Neural electric impulse detection method and system, and terminal

Abstract

Provided are a neural electric impulse detection method and system, and a terminal. The method comprises: acquiring an original neuroelectrophysiological signal, and performing filtering and threshold detection on the original neuroelectrophysiological signal to obtain a first neural electric impulse signal sample (S100); applying a skewed distribution assumption to the first neural impulse signal, obtaining, according to the moment estimation of a skewed distribution, a first probability density parameter, a location parameter, and a scale parameter of the skewed distribution of the first neural electric impulse signal sample, and obtaining, according to the first probability density parameter, the location parameter, and the scale parameter, a first probability density function (S200); determining whether the first probability density parameter is less than zero, and if so, using the first neural electric impulse signal sample as a second neural electric impulse signal sample (S300); using kernel density estimation to perform a calculation on the second neural electric impulse signal sample to obtain a second probability density function (S400); and calculating information divergence between the first probability density function and the second probability density function, determining, according to the information divergence, whether the first neural electric impulse signal sample belongs to a neural electric impulse, and outputting a determination result (S500). The method has the advantages of rapidness, high efficiency, high noise resistance, good specificity, and eliminating the need for template matching.

Description

A neural electrical pulse detection method, system and terminal Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a neural electrical pulse detection method, system, terminal, and computer-readable storage medium. Background Art

[0002] The study of neural electrical activity is a crucial avenue for understanding the brain and a key enabler for the development of cutting-edge brain-computer interfaces. It holds significant value and significance for both human health and national economic development. Neural electrical pulse detection is a core topic in neuroscience and biomedical engineering, requiring the accurate and efficient identification of neuronal firing activity from complex EEG signals. Technological advances, particularly the development of high-throughput electrode arrays, present new challenges for this task: how to overcome the difficulty of rapidly and accurately detecting sparse neural electrical pulses from hundreds or thousands of electrode channels.

[0003] In the existing technology, some studies are based on the prior knowledge of neural electrical pulses obtained by researchers, and artificially set thresholds for detection. This method has low noise resistance or poor specificity; some studies are based on feature detection, that is, on the basis of threshold detection, measurements including but not limited to time domain, frequency domain, entropy, nonlinear dynamics, etc. are extracted as features for detecting and judging electrical pulse signals. The disadvantage of this method is that feature extraction belongs to the dimensionality reduction method, and a large amount of waveform information will inevitably be lost in the process; some studies are based on template matching, and template matching realizes neural electrical pulse detection by calculating the similarity between the waveform to be determined and the template waveform. In this process, the source and number of templates are important factors affecting the detection efficiency and accuracy, which is relatively troublesome and difficult to control; therefore, how to find a fast and efficient neural electrical pulse detection method is a problem that needs to be solved at present.

[0004] Summary of the Invention

[0005] In view of this, the present application provides a neural electrical pulse detection method, system, terminal and computer-readable storage medium to solve the problems of neural electrical pulse detection methods in the prior art, such as low noise resistance, poor specificity, loss of a large amount of waveform information, and complex template matching process.

[0006] This application proposes a method for detecting neural electrical pulses, which includes:

[0007] Acquiring an original neural electrophysiological signal, performing filtering and threshold detection on the original neural electrophysiological signal, and obtaining a first neural electrical pulse signal sample;

[0008] Assuming a skewed distribution for the first neural electrical pulse signal sample, obtaining a first probability density parameter, a location parameter, and a scale parameter of the skewed distribution of the first neural electrical pulse signal sample based on a moment estimate of the skewed distribution, and obtaining a first probability density function based on the first probability density parameter, the location parameter, and the scale parameter;

[0009] determining whether the first probability density parameter is less than zero, and if so, using the first neural electrical pulse signal sample as a second neural electrical pulse signal sample;

[0010] Calculating the second neural electrical pulse signal sample using a kernel density estimation method to obtain a second probability density function;

[0011] Calculate the information divergence between the first probability density function and the second probability density function, determine whether the first neural electrical pulse signal sample belongs to a neural electrical pulse according to the information divergence, and output the determination result.

[0012] Optionally, the acquiring of the original neural electrophysiological signal, filtering and threshold detection on the original neural electrophysiological signal, and obtaining the first neural electrical pulse signal sample specifically includes:

[0013] Acquiring an original neural electrophysiological signal, and filtering the original neural electrophysiological signal using a sixth-order Butterworth filter to obtain a first filtered electrical pulse signal;

[0014] A threshold detection parameter is used to perform threshold detection on the first filtered electrical pulse signal to obtain the first neural electrical pulse signal sample.

[0015] Optionally, making a skewed distribution assumption for the first neural electrical pulse signal sample, obtaining a first probability density parameter, a location parameter, and a scale parameter of the skewed distribution of the first neural electrical pulse signal sample according to a moment estimation of the skewed distribution, and obtaining a first probability density function according to the first probability density parameter, the location parameter, and the scale parameter, specifically includes:

[0016] The skew distribution assumption is made for the first neural electrical pulse signal sample: Y~SN(ξ,ω 2 ,α);

[0017] Wherein, Y represents the first neural electrical pulse signal sample, and SN represents the skewed distribution; Y=ξ+ωX;

[0018] Among them, ξ∈R is the location parameter, ω∈R + is the scale parameter, α is the first probability density parameter, α<0 is a tilted variable, and X is a sample that obeys the standard skewed distribution;

[0019] Obtaining a first probability density parameter, a location parameter, and a scale parameter of the skewed distribution of the first neural electrical pulse signal sample according to the moment estimation of the skewed distribution, and obtaining a first probability density function according to the first probability density parameter, the location parameter, and the scale parameter;

[0020] The mathematical formula of the first probability density function is:

[0021] in, represents the standard Gaussian density function, Φ(α·x) is Cumulative probability distribution function, where x is a random variable.

[0022] Optionally, the using a kernel density estimation method to calculate the second neural electrical pulse signal sample to obtain a second probability density function specifically includes:

[0023] Calculating the second neural electrical pulse signal sample using a Gaussian kernel density estimation method to obtain a second probability density function;

[0024] The calculation formula of the kernel density estimation method is:

[0025] Among them, the kernel function K is the Gaussian kernel x i is the sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is

[0026] Optionally, the using a kernel density estimation method to calculate the second neural electrical pulse signal sample to obtain a second probability density function specifically includes:

[0027] Calculating the second neural electrical pulse signal sample using a linear kernel density estimation method to obtain a second probability density function;

[0028] The calculation formula of the kernel density estimation method is:

[0029] Among them, the kernel function K is a linear kernel x i is the sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is

[0030] Optionally, the using a kernel density estimation method to calculate the second neural electrical pulse signal sample to obtain a second probability density function specifically includes:

[0031] Calculating the second neural electrical pulse signal sample using a cosine kernel density estimation method to obtain a second probability density function;

[0032] The calculation formula of the kernel density estimation method is:

[0033] Among them, the kernel function K is the cosine kernel Among them, π is the ratio of circumference to diameter, x is the ratio of circumference to diameter, i is the sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is

[0034] Optionally, calculating the information divergence between the first probability density function and the second probability density function, determining whether the first neural electrical pulse signal sample belongs to a neural electrical pulse according to the information divergence, and outputting the determination result specifically includes:

[0035] respectively calculating the probability density of the first probability density function and the second probability density function between the first neural electrical impulse signal sample value and the second neural electrical impulse signal sample value;

[0036] Calculating the information divergence between the first probability density function and the second probability density function according to the probability density between the first neural electrical pulse signal sample value and the second neural electrical pulse signal sample value;

[0037] The calculation formula of the information divergence is:

[0038] Where SN(i) represents the first probability density function, KDE(i) represents the second probability density function, and KL(SN,KDE) represents the information divergence.

[0039] Determining whether the first neural electrical pulse signal sample is a neural electrical pulse, and outputting a determination result;

[0040] If the information divergence is less than or equal to the preset threshold, the judgment result is that the first neural electrical pulse signal sample belongs to a neural electrical pulse.

[0041] The present application also proposes a neural electrical pulse detection system, which includes:

[0042] a signal preprocessing module, configured to obtain an original neural electrophysiological signal, perform filtering and threshold detection on the original neural electrophysiological signal, and obtain a first neural electrical pulse signal sample;

[0043] a signal moment estimation module, configured to make a skewed distribution assumption for the first neural electrical pulse signal sample, obtain a first probability density parameter, a location parameter, and a scale parameter of the skewed distribution of the first neural electrical pulse signal sample based on the moment estimation of the skewed distribution, and obtain a first probability density function based on the first probability density parameter, the location parameter, and the scale parameter;

[0044] a parameter determination module, configured to determine whether the first probability density parameter is less than zero, and if so, use the first neural electrical pulse signal sample as a second neural electrical pulse signal sample;

[0045] a signal density estimation module, configured to calculate the second neural electrical pulse signal sample using a kernel density estimation method to obtain a second probability density function;

[0046] A signal judgment module is used to calculate the information divergence between the first probability density function and the second probability density function, judge whether the first neural electrical pulse signal sample belongs to a neural electrical pulse according to the information divergence, and output a judgment result.

[0047] The present application also proposes a terminal comprising: a memory, a processor, and a neural electrical pulse detection program stored in the memory and executable on the processor. When the neural electrical pulse detection program is executed by the processor, the steps of the neural electrical pulse detection method as described above are implemented.

[0048] The present application also proposes a computer-readable storage medium, which stores a neural electrical pulse detection program. When the neural electrical pulse detection program is executed by a processor, the steps of the neural electrical pulse detection method as described above are implemented.

[0049] The beneficial effects of the present application are: different from the existing technology, the present application obtains the original neural electrophysiological signal, filters and thresholds the original neural electrophysiological signal, thereby reducing the noise of the original neural electrophysiological signal and obtaining a first neural electric pulse signal sample, thereby improving the anti-noise ability; secondly, the present application makes a skewed distribution assumption on the first neural electric pulse signal sample, obtains the first probability density parameter, position parameter and scale parameter of the skewed distribution of the first neural electric pulse signal sample according to the moment estimation of the skewed distribution, and obtains the first probability density function according to the first probability density parameter, position parameter and scale parameter, which is convenient for using the density estimation algorithm and judging whether the first neural electric pulse signal sample belongs to a neural electric pulse in the subsequent steps; thirdly The present application determines whether the first probability density parameter is less than zero. If so, the first neural electric pulse signal sample is used as the second neural electric pulse signal sample to avoid the first probability density parameter that does not meet the conditions from entering the next step; in addition, the present application uses the kernel density estimation method to calculate the second neural electric pulse signal sample to obtain the second probability density function, which can quickly and efficiently perform neural electric pulse detection; in addition, the present application calculates the information divergence between the first probability density function and the second probability density function, and determines whether the first neural electric pulse signal sample belongs to a neural electric pulse according to the information divergence, and outputs the judgment result, which has good specificity, does not lose a lot of waveform information, and avoids the complex process of template matching.

[0050] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0052] FIG1 is a flow chart of a preferred embodiment of the neural electrical pulse detection method of the present application;

[0053] FIG2 is a diagram of the original neural electrophysiological signal in the neural electrical pulse detection method of the present application;

[0054] FIG3 is a sample diagram of the first neural electrical pulse signal in the neural electrical pulse detection method of the present application;

[0055] FIG4 is a first type of a large number of neural electrical pulse signal samples in the neural electrical pulse detection method of the present application;

[0056] FIG5 is a sample diagram of the second type of first neural electrical pulse signal in the neural electrical pulse detection method of the present application;

[0057] FIG6 is a statistical histogram of the first type of noise samples in the neural electrical pulse detection method of the present application;

[0058] FIG7 is a statistical histogram of the second type of noise samples in the neural electrical pulse detection method of the present application;

[0059] FIG8 is a statistical histogram of the third type of noise samples in the neural electrical pulse detection method of the present application;

[0060] FIG9 is a statistical histogram of the fourth type of noise samples in the neural electrical pulse detection method of the present application;

[0061] FIG10 is a histogram of a single neural electrical pulse signal in the neural electrical pulse detection method of the present application;

[0062] FIG11 is a sample theoretical SN probability density distribution diagram of the neural electrical pulse detection method of the present application;

[0063] FIG12 is a probability density distribution diagram after Gaussian kernel density estimation in the neural electrical pulse detection method of the present application;

[0064] FIG13 is a schematic diagram showing the principle of a preferred embodiment of the neural electrical pulse detection system of the present application;

[0065] FIG14 is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present application. DETAILED DESCRIPTION

[0066] To enable those skilled in the art to better understand the technical solutions of the present application, the neural electrical pulse detection method, system, terminal, and computer-readable storage medium provided by the present application are further described in detail below in conjunction with the accompanying drawings and specific embodiments. It will be understood that the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work are within the scope of protection of the present application.

[0067] The terms "first," "second," and the like in this application are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0068] The present application provides a neural electrical pulse detection method, system, terminal and computer-readable storage medium to solve the problems of neural electrical pulse detection methods in the prior art, such as low noise resistance, poor specificity, loss of a large amount of waveform information and complex template matching process.

[0069] Please refer to Figures 1 to 12, Figure 1 is a flow chart of a preferred embodiment of the neural electric pulse detection method of the present application; Figure 2 is a diagram of the original neural electrophysiological signal in the neural electric pulse detection method of the present application; Figure 3 is a diagram of a first neural electric pulse signal sample in the neural electric pulse detection method of the present application; Figure 4 is a diagram of a first type of a large number of neural electric pulse signal samples in the neural electric pulse detection method of the present application; Figure 5 is a diagram of a second type of first neural electric pulse signal sample in the neural electric pulse detection method of the present application; Figure 6 is a statistical histogram of the first type of noise sample in the neural electric pulse detection method of the present application; 7 is a statistical histogram of the second type of noise samples in the neural electric pulse detection method of the present application; Figure 8 is a statistical histogram of the third type of noise samples in the neural electric pulse detection method of the present application; Figure 9 is a statistical histogram of the fourth type of noise samples in the neural electric pulse detection method of the present application; Figure 10 is a histogram of a single neural electric pulse signal in the neural electric pulse detection method of the present application; Figure 11 is a sample theoretical SN probability density distribution diagram in the neural electric pulse detection method of the present application; Figure 12 is a probability density distribution diagram after Gaussian kernel density estimation in the neural electric pulse detection method of the present application.

[0070] The present application proposes a method for detecting neural electrical pulses, wherein, as shown in FIG1 , the method for detecting neural electrical pulses comprises the following steps:

[0071] Step S100: obtaining an original neural electrophysiological signal, filtering and threshold detection on the original neural electrophysiological signal, and obtaining a first neural electrical pulse signal sample.

[0072] Specifically, the original neural electrophysiological signal is obtained, filtered and threshold detected, and noise is reduced to obtain a first neural electrical pulse signal sample, thereby improving the anti-noise capability.

[0073] The step S100 of acquiring an original neural electrophysiological signal, filtering and threshold detecting the original neural electrophysiological signal to obtain a first neural electrical pulse signal sample specifically includes:

[0074] An original neural electrophysiological signal is obtained, and the original neural electrophysiological signal is filtered using a sixth-order Butterworth filter to obtain a first filtered electrical pulse signal.

[0075] The first cutoff frequency and the second cutoff frequency of the sixth-order Butterworth filter are 250 Hz and 7000 Hz respectively.

[0076] A threshold detection parameter is used to perform threshold detection on the first filtered electrical pulse signal to obtain the first neural electrical pulse signal sample.

[0077] Among them, the threshold detection parameters are set to the negative peak of the signal greater than 60 microvolts, and the peak-to-peak interval is set to greater than 2 milliseconds, and the peak moment is used as the base point, 1 millisecond forward and 1.5 milliseconds backward are regarded as the first neural electrical pulse signal sample.

[0078] Specifically, as shown in FIG2 , the collected signal is a raw neural electrophysiological signal. The raw neural electrophysiological signal is obtained. These signal sequences usually contain background noise and the neural electrical impulse signal of interest to the researchers. The raw neural electrophysiological signal is filtered using a forward and backward sixth-order Butterworth filter to obtain a first filtered electrical impulse signal. The first and second cutoff frequencies of the sixth-order Butterworth filter are 250 Hz and 7000 Hz, respectively. The first cutoff frequency is the upper cutoff frequency, and the second cutoff frequency is the lower cutoff frequency. The first filtered electrical impulse signal is threshold-detected using a threshold detection parameter to obtain a first neural electrical impulse signal sample.

[0079] Among them, the threshold detection parameters are set to the negative peak of the signal being greater than 60 microvolts, and the peak-to-peak interval being greater than 2 milliseconds, and taking the peak moment as the base point, taking 1 millisecond forward and 1.5 milliseconds backward is regarded as the first neural electrical pulse signal sample, and the threshold detection parameters are set to the negative peak of the signal being greater than 60 microvolts, and the peak-to-peak interval being greater than 2 milliseconds, as shown in Figure 3, and taking the peak moment as the base point, taking 1 millisecond forward and 1.5 milliseconds backward is regarded as the potential first neural electrical pulse signal sample.

[0080] Step S200: Make a skewed distribution assumption for the first neural electrical pulse signal sample, obtain a first probability density parameter, position parameter and scale parameter of the skewed distribution of the first neural electrical pulse signal sample based on the moment estimation of the skewed distribution, and obtain a first probability density function based on the first probability density parameter, the position parameter and the scale parameter.

[0081] Specifically, since the distribution curve of the first neural electrical pulse signal sample belongs to a left-right asymmetric data frequency distribution, it is more consistent with a skewed distribution. Therefore, a skewed distribution assumption is made for the first neural electrical pulse signal sample, and the first probability density parameter, position parameter and scale parameter of the skewed distribution of the first neural electrical pulse signal sample are obtained according to the moment estimation of the skewed distribution.

[0082] It should be noted that the assumption of the SN distribution of neural electrical impulses in this application is based on statistical inference of a large number of samples. As shown in Figures 4 and 5, which are statistical histograms of two types of neural electrical impulse signals, respectively, it can be seen that although the different types of neural electrical impulse signals vary in size, they all belong to the SN distribution, and their distribution parameter α is less than 0.

[0083] As shown in Figures 6, 7, 8 and 9, the statistical histograms of noise samples of different categories show that the statistical histograms of noise samples of different categories have different performances and are not SN distributions with α < 0.

[0084] The step S200 includes making a skewed distribution assumption for the first neural electrical pulse signal sample, obtaining a first probability density parameter, a location parameter, and a scale parameter of the skewed distribution of the first neural electrical pulse signal sample based on moment estimation of the skewed distribution, and obtaining a first probability density function based on the first probability density parameter, the location parameter, and the scale parameter. Specifically, the step S200 includes:

[0085] The skew distribution assumption is made for the first neural electrical pulse signal sample: Y~SN(ξ,ω 2 ,α);

[0086] Wherein, Y represents the first neural electrical pulse signal sample, and SN represents the skewed distribution; Y=ξ+ωX;

[0087] Among them, ξ∈R is the location parameter, ω∈R + is the scale parameter, α is the first probability density parameter, α<0 is a tilted variable, and X is a sample that obeys the standard skewed distribution;

[0088] Obtaining a first probability density parameter, a location parameter, and a scale parameter of the skewed distribution of the first neural electrical pulse signal sample according to the moment estimation of the skewed distribution, and obtaining a first probability density function according to the first probability density parameter, the location parameter, and the scale parameter;

[0089] The mathematical formula of the first probability density function is:

[0090] in, represents the standard Gaussian density function, Φ(α·x) is Cumulative probability distribution function, where x is a random variable.

[0091] Specifically, the Skew-Normal distribution (SN distribution) assumption is made for the first neural electrical impulse signal sample, and the formula can be obtained: Y~SN(ξ,ω 2 ,α),

[0092] Wherein, Y represents the first neural electrical pulse signal sample, and SN represents the skewed distribution.

[0093] Further, we have the formula: Y=ξ+ωX;

[0094] Among them, ξ∈R is the location parameter, ω∈R + is the scale parameter, α is the first probability density parameter, α<0 is a tilted variable, and X is a sample that obeys the standard skewed distribution;

[0095] Obtaining a first probability density parameter of the skewed distribution of the first neural electrical pulse signal sample according to the moment estimation of the skewed distribution;

[0096] Among them, the mathematical formula of probability density function is: in, represents the standard Gaussian density function, Φ(α·x) is Cumulative probability distribution function, where x is a random variable.

[0097] Under the above premise, the SN distribution probability density parameter of the first neural electrical impulse signal sample Y is obtained according to the moment estimation of the skewed probability density distribution, thereby obtaining the theoretical probability density function of the first neural electrical impulse signal sample Y, namely SN-pdf.

[0098] Figures 10, 11, and 12 show the estimated results for a single neural pulse sample. The Gaussian kernel density estimation method also meets expectations. Figure 10 shows a histogram of a single neural pulse signal, Figure 11 shows the theoretical SN probability density distribution for this sample, and Figure 12 shows the probability density distribution after Gaussian kernel density estimation. These experimental results demonstrate that probability density estimation can be a fast and efficient method for neural pulse detection.

[0099] Step S300: Determine whether the first probability density parameter is less than zero. If so, use the first neural electrical pulse signal sample as the second neural electrical pulse signal sample.

[0100] Specifically, it is determined whether the first probability density parameter of the theoretical SN distribution is less than zero, that is, whether the condition α<0 is satisfied. If so, the second neural electrical pulse signal sample is obtained; if not, the first neural electrical pulse signal sample is rejected.

[0101] Step S400: Calculate the second neural electrical pulse signal sample using a kernel density estimation method to obtain a second probability density function.

[0102] Specifically, the second neural electrical pulse signal sample is calculated using a kernel density estimation method to obtain a second probability density function, which can quickly and efficiently perform neural electrical pulse detection.

[0103] The step S400 of calculating the second neural electrical pulse signal sample using a kernel density estimation method to obtain a second probability density function specifically includes:

[0104] Calculating the second neural electrical pulse signal sample using a Gaussian kernel density estimation method to obtain a second probability density function;

[0105] The calculation formula of the kernel density estimation method is:

[0106] Among them, the kernel function K is the Gaussian kernel x i is the sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is

[0107] Specifically, the idea of ​​kernel density estimation is used to estimate the true probability density distribution (KDE-pdf) of the second neural electrical impulse signal sample. The Gaussian kernel density estimation method is used for calculation. The calculation formula of the Gaussian kernel density estimation method is: Among them, the kernel function is Gaussian kernel x iis the sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is The second probability density function is obtained. The Gaussian kernel density estimation can handle data distribution of arbitrary shapes and has strong flexibility and adaptability.

[0108] Optionally, the choice of bandwidth has an important impact on the accuracy of the estimation results, and the kernel density estimation results can be made more accurate by changing the bandwidth calculation method.

[0109] Alternatively, the step S400: using a kernel density estimation method to calculate the second neural electrical pulse signal sample to obtain a second probability density function specifically includes:

[0110] Calculating the second neural electrical pulse signal sample using a linear kernel density estimation method to obtain a second probability density function;

[0111] The calculation formula of the kernel density estimation method is:

[0112] Among them, the kernel function K is a linear kernel x i is the sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is

[0113] Specifically, the second neural electrical pulse signal sample is calculated using a linear kernel density estimation method to obtain a second probability density function. The linear kernel density estimation method has a relatively simple operation process and a fast operation speed.

[0114] Alternatively, the step S400: using a kernel density estimation method to calculate the second neural electrical pulse signal sample to obtain a second probability density function specifically includes:

[0115] Calculating the second neural electrical pulse signal sample using a cosine kernel density estimation method to obtain a second probability density function;

[0116] The calculation formula of the kernel density estimation method is:

[0117] Among them, the kernel function K is the cosine kernel Among them, π is the ratio of circumference to diameter, x is the ratio of circumference to diameter, i is the sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is

[0118] Specifically, the second neural electrical pulse signal sample is calculated using a triangular kernel density estimation method to obtain a second probability density function.

[0119] Optionally, the kernel density estimation method may also use a polynomial kernel, a Laplace kernel, a sigmoid kernel, a triangular kernel, or an exponential kernel, which may be selected as needed and will not be described in detail here.

[0120] Step S500: Calculate the information divergence between the first probability density function and the second probability density function, determine whether the first neural electrical pulse signal sample belongs to a neural electrical pulse according to the information divergence, and output the determination result.

[0121] Specifically, by calculating the information divergence between the first probability density parameter and the second probability density function, it is determined whether the first neural electrical pulse signal sample belongs to a neural electrical pulse. This method has good specificity, does not lose a large amount of waveform information, and avoids the complex process of template matching.

[0122] The step S500 of calculating the information divergence between the first probability density function and the second probability density function, determining whether the first neural electrical pulse signal sample belongs to a neural electrical pulse according to the information divergence, and outputting the determination result specifically includes:

[0123] respectively calculating the probability density of the first probability density function and the second probability density function between the first neural electrical impulse signal sample value and the second neural electrical impulse signal sample value;

[0124] Calculating the information divergence between the first probability density function and the second probability density function according to the probability density between the first neural electrical pulse signal sample value and the second neural electrical pulse signal sample value;

[0125] The calculation formula of the information divergence is:

[0126] Where SN(i) represents the first probability density function, KDE(i) represents the second probability density function, and KL(SN,KDE) represents the information divergence.

[0127] Determining whether the first neural electrical pulse signal sample is a neural electrical pulse, and outputting a determination result;

[0128] If the information divergence is less than or equal to the preset threshold, the judgment result is that the first neural electrical pulse signal sample belongs to a neural electrical pulse.

[0129] Specifically, the probability density of the first probability density parameter (SN-pdf) and the second probability density function (KDE-pdf) between the first neural electrical impulse signal sample value and the second neural electrical impulse signal sample value, that is, the probability density between the maximum value of Y max(Y) and the minimum value of Y min(Y), is calculated respectively, and the information divergence between the first probability density parameter and the second probability density function is calculated. The calculation formula of the information divergence is:

[0130] Where SN(i) represents the first probability density parameter, KDE(i) represents the second probability density parameter, and KL(SN, KDE) represents the information divergence, which indicates the inconsistency or similarity of the two distributions. The more similar the two distributions are, the closer KL is to 0, and vice versa.

[0131] Optionally, calculating the KL divergence between two distributions is essentially a method for calculating entropy, and can also be changed to other entropy measures.

[0132] Finally, determine whether the first neural electrical pulse signal sample belongs to a neural electrical pulse, and compare the calculated information divergence KL with the preset threshold Th. If the information divergence KL is greater than the preset threshold Th, the first neural electrical pulse signal sample is rejected. If the information divergence is less than or equal to the preset threshold, the first neural electrical pulse signal sample is accepted. The judgment result is that the first neural electrical pulse signal sample belongs to a neural electrical pulse.

[0133] Compared with the feature extraction solution, this application can reduce the dependence on the researcher's engineering experience. The feature extraction process requires researchers to select appropriate features based on their own engineering practice experience, such as statistical features (mean, variance and quantile, etc.), spectral features (energy and spectral density, etc.), entropy features (sample entropy, differential entropy and fuzzy entropy, etc.) and other nonlinear features (fractal dimension and Lyapunov index, etc.). How to select or combine the above features for the detection of neural electrical pulse signals is usually decided by the engineering developer, and such a decision-making process often depends on the developer's familiarity with the feature extraction technology and the characteristics of the neural electrical pulses. The neural electrical pulse detector finally obtained by this scheme usually does not have strong robustness.

[0134] Compared with the template matching solution, this application does not need to prepare a suitable template in advance, nor does it need to extract the template during the detection process (online template extraction). Template matching requires preparing enough templates in advance to minimize the missed detection rate. If it is assumed that the neural electrical impulse signals emitted by each neuron are different, then the brain has a total of about 80 billion neurons, which is a number that cannot be prepared in advance. The method of online template extraction requires continuous learning so that the template is updated to a more stable state. This process will cause the time cost to rise rapidly.

[0135] Compared with the solution of automatically extracting features using a neural network model, this application does not require a large number of samples to be prepared in advance. There are two common solutions for extracting features using neural networks, one is a supervised autoencoder and the other is an unsupervised autoencoder-decoder. The former requires a large number of manually labeled samples so that the neural network can learn a coding model that automatically extracts neural electrical pulse features. The latter, in the process of learning a large amount of data, learns a model that maximizes the difference between samples of different classes and minimizes the difference in features of samples of the same class. This model can be used for sorting neural electrical pulses, but is rarely used as a tool for detecting neural electrical pulses.

[0136] Please refer to Figures 13 and 14. Figure 13 is a schematic diagram of the principle of a preferred embodiment of the neural electrical pulse detection system of the present application; Figure 14 is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present application.

[0137] In some embodiments, as shown in FIG13 , based on the above-mentioned neural electrical pulse detection method, the present application further proposes a neural electrical pulse detection system, the neural electrical pulse detection system comprising:

[0138] The signal preprocessing module 51 is used to obtain the original neural electrophysiological signal, filter and threshold the original neural electrophysiological signal, and obtain a first neural electrical pulse signal sample;

[0139] a signal moment estimation module 52, configured to make a skewed distribution assumption for the first neural electrical pulse signal sample, obtain a first probability density parameter, a location parameter, and a scale parameter of the skewed distribution of the first neural electrical pulse signal sample based on the moment estimation of the skewed distribution, and obtain a first probability density function based on the first probability density parameter, the location parameter, and the scale parameter;

[0140] a parameter determination module 53, configured to determine whether the first probability density parameter is less than zero, and if so, use the first neural electrical pulse signal sample as a second neural electrical pulse signal sample;

[0141] a signal density estimation module 54, configured to calculate the second neural electrical pulse signal sample using a kernel density estimation method to obtain a second probability density function;

[0142] The signal judgment module 55 is used to calculate the information divergence between the first probability density function and the second probability density function, judge whether the first neural electrical pulse signal sample belongs to a neural electrical pulse according to the information divergence, and output the judgment result.

[0143] In some embodiments, as shown in FIG14 , based on the above-mentioned neural electrical pulse detection method and system, the present application also proposes a terminal, which includes: a memory 20, a processor 10, and a display 30. FIG14 only shows some components of the terminal, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0144] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal. Furthermore, the memory 20 may include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software installed in the terminal and various types of data, such as program code of the terminal. The memory 20 may also be used to temporarily store data that has been output or is about to be output.

[0145] In one embodiment, a neural electrical pulse detection program 40 is stored in the memory 20 , and the neural electrical pulse detection program 40 can be executed by the processor 10 , thereby implementing the neural electrical pulse detection method of the present application.

[0146] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, configured to execute program codes or process data stored in the memory 20, such as executing the neural electrical pulse detection method.

[0147] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.

[0148] The present application also proposes a computer-readable storage medium, which stores a neural electrical pulse detection program. When the neural electrical pulse detection program is executed by a processor, the steps of the neural electrical pulse detection method described above are implemented.

[0149] In summary, the present application obtains original neural electrophysiological signals from animal or human brains, performs filtering and threshold detection on the original neural electrophysiological signals, thereby reducing the noise of the original neural electrophysiological signals and obtaining a first neural electrical pulse signal sample, thereby improving the anti-noise ability; secondly, the present application makes a skewed distribution assumption on the first neural electrical pulse signal sample, and obtains the first probability density parameter, position parameter and scale parameter of the skewed distribution of the first neural electrical pulse signal sample according to the moment estimation of the skewed distribution, so as to facilitate the use of density estimation algorithm and judgment of whether the first neural electrical pulse signal sample belongs to a neural electrical pulse in subsequent steps; thirdly, the present application compares the first probability density parameter The number satisfies α<0. If so, a second neural electrical pulse signal sample is obtained. After the initial judgment, a qualified second neural electrical pulse signal sample is obtained, avoiding the first probability density parameter that does not meet the conditions from entering the next step; in addition, the present application uses the kernel density estimation method to calculate the second neural electrical pulse signal sample to obtain a second probability density function, which can quickly and efficiently perform neural electrical pulse detection; in addition, the present application determines whether the first neural electrical pulse signal sample belongs to a neural electrical pulse by calculating the information divergence between the first probability density parameter and the second probability density function. It has good specificity, will not lose a lot of waveform information, and avoids the complex process of template matching.

[0150] It should be noted that the various optional implementation methods introduced in the embodiments of the present application can be implemented in combination with each other or can be implemented separately, and the embodiments of the present application do not limit this.

[0151] In the description of this application, it should be understood that the terms "upper", "lower", "left", "right", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, and a specific orientation structure and operation. Therefore, it cannot be understood as a limitation on this application. In addition, "first" and "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "multiple" means two or more.

[0152] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0153] The above embodiments are described with reference to the accompanying drawings. Other different forms and embodiments are also possible without departing from the principles of the present application, and therefore the present application should not be construed as limiting the embodiments presented herein. Rather, these embodiments are provided so that the present application will be perfect and complete, and will convey the scope of the present application to those skilled in the art. In the accompanying drawings, component sizes and relative sizes may be exaggerated for clarity. The terms used herein are for the purpose of describing specific embodiments only and are not intended to be limiting. The terms "comprising" and / or "including" when used in this specification indicate the presence of the features, integers, components and / or components, but do not exclude the presence or increase of one or more other feature integers, components, components and / or their groups. Unless otherwise indicated, when stated, a numerical range includes the upper and lower limits of the range and any sub-ranges therebetween.

[0154] The above descriptions are only some embodiments of the present application and do not limit the scope of protection of the present application. Any equivalent device or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the scope of patent protection of this application.

Claims

1. A method for detecting nerve electrical pulses, characterized in that, it includes: Obtain the original nerve electrophysiological signal, perform pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electrical pulse signal sample; Make a skewed distribution assumption for the first nerve electrical pulse signal sample, obtain the first probability density parameter, position parameter, and scale parameter of the skewed distribution of the first nerve electrical pulse signal sample according to the moment estimation of the skewed distribution, and obtain the first probability density function according to the first probability density parameter, the position parameter, and the scale parameter; Judge whether the first probability density parameter is less than zero. If so, use the first nerve electrical pulse signal sample as the second nerve electrical pulse signal sample; Use the kernel density estimation method to calculate the second nerve electrical pulse signal sample to obtain the second probability density function; Calculate the information divergence between the first probability density function and the second probability density function, and judge whether the first nerve electrical pulse signal sample belongs to a nerve electrical pulse according to the information divergence, and output the judgment result.

2. The method for detecting nerve electrical pulses according to claim 1, characterized in that, The step of obtaining the original nerve electrophysiological signal, performing pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electrical pulse signal sample specifically includes: Obtain the original nerve electrophysiological signal, perform pass filtering on the original nerve electrophysiological signal using a sixth-order Butterworth filter to obtain a first filtered electrical pulse signal; Use the threshold detection parameter to perform threshold detection on the first filtered electrical pulse signal to obtain the first nerve electrical pulse signal sample.

3. The method for detecting nerve electrical pulses according to claim 1, characterized in that, The step of making a skewed distribution assumption for the first nerve electrical pulse signal sample, obtaining the first probability density parameter, position parameter, and scale parameter of the skewed distribution of the first nerve electrical pulse signal sample according to the moment estimation of the skewed distribution, and obtaining the first probability density function according to the first probability density parameter, the position parameter, and the scale parameter specifically includes: Make a skewed distribution assumption for the first nerve electrical pulse signal sample: Y~SN(ξ,ω 2 ,α); Where Y represents the first nerve electrical pulse signal sample, and SN represents the skewed distribution; Y = ξ + ωX; where ξ ∈ R is the location parameter, ω ∈ R + is the scale parameter, α is the first probability density parameter, α < 0 is the skewness variable, and X is a sample following the standard skewed distribution; Obtain the first probability density parameter, position parameter, and scale parameter of the skewed distribution of the first nerve electrical pulse signal sample according to the moment estimation of the skewed distribution, and obtain the first probability density function according to the first probability density parameter, the position parameter, and the scale parameter; The mathematical formula of the first probability density function is as follows: Among them, Denote the standard Gaussian density function, and Φ(α·x) is Cumulative probability distribution function, where x is a random variable.

4. The method for detecting nerve electrical pulses according to claim 3, characterized in that, The step of using the kernel density estimation method to calculate the second nerve electrical pulse signal sample to obtain the second probability density function specifically includes: Use the Gaussian kernel density estimation method to calculate the second nerve electrical pulse signal sample to obtain the second probability density function; The calculation formula of the kernel density estimation method is as follows: Among them, the kernel function K is a Gaussian kernel x i is a sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is 5. The method for detecting nerve electrical pulses according to claim 3, characterized in that, Calculating the second probability density function by using the kernel density estimation method for the second neural electrical pulse signal sample, specifically including: Calculating the second probability density function by using the linear kernel density estimation method for the second neural electrical pulse signal sample; The calculation formula of the kernel density estimation method is as follows: Among them, the kernel function K is a linear kernel x < h, x i is a sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is 6. The neural electrical pulse detection method according to claim 3, characterized in that Calculating the second probability density function by using the kernel density estimation method for the second neural electrical pulse signal sample, specifically including: Calculating the second probability density function by using the cosine kernel density estimation method for the second neural electrical pulse signal sample; The calculation formula of the kernel density estimation method is as follows: Among them, the kernel function K is a cosine kernel x < h, where π is the circumference ratio, x i is a sample point, n is the number of sample points, h is the bandwidth, and the bandwidth is 7. The neural electrical pulse detection method according to claim 1, characterized in that Calculating the information divergence between the first probability density function and the second probability density function, and judging whether the first neural electrical pulse signal sample belongs to a neural electrical pulse according to the information divergence, and outputting a judgment result, specifically including: Calculating the probability densities of the first probability density function and the second probability density function between the first neural electrical pulse signal sample value and the second neural electrical pulse signal sample value respectively; Calculating the information divergence between the first probability density function and the second probability density function according to the probability densities between the first neural electrical pulse signal sample value and the second neural electrical pulse signal sample value; The calculation formula of the said information divergence is as follows: wherein, SN(i) represents the first probability density function, KDE(i) represents the second probability density function, and KL(SN, KDE) represents the information divergence; Judging whether the first neural electrical pulse signal sample belongs to a neural electrical pulse, and outputting a judgment result; If the information divergence is less than or equal to a preset threshold, the judgment result is that the first neural electrical pulse signal sample belongs to a neural electrical pulse.

8. A neural electrical pulse detection system, characterized in that The neural electrical pulse detection system includes: A signal preprocessing module, configured to obtain an original neurophysiological signal, perform filtering and threshold detection on the original neurophysiological signal, and obtain a first neural electrical pulse signal sample; A signal moment estimation module, configured to make a skewed distribution assumption for the first neural electrical pulse signal sample, obtain a first probability density parameter, a position parameter, and a scale parameter of the skewed distribution of the first neural electrical pulse signal sample according to the moment estimation of the skewed distribution, and obtain a first probability density function according to the first probability density parameter, the position parameter, and the scale parameter; A parameter judgment module, configured to judge whether the first probability density parameter is less than zero, and if so, use the first neural electrical pulse signal sample as a second neural electrical pulse signal sample; A signal density estimation module, configured to calculate a second probability density function by using the kernel density estimation method for the second neural electrical pulse signal sample; A signal judgment module, configured to calculate the information divergence between the first probability density function and the second probability density function, judge whether the first neural electrical pulse signal sample belongs to a neural electrical pulse according to the information divergence, and output a judgment result.

9. A terminal, characterized in that The terminal includes: a memory, a processor, and a nerve electrical pulse detection program stored on the memory and executable on the processor. When the nerve electrical pulse detection program is executed by the processor, the steps of the nerve electrical pulse detection method according to any one of claims 1-7 are implemented.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a nerve electrical pulse detection program, and when the nerve electrical pulse detection program is executed by a processor, the steps of the nerve electrical pulse detection method according to any one of claims 1-7 are implemented.

Images