WO2016080341A1 - 脳波による類似度の評価方法、評価装置、評価システム及びプログラム - Google Patents
脳波による類似度の評価方法、評価装置、評価システム及びプログラム Download PDFInfo
- Publication number
- WO2016080341A1 WO2016080341A1 PCT/JP2015/082101 JP2015082101W WO2016080341A1 WO 2016080341 A1 WO2016080341 A1 WO 2016080341A1 JP 2015082101 W JP2015082101 W JP 2015082101W WO 2016080341 A1 WO2016080341 A1 WO 2016080341A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- stimulus
- electroencephalogram
- target
- stimuli
- data
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/291—Bioelectric electrodes therefor specially adapted for particular uses for electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/12—Healthy persons not otherwise provided for, e.g. subjects of a marketing survey
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
- A61B5/378—Visual stimuli
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
Definitions
- the present invention relates to a method, an evaluation apparatus, an evaluation system, and a program for visualizing and evaluating brain information related to similarity evaluation for a plurality of stimuli.
- the meaning of brain waves has been given by examining the correlation between the evaluation results of questionnaires for various types of emotions such as pleasant discomfort obtained from questionnaires and the brain waves.
- the correlation between the electroencephalogram and each emotion type is high, the strength of each emotion can be estimated from the electroencephalogram to some extent, but if the correlation is low, there is a problem that the probability of correctly estimating the emotion from the electroencephalogram becomes low.
- the logic of “Emotional state is generally observed when such an EEG is observed” is used from a large number of subjects' databases. There is a question of whether there is any scientifically meaningful data analysis. In addition, it is not clear what it means to extract information from the brain waves that can be understood from the questionnaire.
- the research group of the present invention has advanced research and development on a brain information analysis method aiming at performing a sensitivity evaluation that eliminates subject's subjective bias as much as possible.
- a dimension compression technique based on the difference in EEG response (potential change amplitude data) when simply presenting various stimuli continuously (see Patent Document 1).
- multi-channel EEG data obtained from a plurality of measurement locations for a plurality of sensory stimuli is dimensionally compressed, and the distribution of the stimuli is displayed on a two-dimensional plane.
- We proposed a display method for visualizing brain information characterized in that near stimuli display similar brain activity compared to distant stimuli.
- Patent Document 2 proposes that a specific decision is made in the brain based on the discriminant function and the success rate obtained by analyzing the electroencephalogram data obtained by measuring the electroencephalogram after presentation of the stimulus. Further, in Patent Document 3, the brain wave data after the stimulus presentation is analyzed and specified using a function for estimating the intracerebral processing process related to the decision making for each trial of the “message component” that is a cognitive task. We decided that the decision-making was made in the brain, and proposed a technology to support communication by combining messages. With the techniques of Patent Documents 2 and 3, for example, it is possible to support communication for people with movement disabilities who are difficult to speak and write, and those with severe movement disabilities who are difficult to input various devices using their hands and feet.
- Patent Document 4 proposes an apparatus and a method for ordering survey objects by electroencephalogram analysis.
- McClure SM Li J, Tomlin D, Cypert KS, Monogua LM, Montagu PR. “Neural Correlates of Behavior Preferred for Cultural Families Links” Neuron 44, p379-387, 2004
- Patent Document 1 proposed by the present inventors, since the brain information when the subject passively receives the stimulus is targeted, the subject is actively receiving the stimulus. There is a problem that brain information is not subject to evaluation.
- the inventors of the present invention have been conducting research on evaluation of brain information when a subject actively receives a stimulus.
- the inventors of the present invention need to discriminate one of a plurality of types of stimuli to be presented to the subject (refers to a cognitive task that requires determination of “select” or “do not select” in the head).
- a system to acquire brain wave data including brain information when actively receiving stimuli was constructed using.
- the strength of the electroencephalogram response when each target stimulus is selected and distinguished from other stimuli in the brain is determined by an indicator such as discriminant analysis.
- the system which compared and unambiguously arranged was developed (refer patent document 4).
- Patent Document 4 The present inventors thought that the system of Patent Document 4 would be a very powerful tool when evaluating brain information with little subjective bias including subconscious activities.
- the analysis result is limited to the identification of the stimulus having the strongest “degree of interest in the brain” or one-dimensional quantitative data (interpretable as order data). As in 1, it is impossible to overview the similarity of all stimuli on a map.
- the technique of Patent Document 4 is limited to the brain wave data when “selected”, the brain information included in the brain wave data when “not selected” remains unused. .
- the present invention is intended to solve these problems, and an object thereof is to provide an apparatus, a method, a system, and a program for evaluating stimulation similarity by electroencephalogram using data obtained by simple electroencephalogram measurement. And Another object of the present invention is to visualize brain information.
- the present invention has the following features in order to achieve the above object.
- brain wave data related to cognitive processing for a plurality of sensory stimuli is dimensionally compressed, and the distribution of the stimuli is displayed on a two-dimensional plane or three-dimensionally. It is characterized by evaluating the similarity of brain information.
- the electroencephalogram data related to the cognitive processing includes electroencephalogram data when a stimulus is selected as a target and electroencephalogram data caused by a non-target stimulus event.
- the dimension compression is based on a combination of multivariate analysis methods.
- the brain information similarity evaluation apparatus of the present invention includes a stimulus presentation unit, an electroencephalogram measurement unit, and an evaluation processing unit that evaluates the similarity of a stimulus based on electroencephalogram data
- the stimulus presentation unit includes a plurality of senses.
- Stimulus is presented as a plurality of stimulation events each consisting of a target and a non-target each time
- the electroencephalogram measurement means measures the electroencephalogram immediately after the stimulus presentation by the stimulus presentation means
- the evaluation processing means comprises a plurality of senses
- the electroencephalogram data during the cognitive task for the stimulus is subjected to dimensional compression by a combination of multivariate analysis methods, and points corresponding to the stimulus are displayed on a two-dimensional plane or in three dimensions.
- the brain information similarity evaluation system obtains electroencephalogram data by measuring electroencephalograms related to cognitive processing for a plurality of sensory stimuli, and combines the electroencephalogram data with a combination of multivariate analysis methods. Compression is performed to display points corresponding to the stimulus on a two-dimensional plane or in three dimensions.
- the program of the present invention provides a computer with a plurality of sensory stimuli as a plurality of stimulus events consisting of a target and a non-target, respectively, and a plurality of sensory stimuli presented by the stimulus presentation unit.
- EEG data during the cognitive task is subjected to dimensional compression by a plurality of multivariate analysis methods, and points corresponding to the stimulus are displayed on a two-dimensional plane or in three dimensions.
- the present invention also evaluates the brain information when the subject is actively receiving a stimulus that the cognitive task is being performed, a highly reliable result was obtained.
- EEG data associated with cognitive processing is dimensionally compressed and the distribution of the stimulus is displayed on a two-dimensional plane, so that a near-distance stimulus has similar brain activity to a far-distance stimulus. Can be displayed. That is, the similarity of information in the brain with respect to the stimulus can be evaluated based on the distance between the displayed stimuli.
- brain activity of the subject is measured non-invasively by the electroencephalogram, information in the brain can be easily visualized.
- brain activity is measured directly, it is more reliable than questionnaires that are susceptible to conscious bias.
- brain activity is directly measured, it is possible to visualize unconscious impressions, sensibility information, and the like that are difficult to measure by conventional questionnaire surveys.
- brain activity data that has been too complex to be meaningful in the past is analyzed in EEG data while performing a cognitive task, and is displayed in two dimensions by compressing dimensions from multiple dimensions.
- Two-dimensional display shows that objects with a close distance on the map are judged to be “similar” in the brain, and objects that are far apart are judged to be “different” in the brain
- information in the brain can be visualized.
- the averaged data for each group of subjects can be visualized, it can be used in marketing surveys instead of questionnaire surveys on new product development.
- FIG. 5 is a diagram for explaining the first embodiment, and shows the strength of the electroencephalogram with a discrimination score.
- the embodiment of the present invention realizes visualization of brain information related to similarity evaluation for a plurality of stimuli by analyzing an electroencephalogram. More specifically, the embodiment of the present invention performs multivariate analysis on EEG data such as multi-channels measured non-invasively from the scalp, so that a plurality of stimuli (visual stimuli such as products) can be obtained. It is a technology that visualizes brain information for similarity as a low-dimensional structure.
- Patent Document 4 since the technique of Patent Document 4 is limited to the brain wave data when “selected”, the brain information included in the brain wave data when “not selected” remains unused. Met. The present inventors pay attention to the fact that information on the degree of similarity with the “selected” stimulus may be included by analyzing the characteristics of the electroencephalogram data when “not selected”. Developed.
- the embodiment of the present invention is a system capable of visualizing brain information related to similarity evaluation for a plurality of stimuli included in electroencephalogram data accompanying cognitive processing.
- the electroencephalogram data associated with the cognitive process or the electroencephalogram data related to the cognitive process for a plurality of sensory stimuli is, for example, when counting sensory stimuli targeted in the continuously presented sensory stimuli. It is the brain wave that occurs.
- a plurality of multivariate analyzes are used. Multiple multivariate analysis refers to visualizing in a low-dimensional space by using a dimension compression technique such as a multidimensional scale construction method, focusing on a score that can be referred to as a result of pattern identification such as discriminant analysis.
- Embodiments of the present invention focus on brain wave components (event-related potentials) that can be recorded on brain activity, particularly on the scalp, and that reflect cognitive processing evoked by stimulus input. By analyzing the brain responsiveness to the presentation, the similarity of a plurality of stimulation events is evaluated.
- the event-related potential of interest in the present invention is a transient electroencephalogram that occurs in conjunction with the occurrence timing of an external or internal event, such as P300 (a positive potential change that increases after 300 milliseconds after presentation of a stimulus). is there.
- Examples of the stimulus event include physical sensory stimuli (sensory stimuli such as visual, auditory, olfactory, taste, and tactile sensations) and verbal stimuli related to a plurality of evaluation objects.
- the present invention mainly includes elements of stimulus event presentation, electroencephalogram measurement, evaluation processing by electroencephalogram data analysis, and presentation of evaluation results.
- the device according to the embodiment of the present invention includes an electroencephalogram measurement headgear, a data analysis computer, and a stimulus presentation device (for example, a display screen).
- FIG. 1 is a diagram schematically showing an apparatus and method according to the present embodiment.
- the stimulus presentation display screen is shown to the subject, and the subject's scalp electroencephalogram is measured and recorded by the electroencephalograph (the electroencephalogram amplifier 4 in the figure).
- the subject wears an electroencephalograph electrode 3 for measuring an electroencephalogram on the head.
- a head-mounted device with an electroencephalograph electrode fixed is used.
- Various visual stimuli are presented on the display screen (monitor), and electroencephalogram raw waveform data is obtained by an electroencephalograph.
- FIG. 1 The result of analyzing the electroencephalogram data by a processing device such as the computer 6 and evaluating the brain information on the similarity of stimulation is shown on a display screen or the like.
- thick arrows are shown from the head where the electroencephalogram electrode is located to the electroencephalogram amplifier 4, and from the electroencephalogram amplifier 4 to the computer 6, but this schematically shows that signals are transmitted by wire or wirelessly. It is illustrated.
- FIG. 2 is an example of a head-mounted member (headgear) to which an electroencephalograph electrode used in the present embodiment is fixed.
- the headgear includes an electroencephalogram measurement electrode fixedly held by the headgear, wiring for electrically connecting the electrode and the electroencephalograph main body, and a wireless transmission unit for transmitting the measured electroencephalogram data.
- brain waves from a single electrode or a plurality of electrodes placed on the scalp are measured around the top of the head, which is effective for measuring brain waves reflecting increased attention.
- FIG. 3 is a diagram schematically showing the presentation of the stimulation event and the response of the subject's brain wave to this over time in the present embodiment.
- a stimulus event also referred to as an alerting event or a test stimulus event
- a simple graphic is presented to the subject one event (one sheet) at a time.
- the brain wave of the subject who saw this is measured by an electroencephalograph with an electrode attached to the head of the subject, and the electroencephalogram is analyzed by an electroencephalogram analysis processing device such as a computer.
- Stimulus events are symbols, illustrations, pictures, photos, etc.
- the electroencephalogram corresponding to a plurality of stimulation events whose stimulation events change over time is schematically illustrated. Specifically, it is performed by (a) stimulus event presentation, brain wave measurement for the stimulus event, and (b) stimulus similarity evaluation processing based on brain wave data as follows.
- a display process is also provided as appropriate by visualizing the result of the evaluation process with a diagram or the like.
- a plurality of stimulus events related to various objects whose similarity is to be evaluated for example, one of eight figures is taught to a subject as a “target” (also referred to as a target), and sequentially presented stimulus events are the target.
- a cognitive task for counting the number of presentations in the head is performed for each subject, and the electroencephalogram at that time is measured. Electroencephalograms from single or multiple electrodes placed on the scalp around the top of the head are measured. The measurement is performed according to the following procedure.
- visual stimuli such as product photographs and illustrations
- visual stimuli fruit pictures in FIG. 3
- sensory stimuli such as auditory sense, olfactory sense, taste sense, and tactile sense instead of visual stimuli, it is also presented as time passes.
- one of a plurality of visual stimuli (in FIG. 3, a plurality of fruit pictures) is defined as “target”, and the other stimuli are collectively referred to as “non-target”. Define.
- targets and “non-targets” are repeatedly presented in a pseudo-random manner, each time a “target” is presented, the subject is caused to recite in the head.
- successive stimulus presentation attempts to detect a specific target are collectively referred to as a “game”.
- the electroencephalogram data shown in the lower part of FIG. 3 is an example of electroencephalogram data corresponding to each visual stimulus when “target” is taught as an apple and the subject is presented with the visual stimulus and counted.
- the electroencephalogram data for the visual stimulus of the target (apple) has a larger response of the electroencephalogram than the electroencephalogram data for the visual stimulus of the non-target (banana, grape, mandarin).
- the electroencephalogram data for the target visual stimulus out of the electroencephalogram data is often large in response to the electroencephalogram compared to the electroencephalogram data for the non-target test stimulus. ing.
- model formulas that discriminate between “target” and “non-target” by using pattern discrimination technology (linear discriminant analysis, etc.) (Set so that the discrimination score for the target becomes high) is generated, and the discrimination score immediately after the presentation of each stimulus is calculated.
- a cross-validation method is used to avoid duplication of model data and prediction target data.
- FIG. 4 is a table showing the discrimination score of the electroencephalogram data for each test stimulus when the target is the stimulus type in the left column of the figure, taking a simple example of four stimulus types. For example, in the first row, when the target is banana, the discrimination score for the stimulation event banana is 4, the discrimination score for the stimulation event grape is -3, the discrimination score for the stimulation event apple is -5, and the discrimination score for the stimulation event orange The score is -4.
- FIG. 5 is a diagram showing the result of similarity evaluation obtained by plotting.
- discriminant model formulas generated from data of all the remaining games (first and third to eighth games) other than that game are used.
- the discriminant model formula can be interpreted as valid if the decoding accuracy is high enough that the number of games successfully decoded in all games.
- x is a value of electroencephalogram data (voltage) at a certain point in a certain channel.
- the type of x includes a type (n) obtained by multiplying the number of channels (the number of channels corresponding to the number of measurement points to obtain brain wave data at a plurality of measurement points on the scalp of the subject's head) and the data point.
- the weighting coefficient w and the constant term c for each electroencephalogram data can be obtained by linear discriminant analysis.
- the cumulative discriminant score that adds the discriminant score for the number of stimulus presentations for each stimulus event may be obtained. Alternatively, addition averaging may be performed.
- the physical distance between the stimuli is calculated based on the discrimination score reflecting the similarity between the stimuli.
- the Euclidean distance is calculated, and the target stimulus type ⁇ test stimulus data array is converted into a triangular matrix.
- the following equation (Formula 2) is a formula for calculating the Euclidean distance (ed) of the distance between the individual i and the individual j.
- p indicates the number of test stimuli.
- X indicates a discrimination score between the individual i and the individual j.
- the multidimensional scale construction method is a technique for visualizing and constructing the relationship of stimulus types in a low dimension based on the Euclidean distance. Specifically, the distance in the case where a stimulus in some dimensions (d ij, correctly obtained by imparting chevron on the d) 2 sum is minimum difference between the distance (d ij) between the stimulus and Find the coordinate value so that This can be obtained from the stress value shown in the following equation (Equation 3).
- the validity of the obtained plot can be evaluated as an explanation rate by looking at the square of the correlation of the distance calculated from the relationship between the Euclidean distance and the coordinate value calculated by the multidimensional scaling method.
- the relationship between stimuli is visualized by a multidimensional scaling method, and the validity of similarity evaluation between stimuli based on brain information is ensured by the explanation rate.
- FIG. 6 is a diagram showing a comparison of similarity evaluation results.
- the Landolt ring which is often used in ophthalmological vision tests, was verified using visual stimuli. Specifically, when eight types of Landolt rings (eight types with different cut directions divided by 45 degrees) are presented to the subject over time, an object with a cut at a specific angle is defined as a “target”.
- the experiment and data analysis were performed according to the procedure described above. As a result, it was possible to confirm that the arrangements were close to the ring structure such that the small differences in the Landolt rings were arranged close to each other. Such an arrangement is an arrangement with a probability that is unlikely to occur by chance.
- FIG.6 (B)
- 6A is a theoretical value corresponding to the actual measurement value of FIG. 6B.
- the present invention is useful as a highly reliable and simple marketing survey technique that can replace the conventional questionnaire survey.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Psychiatry (AREA)
- Entrepreneurship & Innovation (AREA)
- Fuzzy Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Epidemiology (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
本実施の形態を、図を参照して以下説明する。図1は、本実施の形態による装置及び方法を模式的に示す図である。図1の被験者への刺激提示1で図示されるように、刺激提示用の表示画面を被験者に見せて、被験者の頭皮上脳波を脳波計(図中、脳波アンプ4)により計測記録する。被験者は、脳波を測定するための脳波計電極3を頭に装着する。例えば、脳波計電極を固定した頭部装着装置を用いる。表示画面(モニター)に様々な視覚刺激を提示して、脳波計により脳波生波形のデータを得る。脳波生波形のデータをコンピューター6等の処理装置で解析処理して、刺激の類似度の脳内情報を評価した結果を表示画面等で示す。図1において、脳波電極の位置する頭部から脳波アンプ4に、そして、脳波アンプ4からコンピューター6に、太い矢印を図示したが、これは有線又は無線により信号が伝達されることを模式的に図示したものである。
本実施の形態では、以下に示す交差検証法を用いてデータを分割した後、判別モデル式を生成し、「標的」解読の成否判断を行う。まず、解読成否の判断を行う当該ゲーム(例えば第1ゲーム)以外の残りのゲーム(第2~8ゲーム)において「標的」もしくは「非標的」としてテスト刺激が提示された時の脳波データから判別モデル式を作成後、当該ゲーム(第1ゲーム)における各刺激事象に対して、判別得点を算出し、上述した解読成否の判断を行う。別のゲーム(例えば第2ゲーム)での解読成否の判断にはそのゲームを除く残り全てのゲーム(第1および第3~8ゲーム)のデータから生成した判別モデル式を用いる。このように、判別対象となるデータをモデル式の生成過程から除外することによって解読成否の判断における過大評価を避けることができる。また、交差検証法を用いても、全ゲーム中、何ゲームで解読を成功したかという解読精度が十分高い場合は、判別モデル式が妥当であると解釈できる。
例えば、次式で表される線形判別関数によって各画像(視覚刺激)提示1回分に対する判別得点(y)を算出する。
二次元圧縮後のデータを、二次元平面上にプロットする。評価対象物ごとにプロットすると、二次元平面上に、各評価対象物の点がプロットされ、これにより複数の評価対象物が分布した二次元分布図(脳情報地図)を作成できる(図5参照)。
3 被験者の脳波計電極
4 脳波アンプ
6 コンピューター
Claims (6)
- 複数の感覚刺激に対する認知的処理と関連した脳波データを、次元圧縮して、前記刺激の分布を二次元平面上又は三次元で表示することにより、複数の感覚刺激に対する脳情報の類似度を評価することを特徴とする評価方法。
- 前記認知的処理と関連した脳波データは、刺激を標的として選択した時の脳波データ及び非標的の刺激事象により生起される脳波データを含むことを特徴とする請求項1記載の評価方法。
- 前記次元圧縮は、多変量解析法の組み合わせによることを特徴とする請求項1記載の評価方法。
- 刺激提示手段と、脳波測定手段と、脳波データに基づき刺激の類似度を評価する評価処理手段とを備え、
前記刺激提示手段は、複数の感覚刺激を、標的及び非標的からなる複数の刺激事象として、それぞれ複数回提示し、
前記脳波測定手段は、前記刺激提示手段による刺激提示直後の脳波を計測し、
前記評価処理手段は、複数の感覚刺激に対する認知課題を遂行中の脳波データを、多変量解析法の組み合わせにより次元圧縮を行って、二次元平面上又は三次元に前記刺激に対応する点を表示することを特徴とする脳情報の類似度の評価装置。 - 複数の感覚刺激に対する認知的処理と関連した脳波を計測して脳波データを得て、該脳波データに対して、多変量解析法の組み合わせにより次元圧縮を行って、二次元平面上又は三次元に前記刺激に対応する点を表示することを特徴とする脳情報の類似度の評価システム。
- コンピューターを、
複数の感覚刺激を、標的及び非標的からなる複数の刺激事象として、それぞれ複数回提示する刺激提示手段と、前記刺激提示手段により提示される複数の感覚刺激に対する認知課題を遂行中の脳波データを、複数の多変量解析法により次元圧縮を行って、二次元平面上又は三次元に前記刺激に対応する点を表示する、前記脳波データに基づき刺激の類似度を評価する評価処理手段と、評価結果を提示する提示手段として機能させるためのプログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016560207A JP6472144B2 (ja) | 2014-11-17 | 2015-11-16 | 脳波による類似度の評価方法、評価装置、評価システム及びプログラム |
US15/527,144 US10786173B2 (en) | 2014-11-17 | 2015-11-16 | Similarity evaluation method using brain waves, evaluation device, evaluation system, and program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014232786 | 2014-11-17 | ||
JP2014-232786 | 2014-11-17 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016080341A1 true WO2016080341A1 (ja) | 2016-05-26 |
Family
ID=56013878
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2015/082101 WO2016080341A1 (ja) | 2014-11-17 | 2015-11-16 | 脳波による類似度の評価方法、評価装置、評価システム及びプログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US10786173B2 (ja) |
JP (1) | JP6472144B2 (ja) |
WO (1) | WO2016080341A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108429853A (zh) * | 2018-02-12 | 2018-08-21 | 广东欧珀移动通信有限公司 | 电子装置、网络切换方法及相关产品 |
JP2019096977A (ja) * | 2017-11-21 | 2019-06-20 | 富士通株式会社 | 可視化方法、可視化装置及び可視化プログラム |
US10786173B2 (en) | 2014-11-17 | 2020-09-29 | National Institute Of Advanced Industrial Science And Technology | Similarity evaluation method using brain waves, evaluation device, evaluation system, and program |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108784690A (zh) * | 2018-06-19 | 2018-11-13 | 苏州修普诺斯医疗器械有限公司 | 移动脑电信号传输系统及信号传输方法 |
US11157081B1 (en) | 2020-07-28 | 2021-10-26 | Shenzhen Yunyinggu Technology Co., Ltd. | Apparatus and method for user interfacing in display glasses |
CN112315471A (zh) * | 2020-10-22 | 2021-02-05 | 垒途智能教科技术研究院江苏有限公司 | 基于智能迷宫的大脑训练评价系统及其评价方法 |
TWI802908B (zh) * | 2021-06-15 | 2023-05-21 | 南開科技大學 | 提供作答建議的輔助分析系統及其方法 |
CN114190954A (zh) * | 2021-12-23 | 2022-03-18 | 宁波大学医学院附属医院 | 一种患者认知功能评估方法及系统 |
CN114469136B (zh) * | 2022-02-14 | 2023-09-22 | 中南大学 | 一种热舒适度评价方法、系统及可存储介质 |
WO2024121115A1 (en) * | 2022-12-06 | 2024-06-13 | Stichting Radboud Universiteit | Processing of event-evoked physiological signals |
CN118411008B (zh) * | 2024-07-04 | 2024-10-29 | 上海华模科技有限公司 | 一种飞行员训练心理情绪同步管理方法及系统 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5799945A (en) * | 1980-12-12 | 1982-06-21 | Kogyo Gijutsuin | Brain wave shape relation display apparatus |
JP2000254239A (ja) * | 1999-03-08 | 2000-09-19 | Apollo Mec:Kk | 磁気治療器 |
JP2004342119A (ja) * | 2004-06-11 | 2004-12-02 | Kenji Mimura | 商品デザイン評価方法 |
JP2010274035A (ja) * | 2009-06-01 | 2010-12-09 | National Institute Of Advanced Industrial Science & Technology | 脳情報を表示する地図、作成方法及び該地図の使用方法 |
JP2011104340A (ja) * | 2009-10-23 | 2011-06-02 | Tottori Univ | 生体信号解析装置、生体信号解析方法、生体信号解析プログラム |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7647098B2 (en) * | 2005-10-31 | 2010-01-12 | New York University | System and method for prediction of cognitive decline |
DE102005061326A1 (de) | 2005-12-20 | 2007-06-21 | Basell Polyolefine Gmbh | Verfahren zur Herstellung von Metallocenen aus recycelten, substituierten Cyclopentadienylderivaten |
NZ627239A (en) * | 2008-03-26 | 2015-12-24 | Theranos Inc | Methods and systems for assessing clinical outcomes |
GB0906029D0 (en) * | 2009-04-07 | 2009-05-20 | Nat Univ Ireland Cork | A method of analysing an electroencephalogram (EEG) signal |
CN102804809B (zh) * | 2010-02-23 | 2015-08-19 | 皇家飞利浦电子股份有限公司 | 音频源定位 |
JP5544620B2 (ja) | 2010-09-01 | 2014-07-09 | 独立行政法人産業技術総合研究所 | 意思伝達支援装置及び方法 |
JP5472746B2 (ja) | 2010-09-28 | 2014-04-16 | 独立行政法人産業技術総合研究所 | 意思伝達支援装置及び方法 |
JP6146760B2 (ja) * | 2012-02-28 | 2017-06-14 | 国立研究開発法人産業技術総合研究所 | 序列化装置、序列化方法及びプログラム |
BR112015007002B1 (pt) * | 2012-09-28 | 2022-10-18 | The Regents Of The University Of California | Método e sistema para fornecer avaliação cognitiva ou sensorial de um indivíduo |
WO2016080341A1 (ja) | 2014-11-17 | 2016-05-26 | 国立研究開発法人産業技術総合研究所 | 脳波による類似度の評価方法、評価装置、評価システム及びプログラム |
-
2015
- 2015-11-16 WO PCT/JP2015/082101 patent/WO2016080341A1/ja active Application Filing
- 2015-11-16 US US15/527,144 patent/US10786173B2/en active Active
- 2015-11-16 JP JP2016560207A patent/JP6472144B2/ja active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5799945A (en) * | 1980-12-12 | 1982-06-21 | Kogyo Gijutsuin | Brain wave shape relation display apparatus |
JP2000254239A (ja) * | 1999-03-08 | 2000-09-19 | Apollo Mec:Kk | 磁気治療器 |
JP2004342119A (ja) * | 2004-06-11 | 2004-12-02 | Kenji Mimura | 商品デザイン評価方法 |
JP2010274035A (ja) * | 2009-06-01 | 2010-12-09 | National Institute Of Advanced Industrial Science & Technology | 脳情報を表示する地図、作成方法及び該地図の使用方法 |
JP2011104340A (ja) * | 2009-10-23 | 2011-06-02 | Tottori Univ | 生体信号解析装置、生体信号解析方法、生体信号解析プログラム |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10786173B2 (en) | 2014-11-17 | 2020-09-29 | National Institute Of Advanced Industrial Science And Technology | Similarity evaluation method using brain waves, evaluation device, evaluation system, and program |
JP2019096977A (ja) * | 2017-11-21 | 2019-06-20 | 富士通株式会社 | 可視化方法、可視化装置及び可視化プログラム |
JP7062923B2 (ja) | 2017-11-21 | 2022-05-09 | 富士通株式会社 | 可視化方法、可視化装置及び可視化プログラム |
CN108429853A (zh) * | 2018-02-12 | 2018-08-21 | 广东欧珀移动通信有限公司 | 电子装置、网络切换方法及相关产品 |
Also Published As
Publication number | Publication date |
---|---|
US20170340230A1 (en) | 2017-11-30 |
JPWO2016080341A1 (ja) | 2017-09-28 |
JP6472144B2 (ja) | 2019-02-20 |
US10786173B2 (en) | 2020-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6472144B2 (ja) | 脳波による類似度の評価方法、評価装置、評価システム及びプログラム | |
JP6146760B2 (ja) | 序列化装置、序列化方法及びプログラム | |
Bulagang et al. | A review of recent approaches for emotion classification using electrocardiography and electrodermography signals | |
Fritz et al. | Using psycho-physiological measures to assess task difficulty in software development | |
Wang et al. | Prediction of product design decision Making: An investigation of eye movements and EEG features | |
Nourbakhsh et al. | GSR and blink features for cognitive load classification | |
JP6404239B2 (ja) | 認知機能評価装置、認知機能評価装置の作動方法、システム及びプログラム | |
Zhu et al. | Detecting emotional reactions to videos of depression | |
US20170112427A1 (en) | Multimodal health assessment with neuro-opthalmological saccade tests | |
JP5414039B2 (ja) | 脳情報の表示方法及び装置 | |
Torres et al. | Emotion recognition related to stock trading using machine learning algorithms with feature selection | |
Samima et al. | EEG-based mental workload estimation | |
Jamal et al. | Integration of EEG and eye tracking technology: a systematic review | |
Sabio et al. | A scoping review on the use of consumer-grade EEG devices for research | |
Wang et al. | A CNN-based personalized system for attention detection in wayfinding tasks | |
JP6628341B2 (ja) | 意思解読装置及び意思伝達支援装置 | |
Takada et al. | Human error prediction using heart rate variability and electroencephalography | |
Buettner et al. | Machine Learning Based Diagnostics of Developmental Coordination Disorder using Electroencephalographic Data | |
Ivanitsky | Individual stable patterns of human brain rhythms as a reflection of mental processes | |
Sturgess et al. | Validating IMPACT: A new cognitive test battery for defence | |
Mir et al. | Assessing neural markers of attention during exposure to construction noise using machine learning classification of electroencephalogram data | |
AU2021102774A4 (en) | A system and a method for assessing mental ability of a user using an electroencephalogram | |
Conley | Learning User Experience Design (LUX): Adding the “L” to UX research using biometric sensors | |
Camilleri et al. | Assessing Task Difficulty in Software Testing using Biometric Measures | |
Wölfel et al. | Identification of Unreliable Data in in-VR Surveys using Biosignal Sensors |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15860098 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2016560207 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15527144 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 15860098 Country of ref document: EP Kind code of ref document: A1 |