Skill proficiency evaluation method based on beta-alpha brain electrical index measurement

Abstract

The application discloses a skill proficiency evaluation method based on a beta-alpha brain electrical index, characterized in that a consciousness control processing benchmark task, an automatic processing benchmark task and a professional skill test task are set, and brain electrical signals of a person to be tested are collected; according to preprocessed brain electrical data, the average value of baseline normalized waveband power of alpha and beta wavebands within 300-450 ms is calculated; a beta-alpha index is constructed, and the beta-alpha index value when the person to be tested correctly judges in the first professional skill test task is calculated i TR i , and the beta-alpha index value when the person to be tested incorrectly judges is calculated TW i The positive familiarity score of the person to be tested is calculated as Score+= Total 熟悉+ / N, and the greater the value, the higher the familiarity; the negative familiarity score of the person to be tested is calculated as Score-= Total 熟悉‑ / N, and the greater the value, the higher the habitual error; the method has the advantage that the task-specific change of alpha and beta wavebands in brain electrical signal data is analyzed, a beta-alpha combined index is constructed, and the familiarity of the person to be tested to a specific professional skill problem is objectively and directly evaluated.​

Description

Technical Field

[0001] This invention relates to the field of electroencephalography (EEG) neurofunctional measurement technology, and in particular to a method for evaluating skill proficiency based on β-α EEG index measurement. Background Technology

[0002] In every industry, those who are proficient in specific professional fields are crucial and scarce experts. The main difference between them and ordinary industry workers who, while possessing knowledge, can also make accurate judgments through careful consideration, lies in their level of proficiency. This difference stems from the different ways the brain processes specific problems. Experts operate more in an intuitive, automated mode of brain processing, while ordinary industry workers tend to rely more on conscious control. Becoming a domain expert from an ordinary industry worker requires a long period of learning, practice, reflection, and comprehensive training, necessitating continuous accumulation and a transformation in processing methods. However, currently, there is still a lack of direct and accurate methods for evaluating this level of proficiency based on brain processing methods, which to some extent affects the accurate assessment and effective training of professionals in these fields.

[0003] Existing research shows that EEG activity characteristics can reflect individual differences in information processing and decision-making patterns, especially the neural oscillations in the β and α bands, which play a crucial role in cognitive decision-making. This invention constructs a β-α index for measurement and analysis, and proposes an evaluation method for measuring proficiency by observing differences in this index signal under specific conditions. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a skill proficiency evaluation method based on β-α EEG index measurement. This method can effectively assess an individual's proficiency in a specific professional field by analyzing the conditional differences in EEG signals.

[0005] The technical solution adopted by this invention to solve the above-mentioned technical problems is: a skill proficiency evaluation method based on β-α EEG index measurement, comprising the following specific steps:

[0006] (1) The subject wears a multi-channel EEG measurement device to record EEG signals;

[0007] (2) Set up a baseline task for consciousness control processing, an automatic processing baseline task, and a professional skills test task. The professional skills test task includes two situations: correct and incorrect judgments by the participants. Collect the EEG signals of the test subjects in the three types of tasks to obtain the raw EEG data of the test subjects.

[0008] (3) Preprocess the raw EEG data, including signal amplification, segmentation, signal noise reduction, bandpass filtering and artifact removal.

[0009] (4) Based on the preprocessed EEG data, calculate the baseline normalized band power average of α and β within a time window of 300-450ms under different tasks for the test subjects, and calculate the index value of β-α, that is: the baseline normalized band power average of β minus the baseline normalized band power average of α.

[0010] (5) Compare the changes in the β-α index values ​​of the test subjects under different tasks, and calculate the average β-α index value S of the baseline task of consciousness control processing. CP And the average β-α index value S for automatically processing benchmark tasks AP There are N professional skills, each corresponding to a test task. Calculate the average β-α index value TR for correctly judging the i-th professional skill in the test task. i i∈N, if TR i <(S CP +2S AP If ) / 3, it indicates that the subject's i-th professional skill has reached a positive proficiency level; calculate the average β-α index value TW when making incorrect judgments in the test task for each i-th professional skill. i i∈N, if TW i <(S CP +2S AP If ) / 3, it means that the subject's i-th professional skill has reached a negative level of proficiency, i.e., habitual error; count the total number of skills that have reached a positive level of proficiency and have a correct number > 2 × the number of errors. 熟悉+ Then the subject's final positive familiarity score is: Score + = Total 熟悉+ / N, the larger the value, the higher the level of proficiency in the field; Total represents the total number of skills that have reached a negative level of proficiency and have more than 2 times the number of correct answers. 熟悉- Then the subject's final negative familiarity score is: Score - = Total 熟悉- / N, the larger the value, the higher the habitual errors in the professional skills of that field.

[0011] Furthermore, in step (2), the consciousness control processing benchmark task is a mental arithmetic task of square roots within 20, the automatic processing benchmark task is a mental arithmetic task of addition and subtraction within 3, and the professional skills test task includes two situations: correct and incorrect judgments by the participants. These are the main skills, knowledge and decision-making of different professional fields. Each professional skills test task includes four components: background description, question, correct answer and distractor answer. The question part requires concise text. The test extracts the EEG data of the test subjects within 2000ms from the display of the question. The consciousness control processing benchmark task and the automatic processing benchmark task each contain more than 20 tasks. The number of professional skills test tasks is set according to the actual situation, and each task is repeated 3 times.

[0012] Furthermore, in step (3), during the preprocessing of the raw EEG data, the raw EEG data is subjected to bandpass filtering of 0.5 to 40 Hz, and independent component analysis and data reconstruction are performed using the FastICA algorithm based on the principle of maximum negative entropy, so as to effectively remove artifact interference; and the α and β bands of the preprocessed EEG data are retained as target data for subsequent analysis.

[0013] Furthermore, in step (4), the method for calculating the baseline-normalized band power index value is as follows:

[0014] (4-1) Perform wavelet transform on the preprocessed EEG data to obtain the band power values ​​of α and β bands in the CPz channel in the interval of 300-450ms after the appearance of the stimulus (problem display) page;

[0015] (4-2) For the baseline tasks of consciousness control processing, automatic processing, professional skills test tasks with correct judgment, and professional skills test tasks with incorrect judgment, the band power was calculated separately. The baseline was set from -300ms to -100ms before stimulation, and the baseline-normalized band power (dB) was obtained. The calculation relationship is as follows: Palpha_Scp_dB=10×log10(Palpha_Scp / base_α_Scp)

[0016] Pbeta_Scp_dB=10×log 10(Pbeta_Scp / base_β_Scp)

[0017] Palpha_Sap_dB=10×log 10(Palpha_Sap / base_α_Sap)

[0018] Pbeta_Sap_dB=10×log 10(Pbeta_Sap / base_β_Sap)

[0019] Palpha_Tr_dB i = 10 × log 10(Palpha_Tr i / base_α_Tr i )

[0020] Pbeta_Tr_dB i = 10 × log 10(Pbeta_Tr i / base_β_Tr i )

[0021] Palpha_Tw_dB i = 10 × log 10(Palpha_Tw i / base_α_Tw i )

[0022] Pbeta_Tw_dB i = 10 × log 10(Pbeta_Tw i / base_β_Tw i )

[0023] Wherein: Palpha represents alpha band power, Pbeta represents beta band power, Scp represents the baseline task for consciousness control processing, Sap represents the baseline task for automatic processing, Tr represents a skill test task with correct judgment, and Tw represents a skill test task with incorrect judgment. This indicates that the average value is calculated for this type of task, i.e.: This represents the average of multiple repeated tests for the i-th professional skill test task, i.e.: k is the frequency value, ranging from 9 to 30 Hz; dB represents the value obtained after baseline normalization; base represents the average band power during the baseline period of -300 ms to -100 ms before stimulation. For example, Palpha_Scp represents the alpha band power in the baseline task of conscious control processing, Palpha_Scp_dB represents Palpha_Scp after baseline normalization, and base_α_Scp represents the average band power of the alpha band in the baseline task of conscious control processing during the baseline period of -300 ms to -100 ms before stimulation.

[0024] Furthermore, in step (5), S is calculated based on the β-α index value.CP S AP TR i TW i Total 熟悉+ Total 熟悉- The formulas for calculating Score+ and Score- are as follows:

[0025] S CP =Pbeta_Scp_dB-Palpha_Scp_dB,S AP =Pbeta_Sap_dB - Palpha_Sap_dB

[0026] TR i =Pbeta_Tr_dB i -Palpha_Tr_dB i TW i =Pbeta_Tw_dB i -Palpha_Tw_dB i

[0027] Score + = Total 熟悉+ / N

[0028] Score = Total 熟悉- / N.

[0029] Compared with the prior art, the advantages of the present invention are:

[0030] (1) This method objectively and directly assesses the brain processing patterns of test subjects for specific professional skills problems by analyzing the task-specific changes in the α and β bands in EEG signal data. It plays an important role in measuring the skill familiarity of test subjects and in the reasonable identification, selection and training of professional skills experts. This method also proposes a formatted processing standard for professional skills test questions that is convenient for EEG testing: background description, question, correct answer, and distractor answer.

[0031] (2) This method uses the baseline normalized band power values ​​of α and β to construct the β-α combined index and extract neural activity features in the key time window of 300-450ms. It is simple, sensitive and efficient for identifying processing patterns and familiarity. Attached Figure Description

[0032] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0033] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0034] As shown in the figure, the skill proficiency evaluation method based on β-α EEG index measurement includes the following specific steps:

[0035] (1) The subject wears a multi-channel EEG measurement device to record EEG signals; the multi-channel EEG measurement device can use an existing EEG acquisition system, such as the EMOTIV EPOC FlexSaline Sensor Kit EEG acquisition system.

[0036] (2) Set a baseline task for consciousness control processing, using a mental arithmetic task involving square roots within 20: such as... There are 20 questions in total. The stimulus display order is as follows: the question is displayed, and after a random time interval of 600ms to 1000ms, the correct answer and distractor answers are displayed, waiting for the subject to press a button to select. The baseline task is automatically processed, using mental arithmetic tasks involving addition and subtraction within numbers 3, such as 1+1=?, with 20 questions in total, and the stimulus display order is the same as above. The professional skills test tasks include both correct and incorrect judgments by the participants, using key skills and decision-making questions from different professional fields. Each test task includes four components: background description, question, correct answer, and distractor answer, with the question section requiring concise text. For example, in the vehicle driving skills response decision-making question, the background description is "You are driving a vehicle on a city road and encounter a traffic light signal at an intersection. Please decide your driving behavior according to the signal light.", the question is "Red light," the correct answer is "Brake," and the distractor answer is "Turn left." The number of professional skills test tasks is set according to the actual situation, and each task is repeated 3 times. The stimulus display sequence is as follows: background description is displayed for 10 seconds, then disappears, followed by the display of the question. After a random interval of 600ms to 1000ms, the correct answer and distractor answers are displayed, and the subject is asked to select an answer by pressing a key. The EEG signals of the subjects are collected from the start of the question display to 2000ms in the three types of tasks to obtain the raw EEG data of the subjects.

[0037] (3) Preprocessing of raw EEG data includes signal amplification, segmentation, signal denoising, bandpass filtering, and artifact removal. Among them, the raw EEG data is bandpass filtered at 0.5-40Hz, and independent component analysis and data reconstruction are performed using the FastICA algorithm based on the principle of maximum negative entropy to effectively remove interference from electrooculography, electromyography, and other artifacts. The preprocessed EEG data retains α (9-13Hz) and β (14-30Hz) as target data for subsequent analysis, providing clear and reliable basic signals for familiarity assessment.

[0038] (4) Based on the preprocessed EEG data, calculate the baseline-normalized band power averages of α and β within a time window of 300–450 ms for the subjects under different tasks, and calculate the index value of β-α, i.e., the baseline-normalized band power average of β minus the baseline-normalized band power average of α; specifically:

[0039] (4-1) Perform wavelet transform on the preprocessed EEG data to obtain the band power values ​​of α and β bands in the CPz channel in the interval of 300-450ms after the question display page appears;

[0040] (4-2) For the baseline tasks of consciousness control processing, automatic processing, professional skills test tasks with correct judgment, and professional skills test tasks with incorrect judgment, the band power was calculated separately. The baseline was set from -300ms to -100ms before stimulation, and the baseline-normalized band power (dB) was obtained. The calculation relationship is as follows: Palpha_Scp_dB=10×log10(Palpha_Scp / base_α_Scp)

[0041] Pbeta_Scp_dB=10×log 10(Pbeta_Scp / base_β_Scp)

[0042] Palpha_Sap_dB=10×log 10(Palpha_Sap / base_α_Sap)

[0043] Pbeta_Sap_dB=10×log 10(Pbeta_Sap / base_β_Sap)

[0044] Palpha_Tr_dB i = 10 × log 10(Palpha_Tr i / base_α_Tr i )

[0045] Pbeta_Tr_dB i = 10 × log 10(Pbeta_Tr i / base_β_Tr i )

[0046] Palpha_Tw_dB i = 10 × log 10(Palpha_Tw i / base_α_Twi )

[0047] Pbeta_Tw_dB i = 10 × log 10(Pbeta_Tw i / base_β_Tw i )

[0048] Wherein: Palpha represents alpha band power, Pbeta represents beta band power, Scp represents the baseline task for consciousness control processing, Sap represents the baseline task for automatic processing, Tr represents a skill test task with correct judgment, and Tw represents a skill test task with incorrect judgment. This indicates that the average value is calculated for this type of task, i.e.: This represents the average of multiple repeated tests for the i-th professional skill test task, i.e.: k is the frequency value, ranging from 9 to 30 Hz; dB represents the value obtained after baseline normalization; base represents the average band power during the baseline period of -300 ms to -100 ms before stimulation. For example, Palpha_Scp represents the alpha band power in the baseline task of conscious control processing, Palpha_Scp_dB represents Palpha_Scp after baseline normalization, and base_α_Scp represents the average band power of the alpha band in the baseline task of conscious control processing during the baseline period of -300 ms to -100 ms before stimulation.

[0049] (5) Compare the changes in the β-α index values ​​of the test subjects under different tasks, and calculate the average β-α index value S of the baseline task of consciousness control processing. CP And the average β-α index value S for automatically processing benchmark tasks AP There are N professional skills, each corresponding to a test task. Calculate the average β-α index value TR for correctly judging the i-th professional skill in the test task. i i∈N, if TR i <(S CP +2S AP If ) / 3, it indicates that the subject's i-th professional skill has reached a positive proficiency level; calculate the average β-α index value TW when making incorrect judgments in the test task for each i-th professional skill. i i∈N, if TW i <(S CP +2S AP If ) / 3, it means that the subject's i-th professional skill has reached a negative level of proficiency, i.e., habitual error; count the total number of skills that have reached a positive level of proficiency and have a correct number > 2 × the number of errors.熟悉+ Then the subject's final positive familiarity score is: Score + = Total 熟悉+ / N, the larger the value, the higher the level of proficiency in the field; Total represents the total number of skills that have reached a negative level of proficiency and have more than 2 times the number of correct answers. 熟悉- Then the subject's final negative familiarity score is: Score - = Total 熟悉- / N, the larger the value, the higher the rate of habitual errors in the field of expertise. S CP S AP TR i TW i Total 熟悉+ Total 熟悉- The formulas for calculating Score+ and Score- are as follows:

[0050] S CP =Pbeta_Scp_dB-Palpha_Scp_dB,S AP =Pbeta_Sap_dB - Palpha_Sap_dB

[0051] TR i =Pbeta_Tr_dB i -Palpha_Tr_dB i TW i =Pbeta_Tw_dB i -Palpha_Tw_dB i

[0052] Score + = Total 熟悉+ / N

[0053] Score = Total 熟悉- / N.

[0054] The scope of protection of this invention includes, but is not limited to, the above embodiments. The scope of protection is defined by the claims. Any substitutions, modifications, or improvements to this technology that are easily conceived by those skilled in the art fall within the scope of protection of this invention.

Claims

1. A method for evaluating skill proficiency based on β-α electroencephalogram (EEG) index measurements, characterized in that... The specific steps include the following: (1) The subjects were fitted with multi-channel EEG measurement devices to record EEG signals; (2) Set up a consciousness control processing benchmark task, an automatic processing benchmark task, and a professional skills test task. Among them, the consciousness control processing benchmark task is a mental calculation task of square roots within 20, the automatic processing benchmark task is a mental calculation task of addition and subtraction within 3, and the professional skills test task includes two situations: correct and incorrect judgment by the participants. Collect the EEG signals of the test subjects in the three types of tasks and obtain the raw EEG data of the test subjects. (3) Preprocess the raw EEG data, including signal amplification, segmentation, signal noise reduction, bandpass filtering and artifact removal. (4) Based on the preprocessed EEG data, calculate the baseline normalized band power average of α and β within a time window of 300-450ms under different tasks for the test subjects, and calculate the index value of β-α, that is: the baseline normalized band power average of β minus the baseline normalized band power average of α. (5) Compare the changes in the β-α index values ​​of the test subjects under different tasks, and calculate the average β-α index value S of the baseline task of consciousness control processing. CP And the average β-α index value S for automatically processing benchmark tasks AP There are N professional skills, each corresponding to a test task. Calculate the average β-α index value TR for correctly judging the i-th professional skill in the test task. i , i∈N, if TR i < (S CP + 2S AP If ) / 3, it indicates that the subject's i-th professional skill has reached a positive proficiency level; calculate the average β-α index value TW when making incorrect judgments in the test task for each i-th professional skill. i , i∈N, if TW i <(S CP + 2S AP If ) / 3, it means that the subject's i-th professional skill has reached a negative level of proficiency, i.e., a habitual error; the statistics show all those who have reached a positive level of proficiency and Total number of skills 熟悉+ Then the subject's final positive familiarity score is: Score + = Total 熟悉+ / N, the larger the value, the higher the proficiency in that professional skill; statistics are compiled for all those who have reached a negative proficiency level and Total number of skills 熟悉- Then the subject's final negative familiarity score is: Score - = Total 熟悉- / N, the larger the value, the higher the habitual error rate for that professional skill.

2. The skill proficiency evaluation method based on β-α EEG index measurement as described in claim 1, characterized in that: In step (2), the professional skills test task includes two situations: correct and incorrect judgments by the participants. It covers the main skills, knowledge and decision-making of different professional fields. Each professional skills test task includes four components: background description, question, correct answer and distractor answer. The test extracts the EEG data of the test subjects within 2000ms from the time the question is displayed. The consciousness control processing benchmark task and the automatic processing benchmark task each contain more than 20 tasks, and each task is repeated 3 times.

3. The skill proficiency evaluation method based on β-α EEG index measurement as described in claim 1, characterized in that: In step (3), during the preprocessing of the raw EEG data, the raw EEG data is subjected to bandpass filtering of 0.5 to 40 Hz, and independent component analysis and data reconstruction are performed using the FastICA algorithm based on the principle of maximum negative entropy to effectively remove artifact interference; and the α and β bands of the preprocessed EEG data are retained as target data for subsequent analysis.

4. The skill proficiency evaluation method based on β-α EEG index measurement as described in claim 2, characterized in that: In step (4), the method for calculating the baseline normalized band power index is as follows: (4-1) Perform wavelet transform on the preprocessed EEG data to obtain the band power values ​​of α and β bands in the CPz channel in the interval of 300-450ms after the appearance of the stimulus (question display) page; (4-2) For the baseline tasks of consciousness control processing, automatic processing, correct judgment professional skills test tasks, and incorrect judgment professional skills test tasks, the band power was calculated separately. The baseline was set from -300ms to -100ms before stimulation, and the baseline-normalized band power (dB) was obtained. The calculation relationship is as follows: , ， , ， , ， , ， , ， , ， , ， , ， Where: symbol Represents α-band power, symbol Represents beta band power, symbol Indicates the baseline task of consciousness control processing, symbol Indicates automatic processing of baseline tasks, symbol The symbol represents a professional skills test task that indicates the correct judgment. This refers to a professional skills test task where the judgment is incorrect. This indicates an average of the baseline task for conscious control processing or the baseline task for automatic processing, i.e.: , This represents the average of multiple repeated tests for the i-th professional skill test task, i.e.: k is the frequency value, which ranges from 9 to 30 Hz; symbol This represents the value obtained after baseline normalization, with the symbol... This represents the average band power during the baseline period from -300ms to -100ms before stimulation. This indicates the alpha band power in the baseline task of consciousness control processing. Indicates the baseline normalization process , This represents the average band power of the alpha band during the baseline period from -300 ms to -100 ms before stimulation in the baseline task of conscious control processing; This indicates the β-band power in the baseline task of consciousness control processing. Indicates the baseline normalization process , This represents the average band power of the β band during the baseline period from -300 ms to -100 ms before stimulation in the baseline task of conscious control processing; This indicates the α-band power in the automatic processing reference task. Indicates the baseline normalization process , This represents the average band power of the alpha band during the baseline period from -300 ms to -100 ms before stimulation in the automatic processing baseline task; This indicates the β-band power in the automatic processing reference task. Indicates the baseline normalization process , This represents the average band power of the β band during the baseline period from -300 ms to -100 ms before stimulation in the automatic processing baseline task; This represents the α-band power in the i-th professional skills test task where the judgment is correct. Indicates the baseline normalization process , The value represents the average band power of the α band during the baseline period from -300ms to -100ms before stimulation in the i-th professional skills test task where the judgment is correct. This represents the β-band power in the i-th professional skills test task where the judgment is correct. Indicates the baseline normalization process , The value represents the average band power of the β band during the baseline period from -300ms to -100ms before stimulation in the i-th professional skills test task where the judgment is correct. This represents the α-band power in the i-th professional skills test task where the judgment was incorrect. Indicates the baseline normalization process , The value represents the average band power of the α band during the baseline period from -300ms to -100ms before stimulation in the i-th professional skills test task where the judgment was incorrect. This represents the β-band power in the i-th professional skills test task where the judgment was incorrect. Indicates the baseline normalization process , The value represents the average band power of the β band during the baseline period from -300ms to -100ms before stimulation in the i-th professional skills test task where the judgment was incorrect.

5. The skill proficiency evaluation method based on β-α EEG index measurement as described in claim 4, characterized in that: In step (5), S is calculated based on the β-α index value. CP S AP TR i TW i Total 熟悉+ Total 熟悉- The formulas for calculating Score+ and Score- are as follows: , ， , ， , ， , 。

Images