided to the subject 2 may be divided into an oddball task and a passive task. In the odd ball task, the subject 2 must distinguish between standard stimuli and target stimuli, and provide a situation in which the target stimulus is distinguished from standard stimuli by pressing a button of the input unit 30 or the like. On the other hand, the passive task corresponds to a simple listening task, and the subject 2 only needs to passively listen to the provided auditory stimulus.

3 is a flowchart illustrating each step of an EEG signal processing method according to an embodiment.

An EEG signal processing method according to embodiments includes a memory for storing one or more program instructions for performing an operation for processing an EEG signal and a processor for executing the instructions stored in the memory. It can be performed by a computing device, and this device is referred to as a signal processing device in this specification. The apparatus 1 for diagnosing and predicting tinnitus based on brain waves according to the embodiments described above with reference to FIG. 1 may correspond to an example of a signal processing apparatus.

Referring to FIG. 3 , in order to diagnose whether or not the subject has tinnitus symptoms, an auditory stimulation signal to be provided to the subject is first generated and output so that the subject can hear it (S1).

4 is a conceptual diagram illustrating an auditory stimulation signal applied by an EEG signal processing method according to an embodiment. Referring to FIG. 4 , the auditory stimulus signal may be composed of a mixture of two sound stimuli, a standard stimulus (S) and a target stimulus (T). For example, the standard stimulus (S) and the target stimulus (T) may be arranged to have a preset inter-stimulus interval (d). In this case, the interval d between stimuli may be, for example, 1300 to 1700 ms, but is not limited thereto. Also, in one embodiment, the frequency of occurrence of the standard stimulus S and the target stimulus T may be set such that the frequency of occurrence of the standard stimulus S is higher. For example, the standard stimulus S may be presented with a frequency of 80% and the target stimulus T may be presented with a frequency of 20%, but are not limited thereto.

The standard stimulus (S) and the target stimulus (T) are for diagnosing the onset of tinnitus or/or predicting the possibility of tinnitus through a response by which the subject distinguishes the target stimulus (T), and each stimulus has a different frequency. have For example, in one embodiment, the standard stimulus S may be a sound signal having a frequency of 500 Hz. In addition, in one embodiment, the target stimulus T may have a frequency of 8 kHz in the case of a healthy subject, and may be a sound signal having a frequency matching the individual tinnitus pitch of the subject in the case of a subject with tinnitus symptoms.

Referring back to FIG. 3 , the testee's EEG signal may be measured while the auditory stimulation signal as described above is played to the testee (S2). In the case of an odd-ball task corresponding to a top-down information processing approach, when the subject distinguishes a target stimulus from standard stimuli, a response may be provided through a button or the like. Meanwhile, in the case of a manual task corresponding to a bottom-up information processing approach, the subject may listen to an auditory stimulus signal while watching an image or video provided without a specific response. In this case, the image or video is intended to divert the subject's attention from the auditory stimulation signal to the visual stimulation signal, and may be without sound.

In addition, in one embodiment, an EEG signal in a resting state may also be used as information for diagnosing and predicting tinnitus. In the present embodiment, the auditory stimulation signal is intermittently heard by the subject, but the subject's EEG signal is measured in a section where there is no auditory stimulation signal, or the step (S1) of presenting the auditory stimulation signal is omitted, and the subject does not present the auditory stimulation signal. EEG signals of may be measured.

In the brain wave signal processing method according to the embodiments, the time domain analysis method, the frequency domain analysis method, the time-frequency map analysis method, the event-evoked potential (Event-induced potential) in the brain wave signal of the subject measured as described above. It is possible to derive a time point and an activation pattern capable of distinguishing between a normal state and a tinnitus state by extracting features in various ways, such as a Related Potential (ERP) analysis method or a Cross-Frequency Coupling (CFC) analysis method. In addition, it is possible to derive accuracy for all time points by distinguishing a normal state from a tinnitus state using a classifier at every time point of the measured EEG.

For example, using the EEG signal processing method according to the embodiments, depending on the cause of tinnitus, an approach due to a top-down information processing abnormality of the patient's auditory center or a bottom-up approach of the patient's auditory peripheral nerve (Bottom-up) Using an approach due to information processing abnormality, it is possible to distinguish between a normal state and a tinnitus state using EEG signals in the subject's information processing state. In addition, in one embodiment, a normal state and a tinnitus state may be distinguished by cross-frequency tuning (CFC) analysis using a feature extracted from an EEG signal in a subject's resting state.

5 is a conceptual diagram illustrating an analysis process of an EEG signal by an EEG signal processing method according to an embodiment.

3 and 5, the EEG signal 501 of the subject is first measured according to time as an example of the EEG signal using an electrode attached to the subject's head, and features for classifying the state from the EEG signal can be extracted (S3). At this time, each feature value is obtained by analyzing the EEG signal in various ways, and is obtained by methods such as time axis, frequency axis, time-frequency map, event evoked potential (ERP), and cross-frequency tuning (CFC). It may be extracted, but is not limited thereto.

The extracted feature values may be combined into pattern vectors 511, ..., 51N (S4). That is, each of the pattern vectors 511, ..., 51N is a vector having a plurality of components corresponding to feature values. In addition, components included in each of the pattern vectors 511, ..., 51N, that is, feature values may be values extracted by different methods from the same EEG signal for analysis based on multivariate pattern recognition (MVPA). can That is, feature values extracted from the original EEG signal by various methodologies may form pattern vectors 511, ..., 51N corresponding to the corresponding EEG signal. In addition, it is possible to obtain a plurality of pattern vectors 511, ..., 51N respectively corresponding to a plurality of repeated trials through a plurality of measurements.

Next, for pattern classification, pattern signals 521 and 522 may be configured using the pattern vectors 511, ..., 51N (S5). At this time, each of the pattern signals 521 and 522 corresponds to different symptoms (eg, different subjects), and each includes a pattern vector corresponding to a learning set and a pattern vector corresponding to an evaluation set.

In one embodiment, in order to reduce the computational load and increase the signal-to-noise ratio, the pattern vectors 511, ..., 51N are clustered into a certain number of groups and averaged pattern vectors calculated as the average value of the pattern vectors in each group can be converted The classifier may be trained using averaged pattern vectors, and at this time, among the pattern vectors, a certain ratio of pattern vectors may be assigned to a training set, and the remaining pattern vectors may be assigned to an evaluation set for evaluating a learning result. For example, among the k averaged pattern vectors, k-n pattern vectors may be allocated to a training set, and the remaining n pattern vectors may be allocated to an evaluation set to configure pattern signals 521 and 522 (k and n). is any natural number).

Next, the EEG signal can be classified by classifying the pattern signals 521 and 522 generated as described above using a classifier (S6). In one embodiment, a support vector machine (SVM) based classifier may be used as the classifier, but is not limited thereto. The classifier is capable of learning parameters related to an analysis model for classifying normal people and tinnitus patients through machine learning or artificial intelligence techniques using pattern vectors corresponding to the learning set among the pattern signals 521 and 522. can

The classification result of the pattern vectors means the EEG signal corresponding to the pattern vector and the classification result of the subject who provided the corresponding EEG signal. Accordingly, symptom classification may be performed to determine whether or not there is a tinnitus symptom or a possibility of tinnitus occurring in the subject through classification of the pattern vector. For example, a time point at which a feature corresponding to tinnitus is extracted from an EEG signal and a feature pattern (ie, an activation pattern) corresponding to tinnitus may be determined (S7).

In one embodiment, a decoding signal 530 representing the accuracy of the subject's response is generated using feature vectors extracted at all time points of the EEG signal, and a normal state and a tinnitus symptom state are used by a classifier at every time point. By distinguishing the symptoms, the accuracy of symptom classification can be further increased.

6A and 6B are graphs showing the results of analyzing the EEG-based classification accuracy of a subject for an oddball task and a manual task, respectively, by an EEG signal processing method according to an embodiment, and event-evoked potentials (event-evoked potentials, which are a method of time-domain analysis of EEG), respectively. Through ERP) analysis, the response of the subject is expressed as decoding accuracy over time. In addition, FIGS. 7A and 7B are graphs showing results obtained by analyzing the subject's EEG-based classification accuracy for target stimuli and standard stimuli, respectively, by the EEG signal processing method according to an embodiment, similar to FIGS. 6A and 6B . Through (ERP) analysis, the classification accuracy of the corresponding stimulus according to the subject's different stimulus types is shown over time.

As shown, it can be confirmed that the tinnitus patient group has a statistically significant difference in classification accuracy compared to the normal control group. For example, in the Odd Ball task, both the normal group and the tinnitus patient group were able to discriminate the target stimulus, but in the case of the tinnitus patient, the discrimination accuracy was reduced compared to the control group during the time interval of 180 to 680 ms after the stimulus, indicating abnormal hearing symptoms. I was able to confirm. Also, in the case of responses to standard stimuli in the odd ball task and the manual task, the tinnitus patient group showed lower decoding accuracy than the control group in the time interval of 180 to 610 ms after stimulation. In addition, the bars 601, 602, 701, and 702 displayed on each graph in FIGS. 6A, 6B, 7A, and 7B indicate confidence intervals of classification accuracy obtained by statistical methods.

Through the analysis as described above, it is possible to find a time point at which a normal state and a tinnitus state can be distinguished and an activation pattern capable of diagnosing and/or predicting the tinnitus state can be found from the EEG signal.

The operation by the EEG signal processing method according to the embodiments described above may be at least partially implemented as a computer program and recorded on a computer-readable recording medium. The computer-readable recording medium on which the program for implementing the operation by the EEG signal processing method according to the embodiments is recorded includes all kinds of recording devices in which computer-readable data is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. In addition, computer-readable recording media may be distributed in computer systems connected through a network, and computer-readable codes may be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing this embodiment can be easily understood by those skilled in the art to which this embodiment belongs.

The present invention reviewed above has been described with reference to the embodiments shown in the drawings, but this is only exemplary, and those skilled in the art will understand that various modifications and variations of the embodiments are possible therefrom. However, such modifications should be considered within the technical protection scope of the present invention. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

Claims (14)

a stimulus presentation unit configured to output an auditory stimulus signal including a standard stimulus and a target stimulus;
a measuring unit configured to measure an EEG signal of a subject in a resting state or in an information processing state listening to the auditory stimulation signal; and
An analysis unit for extracting one or more features of the measured EEG signal and classifying the EEG signal through multivariate pattern recognition using the one or more features,
The analysis unit is configured to determine the presence or absence of tinnitus symptoms in the subject by extracting features of the EEG signal of a tinnitus patient that can be discriminated against a normal person by discriminating the activation pattern and time point of the EEG,
The analysis unit,
a feature extraction unit configured to generate a pattern vector corresponding to the at least one feature using the EEG signal;
a pattern generator configured to generate a pattern signal including a learning set and an evaluation set by using the plurality of pattern vectors corresponding to the subject's symptoms; and
a classifier configured to determine a symptom of a subject by performing learning using the learning set of the pattern signals and evaluating a learning result using the evaluation set;
The pattern vector includes EEG-based tinnitus diagnosis including feature values extracted by a method including a time domain analysis method, a frequency domain analysis method, a time-frequency map analysis method, an event evoked potential analysis method, and a cross-frequency entrainment analysis method. and a forecasting device.
According to claim 1,
The stimulus presentation unit is further configured to randomly mix a standard stimulus having a first frequency and a target stimulus having a second frequency different from the first frequency to generate the auditory stimulus signal. EEG-based tinnitus diagnosis and prediction device.
delete delete According to claim 1,
The pattern generating unit is further configured to generate the pattern signal using an average value of the pattern vectors generated from a plurality of the brain wave signals.
According to claim 1,
The apparatus for diagnosing and predicting tinnitus based on brain waves further comprising an input unit configured to receive an input signal input in response to the stimulation signal by the subject listening to the auditory stimulation signal.
measuring, by a signal processing device, an EEG signal of a subject in a resting state or in an information processing state of listening to an auditory stimulus signal including a standard stimulus and a target stimulus;
extracting, by the signal processing device, one or more characteristics of the measured EEG signal; and
The signal processing device extracts features of the EEG signal of a tinnitus patient that can be discriminated compared to a normal person by discriminating the activation pattern and time point of the EEG, and multivariate pattern recognition using the one or more features to determine the presence or absence of tinnitus symptoms in the subject. Classifying the brain wave signal,
Classifying the brain wave signal,
generating, by the signal processing device, a pattern vector corresponding to the at least one feature using the EEG signal;
generating, by the signal processing device, a pattern signal including a learning set and an evaluation set using the plurality of pattern vectors corresponding to symptoms of the subject;
performing, by the signal processing device, learning of a classifier using the learning set of the pattern signal; and
determining, by the signal processing device, a symptom of the subject using a learning result of the classifier;
The pattern vector is an EEG signal processing method including feature values extracted by a method including a time domain analysis method, a frequency domain analysis method, a time-frequency map analysis method, an event evoked potential analysis method, and a cross-frequency entrainment analysis method. .
According to claim 7,
The EEG signal processing method further comprising outputting, by the signal processing device, the auditory stimulus signal before the step of measuring the EEG signal.
According to claim 8,
The outputting of the auditory stimulus signal may include generating, by the signal processing device, the auditory stimulus signal by randomly mixing a standard stimulus having a first frequency and a target stimulus having a second frequency different from the first frequency. EEG signal processing method comprising a.
delete delete According to claim 7,
The generating of the pattern signal comprises generating, by the signal processing device, the pattern signal by using an average value of the pattern vectors generated from the plurality of brain wave signals.
According to claim 7,
The EEG signal processing method further comprising receiving, by the signal processing device, an input signal input as a response to the stimulus signal by a subject listening to the auditory stimulus signal.
A computer program stored in a computer-readable recording medium coupled with hardware to execute the EEG signal processing method according to any one of claims 7 to 9, 12 and 13.

Images