Biological signal analysis method and system, storage medium and electronic equipment

Abstract

The invention provides a biological signal analysis method and system, a storage medium and electronic equipment. The method comprises the following steps: acquiring a biological signal of a testee; extracting a spectrum feature of the biological signal in a first specified frequency band; optimizing the spectrum features to obtain a second specified frequency band; and obtaining trigger time of a target phase in the second specified frequency band based on a prediction model so as to stimulate the biological signal based on the trigger time. According to the biological signal analysis method and system, the storage medium and the electronic equipment, the prediction precision of the specific phase point of the biological signal is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of biological signal processing, and relates to a biological signal analysis method, system, storage medium and electronic equipment. Background Art

[0002] Biosignals refer to signals transmitted inside an organism or between an organism and the external environment. These signals can be electrical, chemical, mechanical, optical, biomechanical, and biomagnetic signals. Among them, bioelectric signals include electroencephalogram (EEG), electrocardiogram (ECG or EKG), electromyogram (EMG), and electrooculogram (EOG). The collection, analysis, and interpretation of biosignals are crucial to understanding the physiological and pathological states of organisms. Through biosignals, researchers can monitor and evaluate the health of organisms, develop new diagnostic tools and treatments, and achieve active artificial intervention. Summary of the invention

[0003] The present invention provides a biological signal analysis method, system, storage medium and electronic device for solving the problem of how to accurately find the appropriate intervention point of the biological signal.

[0004] In a first aspect, the present invention provides a method for analyzing biological signals, the method comprising the following steps: obtaining a biological signal of a subject; extracting the spectrum characteristics of the biological signal in a first specified frequency band; optimizing the spectrum characteristics to obtain a second specified frequency band; obtaining the trigger time of a target phase in the second specified frequency band based on a prediction model, so as to stimulate the biological signal based on the trigger time. Through the above-mentioned spectrum optimization, prediction model, etc., the prediction accuracy of a specific phase point of the biological signal is effectively improved.

[0005] In an implementation of the first aspect, it also includes: real-time phase optimization test parameters based on the target phase and the trigger time; the test parameters include the filter order and filter type used when extracting spectral features, the optimization parameters of spectral features, the algorithm type of the prediction model, the length of the target time window, and the time window where the target phase is located. Through the above method, the test parameters can be adjusted in time according to actual application requirements to ensure the accuracy of the prediction of specific phase points of biological signals.

[0006] In an implementation manner of the first aspect, the test parameters are optimized based on a genetic algorithm.

[0007] In an implementation of the first aspect, extracting the spectrum characteristics of the biological signal in the first specified frequency band includes the following steps: performing a first filtering on the biological signal in the first specified frequency band; performing a sliding window processing on the biological signal after the first filtering; performing a fast Fourier transform on the biological signal after the sliding window processing to obtain the spectrum characteristics of the biological signal in the first specified frequency band. Through the above method, the validity and reliability of the spectrum characteristics of the biological signal are guaranteed.

[0008] In an implementation of the first aspect, optimizing the spectrum characteristics and obtaining the second designated frequency band includes the following steps: determining an optimization parameter λ, 0<λ<1; obtaining the energy spectrum density of each frequency in the first designated frequency band; removing the frequencies in the first designated frequency band based on the energy spectrum density in order from low to high, until the energy of the remaining frequency band is less than or equal to λ times the energy of the first designated frequency band; and using the remaining frequency band as the second designated frequency band. Through the above method, the prediction accuracy of the phase point of the biological signal is improved, which not only improves the efficiency of signal processing, but also helps to reduce the computational load of the system.

[0009] In an implementation of the first aspect, obtaining the trigger time of the target phase in the second specified frequency band based on the prediction model includes the following steps: obtaining the real-time phase of the biological signal in the current time window in the second specified frequency band; obtaining the predicted phase in the target time window in the second specified frequency band based on the prediction model and the real-time phase; determining the target phase of the evoked response potential of the biological signal; calculating the position of the predicted phase matching the target phase in the target time window, and calculating the trigger time of the evoked response potential based on the position. In the above manner, the evoked response potential can be stimulated at the target phase, thereby ensuring the effectiveness of biological signal acquisition.

[0010] In an implementation manner of the first aspect, the matching means that a difference between the target phase and the predicted phase within a specified period is less than a preset threshold.

[0011] In an implementation of the first aspect, obtaining the real-time phase of the biological signal in the current time window of the second specified frequency band includes the following steps: performing a first filtering on the biological signal in the first specified frequency band; performing sliding window processing on the biological signal after the first filtering; performing fast Fourier transform on the biological signal after the sliding window processing to obtain the spectrum characteristics of the biological signal in the first specified frequency band, and determining the frequency with the highest energy in the current time window in the first specified frequency band as the center frequency of the first specified frequency band; based on the first filtering, obtaining the first phase offset of the center frequency; performing Hilbert transform on the spectrum characteristics; performing a second filtering on the second specified frequency band of the double value of the positive frequency component of the spectrum characteristics after the Hilbert transform to obtain the filtered frequency domain signal; based on the second filtering, obtaining the second phase offset of the center frequency; performing an inverse fast Fourier transform on the filtered frequency domain signal to obtain the filtered time domain signal; calculating the difference between the phase value of the filtered time domain signal and the first phase offset and the second phase offset, and using the difference as the real-time phase. Through the above method, the real-time phase of the biological signal can be accurately obtained and the algorithm complexity is reduced.

[0012] In an implementation of the first aspect, determining the target phase of the evoked response potential of the biological signal includes the following steps: obtaining the center frequency of the biological signal in the first specified frequency band; obtaining the delay time of the evoked response potential; based on the delay time, calculating the phase offset of the evoked response potential relative to the center frequency; and calculating the target phase of the evoked response potential based on the phase offset. In the above manner, the evoked response potential is emitted exactly at the phase peak.

[0013] In a second aspect, the present invention provides a biological signal analysis system, the system comprising an acquisition module, an extraction module, an optimization module and a stimulation module;

[0014] The acquisition module is used to acquire biological signals of the subject;

[0015] The extraction module is used to extract the frequency spectrum characteristics of the biological signal in the first specified frequency band;

[0016] The optimization module is used to optimize the spectrum characteristics to obtain a second designated frequency band;

[0017] The stimulation module is used to obtain the trigger time of the target phase in the second specified frequency band based on the prediction model, so as to stimulate the biological signal based on the trigger time.

[0018] In a third aspect, the present invention provides an electronic device, the electronic device comprising: a processor and a memory;

[0019] The memory is used to store computer programs;

[0020] The processor is used to execute the computer program stored in the memory so that the electronic device performs the above-mentioned biological signal analysis method.

[0021] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned biological signal analysis method when executed by an electronic device.

[0022] As described above, the biosignal analysis method, system, storage medium and electronic device of the present invention have the following beneficial effects:

[0023] (1) The prediction accuracy of specific phase points of biological signals is effectively improved through spectrum optimization, prediction model, adaptive optimization parameters and other methods;

[0024] (2) The computational complexity of the phase prediction process is effectively reduced, the processing speed is fast, and the system load is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 Shown is a schematic diagram of a scene of an electronic device in an embodiment of the present invention;

[0026] Figure 2 Shown is a flow chart of a biological signal analysis method in one embodiment of the present invention;

[0027] Figure 3 Shown is a flow chart of an embodiment of the present invention for obtaining a trigger time of a target phase within a second specified frequency band based on a prediction model;

[0028] Figure 4 Shown is a flow chart of an embodiment of the present invention for obtaining the real-time phase of a biological signal within a current time window within a second specified frequency band;

[0029] Figure 5 A schematic diagram showing a phase response of a first filter of the present invention in an embodiment;

[0030] Figure 6 A schematic diagram showing a phase response of a second filter of the present invention in one embodiment;

[0031] Figure 7 Shown is a schematic diagram of the structure of a biological signal analysis system in one embodiment of the present invention;

[0032] Figure 8 It is a schematic structural diagram of an electronic device of the present invention in one embodiment. DETAILED DESCRIPTION

[0033] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0034] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0035] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0036] In the present invention, the biological signal includes electroencephalogram (EEG) signal, cortical electroencephalogram (EEG) signal, deep electrode signal, electrooculogram (EOG) signal, electromyography (EMG) signal, electrocardiogram (ECG) signal, magnetic resonance imaging (MRI) signal and / or near-infrared brain imaging signal.

[0037] Electroencephalogram (EEG) is a method of recording the electrical activity of brain neurons by placing electrodes on the scalp. The amplitude of EEG signals varies in different brain regions and under different physiological or pathological conditions. The frequency of EEG signals refers to the oscillation rate of the signal, usually measured in Hertz (Hz). The frequency of EEG signals can be divided into different bands, such as delta waves (0.5-4Hz), theta waves (4-8Hz), alpha waves (8-13Hz), beta waves (13-30Hz) and gamma waves (above 30Hz).

[0038] Electrocortical electroencephalogram (ECoG) is a type of brain electrical activity recorded by placing electrodes on the surface of the cerebral cortex with high spatial and temporal resolution. The amplitude of the ECoG signal reflects the strength of the electrical signal generated by neuronal activity. The amplitude of the ECoG signal varies in different brain regions and under different physiological or pathological conditions. ECoG signals in different frequency bands are associated with different brain functional states.

[0039] Deep electrode signals (SEEG) are captured by electrodes implanted deep in the brain. The amplitude of these signals can reflect the intensity of neuronal group activity. The phase of deep electrode signals reflects the temporal relationship between signals recorded by different electrodes. This phase information is very important for studying synchronization and functional connectivity between brain regions. The frequency of deep electrode signals reflects the dynamic changes in brain activity. Deep electrode signals of different frequency bands are associated with different brain functional states.

[0040] Electrooculogram (EOG) is an objective and quantitative retinal function test method that detects the slow changes in the electrostatic potential of the eye as it adapts to light. In the electrooculogram (EOG), the change in amplitude reflects the functional state of the retinal pigment epithelium-photoreceptor complex.

[0041] Electromyography (EMG) is the measurement of electrical signals that trigger muscle contraction and reflect the degree of muscle contraction. The amplitude of the EMG signal reflects the strength or size of the signal. In EMG, changes in amplitude reflect the degree of muscle activity. The phase of the EMG signal reflects the time relationship between the signals recorded by different electrodes. Frequency analysis can reveal the complexity of muscle activity, including the degree of muscle fatigue.

[0042] The electrocardiogram (ECG) is a graph that records changes in the heart's electrical activity through the body surface, which reflects the electrophysiological process of the heart. The amplitude of the ECG signal is usually around 1mV, reflecting the potential changes produced during the depolarization and repolarization of the heart. Changes in heart rate directly affect the frequency components of the ECG signal, and the normal heart rate range is about 60 to 100 beats per minute. Spectral analysis of ECG signals can help identify the characteristics of heart disease, such as arrhythmia, myocardial ischemia, etc.

[0043] Functional magnetic resonance imaging (fMRI) is a research method that stimulates specific senses to induce neural activity (functional area activation) in the corresponding parts of the cerebral cortex and displays it through magnetic resonance images. The frequency components of fMRI signals reflect the dynamic changes of brain activity.

[0044] Functional near-infrared spectroscopy (fNIRS) is a non-invasive neuroimaging technique that studies brain function by measuring changes in the concentrations of oxygenated hemoglobin (oxy-Hb) and deoxyhemoglobin (deoxy-Hb) in the blood caused by brain activity. The frequency of the fNIRS signal reflects the dynamic changes in brain activity. In addition, frequency domain analysis of fNIRS signals can also reveal low-frequency oscillations (LFOs) of brain activity, which are related to changes in brain hemodynamics.

[0045] The protection scope of the present invention is not limited to the types of biological signals listed in this embodiment. All biological signals that can be directly extended and implemented based on the technical principles of the present invention are included in the protection scope of the present invention. The following uses EEG signals as an example to specifically explain the biological signal analysis method of the present invention.

[0046] In the prior art, neural stimulation methods mainly include open-loop and closed-loop methods. Due to the lack of feedback on actual brain activity, it is difficult to observe the expected experimental results in the open-loop neural stimulation method, which in turn limits the research progress in this field. The closed-loop neural stimulation method can apply stimulation at a specific time point of brain activity based on the real-time collected EEG signals, so as to better regulate the brain neural oscillation and improve the synchronization and stability between neural stimulation and intrinsic brain activity. Among them, neural stimulation includes acoustic stimulation signals, light stimulation signals, electrical stimulation signals, ultrasonic stimulation signals, magnetic stimulation signals and / or vibration stimulation signals. The protection scope of the present invention is not limited to the types of stimulation signals listed in this embodiment. All neural stimulations that can be directly expanded and realized based on the technical principles of the present invention are included in the protection scope of the present invention. However, to achieve closed-loop neural stimulation, the key is to be able to accurately extract the instantaneous phase information of EEG signals in a specific frequency band in real time. At present, Hilbert transform is a commonly used phase extraction method, but it is complex to calculate and has an endpoint effect. In addition, due to calculation and communication delays, the accuracy of real-time phase calculation will be affected. With the increase in the requirements for real-time phase accuracy, a higher calculation frequency is required to meet the conditions, but this will increase the delay of the system.

[0047] The present invention can improve the accuracy of time series analysis by using a prediction model. By predicting the peak time and combining the delay and phase shift, the optimal time for the evoked response potential to synchronize with the actual EEG signal can be calculated. At the same time, the real-time phase of the target frequency band wave can be captured more accurately through spectrum optimization, thereby reducing errors. In the phase prediction process, the optimization of multiple parameters is involved. Based on the error between the predicted value and the actual value, these parameters can be adjusted using an optimization algorithm to improve the accuracy of the prediction.

[0048] The following embodiments of the present invention provide a method for collecting biological numbers, which can be applied to Figure 1 The electronic device 2 shown. Taking the EEG signal as an example, the electronic device 2 sends neural stimulation to the subject, and the subject generates an EEG signal in response to the neural stimulation, so that the biological signal analysis device 1 can collect the EEG signal. The electronic device 2 of the present invention applies neural stimulation at a specific time point based on the EEG signal collected in real time, thereby improving the synchronization and stability between the neural stimulation and the intrinsic brain activity, which is beneficial to the analysis and use of EEG signals. The technical scheme in the embodiment of the present invention will be described in detail below in conjunction with the accompanying drawings in the embodiment of the present invention.

[0049] like Figure 2 As shown, in one embodiment, the biological signal analysis method of the present invention includes steps S1 to S4.

[0050] Step S1, obtaining biological signals of the subject.

[0051] Specifically, the biological signals of the subject are collected based on the biological signal collection device, and the biological signals include electroencephalogram signals, cortical electroencephalogram signals, deep electrode signals, electrooculogram signals, electromyography signals, electrocardiogram signals, magnetic resonance imaging signals or near-infrared brain imaging signals.

[0052] Step S2: extracting the frequency spectrum characteristics of the biological signal in a first specified frequency band.

[0053] Specifically, a first designated frequency band for regulating the biological signal is selected, for example, the first designated frequency band of alpha waves is 7.5-12.5Hz, the first designated frequency band of theta waves is 4.5-7.5Hz, and the first designated frequency band of delta waves is 0.5-4.5Hz. First, the biological signal is first filtered in the first designated frequency band based on the first filter to remove noise and non-correlated frequency components. Among them, Butteworth filter and Chebyshev filter can be used for the first filtering. It should be noted that the filter type and filter order used in the first filtering are optimizable parameters. Then, the biological signal after the first filtering is subjected to N-point sliding window processing. Finally, the biological signal after the sliding window processing is subjected to fast Fourier transform to obtain the spectral characteristics of the biological signal in the first designated frequency band.

[0054] Step S3: Optimize the frequency spectrum characteristics to obtain a second designated frequency band.

[0055] Specifically, optimizing the spectrum characteristics to obtain the second designated frequency band includes the following steps:

[0056] 31) Determine an optimization parameter λ, 0<λ<1. λ is an optimizable parameter used to define the degree of spectrum optimization.

[0057] 32) Obtaining the energy spectrum density of each frequency in the first specified frequency band.

[0058] 33) Based on the energy spectrum density from low to high, remove the frequencies in the first designated frequency band until the energy of the remaining frequency band is less than or equal to λ times the energy of the first designated frequency band. When λ is close to 1, the spectrum feature optimization process is more conservative, less energy is removed, and the second designated frequency band is wider. When λ is close to 0, the spectrum feature optimization process is more aggressive, more energy is removed, and the second designated frequency band is narrower. By adjusting the value of λ, the width of the frequency band and the energy concentration can be balanced, thereby optimizing the prediction accuracy of specific biological signal phase points, which not only improves the efficiency of signal processing, but also helps to reduce the computational load of the system.

[0059] 34) Using the remaining frequency band as the second designated frequency band.

[0060] Step S4: acquiring a trigger time of a target phase in the second specified frequency band based on a prediction model, so as to stimulate the biological signal based on the trigger time.

[0061] Specifically, Figure 3 As shown, obtaining the trigger time of the target phase in the second specified frequency band based on the prediction model includes the following steps:

[0062] 41) Obtaining the real-time phase of the biological signal in the current time window within the second specified frequency band.

[0063] like Figure 4 As shown, obtaining the real-time phase of the biological signal in the current time window in the second specified frequency band includes the following steps:

[0064] a) performing a first filtering on the biosignal in a first designated frequency band. The biosignal is first filtered based on the first filter to remove noise and non-correlated frequency components. A Butteworth filter or a Chebyshev filter can be used for the first filtering. It should be noted that the filter type and filter order used in the first filtering are optimizable parameters. The first designated frequency band of α waves is 7.5-12.5Hz, the first designated frequency band of θ waves is 4.5-7.5Hz, and the first designated frequency band of δ waves is 0.5-4.5Hz.

[0065] b) performing N-point sliding window processing on the biological signal after the first filtering.

[0066] c) performing fast Fourier transform on the biological signal after sliding window processing to obtain the spectrum characteristics of the biological signal in the first specified frequency band, and determining the frequency with the highest energy in the current time window in the first specified frequency band as the center frequency ICF of the first specified frequency band.

[0067] d) Based on the first filtering, obtaining a first phase offset of the center frequency. Wherein, first, obtaining a phase response of the pulse frequency of the first filtering. Wherein, according to the parameters of the first filtering, obtaining Figure 5 The phase response of the pulse frequency of the first filter is shown. Next, the main frequency of the first filter is determined based on the phase response. Finally, the phase offset of the center frequency relative to the main frequency is taken as the first phase offset θ1.

[0068] e) performing Hilbert transformation on the frequency spectrum feature, wherein the negative frequency components of the frequency spectrum feature X[f] after Hilbert transformation are set to zero, and the positive frequency components are multiplied by two to obtain Yi[f].

[0069] f) performing a second filtering of the second specified frequency band on the double value of the positive frequency component of the spectrum feature after Hilbert transformation to obtain a filtered frequency domain signal. Wherein, Yi[f] is subjected to a second filtering of the second specified frequency band based on the second filter. For example, for α waves, a second-order Butterworth bandpass filter with a frequency band of 7.5-12.5 Hz is used; for θ waves, a second-order Butterworth bandpass filter with a frequency band of 4.5-7.5 Hz is used; for δ waves, a second-order Butterworth bandpass filter with a frequency band of 0.5-4.5 Hz is used.

[0070] g) based on the second filtering, obtaining a second phase offset of the center frequency. Wherein, firstly, according to the parameters of the second filtering, obtaining Figure 6 The phase response of the pulse frequency of the second filter is shown. Then the main frequency of the second filter is determined based on the phase response. Finally, the phase offset of the center frequency relative to the main frequency is used as the phase offset θ2 of the second filter.

[0071] h) performing an inverse fast Fourier transform on the filtered frequency domain signal to obtain a filtered time domain signal. The filtered time domain signal is analyzed to obtain a phase value θ of the filtered time domain signal.

[0072] i) Calculate the difference between the phase value of the filtered time domain signal and the first phase offset and the second phase offset, and use the difference as the real-time phase. Calculate θ-θ1-θ2, and use the difference as the real-time phase.

[0073] 42) obtaining a predicted phase within a target time window within the second specified frequency band based on the prediction model and the real-time phase, wherein the real-time phase is input into the prediction model, and the prediction model can output a predicted phase within the target time window within the second specified frequency band.

[0074] In one embodiment, the prediction model may use an autoregressive model Kalman filter algorithm, a maximum likelihood algorithm, a least squares method, etc. The type of prediction algorithm used by the prediction model is also an optimizable parameter.

[0075] 43) Determine the target phase of the evoked response potential of the biological signal. Among them, the target phase is calculated according to the delay of the evoked response potential to ensure that the evoked response potential reaches a peak at the target phase. First, the center frequency of the biological signal in the first specified frequency band is obtained. Then the delay duration of the evoked response potential is obtained. Finally, based on the delay duration, the phase offset of the evoked response potential relative to the center frequency is calculated. For example, assume that the delay duration of the auditory evoked response potential is 62.5ms. In order to make the evoked response potential just emitted at the phase peak, assume that the target frequency band is determined to be the δ frequency band, and after obtaining the sleep regulation parameters, modulate the corresponding sound wave stimulation signal to act on the user's brain. Assuming that the target frequency of the δ frequency band is 2.5Hz and the period is 400ms, the phase offset when the sound wave stimulation signal occurs should be (62.5 / 400)*360=15.625°, so that the EEG signal generates an EEG coupling signal under the action of the stimulation signal. It should be noted that the length of the target time window and the time window where the target phase is located are also optimizable parameters. For example, the time window where the target phase is located may be the phase of the N1th cycle in the future.

[0076] 44) Calculate the position of the predicted phase that matches the target phase within the target time window, and calculate the trigger time of the evoked response potential based on the position, so as to stimulate the biological signal based on the trigger time. Wherein, within the target time window, find the position of the predicted phase that matches the target phase, and determine the trigger time of the evoked response potential based on the position of the matched predicted phase within the target time window, that is, the time corresponding to the position within the target time window, so as to stimulate the biological signal based on the trigger time. It should be noted that the matching means that the difference between the target phase and the predicted phase within a specified period is less than a preset threshold. The stimulation can be acoustic stimulation, light stimulation, electrical stimulation, ultrasonic stimulation, magnetic stimulation and / or vibration stimulation, etc.

[0077] In one embodiment, the biosignal analysis method of the present invention also includes real-time phase optimization test parameters based on the target phase and the trigger time; the test parameters include the filter order and filter type used when extracting spectral features, the optimization parameters of spectral features, the algorithm type of the prediction model, the length of the target time window and the time window where the target phase is located. Wherein, when optimizing the test parameters, fitness can be used for judgment. Test and obtain the test parameter combination that minimizes fitness within a fixed time. In one embodiment, the test parameters are optimized based on a genetic algorithm. The specific steps are as follows:

[0078] a. Determine the fitness function: You can choose mean square error or phase lock coefficient PLV. Mean square error measures the difference between the predicted value and the actual value. The smaller the value, the more accurate the prediction. The phase lock coefficient PLV is used to measure the degree of phase synchronization between the two signals. The closer the value is to 1, the higher the degree of synchronization.

[0079] b. Initialize the population: Select a set of test parameter combinations as the initial population. Each individual represents a test parameter combination.

[0080] c. Calculate fitness: For each individual, calculate its fitness value using the selected fitness function based on the phase at the predicted time point and the actual phase.

[0081] d. Selection operation: Select excellent individuals according to their fitness values ​​as the parents of the next generation. Roulette selection, tournament selection and other methods can be used.

[0082] e. Crossover operation: Perform a crossover operation on the selected parent individuals to generate new offspring individuals. The crossover operation can be performed using single-point crossover, multi-point crossover, and other methods.

[0083] f. Mutation operation: Perform mutation operation on the newly generated offspring individuals to introduce random changes and increase the diversity of the population. The mutation operation can adopt random mutation, Gaussian mutation and other methods.

[0084] g. Repeat steps cf until the stopping condition is met, such as reaching the maximum number of iterations or the fitness value reaches a certain accuracy requirement.

[0085] h. Output the optimal parameter combination: Within a fixed time, the test parameter combination that minimizes the fitness is the optimal test parameter combination.

[0086] i. User test: Allow the user to test with the current optimal parameters. If the fitness is greater than the preset threshold within a fixed time, it will automatically switch to the next optimal test parameter combination. This process can continue until a test parameter combination that meets the performance requirements is found. If the fitness is greater than the threshold within a fixed time, it will jump to the next test parameter. If all test parameters do not meet the requirements, the test parameter with the smallest error will be selected.

[0087] The protection scope of the biological signal analysis method described in the embodiment of the present invention is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present invention are included in the protection scope of the present invention.

[0088] An embodiment of the present invention also provides a biological signal analysis system, which can implement the biological signal analysis method described in the present invention. However, the implementation device of the biological signal analysis system described in the present invention includes but is not limited to the structure of the biological signal analysis system listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present invention are included in the protection scope of the present invention.

[0089] like Figure 7 As shown, in one embodiment, the biological signal analysis system of the present invention includes a first acquisition module 71 , an extraction module 72 , an optimization module 73 and a stimulation module 74 .

[0090] The first acquisition module 71 is used to acquire biological signals of the subject.

[0091] The extraction module 72 is connected to the first acquisition module 71 and is used to extract the frequency spectrum characteristics of the biological signal in the first specified frequency band.

[0092] The optimization module 73 is connected to the extraction module 72 and is used to optimize the frequency spectrum feature to obtain a second designated frequency band.

[0093] The stimulation module 74 is connected to the optimization module 73, and is used to obtain the trigger time of the target phase in the second specified frequency band based on the prediction model, so as to stimulate the biological signal based on the trigger time.

[0094] Among them, the structures and principles of the first acquisition module 71, the extraction module 72, the optimization module 73 and the stimulation module 74 correspond one to one with the steps in the above-mentioned biological signal analysis method, so they are not repeated here.

[0095] In the several embodiments provided by the present invention, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules / units is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0096] The modules / units described as separate components may or may not be physically separated, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention. For example, the functional modules / units in the various embodiments of the present invention may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0097] Those of ordinary skill in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0098] The embodiment of the present invention also provides a computer-readable storage medium. A person of ordinary skill in the art can understand that all or part of the steps in the method for implementing the above embodiment can be completed by instructing the processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state hard disk, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state disk (SSD)), etc.

[0099] An embodiment of the present invention further provides an electronic device, which includes a processor and a memory.

[0100] The memory is used to store computer programs.

[0101] The memory includes: ROM, RAM, disk, USB flash drive, memory card or CD and other media that can store program codes.

[0102] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the electronic device executes the above-mentioned EEG signal acquisition method.

[0103] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0104] like Figure 8As shown, the electronic device of the present invention is in the form of a general computing device. The components of the electronic device may include but are not limited to: one or more processors or processing units 81, a memory 82, and a bus 83 connecting different system components (including the memory 82 and the processing unit 81).

[0105] Bus 83 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0106] Electronic devices typically include a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0107] The memory 82 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 821 and / or cache memory 822. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 823 may be used to read and write non-removable, non-volatile magnetic media ( Figure 8 not shown, usually called a "hard drive"). Although Figure 8 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 83 via one or more data medium interfaces. The memory 82 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0108] A program / utility 824 having a set (at least one) of program modules 8241 may be stored, for example, in the memory 82, such program modules 8241 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 8241 generally perform the functions and / or methods of the embodiments described herein.

[0109] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, displays, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via input / output (I / O) interface 84. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 85. Figure 8 As shown, the network adapter 85 communicates with other modules of the electronic device via the bus 83. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0110] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A biological signal analysis method, characterized in that: The method comprises the following steps: Obtaining biological signals from subjects; Extracting the frequency spectrum characteristics of the biological signal in a first specified frequency band; Optimizing the frequency spectrum characteristics to obtain a second designated frequency band; A trigger time of a target phase in the second specified frequency band is acquired based on the prediction model, so as to stimulate the biological signal based on the trigger time.

2. The biological signal analysis method according to claim 1, characterized in that: Also includes: Real-time phase optimization test parameters based on the target phase and the trigger time; the test parameters include the filter order and filter type used when extracting spectral features, the optimization parameters of spectral features, the algorithm type of the prediction model, the length of the target time window and the time window where the target phase is located.

3. The biological signal analysis method according to claim 2, characterized in that: The test parameters are optimized based on a genetic algorithm.

4. The biological signal analysis method according to claim 1, characterized in that: Extracting the spectrum feature of the biological signal in the first specified frequency band comprises the following steps: Performing a first filtering on the biological signal in a first designated frequency band; performing sliding window processing on the biological signal after the first filtering; Perform a fast Fourier transform on the biological signal after the sliding window processing to obtain the frequency spectrum characteristics of the biological signal in the first specified frequency band.

5. The biological signal analysis method according to claim 1, characterized in that: Optimizing the spectrum characteristics to obtain a second designated frequency band includes the following steps: Determine the optimization parameter λ, 0<λ<1; Acquire the energy spectral density of each frequency in the first specified frequency band; Remove frequencies in the first designated frequency band based on the energy spectral density in descending order until the energy of the remaining frequency band is less than or equal to λ times the energy of the first designated frequency band; The remaining frequency band is used as the second designated frequency band.

6. The biological signal analysis method according to claim 1, characterized in that: Acquiring the trigger time of the target phase in the second specified frequency band based on the prediction model includes the following steps: Acquire the real-time phase of the biological signal in a current time window within the second specified frequency band; Acquire a predicted phase within a target time window within the second specified frequency band based on the prediction model and the real-time phase; determining a target phase of an evoked response potential of the biosignal; The position of the predicted phase matching the target phase within the target time window is calculated, and the triggering time of the evoked response potential is calculated according to the position.

7. The biological signal analysis method according to claim 6, characterized in that: The matching means that the difference between the target phase and the predicted phase within a specified period is less than a preset threshold.

8. The biological signal analysis method according to claim 6, characterized in that: Acquiring the real-time phase of the biological signal in the current time window of the second specified frequency band comprises the following steps: Performing a first filtering on the biological signal in a first designated frequency band; performing sliding window processing on the biological signal after the first filtering; Performing a fast Fourier transform on the biological signal after sliding window processing to obtain the spectrum characteristics of the biological signal in a first specified frequency band, and determining the frequency with the highest energy in the current time window in the first specified frequency band as the center frequency of the first specified frequency band; Based on the first filtering, obtaining a first phase offset of the center frequency; Performing Hilbert transform on the frequency spectrum feature; Performing a second filtering on the second specified frequency band on the double value of the positive frequency component of the frequency spectrum feature after the Hilbert transformation to obtain a filtered frequency domain signal; Based on the second filtering, obtaining a second phase offset of the center frequency; Performing an inverse fast Fourier transform on the filtered frequency domain signal to obtain a filtered time domain signal; The difference between the phase value of the filtered time domain signal and the first phase offset and the second phase offset is calculated, and the difference is used as the real-time phase.

9. The biological signal analysis method according to claim 6, characterized in that: Determining the target phase of the evoked response potential of the biological signal comprises the following steps: Acquire the center frequency of the biological signal in the first specified frequency band; Obtaining the delay time of the evoked response potential; Based on the delay time, calculating the phase shift of the evoked response potential relative to the center frequency; A target phase of the evoked response potential is calculated based on the phase shift.

10. A biological signal analysis system, characterized in that: The system includes an acquisition module, an extraction module, an optimization module and a stimulation module; The acquisition module is used to acquire biological signals of the subject; The extraction module is used to extract the frequency spectrum characteristics of the biological signal in the first specified frequency band; The optimization module is used to optimize the spectrum characteristics to obtain a second designated frequency band; The stimulation module is used to obtain the trigger time of the target phase in the second specified frequency band based on the prediction model, so as to stimulate the biological signal based on the trigger time.

11. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the biological signal analysis method according to any one of claims 1 to 9 is implemented.

12. An electronic device, characterized in that: include: Processor and memory; The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory so as to enable the electronic device to perform the biological signal analysis method according to any one of claims 1 to 9.

Images