Methods, devices, equipment and storage media for generating simulated bioelectric signals

Abstract

This invention relates to the field of bioelectrical signal simulation technology, and provides a method, apparatus, device, and storage medium for generating simulated bioelectrical signals based on dynamic waveform regulation. The method includes: periodically acquiring electrical signal data from a target organism; processing the electrical signal data to extract target feature information; selecting a preset type waveform and setting initial parameters for the preset type waveform based on the target feature information; dynamically adjusting the parameters of the preset type waveform according to real-time signal changes based on a feedback control algorithm; and obtaining a simulated bioelectrical signal based on the adjusted waveform parameters. By adjusting the waveform parameters of the signal in real time to generate simulated bioelectrical signals that conform to individual characteristics, the difference between simulated bioelectrical signals and actual bioelectrical signals can be effectively reduced, improving the universality of the application.

Description

Technical Field

[0001] This invention relates to the field of bioelectric signal simulation technology, and in particular to a method, apparatus, device, and storage medium for generating simulated bioelectric signals based on dynamic waveform modulation. Background Technology

[0002] Simulated bioelectrical signals (such as electromyography, electrocardiography, and electroencephalography) are key technologies in biomedical engineering and rehabilitation equipment. Currently, most methods for generating simulated bioelectrical signals use preset waveform templates or simplified mathematical models. While these methods can reflect the basic morphology and characteristics of bioelectrical signals to some extent, due to the complexity of bioelectrical signals and individual differences, they lack the flexibility to generate diverse signals for different individuals. They also fail to adapt to the physiological characteristics of different individuals, resulting in significant deviations between the generated and actual bioelectrical signals, thus affecting subsequent analysis and applications. Summary of the Invention

[0003] This application provides a method, apparatus, device, and storage medium for generating simulated bioelectric signals based on dynamic waveform modulation. The aim is to generate simulated bioelectric signals that conform to individual characteristics by adjusting the waveform parameters of the signal in real time, which can effectively reduce the difference between simulated bioelectric signals and actual bioelectric signals and improve the universality of the application.

[0004] In a first aspect, embodiments of this application provide a method for generating simulated bioelectric signals based on dynamic waveform modulation, comprising:

[0005] Periodically collect bioelectrical signals from the target object;

[0006] Bioelectric signals are processed to extract target feature information;

[0007] Based on the target feature information, select a preset type waveform and set the initial parameters of the preset type waveform;

[0008] Based on the feedback control algorithm, the parameters of the preset type waveform are dynamically adjusted according to the real-time changes of the bioelectric signal;

[0009] Based on the adjusted waveform parameters, a simulated bioelectric signal is obtained.

[0010] In one embodiment, processing the bioelectrical signal to extract target feature information includes:

[0011] The bioelectric signals are processed to extract time-domain and frequency-domain features, respectively.

[0012] In one embodiment, the bioelectric signal is processed to extract time-domain and frequency-domain features, including:

[0013] Divide the bioelectric signal into multiple time windows;

[0014] Within each time window, the time-domain feature values ​​of the corresponding bioelectric signal are calculated to obtain the time-domain feature vector;

[0015] Within each time window, the time-domain signal is converted into a frequency-domain signal, and the frequency-domain eigenvalues ​​are calculated to obtain the frequency-domain eigenvector.

[0016] In one embodiment, selecting a preset type waveform and setting initial parameters for the preset type waveform based on target feature information includes:

[0017] The dynamic characteristics of bioelectric signals are determined based on time-domain feature vectors, and the frequency composition and spectral distribution of bioelectric signals are determined based on frequency-domain feature vectors.

[0018] Based on the dynamic characteristics, frequency composition, and spectral distribution of the bioelectric signal, select a matching preset waveform type and set the initial parameters of the preset waveform type.

[0019] In one embodiment, based on a feedback control algorithm, the parameters of a preset type of waveform are dynamically adjusted according to real-time changes in the bioelectrical signal, including:

[0020] Real-time extraction of time-domain and frequency-domain features of bioelectrical signals;

[0021] The time-domain and frequency-domain features are compared with the parameters of a preset type of waveform, and the error is determined based on the comparison results.

[0022] Errors are analyzed based on feedback control algorithms to determine control strategies.

[0023] The parameters of the preset waveform type are dynamically adjusted according to the control strategy.

[0024] In one embodiment, the control strategy is determined by analyzing the error based on a feedback control algorithm, including:

[0025] Based on the feedback control algorithm, the magnitude of the error is analyzed, and the adjustment values ​​of the waveform parameters that need to be adjusted are calculated.

[0026] In one embodiment, dynamically adjusting the parameters of a preset type waveform according to a control strategy includes:

[0027] Based on the calculated adjustment values ​​of each waveform parameter, the parameters of the preset type waveform are dynamically adjusted.

[0028] Secondly, embodiments of this application provide a simulated bioelectric signal generation device based on dynamic waveform modulation, comprising:

[0029] The acquisition module is used to periodically acquire bioelectrical signals from the target object;

[0030] The extraction module is used to process bioelectrical signals and extract target feature information;

[0031] The selection module is used to select a preset type of waveform and set the initial parameters of the preset type of waveform based on the target feature information.

[0032] The adjustment module is used to dynamically adjust the parameters of a preset type of waveform based on the real-time changes of bioelectric signals using a feedback control algorithm.

[0033] The generation module is used to obtain simulated bioelectric signals based on the adjusted waveform parameters.

[0034] Thirdly, embodiments of this application provide an electronic device, including:

[0035] Memory and processing modules;

[0036] The memory is used to store computer programs;

[0037] The processing module is used to execute the computer program and, when executing the computer program, to implement the steps of the simulated bioelectric signal generation method based on dynamic waveform regulation as described in the first aspect above.

[0038] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program; when the computer program is executed by one or more processing modules, it causes the one or more processing modules to perform the steps of the analog bioelectric signal generation method based on dynamic waveform modulation as described in the first aspect above.

[0039] This application provides a method, apparatus, device, and storage medium for generating simulated bioelectrical signals based on dynamic waveform modulation. The method includes: periodically acquiring electrical signal data from a target organism; processing the electrical signal data to extract target feature information; selecting a preset type waveform and setting initial parameters for the preset type waveform based on the target feature information; dynamically adjusting the parameters of the preset type waveform according to real-time signal changes based on a feedback control algorithm; and obtaining a simulated bioelectrical signal based on the adjusted waveform parameters. By adjusting the waveform parameters of the signal in real time to generate simulated bioelectrical signals that conform to individual characteristics, the difference between simulated bioelectrical signals and actual bioelectrical signals can be effectively reduced, improving the universality of the application. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A flowchart illustrating the method for generating simulated bioelectric signals based on dynamic waveform modulation provided in this application embodiment;

[0042] Figure 2 A schematic diagram of the structure of the analog bioelectric signal generation device based on dynamic waveform regulation provided in the embodiments of this application;

[0043] Figure 3 A schematic block diagram illustrating the simulated bioelectric signal generation setup based on dynamic waveform modulation provided in this application embodiment. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0046] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0047] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0048] The technical solution provided in this application will be described in detail below with reference to the accompanying drawings.

[0049] Please see Figure 1 , Figure 1This is a flowchart illustrating the simulated bioelectrical signal generation method based on dynamic waveform modulation provided in this application embodiment. The execution entity of this simulated bioelectrical signal generation method based on dynamic waveform modulation is an electronic device that completes the entire process of generating, detecting, and adjusting the simulated bioelectrical signal. The combination of hardware and / or software modules included in this electronic device enables the execution of the steps of the simulated bioelectrical signal generation method based on dynamic waveform modulation. Figure 1 As can be seen, the method for generating simulated bioelectric signals based on dynamic waveform modulation provided in this application includes the following steps:

[0050] S101: Periodically collects bioelectrical signals from the target object.

[0051] Periodic acquisition of bioelectrical signals from a target object refers to the continuous recording of bioelectrical signals generated by the target object (such as human muscles, nerves, heart, etc.) at set time intervals (sampling period). Acquiring these bioelectrical signals allows for monitoring changes in physiological state, serving as a basis for real-time control or diagnosis. Typical applications include monitoring signals such as electrocardiogram (ECG), electroencephalogram (EEG), and electromyography (EMG).

[0052] S102: Process bioelectric signals to extract target feature information.

[0053] Bioelectrical signals (such as electrocardiogram (ECG), electroencephalogram (EEG), and electromyography (EMG) are electrical signals generated by human tissues and organs during physiological activities. These signals usually contain a large amount of noise and redundant information, therefore signal processing is required to extract effective target feature information.

[0054] In one embodiment, processing the bioelectric signal to extract target feature information includes: processing the bioelectric signal to extract time-domain features and frequency-domain features, respectively.

[0055] The analysis of time-domain features focuses on the changes of bioelectrical signals along the time axis, directly using the waveform of the original bioelectrical signal for calculation. This method can capture information such as the trend, amplitude changes, and peak values ​​of the bioelectrical signal. The main time-domain features include: mean, variance and standard deviation, peak-to-peak value, root mean square (RMS) value, and zero crossover rate. Specifically, the mean describes the average value of the bioelectrical signal over a period of time, determining its overall trend; variance and standard deviation measure the volatility and degree of change of the bioelectrical signal; peak-to-peak value is the difference between the maximum and minimum values ​​of the bioelectrical signal, describing its amplitude range; the RMS value assesses the energy level of the bioelectrical signal; and the zero crossover rate detects the frequency of change in the bioelectrical signal. These time-domain features are suitable for analyzing low-frequency signals, detecting sudden events, and describing the energy and trends of bioelectrical signals.

[0056] Frequency domain features reveal the frequency components and periodicity of bioelectrical signals by transforming them from the time domain to the frequency domain (typically using Fourier transform). This is crucial for detecting periodic events and filtering out noise. This embodiment combines time-domain and frequency-domain features to analyze bioelectrical signals, providing more comprehensive information. For example, time-domain features directly reflect the fluctuation trend and energy level of bioelectrical signals, while frequency-domain features reveal hidden periodic components and frequency anomalies.

[0057] In one embodiment, the bioelectric signal is processed to extract time-domain features and frequency-domain features, including: dividing the bioelectric signal into multiple time windows; calculating the time-domain feature value of the corresponding bioelectric signal in each time window to obtain a time-domain feature vector; converting the time-domain signal into a frequency-domain signal in each time window, calculating the frequency-domain feature value to obtain a frequency-domain feature vector.

[0058] Bioelectrical signals (such as electrocardiogram, electroencephalogram, and electromyogram signals) are typically continuous and non-stationary, meaning their characteristics change over time. To better extract these changing features, a time windowing method is often used. This involves dividing the bioelectrical signal into multiple fixed-length segments and calculating features for each segment. A time window refers to the duration of each segment, such as 100 milliseconds, 500 milliseconds, or 1 second. In practical applications, to avoid losing important information, adjacent time windows often overlap, for example, by 50%. Assuming the bioelectrical signal length is N, the time window size is W, and the overlap length is O, then the starting index of the time window is:

[0059] t i =i·(WO) (i=0, 1, 2,...)

[0060] The data in each time window is used to calculate time-domain and frequency-domain features separately.

[0061] The bioelectrical signals within each time window are processed to calculate several time-domain features, forming a time-domain feature vector. Common time-domain features include: mean, standard deviation, peak-to-peak value, and root mean square value. All time-domain feature values ​​are combined into a vector, for example, V1 = [mean, standard deviation, ..., root mean square value]. A corresponding time-domain feature vector is generated for each time window.

[0062] Fourier transform is applied to the bioelectric signal within each time window to obtain the spectrum of the bioelectric signal. Frequency domain information such as main frequency, power spectral density, frequency center, and bandwidth can be extracted from the spectrum. All frequency domain information is combined into a vector, for example, V2 = [main frequency, power spectral density, frequency center, bandwidth...]. A corresponding frequency domain feature vector is generated for each time window.

[0063] Among them, the dominant frequency is used to represent the frequency component with the highest energy in the spectrum, the power spectral density is used to represent the energy distribution of each frequency component, the frequency center is used to represent the centroid of the spectrum, and the bandwidth is used to represent the frequency distribution range of the signal.

[0064] Within each time window, the calculated time-domain and frequency-domain eigenvectors are combined to form the corresponding eigenvector for that time window. The eigenvectors from all time windows are then combined to form the feature matrix of the entire bioelectrical signal, which can be used for subsequent analysis.

[0065] S103: Select a preset waveform type and set the initial parameters of the preset waveform type based on the target feature information.

[0066] The dynamic characteristics and frequency components of bioelectrical signals determine their basic form. By analyzing the time-domain and frequency-domain characteristics of bioelectrical signals, the most suitable waveform model (such as sine wave, square wave, pulse wave, etc.) can be found to describe them. The selection of preset waveform types and the setting of initial parameters will help achieve accurate results in bioelectrical signal reconstruction, filtering, or system simulation.

[0067] In one embodiment, selecting a preset type waveform and setting initial parameters for the preset type waveform based on target feature information includes: determining the dynamic characteristics of the bioelectric signal based on time-domain feature vectors, determining the frequency composition and spectral distribution of the bioelectric signal based on frequency-domain feature vectors; and selecting a matching preset type waveform and setting initial parameters for the preset type waveform based on the dynamic characteristics, frequency composition, and spectral distribution of the bioelectric signal.

[0068] Specifically, dynamic characteristics describe the changing trend, fluctuation amplitude, and transient behavior of bioelectrical signals. The changing trend of bioelectrical signals is determined by whether the mean deviates from zero; the fluctuation amplitude of bioelectrical signals is determined by the fluctuation of standard deviation and peak-to-peak value; and the transient behavior of bioelectrical signals is determined by the magnitude of the zero crossover rate.

[0069] Frequency composition and spectral distribution reflect the energy concentration of bioelectrical signals at different frequencies. Frequency composition includes the dominant frequency, frequency center, and bandwidth. Spectral distribution includes the power spectral density.

[0070] For example, suppose the bioelectrical signal in the i-th time window is: W i Given the time-domain feature vector V1, the frequency-domain feature vector V2, and the preset type waveform y(t), with preset category waveform parameters including amplitude A, frequency f, phase Φ, offset θ, and duty cycle D, the process of selecting a matching preset type waveform based on the dynamic characteristics, frequency composition, and spectral distribution of the bioelectric signal can be expressed as:

[0071] If, based on the time-domain feature vector V1, the zero-crossing rate is determined to be lower than a preset first threshold, and the mean value tends towards zero, then the selected preset waveform type is a sine wave, expressed as:

[0072]

[0073] If the zero-crossing rate is determined to be greater than the second threshold (the second threshold is greater than the first threshold) based on the time-domain feature vector V1, then the selected preset waveform type is a square wave, represented as:

[0074] y(t)=A·sgn(sin(2πft))+θ

[0075] If the zero-crossing rate is determined to be greater than the first threshold and less than the second threshold based on the time-domain feature vector V1, then the preset waveform type is selected as a pulse wave, represented as:

[0076] y(t)=A·δ(t-nT)

[0077] Based on the frequency domain characteristic vector V2, the time window W is determined. i If the internal bioelectrical signal is dominated by a single frequency, then the frequency f of the preset waveform type is set as the main frequency. If it is determined that the time window W is within this range... i When multiple frequencies of internal bioelectrical signals are superimposed, the frequency f of the preset type waveform is set as the center frequency, and the amplitude A of the preset type waveform is determined based on the root mean square value of the time-domain feature vector. The phase of the preset type waveform is determined based on the mean of the time-domain feature vector. Offset θ = V mean Duty cycle (only for square waves or pulse waves)

[0078] in, To preset the initial phase, V RMS V is the root mean square value. mean T is the mean. high The duration of the high-level signal.

[0079] S104: Based on a feedback control algorithm, the parameters of a preset type of waveform are dynamically adjusted according to the real-time changes in the bioelectric signal.

[0080] In one embodiment, based on a feedback control algorithm, the parameters of a preset type waveform are dynamically adjusted according to the real-time changes of the bioelectric signal, including: extracting the time-domain and frequency-domain features of the bioelectric signal in real time; comparing the time-domain and frequency-domain features with the parameters of the preset type waveform respectively, and determining the error based on the comparison results; analyzing the error based on the feedback control algorithm and determining the control strategy; and dynamically adjusting the parameters of the preset type waveform according to the control strategy.

[0081] Specifically, time-domain features reflect the time-series variation trend of a signal, such as average value, peak-to-peak value, and standard deviation. These features can be used to match parameters such as waveform amplitude, phase, and offset.

[0082] For example, assuming the preset waveform type is a sinusoidal function, the amplitude A should be close to half of the peak-to-peak value of the time-domain characteristic, and the difference between amplitude A and half of the peak-to-peak value is the amplitude error. Assuming the preset waveform type is a square wave, the corresponding amplitude A should be close to the root mean square (RMS) value, and the difference between amplitude A and the RMS value is the amplitude error.

[0083] The average value included in the time-domain features can be used to reflect the DC offset of the signal. If the average value is not 0, the value corresponding to that average value is used as the offset error. The zero-crossing rate included in the time-domain features is used to determine the periodicity and phase of the signal. The phase error can be obtained by calculating the difference between the zero-crossing rate and the phase Φ of the bioelectric signal.

[0084] In one embodiment, the control strategy is determined based on error analysis using a feedback control algorithm, including:

[0085] Based on the feedback control algorithm, the magnitude of the error is analyzed, and the adjustment values ​​of the waveform parameters that need to be adjusted are calculated.

[0086] Specifically, if the error value is large, specifically greater than the third threshold, then the first preset parameter, also known as the primary parameter, such as amplitude and frequency, needs to be adjusted to ensure that the waveform basically matches the bioelectric signal. If the error values ​​are all less than the maximum threshold, then the second preset parameter, also known as the secondary parameter, such as phase, offset, and duty cycle, needs to be adjusted to further optimize the bioelectric signal output.

[0087] For example, based on error analysis using a feedback control algorithm, determining the control strategy can be expressed as calculating the adjustment value of the waveform parameter that needs to be adjusted using the following formula:

[0088]

[0089] Where, Δp i (t) represents the adjustment value of the waveform parameter that needs to be adjusted, K p K is the proportionality coefficient. i K is the integral coefficient. d E is the differential coefficient. i (t) represents the i-th error at time t. It should be noted that K... p K i and K d All are pre-set according to the application.

[0090] In one embodiment, dynamically adjusting the parameters of a preset type waveform according to a control strategy includes: dynamically adjusting the parameters of the preset type waveform according to the calculated adjustment values ​​of each waveform parameter.

[0091] S105: Based on the adjusted waveform parameters, the simulated bioelectric signal is obtained.

[0092] Specifically, based on the calculated adjustment values, each waveform parameter is updated to obtain and output a simulated bioelectric signal.

[0093] As can be seen from the above analysis, the simulated bioelectric signal generation method based on dynamic waveform regulation provided in this application includes: periodically acquiring electrical signal data of a target organism; processing the electrical signal data to extract target feature information; selecting a preset type waveform and setting initial parameters of the preset type waveform based on the target feature information; dynamically adjusting the parameters of the preset type waveform according to real-time signal changes based on a feedback control algorithm; and obtaining a simulated bioelectric signal based on the adjusted waveform parameters. By adjusting the waveform parameters of the signal in real time to generate a simulated bioelectric signal that conforms to individual characteristics, the difference between the simulated bioelectric signal and the actual bioelectric signal can be effectively reduced, improving the universality of the application.

[0094] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a simulated bioelectric signal generation device based on dynamic waveform modulation, provided in an embodiment of this application. Figure 2 As can be seen, the simulated bioelectric signal generation device 20 based on dynamic waveform regulation provided in this application includes:

[0095] The acquisition module 201 is used to periodically acquire bioelectrical signals from the target object.

[0096] The extraction module 202 is used to process bioelectric signals and extract target feature information.

[0097] The selection module 203 is used to select a preset type waveform and set the initial parameters of the preset type waveform based on the target feature information.

[0098] The adjustment module 204 is used to dynamically adjust the parameters of a preset type of waveform based on the real-time changes of the bioelectric signal using a feedback control algorithm.

[0099] The generation module 205 is used to obtain simulated bioelectric signals based on the adjusted waveform parameters.

[0100] In one embodiment, the extraction module 202 is specifically used for:

[0101] The bioelectric signals are processed to extract time-domain and frequency-domain features, respectively.

[0102] In one embodiment, the extraction module 202 includes:

[0103] The segmentation unit is used to divide the bioelectric signal into multiple time windows;

[0104] The first obtaining unit is used to calculate the time-domain feature value of the corresponding bioelectric signal within each time window, and obtain the time-domain feature vector;

[0105] The second obtaining unit is used to convert the time-domain signal into a frequency-domain signal within each time window, calculate the frequency-domain eigenvalues, and obtain the frequency-domain eigenvector.

[0106] In one embodiment, the selection module 203 includes:

[0107] The first determining unit is used to determine the dynamic characteristics of the bioelectric signal based on the time-domain feature vector and to determine the frequency composition and spectral distribution of the bioelectric signal based on the frequency-domain feature vector.

[0108] The selection unit is used to select a matching preset type waveform and set the initial parameters of the preset type waveform based on the dynamic characteristics, frequency composition and spectral distribution of the bioelectric signal.

[0109] In one embodiment, the adjustment module 204 includes:

[0110] The extraction unit is used to extract the time-domain and frequency-domain features of bioelectrical signals in real time.

[0111] The comparison unit is used to compare the time-domain features and frequency-domain features with the parameters of a preset type of waveform, and determine the error based on the comparison results.

[0112] The second determining unit is used to analyze errors based on feedback control algorithms and determine control strategies.

[0113] The adjustment unit is used to dynamically adjust the parameters of a preset type of waveform according to the control strategy.

[0114] In one embodiment, the second determining unit is specifically used for:

[0115] Based on the feedback control algorithm, the magnitude of the error is analyzed, and the adjustment values ​​of the waveform parameters that need to be adjusted are calculated.

[0116] In one embodiment, the adjustment unit is specifically used for:

[0117] Based on the calculated adjustment values ​​of each waveform parameter, the parameters of the preset type waveform are dynamically adjusted.

[0118] It should be noted that the specific implementation process of each module or unit mentioned above can be referred to the specific implementation process of each step in the previous method embodiment, and will not be repeated here.

[0119] Please see Figure 3 As shown, Figure 3 A schematic block diagram of a simulated bioelectric signal generation device based on dynamic waveform modulation provided in an embodiment of this application.

[0120] For example, the analog bioelectric signal generation device 30 based on dynamic waveform modulation includes a processing module 301 and a memory 302.

[0121] For example, the processing module 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0122] Specifically, the processing module 301 can be a microcontroller unit (MCU), a central processing unit (CPU), or a digital signal processor (DSP), etc.

[0123] Specifically, the memory 302 can be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a portable hard drive, etc.

[0124] The processing module 301 is used to run the computer program stored in the memory 302, and implements the steps of the above-mentioned method for generating simulated bioelectric signals based on dynamic waveform regulation when executing the computer program.

[0125] For example, the processing module 301 is used to run a computer program stored in the memory 302, and performs the following steps when executing the computer program:

[0126] Periodically collect bioelectrical signals from the target object;

[0127] Bioelectric signals are processed to extract target feature information;

[0128] Based on the target feature information, select a preset type waveform and set the initial parameters of the preset type waveform;

[0129] Based on the feedback control algorithm, the parameters of the preset type waveform are dynamically adjusted according to the real-time changes of the bioelectric signal;

[0130] Based on the adjusted waveform parameters, a simulated bioelectric signal is obtained.

[0131] In one embodiment, processing the bioelectrical signal to extract target feature information includes:

[0132] The bioelectric signals are processed to extract time-domain and frequency-domain features, respectively.

[0133] In one embodiment, the bioelectric signal is processed to extract time-domain and frequency-domain features, including:

[0134] Divide the bioelectric signal into multiple time windows;

[0135] Within each time window, the time-domain feature values ​​of the corresponding bioelectric signal are calculated to obtain the time-domain feature vector;

[0136] Within each time window, the time-domain signal is converted into a frequency-domain signal, and the frequency-domain eigenvalues ​​are calculated to obtain the frequency-domain eigenvector.

[0137] In one embodiment, selecting a preset type waveform and setting initial parameters for the preset type waveform based on target feature information includes:

[0138] The dynamic characteristics of bioelectric signals are determined based on time-domain feature vectors, and the frequency composition and spectral distribution of bioelectric signals are determined based on frequency-domain feature vectors.

[0139] Based on the dynamic characteristics, frequency composition, and spectral distribution of the bioelectric signal, select a matching preset waveform type and set the initial parameters of the preset waveform type.

[0140] In one embodiment, based on a feedback control algorithm, the parameters of a preset type of waveform are dynamically adjusted according to real-time changes in the bioelectrical signal, including:

[0141] Real-time extraction of time-domain and frequency-domain features of bioelectrical signals;

[0142] The time-domain and frequency-domain features are compared with the parameters of a preset type of waveform, and the error is determined based on the comparison results.

[0143] Errors are analyzed based on feedback control algorithms to determine control strategies.

[0144] The parameters of the preset waveform type are dynamically adjusted according to the control strategy.

[0145] In one embodiment, the control strategy is determined by analyzing the error based on a feedback control algorithm, including:

[0146] Based on the feedback control algorithm, the magnitude of the error is analyzed to determine the adjustment value of the waveform parameters that need to be adjusted.

[0147] In one embodiment, dynamically adjusting the parameters of a preset type waveform according to a control strategy includes:

[0148] Based on the calculated adjustment values ​​of each waveform parameter, the parameters of the preset type waveform are dynamically adjusted.

[0149] The specific principles and implementation methods of the simulated bioelectric signal generation device based on dynamic waveform regulation provided in this application embodiment are similar to those of the simulated bioelectric signal generation method based on dynamic waveform regulation in the foregoing embodiments, and will not be repeated here.

[0150] This application embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processing module, causes the processing module to perform the following steps:

[0151] Periodically collect bioelectrical signals from the target object;

[0152] Bioelectric signals are processed to extract target feature information;

[0153] Based on the target feature information, select a preset type waveform and set the initial parameters of the preset type waveform;

[0154] Based on the feedback control algorithm, the parameters of the preset type waveform are dynamically adjusted according to the real-time changes of the bioelectric signal;

[0155] Based on the adjusted waveform parameters, a simulated bioelectric signal is obtained.

[0156] In one embodiment, processing the bioelectrical signal to extract target feature information includes:

[0157] The bioelectric signals are processed to extract time-domain and frequency-domain features, respectively.

[0158] In one embodiment, the bioelectric signal is processed to extract time-domain and frequency-domain features, including:

[0159] Divide the bioelectric signal into multiple time windows;

[0160] Within each time window, the time-domain feature values ​​of the corresponding bioelectric signal are calculated to obtain the time-domain feature vector;

[0161] Within each time window, the time-domain signal is converted into a frequency-domain signal, and the frequency-domain eigenvalues ​​are calculated to obtain the frequency-domain eigenvector.

[0162] In one embodiment, selecting a preset type waveform and setting initial parameters for the preset type waveform based on target feature information includes:

[0163] The dynamic characteristics of bioelectric signals are determined based on time-domain feature vectors, and the frequency composition and spectral distribution of bioelectric signals are determined based on frequency-domain feature vectors.

[0164] Based on the dynamic characteristics, frequency composition, and spectral distribution of the bioelectric signal, select a matching preset waveform type and set the initial parameters of the preset waveform type.

[0165] In one embodiment, based on a feedback control algorithm, the parameters of a preset type of waveform are dynamically adjusted according to real-time changes in the bioelectrical signal, including:

[0166] Real-time extraction of time-domain and frequency-domain features of bioelectrical signals;

[0167] The time-domain and frequency-domain features are compared with the parameters of a preset type of waveform, and the error is determined based on the comparison results.

[0168] Errors are analyzed based on feedback control algorithms to determine control strategies.

[0169] The parameters of the preset waveform type are dynamically adjusted according to the control strategy.

[0170] In one embodiment, the control strategy is determined by analyzing the error based on a feedback control algorithm, including:

[0171] Based on the feedback control algorithm, the magnitude of the error is analyzed, and the adjustment values ​​of the waveform parameters that need to be adjusted are calculated.

[0172] In one embodiment, dynamically adjusting the parameters of a preset type waveform according to a control strategy includes:

[0173] Based on the calculated adjustment values ​​of each waveform parameter, the parameters of the preset type waveform are dynamically adjusted.

[0174] The computer-readable storage medium can be an internal storage unit of the analog bioelectric signal generation device based on dynamic waveform modulation in the aforementioned embodiments, such as a hard drive or memory of the analog bioelectric signal generation device based on dynamic waveform modulation. Alternatively, the computer-readable storage medium can be an external storage device of a multi-channel pulse low-frequency signal generation device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the analog bioelectric signal generation device based on dynamic waveform modulation.

[0175] It should be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application.

[0176] It should also be understood that the term “and / or” as used in this application and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0177] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for generating simulated bioelectric signals based on dynamic waveform modulation, characterized in that, include: Periodically collect bioelectrical signals from the target object; The bioelectric signal is divided into multiple time windows; Within each time window, the time-domain feature values ​​of the corresponding bioelectric signal are calculated to obtain the time-domain feature vector; Within each time window, the time-domain signal is converted into a frequency-domain signal, and the frequency-domain eigenvalues ​​are calculated to obtain the frequency-domain eigenvector. The dynamic characteristics of the bioelectric signal are determined based on the time-domain feature vector, and the frequency composition and spectral distribution of the bioelectric signal are determined based on the frequency-domain feature vector. Based on the dynamic characteristics, frequency composition, and spectral distribution of the bioelectric signal, a matching preset type waveform is selected, and the initial parameters of the preset type waveform are set; the preset type waveform includes a sine wave, a square wave, or a pulse wave; the initial parameters include amplitude, frequency, phase, offset, and duty cycle; Based on a feedback control algorithm, the parameters of the preset type waveform are dynamically adjusted according to the real-time changes of the bioelectric signal; Based on the adjusted waveform parameters, a simulated bioelectric signal is obtained.

2. The method for generating simulated bioelectric signals based on dynamic waveform modulation according to claim 1, characterized in that, The method of dynamically adjusting the parameters of the preset type waveform based on the real-time changes of the bioelectric signal using a feedback control algorithm includes: The time-domain and frequency-domain features of the bioelectrical signal are extracted in real time. The time-domain features and the frequency-domain features are compared with the parameters of the preset type waveform, and the error is determined based on the comparison results. Based on the feedback control algorithm, the error is analyzed to determine the control strategy; The parameters of the preset type waveform are dynamically adjusted according to the control strategy.

3. The method for generating simulated bioelectric signals based on dynamic waveform modulation according to claim 2, characterized in that, The step of analyzing the error based on the feedback control algorithm and determining the control strategy includes: The magnitude of the error is analyzed based on the feedback control algorithm, and the adjustment value of the waveform parameters that need to be adjusted is calculated.

4. The method for generating simulated bioelectric signals based on dynamic waveform modulation according to claim 3, characterized in that, The step of dynamically adjusting the parameters of the preset type waveform according to the control strategy includes: The parameters of the preset type waveform are dynamically adjusted based on the calculated adjustment values ​​of each waveform parameter.

5. A device for generating simulated bioelectric signals based on dynamic waveform modulation, characterized in that, include: The acquisition module is used to periodically acquire bioelectrical signals from the target object; The extraction module is used to divide the bioelectrical signal into multiple time windows; Within each time window, the time-domain feature value of the corresponding bioelectric signal is calculated to obtain the time-domain feature vector; within each time window, the time-domain signal is converted into a frequency-domain signal, and the frequency-domain feature value is calculated to obtain the frequency-domain feature vector. The selection module is used to determine the dynamic characteristics of the bioelectric signal based on the time-domain feature vector, and to determine the frequency composition and spectral distribution of the bioelectric signal based on the frequency-domain feature vector; based on the dynamic characteristics, frequency composition, and spectral distribution of the bioelectric signal, it selects a matching preset type waveform and sets the initial parameters of the preset type waveform; the preset type waveform includes a sine wave, a square wave, or a pulse wave; the initial parameters include amplitude, frequency, phase, offset, and duty cycle; An adjustment module is used to dynamically adjust the parameters of the preset type waveform based on the real-time changes of the bioelectric signal using a feedback control algorithm. The generation module is used to obtain simulated bioelectric signals based on the adjusted waveform parameters.

6. An electronic device, characterized in that, include: Memory and processing modules; The memory is used to store computer programs; The processing module is used to execute the computer program and, when executing the computer program, to implement the steps of the simulated bioelectric signal generation method based on dynamic waveform regulation as described in claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program; When the computer program is executed by one or more processing modules, the one or more processing modules perform the steps of the simulated bioelectric signal generation method based on dynamic waveform modulation as described in claims 1-4.

Images