Measurement and training quantitative evaluation method for cognition flexibility of piano visual playing

Abstract

The invention discloses a measurement and training quantitative evaluation method for cognition flexibility of piano visual playing, and the method comprises the steps: measuring the conversion cost of each stage of piano visual playing training through a task conversion normal form, and synchronously collecting baseline and task state pulse wave signals; a cognitive flexibility objective evaluation model is established by fusing piano visual playing performance and physiological features, and the training effect of piano visual playing is quantified. The method comprises the following steps that behavior performance and pulse wave signals of a subject in task conversion normal form testing and piano visual playing are collected through an end network cloud platform; de-noising the pulse wave signal and then extracting multi-dimensional physiological features; statistical analysis is carried out on the conversion cost, and a correlation coefficient is used to screen features significantly related to the conversion cost; a random forest model is constructed based on the screening features, and the cognitive flexibility level is evaluated; and the training effect of the piano visual playing on the cognitive flexibility is quantified by comparing the score change of each training stage. The invention provides an effective method for testing and training quantitative evaluation of cognitive flexibility.

Description

Technical Field

[0001] The present invention belongs to the fields of cognitive ability assessment and information technology, and particularly relates to a quantitative assessment method for measuring and training the cognitive flexibility of piano sight-reading. Background Art

[0002] Cognitive flexibility is one of the core components of executive function, referring to the ability of an individual to quickly switch cognitive strategies according to environmental demands. Research shows that the level of cognitive flexibility is closely related to learning efficiency, problem-solving, and creative thinking. A high level of cognitive flexibility helps an individual to efficiently switch in a multi-task environment, adapt to a new environment, and solve complex problems, while deficiencies in cognitive flexibility may lead to behavioral rigidity and maladaptation. Therefore, the research on assessment and training methods for cognitive flexibility has important theoretical and practical significance.

[0003] Currently, the commonly used cognitive flexibility assessment methods mainly include two categories: subjective assessment and objective assessment. Subjective assessment is carried out through scales, but there are problems such as strong subjectivity of assessment results and difficulty in quantification. Objective assessment mainly includes two methods: one is the assessment based on behavioral indicators, mainly using the task-switching paradigm, and quantifying the level of cognitive flexibility by measuring the switching cost of the subject when switching different task rules; the other is the assessment based on physiological indicators. Traditional methods mainly use technologies such as electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) to monitor brain activities, but these methods are expensive, complex to operate, and difficult to apply in daily training environments. In recent years, it has been found that heart rate variability (HRV), as an indicator reflecting the activity of the autonomic nervous system, has been proven to be closely related to cognitive function and executive control. And photoplethysmography (PPG) can more conveniently extract information related to HRV and reflect the changes of the autonomic nervous system during the cognitive task process. Compared with ECG, PPG sensors have the advantages of being portable, non-invasive, simple to operate, and low in cost, and are more suitable for real-time monitoring in natural training scenarios.

[0004] In the aspect of cognitive flexibility training, existing research has confirmed that music training can promote the development of executive functions. Among them, piano sight-reading involves the rapid conversion of multi-modal information such as vision, audition, and movement, which highly coincides with the processing characteristics of cognitive flexibility. However, there are two main problems in existing research: one is the lack of a systematic evaluation method that integrates behavioral and physiological indicators; the other is the difficulty in quantifying the dynamic changes in cognitive flexibility during training, resulting in the separation of the evaluation and training processes and reducing the real-time nature of training effect evaluation. Therefore, establishing a set of measurement and training quantification evaluation methods for piano sight-reading on cognitive flexibility has important scientific significance and application value. Summary of the Invention

[0005] The purpose of the present invention is to solve the problems in the prior art such as strong subjectivity of the cognitive flexibility evaluation method, single evaluation dimension, and difficulty in quantifying the training process, and to provide a measurement and training quantification evaluation method for piano sight-reading on cognitive flexibility. This method measures the switching cost of each training stage through a task-switching paradigm, synchronously collects pulse wave signals, and establishes an objective evaluation model by integrating behavioral performance and physiological characteristics. Combining with the random forest algorithm to analyze the selected features, it realizes the dynamic quantification of the change in the level of cognitive flexibility throughout the training process. This evaluation method provides an objective and systematic evaluation means for studying the measurement and training quantification of piano sight-reading on cognitive flexibility.

[0006] To achieve the above object, the present invention adopts the following technical solutions: A measurement and training quantification evaluation method for piano sight-reading on cognitive flexibility, the measurement and training quantification evaluation method of cognitive flexibility includes the following steps: S1. Synchronously collect the pulse wave signals of the subject in the task-switching paradigm test task and the piano sight-reading task through the end-network cloud platform and record the behavioral data; wherein, the task-switching paradigm adopts the cue task-switching paradigm, and in each trial, the subject needs to execute one of the two tasks according to the cue prompt, and the cognitive flexibility level of the subject in switching between different tasks is examined; the piano sight-reading task requires the subject to play the notes according to the time indicator line; S2. Preprocess the collected behavioral data and physiological data, including outlier processing of the test task data, calculation of reaction time switching cost, calculation of playing time fitting degree of the piano sight-reading task data, and denoising processing of the original pulse wave signal; wherein, the reaction time switching cost reflects the cognitive cost paid by the subject during task switching, and the playing time fitting degree reflects the time feature performance of the subject during the sight-reading task; S3. Identify the feature points of the denoised pulse wave signal and extract multi-dimensional features, specifically including the construction of the main wave peak point sequence and the extraction of multi-dimensional physiological features. Among them, the main wave peak point sequence is the basis for analyzing the heart rate variability characteristics; the multi-dimensional physiological features include pulse wave morphology features, heart rate variability features, and blood oxygen saturation features, which are used to reflect the regulation of the autonomic nervous system during the cognitive task process. S4. Conduct a correlation analysis based on the conversion cost and multi-dimensional features and perform feature screening. First, analyze the distribution characteristics of the conversion cost through statistical methods to evaluate the differences in the task conversion ability of the subject group; then, screen out the key physiological features related to the cognitive flexibility level through correlation analysis and variance inflation factor methods; finally, construct a dataset for objectively evaluating the cognitive flexibility level. Among them, the distribution feature analysis can reveal the individual differences in the cognitive flexibility level; the variance inflation factor is a statistical index used to quantify the degree of multi-collinearity between features. S5. Combine the random forest algorithm to fuse behavioral features and physiological features, and achieve an objective evaluation of the cognitive flexibility level through feature selection and model construction. Specifically, based on the dataset established in S4, construct a random forest regression model, which takes the features as input and outputs a quantified cognitive flexibility score; then, use the K-fold cross-validation method to evaluate the model performance, and calculate indicators such as the coefficient of determination (R²) and root mean squared error (RMSE) to ensure the stability and generalization ability of the model. S6. Quantify the training effect of piano sight-reading on cognitive flexibility according to the evaluation results of different piano training stages. First, verify the significance of the difference in the conversion cost before and after training through the paired T-test statistical method to evaluate the statistical significance of the training effect; second, based on the cognitive flexibility scoring model constructed in S5, calculate the change in the cognitive flexibility level at different training stages to quantify the improvement effect brought by the training; finally, intuitively display the change trend of the cognitive flexibility scores of the subject group through a line chart to reflect the continuous impact of piano sight-reading training on cognitive flexibility. Among them, the paired T-test is a statistical method used to compare the differences in the measured values of the same group of subjects at different time points; the line chart visualization method can intuitively display the dynamic changes in cognitive flexibility during the training process.

[0007] Further, the process of step S1 is as follows: S101. Build the experimental environment through the end-to-end cloud platform, including the display, key device, PPG sensor and MIDI piano keyboard, fix the PPG sensor on the tip of the subject's left index finger, transmit the data to the cloud server for storage in real time through the network, and conduct the experiment under appropriate environmental conditions. The purpose of this step is to build a stable and reliable data acquisition system to ensure the synchronous acquisition and transmission of behavioral data and physiological data; S102. In the task switching paradigm test task phase, each trial first presents a central fixation point to guide the subject's attention. Then, a number-letter stimulus pair consisting of a random combination of letters and numbers is presented in the center of the screen, where the left and right positions of the letters and numbers are randomly determined. The color of the stimulus pair serves as the task clue for the current trial, prompting the subject to perform the type of task. When the task clue is orange, the subject needs to judge whether the number is an odd number; when the task clue is blue, the subject needs to judge whether the letter is a vowel. The subject needs to use the index finger and middle finger of the right hand to make a choice by pressing the key. When the subject responds and presses the key, the target stimulus disappears immediately, and then a blank screen of random duration is presented to reduce the impact of the expectation effect on the reaction time. During the test, the reaction time of each trial, the task type of each trial (task repetition or conversion) and the task accuracy are recorded. This step induces the psychological processing process related to cognitive flexibility through the task switching paradigm, requiring the subject to flexibly switch between the two judgment rules, so as to obtain objective behavioral indicators reflecting cognitive flexibility; S103. During the piano sight-reading training stage, a musical score based on the vocal notation is presented in the center of the display, where the numbers 1-7 represent different pitches. The playing speed is controlled by moving a red vertical indicator line from left to right on the score. When the indicator line touches the left edge of the note, it indicates that the note should be played. The score design contains multiple rhythm change points. By adjusting the note length and the number of notes per unit time, the subjects are required to quickly adjust the established rhythm expectations and avoid inertial playing, thereby effectively exerting the cognitive flexibility of the subjects. During the training process, the subject's key pressing time sequence and the standard note playing time sequence are recorded, and the playing time fit is calculated. Each training session lasts 15 minutes. This step systematically trains the cognitive flexibility of the subjects by designing a sight-reading task with a rhythm change pattern to simulate the conversion process in the cognitive task.

[0008] Furthermore, the process of step S2 is as follows: S201. Remove outliers from the trial data in the test task, including removing trials with reaction times below the set threshold and trials with extreme values ​​exceeding multiple standard deviations. For each subject, calculate the average reaction time of the repeated task trials and the switch task trials ( ), and calculate the reaction time switching cost 。Calculate the fitting degree of playing time for the sight-reading reaction time data in the piano sight-reading task. Through the processing of behavioral data in this step, an objective behavioral index reflecting the level of cognitive flexibility and a behavioral index reflecting the piano sight-reading performance are obtained; S202. Decompose the original pulse wave signal using the Improved Complete Empirical Mode Decomposition with adaptive noise (ICEEMDAN) algorithm to obtain multiple Intrinsic Mode Functions (IMFs), hereinafter referred to as IMFs for short. The ICEEMDAN algorithm is developed based on the Empirical Mode Decomposition (EMD). By introducing adaptive noise and ensemble averaging, it reduces the mode mixing phenomenon and improves the stability and accuracy of decomposition. Through this efficient signal decomposition method in this step, intrinsic mode components with different frequency characteristics are extracted from the complex pulse wave signal; S203. For the first several IMF components, use the wavelet threshold denoising method for processing. Select an appropriate wavelet basis for multi-layer decomposition and use a hard threshold function to remove high-frequency noise. Through this wavelet denoising technology in this step, high-frequency noise in the pulse wave signal is removed, improving the signal-to-noise ratio of the signal; S204. Superimpose the first denoised IMF components with the remaining IMF components to obtain a denoised reconstructed signal. Through this step, the denoised signal is combined with other important frequency band information to reconstruct a more accurate and clear pulse wave signal for subsequent analysis; S205. Use the differential method combined with the cubic spline interpolation method to remove the baseline drift. Through this step, the baseline drift in the pulse wave signal is removed, providing a more reliable signal for subsequent physiological analysis; S206. Use the dynamic threshold method based on the correlation coefficient of adjacent cycles to detect and remove abnormal cycles. This step reduces the influence of motion artifact noise introduced by body position changes and improves the waveform quality of the pulse wave signal.

[0009] Furthermore, the process of step S3 is as follows: S301. Based on the pulse wave signal obtained in step S2, use the first-order difference method to identify the main wave peak points of each cycle, and extract the interval sequence between adjacent peak points as the basic data for heart rate variability analysis. Through sequence reconstruction in this step, a standardized data basis is provided for subsequent multi-dimensional feature extraction; S302, analyze the pulse wave morphology and extract the morphological features reflecting the autonomic nervous activity; perform time domain analysis on the time interval sequence obtained in S301 and extract the statistical features reflecting the heart rate variability; when performing spectrum analysis, first perform cubic spline interpolation resampling on the time interval sequence and set the sampling frequency Hz, to ensure the equidistant nature of the data. The Welch method was then used (window length , overlap ratio %) extract the energy distribution characteristics of multiple frequency bands to characterize the autonomic nervous system regulation; construct a Poincaré graph for nonlinear analysis to obtain nonlinear characteristics reflecting the dynamic characteristics of heart rate; and calculate the blood oxygen saturation characteristics based on the photoelectric characteristics of the pulse wave signal. This step obtains physiological characteristics that fully reflect the state of autonomic nervous system regulation through multi-dimensional analysis.

[0010] Furthermore, the process of step S4 is as follows: S401, calculate the mean, standard deviation, maximum, minimum, skewness and kurtosis of the switching cost, and visualize the group differences through box plots. This step provides a basis for subsequent analysis by analyzing the statistical characteristics of cognitive flexibility; S402. Evaluate the strength of the correlation between each feature and the conversion cost through Spearman correlation analysis, and retain the absolute value of the correlation coefficient And the significance level The characteristics of; variance inflation factor VIF analysis was used to eliminate VIF> features to eliminate collinearity and ensure independence between features. , , They are the correlation coefficient comparison threshold, significance level comparison threshold, and inflation factor comparison threshold. This step uses statistical analysis methods to screen out behavioral and physiological characteristics that are significantly related to cognitive flexibility. S403, constructing a data set for objectively evaluating cognitive flexibility based on the behavioral characteristics, physiological characteristics and switching costs screened out in step S402, and randomly dividing the data set into a training set and a test set to provide a standardized data basis for subsequent model training and verification.

[0011] Furthermore, the process of step S5 is as follows: S501. Based on the dataset constructed in step S4, use the recursive feature elimination method based on random forest. In each round, remove the feature with the lowest feature importance score, construct a random forest regression model and train it. The random forest regression model is used to evaluate the cognitive flexibility level of the subject. The parameters include: the number of decision trees, the maximum depth, the number of features when splitting each node, and the minimum number of samples in the leaf node. The input of the random forest regression model is the selected features, and the output is a cognitive flexibility score from 0 to 100 points. The higher the score, the higher the cognitive flexibility level. S502. Use the k-fold cross-validation method to evaluate the performance of the random forest regression model, and calculate indicators such as the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE) to ensure that the model has good generalization ability. This step ensures the reliability of the constructed cognitive flexibility evaluation model through a strict verification method.

[0012] Furthermore, the process of step S6 is as follows: S601. Conduct a paired T-test on the switch cost data of the subject before and after training (if the data is non-normally distributed, use the Wilcoxon signed-rank test), calculate the p-value to evaluate the statistical significance of the training effect; at the same time, calculate Cohen's d effect size to quantify the magnitude of the training effect. Cohen's d effect size is a standardized difference index used to measure the difference between the experimental group and the control group, or the difference between the same group before and after. The larger the effect size, the more significant the difference between them. This step verifies the effect of piano sight-reading training on cognitive flexibility based on the direct comparison of behavioral data. S602. Use the random forest regression model of the cognitive flexibility level constructed in step S5 for scoring, calculate the cognitive flexibility scores of the subject at different training stages, and calculate the relative improvement percentage based on the score changes. This step realizes the quantitative evaluation of the training effect through a standardized scoring system. S603. Display the group score trend through a line chart. This step intuitively presents the change of the cognitive flexibility score during the piano sight-reading training process through a visualization method, and analyzes the overall trend of the training effect.

[0013] Compared with the prior art, the present invention has the following advantages and beneficial effects: (1) The present invention proposes a cognitive flexibility evaluation method that integrates behavioral data and physiological data, improving the limitations of traditional methods that only rely on subjective questionnaires or single behavioral data. Traditional methods have problems such as a single evaluation dimension, lack of objective physiological basis, and difficulty in quantifying the training process. The present invention constructs a more comprehensive cognitive flexibility evaluation system through multi-dimensional index analysis, and combines physiological indicators reflecting the activity of the autonomic nervous system in the pulse wave signal, improving the objectivity and accuracy of the evaluation.

[0014] (2) The present invention combines the adaptive noise complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) algorithm and wavelet threshold denoising technology to preprocess the pulse wave signal. By adaptively decomposing the pulse wave signal, the intrinsic mode functions (IMFs) in the signal are effectively extracted, and then the wavelet denoising technology is used to remove high-frequency noise, finally achieving multi-level signal optimization. This method significantly improves the signal-to-noise ratio of the pulse wave signal, solves the technical problems of signal interference and excessive noise in traditional denoising methods, and effectively improves the accuracy and stability of physiological index extraction.

[0015] (3) The present invention takes piano sight-reading as both a training means and an evaluation tool for cognitive flexibility, and uses the random forest algorithm to establish an evaluation model for the level of cognitive flexibility based on behavioral data and physiological data. Through feature screening and cross-validation techniques, this model realizes the objective evaluation of the cognitive flexibility level of the subjects, and can accurately quantify the effect of piano sight-reading training by comparing the evaluation results of different training stages. The present invention breaks through the limitation of the separation of traditional cognitive training and evaluation, and provides a complete technical solution for the evaluation of the training effect of cognitive flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of a method for quantitatively evaluating the training effect of piano sight-reading on cognitive flexibility disclosed in Embodiment 1 of the present invention; Figure 2 It is a schematic diagram of the experimental process of the task switching paradigm in Embodiment 1 of the present invention; Figure 3 It is a processing flowchart of the original pulse wave signal in Embodiment 1 of the present invention; Figure 4 It is a flowchart of physiological feature extraction in Embodiment 1 of the present invention; Figure 5 It is a decomposition effect diagram of the ICEEMDAN algorithm for the pulse wave in Embodiment 2 of the present invention; Figure 6 It is a pulse wave signal diagram after denoising by ICEEMDAN combined with wavelet threshold in Embodiment 2 of the present invention; Figure 7 It is a pulse wave signal diagram after baseline removal in Embodiment 2 of the present invention; Figure 8This is the detection effect diagram of the main wave peak point of the pulse wave in Embodiment 2 of the present invention. Detailed implementation manners

[0018] In order to enable those skilled in the art of this technology to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of this application.

[0019] The mention of "embodiment" in this application means that the specific features, structures or characteristics described in connection with the embodiment may be included in at least one embodiment of this application. The phrase appears in various positions in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described in this application can be combined with other embodiments.

[0020] Embodiment 1 This embodiment discloses a method for quantitatively evaluating the training of cognitive flexibility by sight-reading the piano, as Figure 1 shown, and the specific steps are as follows: S1. Collect the pulse wave signals of the subjects in the task switching paradigm test task and the piano sight-reading training task through the end-network cloud platform and record the behavioral data; Figure 2 This is the schematic diagram of the experimental process of the above task switching paradigm.

[0021] S101. Build an experimental environment through the end-network cloud platform, including a display, a key device, a PPG sensor (sampling frequency 100Hz) and a MIDI piano keyboard. Fix the PPG sensor on the fingertip of the left index finger of the subject, and transmit the data to the cloud server for storage in real time through the network. The experiment is carried out in a quiet laboratory with appropriate light intensity and a temperature of 20-26°C; S102. In the task switching paradigm test phase, each trial first presents a central fixation point ("+") for 150ms to guide the subject's attention. Then, a number-letter stimulus pair (such as "A4", "B7", etc.) consisting of a random combination of letters and numbers is presented in the center of the screen, where the left and right positions of the letters and numbers are randomly determined. The color of the stimulus pair serves as the task clue of the current trial, prompting the subject to perform the type of task. When the task clue is orange, the subject needs to judge whether the number is an odd number; when the task clue is blue, the subject needs to judge whether the letter is a vowel. The subject needs to use the index finger and middle finger of the right hand to make a choice by pressing a key, where pressing "1" means "yes" and pressing "2" means "no". When the subject responds and presses the key, the target stimulus disappears immediately, and then a blank screen with a random duration of 1.0 to 1.8 seconds is presented to reduce the impact of the expectation effect on the reaction time. During the test, the reaction time of each trial, the task type of each trial (task repetition or conversion) and the task accuracy were recorded, and a total of 49 trials were completed; The reaction formula is: ; For each trial, the reaction time The time it takes for the subject to respond, The time at which the target stimulus is presented.

[0022] S103. During the piano sight-reading training stage, a musical score based on the vocal notation is presented in the center of the display, where the numbers 1-7 represent different pitches. The playing speed is controlled by moving a red vertical indicator line from left to right on the score. When the indicator line touches the left edge of the note, it indicates that the note should be played. The score design contains multiple rhythm change points. By adjusting the note length and the number of notes per unit time, the subjects are required to quickly adjust the established rhythm expectations and avoid inertial playing, thereby effectively exerting the cognitive flexibility of the subjects. During the training process, the subject's key pressing time sequence and the standard note playing time sequence are recorded, and the playing time fit is calculated. Each training session lasts 15 minutes.

[0023] S2. Preprocessing the collected behavioral data and physiological data, including outlier processing of test task data, calculation of reaction time conversion cost and calculation of playing time fit in piano sight-reading task, and denoising of original pulse wave signal; Figure 3 This is the denoising flow chart of the original pulse wave signal.

[0024] S201. Remove outliers from the trial data in the test task, including trials with reaction times less than 200ms and trials with extreme values ​​exceeding 3 standard deviations. For each subject, calculate the average reaction time of the repeated task trials and the switch task trials ( ), and calculate the reaction time switching cost .

[0025] Among them, the formula for the reaction time switching cost is: ; reflects the additional cognitive cost required for task switching, is the average reaction time of repeated task trials, is the average reaction time of switched task trials.

[0026] Calculate the average playing time fitting degree according to the sight-reading time series in the piano sight-reading task and the standard playing time series of notes; Among them, the average playing time fitting degree has the following formula:

[0027] is the standard playing time of the th note, is the sight-reading reaction time of the th note, that is, the playing time between adjacent notes, is the total number of notes in a round of sight-reading training.

[0028] S202. Decompose the original pulse wave signal using the ICEEMDAN algorithm to obtain multiple intrinsic mode functions, hereinafter referred to as IMF for short; S203. For the first 3 IMF components, use the wavelet threshold denoising method for processing. In wavelet threshold denoising, the wavelet basis function is selected as the "db8" wavelet, the number of wavelet decomposition layers is five, and the hard threshold function is used to remove high-frequency noise; Among them, the threshold in the threshold function is selected as the global threshold, and the formula is as follows:

[0029]

[0030] Among them, is the estimated value of the noise standard deviation, is the signal length, is the median absolute deviation, and 0.6745 is the Gaussian distribution correction factor, which is a fixed value.

[0031] S204. Superimpose the first three denoised IMF components and the remaining IMF components to obtain the denoised reconstructed signal; S205. Use the differential method combined with the cubic spline interpolation method to remove the baseline drift. The specific steps are as follows: 1) Calculate the first derivative of the signal and find the starting point of the period as the baseline drift point; 2) Use cubic spline interpolation to fit all the starting points of the periods to obtain the baseline signal; 3) Subtract the baseline signal from the denoised signal to obtain the final signal after removing the baseline.

[0032] S206. Use the dynamic threshold method based on the Pearson correlation coefficient of adjacent periods to perform abnormal period detection and removal.

[0033] ICEEMDAN combined with wavelet threshold denoising and cubic spline interpolation for baseline removal are respectively used to remove high-frequency noise and low-frequency baseline drift in the signal to improve the signal-to-noise ratio of the signal; Subsequently, in order to further filter out the influence of part of the motion artifact noise introduced by the subject's body movement changes, abnormal period detection and removal are performed on the pulse wave signal to improve the waveform quality of the pulse wave signal.

[0034] S3. Identify the characteristic points of the pulse wave signal obtained in step S2 and extract multi-dimensional features, specifically including the construction of the main wave peak point sequence and the extraction of multi-dimensional physiological features; Figure 4 This is the flowchart for the extraction of the physiological features of the above pulse wave signal.

[0035] S301. Based on the pulse wave signal obtained in step S2, use the first-order difference method to identify the main wave peak points of each period, and extract the interval sequence between adjacent peak points as the basic data for heart rate variability analysis.

[0036] S302. Analyze the pulse wave morphology and extract the morphological features reflecting autonomic nerve activity; perform time-domain analysis on the time interval sequence obtained in S301 and extract the statistical features reflecting heart rate variability; when performing spectral analysis, first perform cubic spline interpolation resampling on the time interval sequence, set the sampling frequency to 4 Hz to ensure the equidistant nature of the data. Subsequently, use the Welch method (window length 256, overlap rate 50%) to extract the energy distribution features of multiple frequency bands from it, which are the normalized low-frequency component that can reflect sympathetic and parasympathetic nerve activities , the normalized high-frequency component that can reflect parasympathetic nerve activity , and the ratio of low frequency to high frequency that can reflect the balance between sympathetic and parasympathetic nerves . Among them, and are defined as follows:

[0037]

[0038] A Poincaré diagram is constructed for nonlinear analysis to obtain nonlinear characteristics reflecting the dynamic characteristics of heart rate. At the same time, the blood oxygen saturation characteristics are calculated based on the photoelectric characteristics of the pulse wave signal.

[0039] S4. Based on the correlation analysis between switching cost and multidimensional features, we first analyzed the distribution characteristics of switching cost by statistical methods to evaluate the differences in task switching ability among the subjects. Then, we screened out the key features related to cognitive flexibility level by correlation analysis and variance inflation factor method. Finally, we constructed a data set for objectively evaluating cognitive flexibility level. S401, calculating statistics including the mean, standard deviation, maximum, minimum, skewness and kurtosis of the conversion cost, and visualizing group differences through box plots; S402. Evaluate the strength of the correlation between each feature and the conversion cost through Spearman correlation analysis, and retain the absolute value of the correlation coefficient And the significance level The characteristics of; variance inflation factor VIF analysis was used to eliminate VIF> features to eliminate collinearity and ensure independence between features; S403. A dataset for objectively evaluating the level of cognitive flexibility was constructed through behavioral and physiological characteristics, and the dataset was randomly divided into a training set (80%) and a test set (20%) to provide a standardized data basis for subsequent model training and verification.

[0040] S5. Combine the random forest algorithm to integrate behavioral indicators and physiological characteristics, and achieve objective evaluation of cognitive flexibility level through feature selection and model construction. Specifically, a random forest regression model is built based on the data set established in S4. The model takes features as input and outputs a quantitative cognitive flexibility score. Then, the 10-fold cross-validation method is used to evaluate the model performance, and indicators such as the determination coefficient and root mean square error are calculated to ensure the stability and generalization ability of the model. S501, based on the data set constructed in step S4, using a recursive feature elimination method based on random forest, removing the feature with the lowest feature importance score in each round, constructing and training a random forest regression model, the random forest regression model is used to assess the cognitive flexibility level of the subject, the parameters include: the number of decision trees, the maximum depth, the number of features at each node split, the minimum number of leaf node samples, the input of the random forest regression model is the screened features, and the output is a cognitive flexibility score of 0-100, the higher the score, the higher the level of cognitive flexibility; S502. Use the 10-fold cross-validation method to evaluate the performance of the random forest regression model, calculate indicators such as the coefficient of determination and root mean square error, and ensure that the model has good generalization ability.

[0041] S6. Quantify the training effect of piano sight-reading on cognitive flexibility according to the evaluation results at different piano training stages. First, verify the significance of the difference in switching costs before and after training through the paired T-test statistical method to evaluate the statistical significance of the training effect; second, based on the cognitive flexibility scoring model constructed in S5, calculate the change in cognitive flexibility level at different training stages to quantify the improvement effect brought by the training; finally, intuitively display the change trend of the cognitive flexibility scores of the subject group through a line chart to reflect the continuous impact of piano sight-reading training on cognitive flexibility.

[0042] S601. Conduct a paired T-test on the switching cost data of the subjects before and after training (use the Wilcoxon signed-rank test if the data is non-normally distributed), calculate the p-value to evaluate the statistical significance of the training effect; at the same time, calculate the Cohen's d effect size to quantify the magnitude of the training effect. This step verifies the impact of piano sight-reading training on cognitive flexibility based on the direct comparison of behavioral data; S602. Perform scoring based on the random forest regression model, calculate the cognitive flexibility scores of the subjects at different training stages, and calculate the relative improvement percentage based on the score changes. This step realizes the quantitative evaluation of the training effect through a standardized scoring system; S603. Display the group score trend through a line chart. This step intuitively presents the change of cognitive flexibility scores during the piano sight-reading training process through a visualization method to analyze the overall trend of the training effect.

[0043] Example 2 This example further discloses a method for quantitatively evaluating the measurement and training of the impact of piano sight-reading on cognitive flexibility, as Figure 1 shown. The specific steps are as follows: S1. Refer to the corresponding steps in Example 1 and will not be elaborated here; S2. Refer to the corresponding steps in Example 1 and will not be elaborated here. The decomposition effect of the ICEEMDAN algorithm on the pulse wave signal is as Figure 5 shown, and the pulse wave signal after using ICEEMDAN combined with wavelet threshold denoising is as Figure 6 shown, and the pulse wave signal after removing the baseline is as Figure 7 shown; S3. Refer to the corresponding steps in Example 1 and will not be elaborated here. The detection effect of the main wave peak points is as Figure 8 shown; S4. Refer to the corresponding steps in Example 1 and will not be elaborated here. The distribution characteristics of the switching costs are shown in Table 1; through feature screening and analysis, the top five physiological features significantly correlated with the switching costs are shown in Table 2; Table 1. Summary table of the statistical characteristics of the switching costs of the subjects in all stages

[0044] Table 2. Correlation analysis of the top five physiologically important features and conversion costs

[0045] S5. Refer to the corresponding steps in Example 1, which will not be elaborated here. The indicators of the cognitive flexibility evaluation model are shown in Table 3; Table 3. Indicators of the cognitive flexibility evaluation model

[0046] S6. Refer to the corresponding steps in Example 1, which will not be elaborated here. The changes in the conversion cost of piano sight-reading training are shown in the table.

[0047] Table 4. Changes in conversion cost before and after piano sight-reading training

[0048] In summary, the five physiological characteristics shown in Table 2 mainly reflect the regulation ability of the autonomic nervous system, especially the parasympathetic nervous system, which plays a key role in cognitive resource allocation and is thus closely related to cognitive flexibility; combined with the good fitting effect of 0.68 obtained by the random forest regression model in the test set in Table 3, and the trend of significant decrease in the conversion cost shown in Table 4 after training, it fully verifies the feasibility and effectiveness of the present invention in the quantitative evaluation of cognitive flexibility measurement and training.

[0049] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0050] The above embodiments are the preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications made without departing from the spirit and principle of the present invention shall be equivalent replacement methods and are all included in the protection scope of the present invention.

Claims

1. A method for testing and quantifying the cognitive flexibility of piano sight-reading, characterized in that: The test-training quantitative evaluation method comprises the following steps: S1. Collect the pulse wave signals of the subjects in the task switching paradigm test task and the piano sight-reading task through the end-to-end cloud platform and record the behavioral data; S2, after preprocessing the behavior data, respectively calculating the conversion cost and the playing time fit, and performing denoising on the original pulse wave signal; S3, extracting features from the denoised pulse wave signal to obtain pulse wave morphological features, heart rate variability features, and blood oxygen saturation features; S4. Based on the correlation analysis between the conversion cost and the multidimensional features and feature screening, a data set containing behavioral and physiological features is constructed; S5. Combine behavioral and physiological features with the random forest algorithm to achieve objective assessment of cognitive flexibility through feature selection and model construction; S6. Quantify the training effect of piano sight-reading on cognitive flexibility based on the evaluation results of different piano training stages.

2. The method for quantitatively evaluating the effect of piano sight-reading on cognitive flexibility according to claim 1, characterized in that: The process of step S1 is as follows: S101. An experimental environment is built through the end-to-end cloud platform. The subject responds by pressing buttons and wears a pulse wave sensor to record pulse wave signals. S102, in the task switching paradigm test task phase, target stimuli of letter and number combination are presented on the display, and different judgment tasks are performed according to the task clues; S103: In the piano sight-reading training stage, a music score based on the acoustic handwriting notation is presented on a display, and notes are played according to time indication lines.

3. The method for quantitatively evaluating the effect of piano sight-reading on cognitive flexibility according to claim 1, characterized in that: The process of step S2 is as follows: S201, preprocessing the behavioral data, calculating the reaction time conversion cost of the test task and the playing time fit of the piano sight-reading task; S202, using improved adaptive noise ensemble empirical mode decomposition to decompose the original pulse wave signal to obtain multiple intrinsic mode components, hereinafter referred to as intrinsic mode components IMF; S203, for the front IMF components are processed using wavelet threshold denoising method; S204, the front The IMF components are superimposed on the remaining IMF components to obtain the denoised reconstructed signal; S205, using a cubic spline interpolation fitting curve to remove baseline drift; S206: Detect and remove abnormal cycles of the pulse wave signal.

4. The method for quantitatively evaluating the effect of piano sight-reading on cognitive flexibility according to claim 1, characterized in that: The process of step S3 is as follows: S301, performing feature point recognition to extract the main wave peak sequence of the pulse wave signal; S302, analyzing the pulse wave signal and the main wave peak sequence, and extracting multi-dimensional physiological features including pulse wave morphological features, heart rate variability features, and blood oxygen saturation features.

5. The method for quantitatively evaluating the effect of piano sight-reading on cognitive flexibility according to claim 1, characterized in that: The process of step S4 is as follows: S401. Analyze the distribution characteristics and group differences of switching costs; S402. Screening out behavioral characteristics and physiological characteristics through correlation analysis and variance inflation factor analysis; S401, calculating statistics including the mean, standard deviation, maximum, minimum, skewness and kurtosis of the conversion cost, and visualizing group differences through box plots; S402. Evaluate the strength of the correlation between each feature and the conversion cost through Spearman correlation analysis, and retain the absolute value of the correlation coefficient And the significance level Features; Variance inflation factor (VIF) analysis was used to eliminate VIF> features to eliminate collinearity, , , The correlation coefficient comparison threshold, significance level comparison threshold, and inflation factor comparison threshold are used to screen out behavioral and physiological characteristics that are significantly related to cognitive flexibility. S403. Construct a data set for objectively evaluating the level of cognitive flexibility through behavioral characteristics and physiological characteristics.

6. The method for quantitatively evaluating the effect of piano sight-reading on cognitive flexibility according to claim 1, characterized in that: The process of step S5 is as follows: S501, based on the data set constructed in step S4, using a recursive feature elimination method based on random forest, removing the feature with the lowest feature importance score in each round, constructing and training a random forest regression model, the random forest regression model is used to assess the cognitive flexibility level of the subject, the parameters include: the number of decision trees, the maximum depth, the number of features at each node split, the minimum number of leaf node samples, the input of the random forest regression model is the screened features, and the output is a cognitive flexibility score of 0-100, the higher the score, the higher the level of cognitive flexibility; S502. Use cross validation to evaluate the performance of the random forest regression model.

7. A method for testing and quantifying the effect of piano sight-reading on cognitive flexibility according to claim 1, characterized in that: The process of step S6 is as follows: S601, verifying the significant difference of the conversion cost before and after training through paired T test; S602, scoring based on the random forest regression model, calculating the cognitive flexibility scores of the subjects at different training stages, and calculating the relative improvement percentage based on the score changes; S603. Display the group score trend through a line graph.

Images