Emotional State Detection System Based on Electrophysiological Data

Abstract

The present invention relates to the technical field of bioinformatics processing, specifically an emotion state detection system based on electrophysiological data. The system includes a signal reception and calibration module, a signal anomaly detection module, an emotion pattern analysis module, and an emotion output module. In the present invention, through the precise calibration and time synchronization of electrocardiogram, electroencephalogram, and skin electrical activity signals, the usability of the signals and the data accuracy are improved, ensuring the reliability of emotion state detection. Advanced signal processing techniques are used to precisely eliminate abnormal indicators, improving the purity of the signals and providing a solid foundation for the precise analysis of emotion characteristics. By comprehensively analyzing multiple physiological signals, the system is allowed to respond in real time to subtle changes in emotions. By adjusting signal processing parameters, the system adaptability and reaction speed are optimized based on the emotion stability index, improving the accuracy of emotion detection and making the system more efficient and sensitive in mental health monitoring and human-computer interaction.

Description

Technical Field

[0001] The present invention relates to the technical field of bioinformatics processing, and particularly to an emotional state detection system based on electrophysiological data. Background Art

[0002] The technical field of bioinformatics processing focuses on using computational methods to process and analyze biological data. The main tasks in this field include collecting, storing, analyzing, and integrating biological data to provide in-depth analysis of biological systems. With wide applications ranging from genomics, proteomics to complex biological systems and bioelectrical signal analysis, bioinformatics processing technology enables scientists to analyze large amounts of biological data, discover current biomarkers, design drugs, and better understand the basis of genetic diseases. A key application in this field is to extract useful information from bioelectrical signals through pattern recognition and signal processing techniques to support clinical diagnosis and biomedical research.

[0003] Among them, an emotional state detection system is a technology that recognizes an emotional state based on monitoring and analyzing an individual's physiological signals. Such a system uses physiological indicators such as heart rate, skin electrical activity, and brain waves, and analyzes the data through specialized algorithms to infer an individual's emotional state, such as happiness, sadness, anger, etc. The main uses of the emotional state detection system include applications in mental health monitoring, user experience research, and augmented reality technology, assisting in improving the human-computer interaction experience, and providing more personalized services and products that respond to the user's emotional needs.

[0004] When dealing with and analyzing bioelectrical signals, the prior art faces problems of inconsistent signal quality and synchronization difficulties, especially in the case of multiple signal sources, such as the signal fusion processing of electrocardiogram, brain waves, and skin electrical activity. This leads to inaccurate data analysis, thereby affecting the accurate recognition of emotional states. Traditional technologies lack effective mechanisms for processing abnormal signals and are difficult to accurately remove noise and outliers from complex biological signals, restricting the effectiveness and general adaptability of emotional detection systems in practical applications. For example, in the absence of effective removal of abnormal signals, misjudgments may occur in mental health monitoring, and in user experience research, incorrect data leads to misinterpretation of the user's emotions, restricting the application of bioinformatics processing technology in a wider range of fields. Summary of the Invention

[0005] The purpose of the present invention is to solve the drawbacks existing in the prior art, and to propose an emotional state detection system based on electrophysiological data.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: The emotional state detection system based on electrophysiological data includes:

[0007] The signal reception and calibration module receives signals of electrocardiogram, electroencephalogram, and skin electrical activity, performs signal calibration and corrects time deviation to obtain calibrated signals, and synchronizes electrocardiogram waveforms, electroencephalogram patterns, and skin electrical responses based on the calibrated signals to acquire synchronized electrophysiological data;

[0008] Based on the synchronized electrophysiological data, the signal anomaly detection module uses a convolutional neural network to identify arrhythmia and abnormal electroencephalogram waves, obtains anomaly indicators, eliminates and corrects the anomaly indicators, and generates purified electrophysiological signals;

[0009] The emotion pattern analysis module uses the purified electrophysiological signals to analyze electrocardiogram waveforms and electroencephalogram patterns through an autoregressive moving average model to obtain preliminary emotion features, and performs emotion annotation through the preliminary emotion features to generate emotion classification results;

[0010] The emotion output module uses the emotion classification results, receives emotion marker data, calculates the emotion change frequency and intensity within different time periods, determines the statistical characteristics of emotion fluctuations, obtains an emotion stability index, adjusts signal processing parameters according to the emotion stability index, optimizes signal analysis accuracy, and generates adjusted emotion recognition results.

[0011] As a further solution of the present invention, the steps for obtaining the synchronized electrophysiological data are specifically as follows:

[0012] By receiving signals of electrocardiogram, electroencephalogram, and skin electrical activity, execute a time calibration algorithm to eliminate the time deviation caused by transmission delay, and obtain a set of time-calibrated signals;

[0013] Perform synchronization processing on the set of time-calibrated signals, using the formula:

[0014]

[0015] Calculate the difference of each physiological signal to generate a set of synchronized signals, where x i,a represents the sample value of the i-th signal, represents the average value of signal samples, n represents the number of samples, and S a represents the synchronization degree;

[0016] Utilize the set of synchronized signals to optimize signal processing by dynamically adjusting synchronization parameters to acquire synchronized electrophysiological data.

[0017] As a further solution of the present invention, the steps for obtaining the anomaly indicators are specifically as follows:

[0018] Extract the features of electrocardiogram and brain waves from the synchronized electrophysiological data, including wave peaks, wave valleys, and signal intensities, and use target digital signal processing techniques to extract feature information to obtain a physiological signal feature set;

[0019] Based on the physiological signal feature set, perform the identification of arrhythmia and abnormal brain waves, using the formula:

[0020] I b = σ(W b ·F b + b b )

[0021] Through the propagation of the network, obtain abnormal pattern data, where σ represents the activation function, W b represents the weight of the convolutional layer, b b represents the bias, I b represents the abnormal pattern data, and F b represents the physiological signal feature set;

[0022] Analyze the abnormal pattern data, calculate the frequency and severity of the differential abnormal patterns, and obtain abnormal indicators according to the preset critical threshold.

[0023] As a further solution of the present invention, the steps for obtaining the purified electrophysiological signal are specifically as follows:

[0024] Based on the abnormal indicators, analyze the electrocardiogram and electroencephalogram signals, identify the positions of arrhythmia and abnormal brain waves, and generate a list of abnormal segments;

[0025] Apply a filter to the list of abnormal segments for processing, perform data correction, finely adjust the signal, and reduce noise interference, using the formula:

[0026] R c = α c ·L c - β c ∑(γ c ·L c + δ c )

[0027] Output the corrected signal data set, where α c 、β c 、γ c and δ c are parameters adjusted according to the abnormal signal intensity and frequency respectively, R c represents the corrected signal data set, and L c represents the marked abnormal segment;

[0028] Evaluate the corrected signal data set, perform statistical analysis and verify the signal quality. Use frequency distribution detection to verify the physiological credibility and integrity of the signal, and generate purified electrophysiological signals.

[0029] As a further aspect of the present invention, the step of obtaining the preliminary emotion features is specifically as follows:

[0030] By performing frequency domain analysis on the purified electrophysiological signals, using Fourier transform to convert the signals from the time domain to the frequency domain, calculate the spectral density of the electrocardiogram and electroencephalogram signals, and generate the spectral density features of the electrocardiogram and electroencephalogram.

[0031] According to the spectral density features of the electrocardiogram and electroencephalogram, apply the autoregressive moving average model, combine with the waveform data of the electrocardiogram and electroencephalogram signals, and use the formula:

[0032]

[0033] Calculate the electrophysiological signal features associated with emotions to obtain the autoregressive and moving average parameters of the emotional state. Among them, α d and β d represent the autoregressive and moving average coefficients respectively, y j-d represents the original electrocardiogram or electroencephalogram signal value of the jth signal, ∈ j-d represents the original prediction error, m represents the number of samples, and A d represents the autoregressive and moving average parameters of the emotional state;

[0034] Use the autoregressive and moving average parameters of the emotional state to perform threshold analysis and identify emotional changes. Set the emotional detection threshold, and compare whether the prediction error of each calculation period exceeds the threshold to verify the change of the emotional state and obtain the preliminary emotion features.

[0035] As a further aspect of the present invention, the step of obtaining the emotion classification result is specifically as follows:

[0036] Based on the preliminary emotion features, assign the corresponding emotional state to each time point according to the changes in the electrocardiogram and electroencephalogram signals, and obtain the labeled time series data;

[0037] Use the labeled time series data as the input, apply the weighted calculation method and combine multiple emotion features, and use the formula:

[0038]

[0039] Calculate the total emotion score to obtain the emotion score sequence. Among them, E h represents the total emotion score, w k,h represents the weight of the emotion feature k, F k,h is the standardized score of the emotion feature k, bh is the bias term, and K represents the total emotional feature quantity;

[0040] Based on the emotional score sequence, using the support vector machine algorithm, map the continuous emotional scores to emotional categories, including happiness, sadness, and anger, and classify the emotional states at each time point to generate an emotional classification result.

[0041] As a further solution of the present invention, the obtaining step of the emotional stability index is specifically as follows:

[0042] By analyzing the emotional label data of the emotional classification result, establish an index for the emotional changes in each time period, and convert the emotional data into a time series format to generate an initial emotional data time series;

[0043] Based on the initial emotional data time series, calculate the emotional fluctuation characteristics within different time periods, determine the change frequency and intensity of emotions, and use the formula:

[0044]

[0045] Obtain the emotional fluctuation characteristic data, where F g represents the emotional fluctuation contribution degree, r t,g represents the emotional change frequency at time point t, e t,g is the emotional intensity at time point t, b g is the bias term, and T represents the total number of time points;

[0046] Based on the emotional fluctuation characteristic data, by combining the standard deviation and coefficient of variation of the emotional fluctuation, evaluate the overall stability of emotions and the predictability of the emotional state within the measurement period, and generate an emotional stability index.

[0047] As a further solution of the present invention, the obtaining step of the adjusted emotional recognition result is specifically as follows:

[0048] Based on the emotional stability index, evaluate whether the current signal processing parameters are suitable for the current emotional index. By comparing the current emotional index with a predetermined threshold, if the index shows a large deviation, trigger the parameter adjustment process, and use the formula:

[0049] P u = α u ×ISI u + β u

[0050] Generate the preliminarily adjusted signal processing parameters, where ISI u represents the emotional stability index, α u is the emotional change sensitivity coefficient, β u is the baseline correction coefficient, Pu Signal processing parameters representing preliminary adjustment;

[0051] Apply the preliminarily adjusted signal processing parameters to signal analysis, conduct simulation tests and evaluate the impact on emotion recognition accuracy. By performing multiple simulations, apply the formula:

[0052] E u = γ u × P 2 u + δ u

[0053] Estimate the recognition accuracy, verify the effect of the new parameter settings, and generate simulation test results. Among them, γ u represents the adjustment coefficient, δ u is the constant offset, E u represents the simulation test results, and P u represents the preliminarily adjusted signal processing parameters;

[0054] Adjust and solidify the signal processing parameters according to the simulation test results. By comparing the emotion recognition results before and after adjustment, verify the advantages of the new parameters, and output the adjusted emotion recognition results.

[0055] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0056] In the present invention, through the meticulous calibration and time synchronization processing of electrocardiogram, electroencephalogram, and skin electrical activity signals, the availability and data accuracy of the signals are significantly improved, ensuring the quality of the basic data for subsequent analysis, thereby enhancing the reliability of emotion state detection. In anomaly detection, through advanced signal processing techniques, abnormal indicators are accurately eliminated, not only improving the purity of the signals but also laying a solid foundation for the accurate analysis of emotion features. By comprehensively referring to multiple physiological signals, a deeper analysis of complex emotion states is achieved, allowing for real-time response to subtle changes in emotions. By applying the emotion stability index, the signal processing parameters are adjusted to further optimize the adaptability and response speed of the system, effectively improving the accuracy and response speed of the emotion detection system, making its application in mental health monitoring and human-computer interaction experience more efficient and sensitive. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is the system flowchart of the present invention;

[0058] Figure 2 is the flowchart of synchronizing electrophysiological data in the present invention;

[0059] Figure 3 is the flowchart of abnormal indicators in the present invention;

[0060] Figure 4Flow chart of the purified electrophysiological signal in the present invention;

[0061] Figure 5 Flow chart of the preliminary emotion features in the present invention;

[0062] Figure 6 Flow chart of the emotion classification result in the present invention;

[0063] Figure 7 Flow chart of the emotion stability index in the present invention;

[0064] Figure 8 Flow chart of the adjusted emotion recognition result in the present invention. Detailed implementation manners

[0065] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0066] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more unless otherwise specifically defined.

[0067] Please refer to Figure 1 , the emotion state detection system based on electrophysiological data includes:

[0068] The signal reception and calibration module receives the signals of electrocardiogram, electroencephalogram, and skin electrical activity, performs signal calibration and corrects the time deviation to obtain the calibrated signal, and synchronizes the electrocardiogram waveform, electroencephalogram pattern, and skin electrical response according to the calibrated signal to obtain the synchronized electrophysiological data;

[0069] The signal anomaly detection module, based on the synchronized electrophysiological data, uses a convolutional neural network to identify arrhythmia and abnormal brain waves, obtains the anomaly index, eliminates and corrects the anomaly index, and generates the purified electrophysiological signal;

[0070] The emotion pattern analysis module uses the purified electrophysiological signal to analyze the electrocardiogram waveform and electroencephalogram pattern through an autoregressive moving average model to obtain the preliminary emotion features, and performs emotion annotation through the preliminary emotion features to generate the emotion classification result;

[0071] The emotion output module uses the emotion classification results, receives emotion marker data, calculates the emotion change frequency and intensity within different time periods, determines the statistical characteristics of emotion fluctuations, obtains the emotion stability index, adjusts the signal processing parameters according to the emotion stability index, optimizes the signal analysis accuracy, and generates the adjusted emotion recognition results.

[0072] The calibrated signals include heart rate synchronization data, brain wave frequency matching data, and galvanic skin response time alignment data. The synchronized electrophysiological data includes aligned electrocardiograms, standardized electroencephalograms, and synchronized electrodermal graphs. The abnormal indicators include arrhythmia types and abnormal electroencephalogram bands. The purified electrophysiological signals include denoised electrocardiogram signals, filtered electroencephalogram signals, and corrected galvanic skin signals. The preliminary emotion features include electrocardiogram emotion indicators and electroencephalogram emotion patterns. The emotion classification results include the recognized basic emotion types and emotion response levels. The emotion stability index includes the emotion fluctuation frequency and emotion response intensity measurement. The adjusted emotion recognition results include the optimized classification accuracy and parameter adjustment details.

[0073] Please refer to Figure 2 , and the specific steps for obtaining the synchronized electrophysiological data are as follows:

[0074] By receiving the signals of electrocardiograms, brain waves, and galvanic skin activities, execute the time calibration algorithm to eliminate the time deviation caused by transmission delay, and obtain the time-calibrated signal set;

[0075] According to the original electrocardiogram, brain wave, and galvanic skin activity data collected by the sensors, execute the time calibration algorithm to eliminate the time deviation caused by transmission delay. The collected original data undergoes a preprocessing stage, including filtering and denoising, to ensure the clarity and usability of the data. The filters used in this stage are customized according to the characteristics of the signals. For example, band-pass filters are used for electrocardiogram data to eliminate high-frequency and low-frequency noise, while different types of filters are required for brain wave and galvanic skin activity data. Each group of data is time-synchronized after calibration to ensure the signal alignment in the subsequent processing stage. The network time protocol is used for time calibration to ensure the alignment of timestamps on all devices, involving complex signal processing techniques such as signal resampling and time interpolation. This processing ensures the accuracy and synchronization of the data before entering the analysis stage, and obtains the time-calibrated signal set.

[0076] Perform synchronization processing on the time-calibrated signal set using the formula:

[0077]

[0078] Calculate the difference of each physiological signal to generate the synchronized signal set, where x i,a represents the sample value of the i-th signal, represents the average value of the signal samples, n represents the number of samples, and S a represents the synchronization degree;

[0079] The advantage of the formula is that it provides a method to quantify the synchronization error and can effectively evaluate the accuracy of the synchronous processing of different physiological signals;

[0080] S a represents the synchronization degree, which is a quantitative index used to measure the accuracy of synchronization between multiple physiological signals (such as electrocardiogram, electroencephalogram, skin electrical activity);

[0081] Given n = 3 (representing three signals of electrocardiogram, electroencephalogram, and skin electrical activity), let the electrocardiogram signal value be x 1,a = 0.45 mv, the electroencephalogram signal value be x 2,a = 0.48 mv, and the skin electrical activity signal value be x 3,a = 0.47 mv, and the average value of all signals Substitute the values into the formula to calculate the synchronization degree:

[0082]

[0083] This result indicates that the synchronization error is very small, indicating that the signal synchronous processing has achieved high precision and provides a reliable data basis for the next step of analysis.

[0084] Using the synchronized signal set, optimize the signal processing by dynamically adjusting the synchronization parameters to obtain synchronous electrophysiological data;

[0085] Using the synchronized signal set generated in the previous step, optimize the signal processing by dynamically adjusting the synchronization parameters to ensure the synchronization accuracy of the finally output physiological signals. The dynamic adjustment involves calculating the statistical characteristics of each signal, such as the mean and standard deviation, and adjusting the parameters of the synchronization algorithm according to the characteristics. For example, adjust the time window or resampling rate. The process is iterative. Each iteration will evaluate the synchronization accuracy and adjust the parameters according to the evaluation results until the preset accuracy standard is reached, and finally obtain synchronous electrophysiological data.

[0086] Please refer to Figure 3 , and the specific steps for obtaining the abnormal index are as follows:

[0087] Extract the characteristics of the electrocardiogram and electroencephalogram from the synchronous electrophysiological data, including wave peaks, wave valleys, and signal intensities, and use target digital signal processing technology to extract the characteristic information to obtain the physiological signal characteristic set;

[0088] Extract the features of electrocardiogram (ECG) and electroencephalogram (EEG) from synchronous electrophysiological data. The process involves precisely measuring the time and amplitude of each waveform to ensure the extraction of the most critical features from physiological signals, such as the R-wave peak and Q-wave valley of the ECG, and the α-wave and β-wave of the EEG. These features reflect the basic patterns of heart and brain activities and are processed through specially designed filters and signal processing algorithms to ensure that the extracted features are free from noise interference. The feature data obtained through processing is the key basis for identifying physiological abnormal states and provides the necessary input for subsequent machine learning models for further analysis and anomaly detection.

[0089] Based on the physiological signal feature set, identify arrhythmias and abnormal EEGs using the formula:

[0090] I b = σ(W b ·F b + b b )

[0091] Through the propagation of the network, obtain the abnormal pattern data. Here, σ represents the activation function, W b represents the weight of the convolutional layer, b b represents the bias, I b represents the abnormal pattern data, and F b represents the physiological signal feature set;

[0092] The advantage of the formula is that through the convolution operation, it can effectively extract the patterns of arrhythmias and abnormal EEGs from the ECG and EEG features. The convolutional layer can capture the local dependencies and spatial hierarchical structures in the feature data, enhancing the model's ability to detect physiological signal abnormalities;

[0093] Set the weight matrix of W b to [0.5, -0.2, 0.8], the bias b b to 0.1, the activation function σ uses ReLU, and the input feature F b is [1, 0, 1]. The calculation process is as follows:

[0094] W b ·F b + b b = 0.5 × 1 + (-0.2) × 0 + 0.8 × 1 + 0.1 = 1.4

[0095] I b = σ(1.4) = max(0, 1.4) = 1.4

[0096] This result indicates that under the given weights and features, the network successfully identifies the abnormal pattern and outputs 1.4, indicating the intensity of the detected abnormality. The larger this value, the more obvious the abnormality, which provides an important basis for clinical diagnosis.

[0097] Analyze the abnormal pattern data, calculate the frequency and severity of the differentiated abnormal patterns, and obtain the abnormal indicators according to the preset critical thresholds.

[0098] Analyze the abnormal pattern data identified by the convolutional neural network, refer to the clinical significance of the differentiated abnormal patterns, calculate the statistical indicators of the patterns, such as the occurrence frequency and duration, determine which abnormal patterns are transient or sporadic, indicating long-term health problems, judge the severity of the abnormality through the set critical thresholds, classify each abnormal state, and integrate the analysis results into the final abnormal indicators, which describe in detail the types, frequencies, and severities of the detected arrhythmias and abnormal brain waves.

[0099] Please refer to Figure 4 , and the specific steps for obtaining the purified electrophysiological signals are as follows:

[0100] Based on the abnormal indicators, analyze the electrocardiogram and electroencephalogram signals, identify the locations of arrhythmias and abnormal brain waves, and generate a list of abnormal segments.

[0101] For the identified abnormal segments in the synchronous electrophysiological signals, conduct a detailed time-point analysis, select appropriate filtering techniques to accurately remove interference according to the specific frequencies and amplitudes of the irregular patterns in the electrocardiogram and electroencephalogram signals, use advanced signal processing techniques such as the fast Fourier transform (FFT) to analyze the frequency-domain characteristics of the abnormal segments, so as to locate the accurate start and end time points. The precise positioning of the abnormal segments in the signals is the key basis for the subsequent correction processing. Through this process, a detailed list of abnormal segments can be generated, which will be used as the basis for the next cleaning and correction operations, laying a solid foundation for achieving high-precision signal correction.

[0102] Apply a filter to the list of abnormal segments for processing, perform data correction, fine-tune the signal, and reduce noise interference. Use the formula:

[0103] R c = α c ·L c - β c ∑(γ c ·L c + δ c )

[0104] Output the corrected signal data set, where α c , β c , γ c , and δ c are parameters adjusted according to the abnormal signal strength and frequency respectively, R c represents the corrected signal data set, and L c represents the marked abnormal segments.

[0105] The advantage of the formula is that by adjusting four key parameters (α c , β c , γ c , δ c ), it allows for flexible control of the contributions of various components during the signal correction process, thereby improving the correction accuracy and reducing non-critical signal distortion. It is particularly suitable for processing physiological signals with high variability. This formula combines linear amplification and non-linear combination to optimize the processing of abnormal signal segments;

[0106] The following parameter values are obtained as follows:

[0107] α c = 0.95, representing the adjustment coefficient of the overall signal, which determines the degree of signal amplification or attenuation;

[0108] β c = 0.1, determining the contribution of the abnormal signal component to the final output signal;

[0109] γ c = 1.5, adjusting the weight of a single abnormal signal term;

[0110] δ c = 0.05, adding a constant offset to the correction term to handle baseline drift;

[0111] L c represents a typical set of abnormal signals, containing three signal segments: L c = {0.2, -0.3, 0.15};

[0112] The calculation process is as follows:

[0113] R c = 0.95·{0.2, -0.3, 0.15} - 0.1·∑(1.5·{0.2, -0.3, 0.15} + 0.05)

[0114] Calculate each term:

[0115] = {0.19, -0.285, 0.1425} - 0.1

[0116] ·{(1.5·0.2 + 0.05), (1.5· -0.3 + 0.05), (1.5·0.15 + 0.05)}

[0117] = {0.19, -0.285, 0.1425} - 0.1·{0.35, -0.4, 0.275}

[0118] = {0.19, -0.285, 0.1425} - {0.035, -0.04, 0.0275}

[0119] = {0.155, -0.245, 0.115}

[0120] This result indicates that after adjustment by the above formula, the abnormal parts in the original signal have been effectively corrected. Each signal segment has undergone specific adjustments to ensure the purification and quality improvement of the entire signal, so that the corrected signal R c is more suitable for further analysis and diagnostic use.

[0121] Evaluate the corrected signal dataset, conduct statistical analysis and verify the signal quality. Use frequency distribution detection to verify the physiological credibility and integrity of the signal, and generate purified electrophysiological signals;

[0122] The signals that have undergone deep cleaning and correction need to be evaluated for quality. Pass the signals through a series of statistical analysis programs to test their signal-to-noise ratio and fidelity, ensure that all processed signals do not lose key information for clinical diagnosis. Apply frequency distribution testing and complexity analysis to evaluate the overall structure and functionality of the signal, ensure its effectiveness and reliability in medical research and diagnostic applications. Through a series of evaluation steps, generate purified electrophysiological signals. The signals integrate the achievements of all previous steps and provide high-quality data resources for further medical analysis.

[0123] Please refer to Figure 5 , and the specific steps for obtaining preliminary emotional characteristics are as follows:

[0124] By performing frequency-domain analysis on the purified electrophysiological signals, use Fourier transform to convert the signals from the time domain to the frequency domain, calculate the spectral density of electrocardiogram and electroencephalogram signals, and generate spectral density characteristics of electrocardiogram and electroencephalogram;

[0125] By performing fast Fourier transform on the purified electrophysiological signals, this process involves converting the time-series signals into frequency-domain signals, analyzing the frequency characteristics of electrocardiogram and electroencephalogram signals. Frequency analysis can reveal the main components and noise levels in the signals, thereby judging the clarity and usability of the signals. By calculating the frequency distribution, the variability and stability of heart rate and brain waves can be further analyzed. This process requires window function processing of the time-series data and calculation of the Fourier transform of each window to obtain the spectral density distribution during the entire recording period, and generate spectral density characteristics of electrocardiogram and electroencephalogram.

[0126] According to the spectral density characteristics of electrocardiogram and electroencephalogram, apply the autoregressive moving average model, combine with the waveform data of electrocardiogram and electroencephalogram signals, and use the formula:

[0127]

[0128] Calculate the electrophysiological signal features related to emotions to obtain the autoregressive and moving average parameters of the emotional state. Among them, α d and β d represent the autoregressive and moving average coefficients respectively, y j-d represents the original electrocardiogram or electroencephalogram signal value of the jth signal, ∈ j-d represents the original prediction error, m represents the number of samples, and A d represents the autoregressive and moving average parameters of the emotional state;

[0129] The advantage of the formula is that it combines the autoregressive coefficient and the moving average coefficient to predict emotional changes. By adding a square term, the sensitivity to extreme values is enhanced, which helps to more accurately identify the abnormal changes in electrocardiogram and electroencephalogram signals during emotional fluctuations;

[0130] Refer to a simplified example, where the number of samples m = 10, the autoregressive coefficient α d = 0.5, the moving average coefficient β d = 0.3, the original electrocardiogram or electroencephalogram signal value y j-d takes 0.8, and the original prediction error ∈ j-d takes 0.2. Substituting into the formula gives:

[0131]

[0132] This result shows that under the given autoregressive and moving average parameters, the predicted error eigenvalue of the emotional state is 0.332, indicating a moderate degree of fluctuation in the emotional state of electrocardiogram and electroencephalogram signals, which helps to further analyze and process electrocardiogram and electroencephalogram signals to identify emotional changes.

[0133] Utilize the autoregressive and moving average parameters of the emotional state to conduct threshold analysis and identify emotional changes. Set the emotional detection threshold, and compare whether the prediction error of each calculation cycle exceeds the threshold to verify the change of the emotional state and obtain the preliminary emotional features;

[0134] Utilize the calculated electrophysiological features related to emotions to identify significant emotional changes by setting a threshold. The process involves comparing the prediction error of the calculation cycle with the set threshold. This threshold is determined based on the statistical analysis of historical data to ensure that emotional fluctuations inconsistent with the normal state can be effectively identified. After setting the threshold, detect significant emotional changes by comparing whether the error value exceeds the threshold cycle by cycle. If the prediction error exceeds the threshold, it is marked as a significant emotional change. This method can not only dynamically track the changes in the emotional state but also take corresponding response measures in a timely manner when significant emotional changes occur, ensuring the accuracy and real-time nature of emotional analysis. The determined emotional changes are marked as preliminary emotional features.

[0135] Please refer to Figure 6 , the steps for obtaining the emotion classification results are specifically as follows:

[0136] Based on the preliminary emotion features and according to the changes in electrocardiogram and electroencephalogram signals, assign the corresponding emotion states to each time point to obtain the marked time series data;

[0137] Take the preliminary emotion change markers obtained from the previous analysis as the starting step. This marker is based on the significant changes in electrocardiogram and electroencephalogram signals. Through advanced signal processing techniques, such as filtering and feature extraction, analyze the signals at each time point to determine whether there are significant emotion changes. This involves batch data collection and preprocessing, including noise removal and normalization, to ensure data quality and processing consistency. Each valid emotion change is marked and converted into a series of marked time series data that can be used for further analysis. The data will be used as the input of the emotion recognition model to provide the basic data for subsequent emotion classification.

[0138] Take the marked time series data as the input, apply the weighted calculation method and combine multiple emotion features, using the formula:

[0139]

[0140] Calculate the total emotion score to obtain the emotion score series, where E h represents the total emotion score, w k,h represents the weight of emotion feature k, F k,h is the normalized score of emotion feature k, b h is the bias term, and K represents the total amount of emotion features;

[0141] The benefit of the formula is that by adding a bias term to adjust the baseline of the emotion score, it allows the model to maintain flexibility in different individuals and situations, thereby improving the overall accuracy and adaptability of emotion recognition;

[0142] There are 3 emotion features set, with weights w 1,h = 0.5, w 2,h = 0.3, w 3,h = 0.2, corresponding emotion feature scores are F 1,h = 70, F 2,h = 60, F 3,h = 50, and the bias term is b h = 5. The formula calculation process is as follows:

[0143] E h = (0.5·70 + 0.3·60 + 0.2·50 + 5) = (35 + 18 + 10 + 5) = 68

[0144] The result shows that the comprehensive emotion score is 68, which represents a moderate emotional response for the identified emotional state under the given weights and features. This score will be used for further classification judgment.

[0145] Based on the emotion score sequence, using the support vector machine algorithm, the continuous emotion scores are mapped to emotion categories, including happiness, sadness, and anger, and the emotional state at each time point is classified to generate emotion classification results.

[0146] Using the emotion score sequence for classification, by adopting classification algorithms in machine learning, such as support vector machines or decision trees, the algorithm learns how to map emotion scores to specific emotion categories through training data. The classification process includes model training, validation, and testing to ensure the accuracy and reliability of the classification results. Through the analysis and processing of differential emotion scores, the algorithm can identify specific emotional states, such as happiness, sadness, or anger. The emotional state at each time point is accurately classified, providing intuitive emotion recognition results for the end user.

[0147] Please refer to Figure 7 , and the specific steps for obtaining the emotional stability index are as follows:

[0148] By analyzing the emotion marker data of the emotion classification results, an index is established for the emotional changes in each time period, and the emotion data is converted into a time series format to generate an initial emotion data time series.

[0149] The analysis process starts by extracting the emotion marker data at key time points from the emotion classification results, which involves screening the data associated with specific time points from a batch of emotion records and performing time series analysis on the extracted data to conduct in-depth research on the dynamic changes of emotions. First, each marker is sorted by time to ensure the coherence and logical correctness of the analysis. By comparing the changes in emotion intensity between each consecutive time point, the emotion fluctuation frequency is calculated. The processing process not only refers to the absolute value of emotion intensity but also includes the change speed and trend of emotion intensity. Through refined steps, the patterns of emotional changes can be accurately captured, laying a solid data foundation for the next in-depth analysis, generating a series of time series emotion data ready for further analysis. The data will be directly used to evaluate the statistical characteristics of emotion fluctuations, ensuring the high quality of data processing and the reliability of analysis results.

[0150] Based on the initial emotion data time series, calculate the emotion fluctuation characteristics within differential time periods, determine the change frequency and intensity of emotions, using the formula:

[0151]

[0152] Obtain the emotion fluctuation characteristic data, where F gRepresents the contribution degree of emotional fluctuation, r t,g Represents the emotional change frequency at time point t, e t,g Is the emotional intensity at time point t, b g Is the bias term, T represents the total time point;

[0153] The benefit of the formula is that it refers to the frequency and intensity of emotional changes through the way of time series weighting, improving the flexibility and accuracy of emotional change characteristic analysis;

[0154] Set to monitor the emotional data for T = 30 days, where the emotional change frequency r t,g And emotional intensity e t,g Are obtained by actual monitoring. For example, on a certain day, r 15,g = 0.8, e 15,g = 0.5, set the bias term b g = 0.1, then the emotional fluctuation contribution degree on this day is F g = 0.8×0.5 + 0.1 = 0.5. By accumulating for all days, the total emotional fluctuation characteristics within the entire time period are obtained, which can accurately quantify the emotional changes of each day and even each moment, and accumulate its impact on the overall emotional stability. This calculation method not only scientifically reflects the actual changes of emotions, but also can assist psychologists and researchers to better analyze the essence and influencing factors of emotional fluctuations. The result shows that by calculating through the formula, the frequency and intensity of emotional changes can be comprehensively referred to, reflecting emotional stability.

[0155] Based on the emotional fluctuation characteristic data, by combining the standard deviation and coefficient of variation of emotional fluctuations, evaluate the overall emotional stability, measure the predictability of emotional states within the measurement period, and generate an emotional stability index;

[0156] In the final stage of obtaining the emotional stability index, deeply analyze the statistical characteristics of emotional data. Through the organized time series emotional data, use statistical methods to calculate the basic statistical quantities of the data, such as mean, median, standard deviation, and coefficient of variation, etc. Statistical indicators assist us in analyzing the universality and abnormality of emotional fluctuations. The standard deviation provides a measure of the amplitude of emotional intensity fluctuations, while the coefficient of variation reflects the volatility of emotional intensity relative to the average level. Through quantitative indicators, it can be revealed that the emotional changes are not only in terms of their intensity, but also in terms of the regularity and predictability of their fluctuations. By comparing the emotional data in different time periods (such as weekdays and weekends), the specific impact of life events on emotional stability can be identified. The detailed analysis will accumulate into the key data for calculating the emotional stability index. The index can comprehensively reflect the individual's emotional fluctuation status and mental health status, providing a scientific basis for subsequent psychological intervention and emotional management.

[0157] Please refer to Figure 8, the steps to obtain the adjusted emotion recognition results are specifically as follows:

[0158] Based on the emotion stability index, evaluate whether the current signal processing parameters are suitable for the current emotion index. By comparing the current emotion index with a predetermined threshold, if the index shows a large deviation, trigger the parameter adjustment process, using the formula:

[0159] P u = α u ×ISI u + β u

[0160] Generate the preliminarily adjusted signal processing parameters, where ISI u represents the emotion stability index, α u is the emotion change sensitivity coefficient, β u is the baseline correction coefficient, and P u represents the preliminarily adjusted signal processing parameters;

[0161] The advantage of the formula is that by combining the emotion stability index and the adjustment parameters, this formula enables the signal processing parameters to more accurately reflect the user's emotion changes and optimizes the accuracy of emotion recognition. Based on the latest emotion stability index ISI u , this formula adjusts the signal processing parameters to more delicately capture emotion fluctuations, where α u reflects the sensitivity of emotion changes to signal processing, while β u is the baseline adjustment coefficient to ensure system stability in the absence of significant emotion changes;

[0162] To verify the effectiveness of the adjustment of the signal processing parameter P u , a series of simulation tests were conducted. First, set the simulated emotion stability index ISI u = 0.55. According to the previously set adjustment parameter α u = 2.0 and the baseline adjustment coefficient β u = 0.6, calculate the current signal processing parameter: P u = 2.0×0.55 + 0.6 = 1.7;

[0163] Use this new parameter P u to perform signal parsing simulation in a controlled environment. The simulation includes signal inputs with different emotion intensities, and evaluate the accuracy and response time of emotion recognition before and after parameter adjustment.

[0164] Apply the preliminarily adjusted signal processing parameters to signal parsing, conduct simulation tests and evaluate the impact on emotion recognition accuracy. By performing multiple simulations, use the formula:

[0165] E u = γ u×P 2 u +δ u

[0166] Estimate the recognition accuracy, verify the effect of the new parameter settings, and generate simulated test results, where γ u represents the adjustment coefficient, and δ u is the constant offset, and E u represents the simulated test result, and P u represents the signal processing parameters of the preliminary adjustment;

[0167] In the simulation test, use the formula E u =γ u ×P 2 u +δ u , to predict the accuracy of emotion recognition, where γ u =0.05, and δ u =0.1. Substitute the adjusted signal processing parameters and calculate E u =0.05×(1.7) 2 +0.1 = 0.1445+0.1 = 0.2445;

[0168] This result represents the expected performance of the adjusted system in the simulated emotion recognition task. By comparing the E u values before and after adjustment, evaluate the actual effect of parameter adjustment on improving the accuracy of emotion recognition;

[0169] Experimental data shows that the recognition accuracy of the system after parameter adjustment has been significantly improved when dealing with complex emotion changes, the misrecognition rate has decreased, and the overall performance of the system has been optimized. Through this method, verify the necessity and effectiveness of parameter adjustment, ensure that each adjustment is based on sufficient experimental verification and data support, and greatly improve the sensitivity and recognition accuracy of the system to emotion changes.

[0170] Adjust and solidify the signal processing parameters according to the simulation test results. By comparing the emotion recognition results before and after adjustment, verify the advantages of the new parameters and output the adjusted emotion recognition results;

[0171] The ultimate goal of the adjustment is to solidify the current signal processing parameters into the emotion recognition system to achieve long-term stable operation. This step involves ultimate verification, that is, the adjusted parameter P uIt is formally applied to the actual emotion recognition environment, and continuous performance monitoring is carried out. The monitoring process includes real-time data capture, logging of emotion recognition results, error analysis, etc. It can evaluate the performance of new parameters in actual applications in real time, and adjust the parameters in a timely manner to adapt to the emotion change patterns of different users. This not only improves the accuracy of emotion recognition, but also optimizes the user experience, makes the system more user-friendly, and meets the needs of a wider range of users.

[0172] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An emotional state detection system based on electrophysiological data, characterized in that: The system comprises: The signal receiving and calibration module receives the signals of electrocardiogram, brain wave and skin electrical activity, performs signal calibration and corrects the time deviation to obtain the calibrated signal, and synchronizes the electrocardiogram waveform, brain wave pattern and skin electrical response according to the calibrated signal to obtain the synchronized electrophysiological data; The signal anomaly detection module uses a convolutional neural network to identify arrhythmias and abnormal brain waves based on the synchronized electrophysiological data, obtains abnormal indicators, removes and corrects the abnormal indicators, and generates purified electrophysiological signals; The emotion pattern analysis module uses the purified electrophysiological signal to analyze the electrocardiogram waveform and the electroencephalogram pattern through an autoregressive moving average model to obtain preliminary emotion characteristics, and performs emotion labeling through the preliminary emotion characteristics to generate emotion classification results; The steps for obtaining the preliminary emotion features are specifically as follows: By performing frequency domain analysis on the purified electrophysiological signal, converting the signal from the time domain to the frequency domain using Fourier transform, calculating the spectrum density of the electrocardiogram and electroencephalogram signals, and generating the spectrum density features of the electrocardiogram and electroencephalogram; According to the spectral density characteristics of the ECG and EEG, the autoregressive moving average model is applied, combined with the waveform data of the ECG and EEG signals, and the formula is adopted: Calculate the electrophysiological signal characteristics associated with emotions and obtain the autoregressive and moving average parameters of the emotional state, where α d and β d Represent the autoregressive and moving average coefficients, y j-d Represents the original ECG or EEG signal value of the jth signal, ∈ j-d represents the original prediction error, m represents the number of samples, A d represents the autoregressive and moving average parameters of the emotional state; Using the emotional state autoregression and moving average parameters, threshold analysis is performed to identify emotional changes, an emotional detection threshold is set, and the prediction error of each calculation cycle is compared to see whether it exceeds the threshold, the change of emotional state is verified, and preliminary emotional characteristics are obtained; The steps for obtaining the emotion classification results are specifically as follows: By using the preliminary emotional features, according to the changes in the electrocardiogram and electroencephalogram signals, a corresponding emotional state is assigned to each time point to obtain labeled time series data; The labeled time series data is used as input, a weighted calculation method is applied and multiple emotion features are combined, and the formula is adopted: Calculate the total sentiment score and get the sentiment score sequence, where E h represents the total sentiment score, w k,h represents the weight of the emotion feature k, F k,h is the standardized score of emotion feature k, b h is the bias term, K represents the total emotional feature quantity; Based on the emotion score sequence, a support vector machine algorithm is used to map the continuous emotion scores to emotion categories, including happiness, sadness, and anger, and the emotion state at each time point is classified to generate an emotion classification result; The emotion output module uses the emotion classification result, receives emotion tagging data, calculates the frequency and intensity of emotion changes in differentiated time periods, determines the statistical characteristics of emotion fluctuations, obtains an emotion stability index, adjusts signal processing parameters according to the emotion stability index, optimizes signal analysis accuracy, and generates adjusted emotion recognition results.

2. The emotional state detection system based on electrophysiological data according to claim 1, characterized in that: The steps for acquiring the synchronous electrophysiological data are specifically as follows: By receiving the signals of electrocardiogram, brain wave and skin electrical activity, executing the time calibration algorithm, the time deviation caused by the transmission delay is eliminated, and the signal set after time calibration is obtained; The time-calibrated signal set is synchronized using the formula: Calculate the difference of each physiological signal and generate a synchronized signal set, where x i,a represents the sample value of the i-th signal, represents the average value of the signal samples, n represents the number of samples, S a Indicates the degree of synchronization; The synchronized signal set is utilized to optimize signal processing by dynamically adjusting synchronization parameters to obtain synchronized electrophysiological data.

3. The emotional state detection system based on electrophysiological data according to claim 2, characterized in that: The steps for obtaining the abnormal indicators are specifically as follows: Extracting features of electrocardiogram and brain waves from the synchronized electrophysiological data, including peaks, troughs and signal strengths, and extracting feature information using a target digital signal processing technique to obtain a physiological signal feature set; Based on the physiological signal feature set, arrhythmia and abnormal brain waves are identified using the formula: I b =σ(W b ·F b +b b ) Through the propagation of the network, the abnormal pattern data is obtained, where σ represents the activation function and W b represents the weight of the convolutional layer, b b Indicates bias, I b Indicates abnormal mode data, F b represents a physiological signal feature set; The abnormal pattern data is analyzed, the frequency and severity of the differentiated abnormal patterns are calculated, and the abnormal indicators are obtained according to the preset critical thresholds.

4. The emotional state detection system based on electrophysiological data according to claim 3, characterized in that: The steps of obtaining the purified electrophysiological signal are specifically as follows: Based on the abnormal indicators, analyzing the ECG and EEG signals, identifying the locations of arrhythmias and abnormal EEG waves, and generating an abnormal segment list; Apply a filter to the abnormal section list to process the data, fine-tune the signal, reduce noise interference, and use the formula: R c =a c ·L c -b c ∑(γ c ·L c +d c ) Output the corrected signal data set, where α c , β c , γ c and δ c are parameters adjusted according to the abnormal signal strength and frequency, R c represents the corrected signal data set, L c Indicates the abnormal segment of the mark; The corrected signal data set is evaluated, statistical analysis is performed and signal quality is verified, frequency distribution detection is used to verify the physiological credibility and integrity of the signal, and a purified electrophysiological signal is generated.

5. The emotional state detection system based on electrophysiological data according to claim 1, characterized in that: The steps for obtaining the emotional stability index are specifically as follows: By analyzing the emotion tag data of the emotion classification result, an index is established for the emotion change in each time period, and the emotion data is converted into a time series format to generate an initialized emotion data time series; Based on the initialized emotional data time series, calculate the emotional fluctuation characteristics within the differentiated time period, determine the frequency and intensity of emotional changes, and use the formula: Get emotional fluctuation characteristic data, where F g represents the contribution of emotional fluctuations, r t,g represents the frequency of emotion change at time point t, e t,g is the emotional intensity at time point t, b g is the bias term, T represents the total time points; Based on the emotion fluctuation characteristic data, by combining the standard deviation and coefficient of variation of emotion fluctuation, the overall stability of emotion is evaluated, the predictability of the emotion state within the measurement period is measured, and the emotion stability index is generated.

6. The emotional state detection system based on electrophysiological data according to claim 5, characterized in that: The steps for obtaining the adjusted emotion recognition result are specifically as follows: Based on the emotional stability index, it is evaluated whether the current signal processing parameters are adapted to the current emotional index. By comparing the current emotional index with a predetermined threshold, if the index shows a large deviation, the parameter adjustment process is triggered, using the formula: P u =a u ×ISI u +b u Generate preliminary adjustment signal processing parameters, where ISI u represents the emotional stability index, α u is the coefficient of sensitivity to emotion change, β u is the baseline correction factor, P u represents the initial adjustment of signal processing parameters; The signal processing parameters adjusted in the preliminary manner are applied to signal analysis, simulation tests are performed and the impact on emotion recognition accuracy is evaluated by performing multiple simulations and applying the formula: Estimate recognition accuracy, verify the effect of new parameter settings, and generate simulation test results, where γ u represents the adjustment factor, δ u is a constant offset, E u represents the simulation test results, P u represents the initial adjustment of signal processing parameters; The signal processing parameters are adjusted and solidified according to the simulation test results, the advantages of the new parameters are verified by comparing the emotion recognition results before and after the adjustment, and the adjusted emotion recognition results are output.

Images