CN117357134B - Nerve electric pulse detection method, system and terminal - Google Patents
Nerve electric pulse detection method, system and terminal Download PDFInfo
- Publication number
- CN117357134B CN117357134B CN202311675784.3A CN202311675784A CN117357134B CN 117357134 B CN117357134 B CN 117357134B CN 202311675784 A CN202311675784 A CN 202311675784A CN 117357134 B CN117357134 B CN 117357134B
- Authority
- CN
- China
- Prior art keywords
- electric pulse
- nerve
- pulse signal
- probability density
- signal sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000005036 nerve Anatomy 0.000 title claims abstract description 286
- 238000001514 detection method Methods 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 89
- 238000009826 distribution Methods 0.000 claims abstract description 84
- 238000001914 filtration Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims description 99
- 238000004364 calculation method Methods 0.000 claims description 19
- 230000000008 neuroelectric effect Effects 0.000 claims description 12
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 238000005315 distribution function Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 description 21
- 230000008569 process Effects 0.000 description 16
- 238000000605 extraction Methods 0.000 description 6
- 210000004556 brain Anatomy 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/372—Analysis of electroencephalograms
- A61B5/374—Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/388—Nerve conduction study, e.g. detecting action potential of peripheral nerves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The application discloses a nerve electric pulse detection method, a nerve electric pulse detection system and a nerve electric pulse detection terminal, wherein the nerve electric pulse detection method comprises the following steps: band-pass filtering and threshold detection are carried out on the original nerve electrophysiological signals to obtain a first nerve electric pulse signal sample; making a bias distribution assumption, estimating according to the moment of the bias distribution to obtain a first probability density parameter, a position parameter and a scale parameter of the bias distribution of the first nerve electric pulse signal sample, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter; judging whether the first probability density parameter is smaller than zero, if so, taking the first nerve electric pulse signal sample as a second nerve electric pulse signal sample; calculating a second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function; and (3) calculating the information divergence between the two, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulses, and outputting a judging result, thereby having the advantages of high speed, high efficiency, high noise resistance and no need of template matching.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence, and in particular, to a neural electric pulse detection method, system, terminal, and computer readable storage medium.
Background
The research of nerve electric activity is an important way for human to know and recognize the brain, is an important grip for developing a front brain-computer interface, and has important value and significance for human life health and national economic development. The nerve electric pulse detection is a core topic in the fields of neuroscience and biomedical engineering, and relates to accurately and efficiently identifying the discharging activity of neurons from complex brain electrical signals. Advances in technology, and in particular the development of high flux electrode arrays, present new challenges to the task of overcoming the challenge of rapidly and accurately detecting sparse nerve electrical pulses in hundreds of electrode channels.
In the prior art, some researches are based on priori knowledge of nerve electric pulse obtained by researchers, and a threshold is set manually for detection, and the method has low noise resistance or poor specificity; some researches are based on feature detection, namely, on the basis of threshold detection, measures including but not limited to time domain, frequency domain, entropy, nonlinear dynamics and the like are extracted as features for detecting and judging the power pulse signals, and the method has the defects that the feature extraction belongs to a dimension reduction method, and a large amount of waveform information is inevitably lost in the process; some researches are based on template matching, wherein the template matching is to realize nerve electric pulse detection by calculating the similarity between undetermined waveforms and template waveforms, and the source and the number of templates in the process are important factors influencing the detection efficiency and the accuracy, and are relatively troublesome and difficult to control; therefore, how to find a rapid and efficient nerve electric pulse detection method is a problem to be solved at present.
Disclosure of Invention
In view of this, the present application provides a neural electric pulse detection method, system, terminal and computer readable storage medium, so as to solve the problems of low noise immunity, poor specificity, loss of a large amount of waveform information, and complex template matching process in the neural electric pulse detection method in the prior art.
The application provides a nerve electric pulse detection method, which comprises the following steps:
acquiring an original nerve electrophysiological signal, and performing band-pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electric pulse signal sample;
performing bias distribution assumption on the first nerve electric pulse signal sample, estimating according to the moment of bias distribution to obtain a first probability density parameter, a position parameter and a scale parameter of bias distribution of the first nerve electric pulse signal sample, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter;
judging whether the first probability density parameter is smaller than zero, if so, taking the first nerve electric pulse signal sample as a second nerve electric pulse signal sample;
calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function;
And calculating information divergence between the first probability density function and the second probability density function, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulse according to the information divergence, and outputting a judging result.
Optionally, the acquiring an original nerve electrophysiological signal, performing band-pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electrical pulse signal sample, which specifically includes:
acquiring an original nerve electrophysiological signal, and performing band-pass filtering on the original nerve electrophysiological signal by using a sixth-order Butterworth filter to obtain a first filtering electric pulse signal;
and performing threshold detection on the first filtering electric pulse signal by using a threshold detection parameter to obtain the first nerve electric pulse signal sample.
Optionally, the performing a bias distribution assumption on the first nerve electric pulse signal sample, estimating according to a moment of the bias distribution to obtain a first probability density parameter, a position parameter and a scale parameter of the bias distribution of the first nerve electric pulse signal sample, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter, including:
Making a bias distribution assumption on the first neuroelectric pulse signal sample:
；
wherein Y represents the first nerve electric pulse signal sample, and SN represents the bias distribution;
；
wherein,for the position parameter +.>Is a scale parameter->As a first probability density parameter, a second probability density parameter,x is a sample obeying standard deviation distribution for the inclination variable;
obtaining first probability density parameters, position parameters and scale parameters of the bias distribution of the first nerve electric pulse signal sample according to the moment estimation of the bias distribution, and obtaining a first probability density function according to the first probability density parameters, the position parameters and the scale parameters;
the mathematical formula of the first probability density function is:；
wherein,representing a standard gaussian density function, +.>Is->The cumulative probability distribution function, x is a random variable.
Optionally, the calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function specifically includes:
calculating the second nerve electric pulse signal sample by using a Gaussian kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionIs Gaussian kernel- >，/>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->。
Optionally, the calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function specifically includes:
calculating the second nerve electric pulse signal sample by using a linear kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionIs a linear nucleus->，/>，/>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->。
Optionally, the calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function specifically includes:
calculating the second nerve electric pulse signal sample by using a cosine kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionFor cosine kernel->，/>Wherein->Is of circumference rate>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->。
Optionally, the calculating the information divergence between the first probability density function and the second probability density function, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulse according to the information divergence, and outputting a judging result specifically includes:
Calculating probability densities of the first probability density function and the second probability density function between the first nerve electrical pulse signal sample value and a second nerve electrical pulse signal sample value, respectively;
calculating an information divergence between the first probability density function and the second probability density function according to the probability density between the first nerve electric pulse signal sample value and the second nerve electric pulse signal sample value;
the calculation formula of the information divergence is as follows:；
wherein,representing a first probability density function, +.>A second probability density function is represented and,representing information divergence;
judging whether the first nerve electric pulse signal sample belongs to nerve electric pulses or not, and outputting a judging result;
if the information divergence is smaller than or equal to a preset threshold value, the judgment result is that the first nerve electric pulse signal sample belongs to nerve electric pulses.
The application also proposes a nerve electric pulse detection system, the nerve electric pulse detection system includes:
the signal preprocessing module is used for acquiring an original nerve electrophysiological signal, and carrying out band-pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electric pulse signal sample;
The signal moment estimation module is used for making a bias distribution assumption on the first nerve electric pulse signal sample, obtaining a first probability density parameter, a position parameter and a scale parameter of the bias distribution of the first nerve electric pulse signal sample according to the moment estimation of the bias distribution, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter;
the parameter judging module is used for judging whether the first probability density parameter is smaller than zero, and if yes, the first nerve electric pulse signal sample is used as a second nerve electric pulse signal sample;
the signal density estimation module is used for calculating the second nerve electric pulse signal sample by using a nuclear density estimation method to obtain a second probability density function;
the signal judging module is used for calculating the information divergence between the first probability density function and the second probability density function, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulse or not according to the information divergence, and outputting a judging result.
The application also proposes a terminal, the terminal includes: the nerve electric pulse detection device comprises a memory, a processor and a nerve electric pulse detection program stored in the memory and capable of running on the processor, wherein the nerve electric pulse detection program realizes the steps of the nerve electric pulse detection method when being executed by the processor.
The present application also proposes a computer readable storage medium storing a nerve electric pulse detection program which, when executed by a processor, implements the steps of the nerve electric pulse detection method as described.
The beneficial effects of this application are: compared with the prior art, the method and the device have the advantages that the original nerve electrophysiological signals are obtained, the band-pass filtering and the threshold detection are carried out on the original nerve electrophysiological signals, so that the noise of the original nerve electrophysiological signals is reduced, a first nerve electric pulse signal sample is obtained, and the noise resistance is improved; secondly, by making an off-state distribution assumption on the first nerve electric pulse signal sample, obtaining a first probability density parameter, a position parameter and a scale parameter of the off-state distribution of the first nerve electric pulse signal sample according to moment estimation of the off-state distribution, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter, so that a density estimation algorithm is conveniently used in the subsequent step and whether the first nerve electric pulse signal sample belongs to nerve electric pulses is judged; thirdly, judging whether the first probability density parameter is smaller than zero, if so, taking the first nerve electric pulse signal sample as a second nerve electric pulse signal sample, and avoiding the first probability density parameter which does not meet the condition from entering the next step; in addition, the method calculates the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function, so that nerve electric pulse detection can be performed quickly and efficiently; in addition, the information divergence between the first probability density function and the second probability density function is calculated, whether the first nerve electric pulse signal sample belongs to nerve electric pulses is judged according to the information divergence, a judgment result is output, the specificity is good, a large amount of waveform information is not lost, and the complex process of template matching is avoided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a preferred embodiment of the nerve electrical pulse detection method of the present application;
FIG. 2 is a diagram of raw neuro-electrophysiologic signals in the neuro-electrical pulse detection method of the present application;
FIG. 3 is a graph of a first neuroelectric pulse signal sample in the neuroelectric pulse detection method of the present application;
FIG. 4 is a sample of a first type of a plurality of nerve electrical pulse signals in the nerve electrical pulse detection method of the present application;
FIG. 5 is a graph of a second class of first nerve electrical pulse signal samples in the nerve electrical pulse detection method of the present application;
FIG. 6 is a statistical histogram of a first type of noise samples in the neural electrical pulse detection method of the present application;
FIG. 7 is a statistical histogram of a second type of noise samples in the neural electrical pulse detection method of the present application;
FIG. 8 is a statistical histogram of a third type of noise samples in the neural electrical pulse detection method of the present application;
FIG. 9 is a statistical histogram of a fourth type of noise samples in the neural electrical pulse detection method of the present application;
FIG. 10 is a histogram of a single nerve electrical pulse signal in the nerve electrical pulse detection method of the present application;
FIG. 11 is a graph of sample theoretical SN probability density distribution in the neural electrical pulse detection method of the present application;
FIG. 12 is a probability density distribution graph after Gaussian kernel density estimation in the neural electrical pulse detection method of the present application;
FIG. 13 is a schematic diagram of a preferred embodiment of the nerve electrical pulse detection system of the present application;
FIG. 14 is a schematic view of an operating environment of a preferred embodiment of the terminal of the present application.
Detailed Description
In order to better understand the technical solutions of the present application, the following describes in further detail the neural electric pulse detection method, system, terminal and computer readable storage medium provided in the present application with reference to the accompanying drawings and detailed description. It is to be understood that the described embodiments are merely some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The terms "first," "second," and the like in this application are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The application provides a nerve electric pulse detection method, a nerve electric pulse detection system, a nerve electric pulse detection terminal and a nerve electric pulse detection computer readable storage medium, and aims to solve the problems that in the prior art, the nerve electric pulse detection method is low in noise resistance, poor in specificity, capable of losing a large amount of waveform information and complex in template matching process.
Referring to fig. 1 to 12, fig. 1 is a flowchart of a preferred embodiment of a neural electric pulse detection method of the present application; FIG. 2 is a diagram of raw neuro-electrophysiologic signals in the neuro-electrical pulse detection method of the present application; FIG. 3 is a graph of a first neuroelectric pulse signal sample in the neuroelectric pulse detection method of the present application; FIG. 4 is a sample of a first type of a plurality of nerve electrical pulse signals in the nerve electrical pulse detection method of the present application; FIG. 5 is a graph of a second class of first nerve electrical pulse signal samples in the nerve electrical pulse detection method of the present application; FIG. 6 is a statistical histogram of a first type of noise samples in the neural electrical pulse detection method of the present application; FIG. 7 is a statistical histogram of a second type of noise samples in the neural electrical pulse detection method of the present application; FIG. 8 is a statistical histogram of a third type of noise samples in the neural electrical pulse detection method of the present application; FIG. 9 is a statistical histogram of a fourth type of noise samples in the neural electrical pulse detection method of the present application; FIG. 10 is a histogram of a single nerve electrical pulse signal in the nerve electrical pulse detection method of the present application; FIG. 11 is a graph of sample theoretical SN probability density distribution in the neural electrical pulse detection method of the present application; fig. 12 is a probability density distribution diagram after gaussian kernel density estimation in the nerve electric pulse detection method of the present application.
The application provides a nerve electric pulse detection method, wherein as shown in fig. 1, the nerve electric pulse detection method comprises the following steps:
step S100: and acquiring an original nerve electrophysiological signal, and carrying out band-pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electric pulse signal sample.
Specifically, an original nerve electrophysiological signal is obtained, the original nerve electrophysiological signal is subjected to band-pass filtering and threshold detection, the original nerve electrophysiological signal is subjected to noise reduction, a first nerve electrical pulse signal sample is obtained, and noise resistance is improved.
The step S100: the method comprises the steps of obtaining an original nerve electrophysiological signal, carrying out band-pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electrical pulse signal sample, and specifically comprising the following steps:
and obtaining an original nerve electrophysiological signal, and carrying out band-pass filtering on the original nerve electrophysiological signal by using a sixth-order Butterworth filter to obtain a first filtering electric pulse signal.
Wherein the first cut-off frequency and the second cut-off frequency of the sixth-order butterworth filter are 250 hz and 7000 hz, respectively.
And performing threshold detection on the first filtering electric pulse signal by using a threshold detection parameter to obtain the first nerve electric pulse signal sample.
The threshold detection parameter is set to be that the negative peak value of the signal is larger than 60 micro volts, the peak-to-peak distance is set to be larger than 2 milliseconds, the peak time is taken forward for 1 millisecond, and the backward for 1.5 milliseconds is taken as the first nerve electric pulse signal sample.
Specifically, as shown in fig. 2, the acquired signals are original nerve electrophysiological signals, the original nerve electrophysiological signals are acquired, background noise and nerve electrical pulse signals focused by researchers are generally contained in the signal sequences, and the original nerve electrophysiological signals are subjected to band-pass filtering by using front-back sixth-order butterworth filters to obtain first filtered electrical pulse signals, wherein the first cutoff frequency and the second cutoff frequency of the sixth-order butterworth filters are respectively 250 hz and 7000 hz, the first cutoff frequency is the upper limit cutoff frequency, and the second cutoff frequency is the lower limit cutoff frequency. And performing threshold detection on the first filtered electrical pulse signal by using the threshold detection parameter to obtain a first nerve electrical pulse signal sample.
The threshold detection parameter is set to be that the negative peak value of the signal is greater than 60 micro volts, the peak-peak interval is set to be greater than 2 milliseconds, the peak time is taken as a base point, 1 millisecond is taken forwards, 1.5 milliseconds are taken backwards to be regarded as a first nerve electric pulse signal sample, the threshold detection parameter is set to be that the negative peak value of the signal is greater than 60 micro volts, the peak-peak interval is greater than 2 milliseconds, as shown in fig. 3, the peak time is taken forwards to be 1 millisecond, and the peak time is taken backwards to be 1.5 milliseconds to be regarded as a potential first nerve electric pulse signal sample.
Step S200: and carrying out bias distribution assumption on the first nerve electric pulse signal sample, estimating according to the moment of bias distribution to obtain a first probability density parameter, a position parameter and a scale parameter of bias distribution of the first nerve electric pulse signal sample, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter.
Specifically, the distribution curve of the first nerve electric pulse signal sample belongs to the data frequency distribution with left-right asymmetry and accords with the bias distribution, so that a bias distribution assumption is made on the first nerve electric pulse signal sample, and the first probability density parameter, the position parameter and the scale parameter of the bias distribution of the first nerve electric pulse signal sample are obtained according to the moment estimation of the bias distribution.
It should be noted that SN distribution of nerve electric pulses in the present application is assumed to be derived from statistical inference of a large number of samples. As shown in FIG. 4 and FIG. 5, the statistical histograms of the two types of nerve electric pulse signals respectively show that the nerve electric brain signals of different types belong to SN distribution though different in size, and the distribution parameters are as followsIs less than 0
As shown in fig. 6, 7, 8 and 9, the statistical histograms of the noise samples of different classes are different and non-identical SN distribution of (c).
Wherein, the step S200: performing bias distribution assumption on the first nerve electric pulse signal sample, obtaining a first probability density parameter, a position parameter and a scale parameter of bias distribution of the first nerve electric pulse signal sample according to moment estimation of bias distribution, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter, wherein the method specifically comprises the following steps:
making a bias distribution assumption on the first neuroelectric pulse signal sample:
；
wherein Y represents the first nerve electric pulse signal sample, and SN represents the bias distribution;
；
wherein,for the position parameter +.>Is a scale parameter->As a first probability density parameter, a second probability density parameter,x is a sample obeying standard deviation distribution for the inclination variable;
obtaining first probability density parameters, position parameters and scale parameters of the bias distribution of the first nerve electric pulse signal sample according to the moment estimation of the bias distribution, and obtaining a first probability density function according to the first probability density parameters, the position parameters and the scale parameters;
the saidThe mathematical formula of the first probability density function is:；
wherein,representing a standard gaussian density function, +. >Is->The cumulative probability distribution function, x is a random variable.
Specifically, a bias distribution (Shew-Normal distribution, SN distribution) assumption is made on the first nerve electrical pulse signal sample, and the formula can be obtained:，
wherein Y represents a first nerve electrical pulse signal sample, and SN represents a bias distribution.
Further, the formula is as follows:；
wherein,for the position parameter +.>Is a scale parameter->As a first probability density parameter, a second probability density parameter,x is a sample obeying standard deviation distribution for the inclination variable;
obtaining a first probability density parameter of the bias distribution of the first nerve electric pulse signal sample according to the moment estimation of the bias distribution;
wherein, the mathematical formula of the probability density function is:wherein->Representing a standard gaussian density function, +.>Is->The cumulative probability distribution function, x is a random variable.
Under the premise, the SN distribution probability density parameter of the first nerve electric pulse signal sample Y is obtained according to the moment estimation of the bias probability density distribution, so that a probability density function of the first nerve electric pulse signal sample Y, namely SN-pdf, is obtained theoretically.
As shown in fig. 10, 11 and 12, the estimated plot of a single neuroelectric pulse sample, it can be seen that the estimation of a single neuroelectric pulse sample and the utilization of gaussian kernel density estimation are also contemplated. As shown in fig. 10, a histogram of a single nerve electric pulse signal is shown in fig. 11, a theoretical SN probability density distribution of the sample is shown in fig. 12, and a probability density distribution estimated by using gaussian kernel density is shown. The experimental results show that the probability density estimation method can be used as a rapid and efficient nerve electric pulse detection method.
Step S300: and judging whether the first probability density parameter is smaller than zero, and if so, taking the first nerve electric pulse signal sample as a second nerve electric pulse signal sample.
Specifically, whether the first probability density parameter of the obtained theoretical SN distribution is smaller than zero is judged, namely whether the first probability density parameter meetsIf yes, obtaining a second nerve electric pulse signal sample, and if not, refusing to accept the first nerve electric pulse signal sample.
Step S400: and calculating the second nerve electric pulse signal sample by using a nuclear density estimation method to obtain a second probability density function.
Specifically, the kernel density estimation method is used for calculating the second nerve electric pulse signal sample to obtain a second probability density function, so that nerve electric pulse detection can be performed rapidly and efficiently.
Wherein, the step S400: calculating the second nerve electric pulse signal sample by using a nuclear density estimation method to obtain a second probability density function, wherein the method specifically comprises the following steps of:
calculating the second nerve electric pulse signal sample by using a Gaussian kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionIs Gaussian kernel- >，/>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->。
Specifically, the idea of kernel density estimation is utilized to estimate the true probability density distribution (KDE-pdf) of the second nerve electric pulse signal sample, a Gaussian kernel density estimation method is used for calculation, and a calculation formula of the Gaussian kernel density estimation method is as follows:wherein the kernel function is Gaussian kernel +.>，/>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->The second probability density function is obtained, and the Gaussian kernel density estimation can process data distribution of any shape, so that the method has high flexibility and adaptability.
Optionally, the selection of the bandwidth has an important influence on the accuracy of the estimation result, and the result of the kernel density estimation can be more accurate by changing the calculation method of the bandwidth.
Alternatively, the step S400: calculating the second nerve electric pulse signal sample by using a nuclear density estimation method to obtain a second probability density function, wherein the method specifically comprises the following steps of:
calculating the second nerve electric pulse signal sample by using a linear kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionIs a linear nucleus- >，/>，/>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->。
Specifically, a linear kernel density estimation method is used for calculating the second nerve electric pulse signal sample to obtain a second probability density function, and the operation process of the linear kernel density estimation method is relatively simple and the operation speed is high.
Alternatively, the step S400: calculating the second nerve electric pulse signal sample by using a nuclear density estimation method to obtain a second probability density function, wherein the method specifically comprises the following steps of:
calculating the second nerve electric pulse signal sample by using a cosine kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionFor cosine kernel->，/>Wherein->Is of circumference rate>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->。
Specifically, a triangle kernel density estimation method is used for calculating the second nerve electric pulse signal sample, so that a second probability density function is obtained.
Optionally, the kernel density estimation method may further use a polynomial kernel, a laplace kernel, a sigmoid kernel, a triangle kernel, and an exponential kernel, which may be specifically selected according to needs, and will not be described in detail herein.
Step S500: and calculating information divergence between the first probability density function and the second probability density function, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulse according to the information divergence, and outputting a judging result.
Specifically, by calculating the information divergence between the first probability density parameter and the second probability density function, whether the first nerve electric pulse signal sample belongs to nerve electric pulse is judged, the specificity is good, a large amount of waveform information is not lost, and the complex process of template matching is avoided.
Wherein, the step S500: calculating information divergence between the first probability density function and the second probability density function, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulse according to the information divergence, and outputting a judging result, wherein the method specifically comprises the following steps of:
calculating probability densities of the first probability density function and the second probability density function between the first nerve electrical pulse signal sample value and a second nerve electrical pulse signal sample value, respectively;
calculating an information divergence between the first probability density function and the second probability density function according to the probability density between the first nerve electric pulse signal sample value and the second nerve electric pulse signal sample value;
the calculation formula of the information divergence is as follows:；
wherein,representing a first probability density function, +.>A second probability density function is represented and, Representing information divergence;
judging whether the first nerve electric pulse signal sample belongs to nerve electric pulses or not, and outputting a judging result;
if the information divergence is smaller than or equal to a preset threshold value, the judgment result is that the first nerve electric pulse signal sample belongs to nerve electric pulses.
Specifically, the probability density of the first probability density parameter (SN-pdf) and the second probability density function (KDE-pdf) between the first nerve electric pulse signal sample value and the second nerve electric pulse signal sample value, that is, the probability density between the maximum value max (Y) of Y and the minimum value min (Y) of Y, is calculated respectively, and the information divergence between the first probability density parameter and the second probability density function is calculated, where the calculation formula of the information divergence is:；
wherein,representing a first probability density parameter, +.>A second probability density parameter is represented and,representing information divergence, i.e. representing inconsistency, or similarity, of two distributions. The more similar the two distributions, the closer the KL is to 0, and vice versa;
alternatively, the calculation of the KL divergence of the two distributions is essentially a calculation method of entropy, and can be modified to other entropy measures.
And finally, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulse, comparing the calculated information divergence KL with a preset threshold Th, if the information divergence KL is larger than the preset threshold Th, negating the first nerve electric pulse signal sample, and if the information divergence is smaller than or equal to the preset threshold, receiving the first nerve electric pulse signal sample, wherein the judgment result is that the first nerve electric pulse signal sample belongs to nerve electric pulse.
The present application may reduce reliance on the engineering experience of researchers compared to feature extraction schemes. The feature extraction process requires researchers to select suitable features according to own engineering practice experience, such as statistical features (mean, variance, quantile and the like), spectral features (energy, spectral density and the like), entropy features (sample entropy, differential entropy, fuzzy entropy and the like) and other nonlinear features (fractal dimension, lyapunov index and the like). How to select or combine the above features for detection of the neuroelectric pulse signals is often decided by engineering developers, and such decision-making process often depends on the familiar feature extraction technology of the developers and the known characteristics of the neuroelectric pulses. The resulting nerve electric pulse detector of this approach is generally not robust.
Compared with the template matching scheme, the method does not need to prepare a proper template in advance, and does not need to extract the template in the detection process (online extraction of the template). Template matching requires preparation of enough templates in advance to minimize the omission factor. If it is assumed that the nerve electric pulse signals emitted from each neuron are not the same, the brain counts about 800 billion neurons, which is a number that cannot be prepared in advance. The method for extracting the template online needs continuous learning, so that the template is updated to a relatively stable state, and the time cost is rapidly increased in the process.
Compared with a scheme of automatically extracting features by using a neural network model, the method does not need to prepare a large number of samples in advance. There are two common schemes for neural network feature extraction, one is a supervised automatic encoder and the other is an unsupervised automatic codec. The former requires a large number of manually labeled samples, so that the neural network learns the coding model that automatically extracts the neural-electric pulse characteristics. The latter is to learn a model for maximizing different types of samples and minimizing characteristic differences of the same types of samples in the process of learning a large amount of data, and the model can be used for sequencing nerve electric pulses and is less used as a nerve electric pulse detection tool.
Referring to fig. 13 to 14, fig. 13 is a schematic diagram of a neural electric pulse detection system according to a preferred embodiment of the present application; FIG. 14 is a schematic view of an operating environment of a preferred embodiment of the terminal of the present application.
In some embodiments, as shown in fig. 13, based on the above-mentioned nerve electric pulse detection method, the present application further proposes a nerve electric pulse detection system, where the nerve electric pulse detection system includes:
the signal preprocessing module 51 is configured to obtain an original nerve electrophysiological signal, and perform band-pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electrical pulse signal sample;
The signal moment estimation module 52 is configured to make a bias distribution assumption on the first nerve electric pulse signal sample, obtain a first probability density parameter, a position parameter and a scale parameter of the bias distribution of the first nerve electric pulse signal sample according to the moment estimation of the bias distribution, and obtain a first probability density function according to the first probability density parameter, the position parameter and the scale parameter;
the parameter judging module 53 is configured to judge whether the first probability density parameter is less than zero, and if yes, take the first nerve electric pulse signal sample as a second nerve electric pulse signal sample;
a signal density estimation module 54, configured to calculate the second neural electric pulse signal sample by using a kernel density estimation method, so as to obtain a second probability density function;
the signal judging module 55 is configured to calculate an information divergence between the first probability density function and the second probability density function, judge whether the first nerve electric pulse signal sample belongs to nerve electric pulses according to the information divergence, and output a judging result.
In some embodiments, as shown in fig. 14, based on the above nerve electric pulse detection method and system, the present application further provides a terminal correspondingly, where the terminal includes: the memory 10, processor 20, display 30, fig. 14 only show some of the components of the terminal, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead.
The memory 20 may in some embodiments be an internal storage unit of the terminal, such as a hard disk or a memory of the terminal. The memory 20 may in other embodiments 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 memory Card (Flash Card) or the like, which are provided on the terminal. Further, the memory 20 may also include both an internal storage unit and an external storage device of the terminal. The memory 20 is used for storing application software installed in the terminal and various data, such as program codes of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output.
In one embodiment, the memory 20 stores a neural electric pulse detection program 40, and the neural electric pulse detection program 40 can be executed by the processor 10, so as to implement the neural electric pulse detection method in the present application.
The processor 10 may in some embodiments be a central processing unit (Central Processing Unit, CPU), microprocessor or other data processing chip for executing program code or processing data stored in the memory 20, for example performing the nerve electrical pulse detection method or the like.
The display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like in some embodiments. The display 30 is used for displaying information at the terminal and for displaying a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.
The present application also proposes a computer readable storage medium storing a nerve electric pulse detection program which, when executed by a processor, implements the steps of the nerve electric pulse detection method as described above.
In summary, the original nerve electrophysiological signal is obtained from the brain of an animal or a human, and the band-pass filtering and the threshold detection are performed on the original nerve electrophysiological signal, so that the noise of the original nerve electrophysiological signal is reduced, a first nerve electric pulse signal sample is obtained, and the noise resistance is improved; secondly, by making a bias distribution assumption on the first nerve electric pulse signal sample, the first probability density parameter, the position parameter and the scale parameter of the bias distribution of the first nerve electric pulse signal sample are obtained according to the moment estimation of the bias distribution, so that a density estimation algorithm is conveniently used in the subsequent step and whether the first nerve electric pulse signal sample belongs to nerve electric pulses is judged; again, the present application compares whether the first probability density parameter is satisfied If yes, a second nerve electric pulse signal sample is obtained, and a qualified second nerve electric pulse signal sample is obtained through primary judgment, so that the first probability density parameter which does not meet the condition is prevented from entering the next step; in addition, the method calculates the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function, so that nerve electric pulse detection can be performed quickly and efficiently; in addition, the information divergence between the first probability density parameter and the second probability density function is calculated, whether the first nerve electric pulse signal sample belongs to nerve electric pulse is judged, the specificity is good, a large amount of waveform information cannot be lost, and the complex process of template matching is avoided.
It should be noted that, the various optional implementations described in the embodiments of the present application may be implemented in combination with each other, or may be implemented separately, which is not limited to the embodiments of the present application.
In the description of the present application, it should be understood that the terms "upper," "lower," "left," "right," and the like indicate an orientation or a positional relationship based on that shown in the drawings, and are merely for convenience of description of the present application and for simplification of the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, as well as a specific orientation configuration and operation. Therefore, it is not to be construed as limiting the present application. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.
In the description of the present application, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art in a specific context.
The embodiments described above are described with reference to the drawings, and other different forms and embodiments are possible without departing from the principles of the present application, and thus the present application should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will convey the scope of the application to those skilled in the art. In the drawings, component dimensions and relative dimensions may be exaggerated for clarity. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. The terms "comprises," "comprising," and/or "includes," when used in this specification, specify the presence of stated features, integers, components, and/or groups thereof, but do not preclude the presence or addition of one or more other features, integers, components, and/or groups thereof. Unless otherwise indicated, numerical ranges are stated to include the upper and lower limits of the range and any subranges therebetween.
The foregoing description is only a partial embodiment of the present application, and is not intended to limit the scope of the present application, and all equivalent devices or equivalent process transformations made by using the descriptions and the drawings of the present application, or direct or indirect application to other related technical fields, are included in the patent protection scope of the present application.
Claims (8)
1. A method for detecting nerve electrical pulses, comprising:
acquiring an original nerve electrophysiological signal, and performing band-pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electric pulse signal sample;
performing bias distribution assumption on the first nerve electric pulse signal sample, estimating according to the moment of bias distribution to obtain a first probability density parameter, a position parameter and a scale parameter of bias distribution of the first nerve electric pulse signal sample, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter;
making a bias distribution assumption on the first neuroelectric pulse signal sample:
；
wherein Y represents the first nerve electric pulse signal sample, and SN represents the bias distribution;
；
wherein,for the position parameter +.>Is a scale parameter- >For the first probability density parameter, +.>X is a sample obeying standard deviation distribution for the inclination variable;
obtaining first probability density parameters, position parameters and scale parameters of the bias distribution of the first nerve electric pulse signal sample according to the moment estimation of the bias distribution, and obtaining a first probability density function according to the first probability density parameters, the position parameters and the scale parameters;
the mathematical formula of the first probability density function is:；
wherein,representing a standard gaussian density function, +.>Is->A cumulative probability distribution function, x being a random variable;
judging whether the first probability density parameter is smaller than zero, if so, taking the first nerve electric pulse signal sample as a second nerve electric pulse signal sample;
calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function, wherein the kernel density estimation comprises a linear kernel density estimation method, a Gaussian kernel density estimation method and a cosine kernel density estimation method;
calculating information divergence between the first probability density function and the second probability density function, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulse according to the information divergence, and outputting a judging result;
Calculating probability densities of the first probability density function and the second probability density function between the first nerve electrical pulse signal sample value and a second nerve electrical pulse signal sample value, respectively;
calculating an information divergence between the first probability density function and the second probability density function according to the probability density between the first nerve electric pulse signal sample value and the second nerve electric pulse signal sample value;
the calculation formula of the information divergence is as follows:；
wherein,representing a first probability density function, +.>Representing a second probability density function->Representing information divergence;
judging whether the first nerve electric pulse signal sample belongs to nerve electric pulses or not, and outputting a judging result;
if the information divergence is smaller than or equal to a preset threshold value, the judgment result is that the first nerve electric pulse signal sample belongs to nerve electric pulses.
2. The method for detecting nerve electric pulse according to claim 1, wherein the obtaining the original nerve electric physiological signal, performing band-pass filtering and threshold detection on the original nerve electric physiological signal, and obtaining a first nerve electric pulse signal sample, specifically includes:
acquiring an original nerve electrophysiological signal, and performing band-pass filtering on the original nerve electrophysiological signal by using a sixth-order Butterworth filter to obtain a first filtering electric pulse signal;
And performing threshold detection on the first filtering electric pulse signal by using a threshold detection parameter to obtain the first nerve electric pulse signal sample.
3. The method for detecting nerve electric pulse according to claim 1, wherein the calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function specifically includes:
calculating the second nerve electric pulse signal sample by using a Gaussian kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionIs Gaussian kernel->，/>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->。
4. The method for detecting nerve electric pulse according to claim 1, wherein the calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function specifically includes:
calculating the second nerve electric pulse signal sample by using a linear kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionIs a linear nucleus->，/>，/>For sample spots +. >For the number of sample points, +.>Is bandwidth, bandwidth is->。
5. The method for detecting nerve electric pulse according to claim 1, wherein the calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function specifically includes:
calculating the second nerve electric pulse signal sample by using a cosine kernel density estimation method to obtain a second probability density function;
the calculation formula of the nuclear density estimation method is as follows:；
wherein the kernel functionFor cosine kernel->，/>Wherein->Is of circumference rate>For sample spots +.>For the number of sample points, +.>Is bandwidth, bandwidth is->。
6. A nerve electrical pulse detection system, the nerve electrical pulse detection system comprising:
the signal preprocessing module is used for acquiring an original nerve electrophysiological signal, and carrying out band-pass filtering and threshold detection on the original nerve electrophysiological signal to obtain a first nerve electric pulse signal sample;
the signal moment estimation module is used for making a bias distribution assumption on the first nerve electric pulse signal sample, obtaining a first probability density parameter, a position parameter and a scale parameter of the bias distribution of the first nerve electric pulse signal sample according to the moment estimation of the bias distribution, and obtaining a first probability density function according to the first probability density parameter, the position parameter and the scale parameter;
Making a bias distribution assumption on the first neuroelectric pulse signal sample:
；
wherein Y represents the first nerve electric pulse signal sample, and SN represents the bias distribution;
；
wherein,for the position parameter +.>Is a scale parameter->For the first probability density parameter, +.>X is a sample obeying standard deviation distribution for the inclination variable;
obtaining first probability density parameters, position parameters and scale parameters of the bias distribution of the first nerve electric pulse signal sample according to the moment estimation of the bias distribution, and obtaining a first probability density function according to the first probability density parameters, the position parameters and the scale parameters;
the mathematical formula of the first probability density function is:；
wherein,representing a standard gaussian density function, +.>Is->A cumulative probability distribution function, x being a random variable;
the parameter judging module is used for judging whether the first probability density parameter is smaller than zero, and if yes, the first nerve electric pulse signal sample is used as a second nerve electric pulse signal sample;
the signal density estimation module is used for calculating the second nerve electric pulse signal sample by using a kernel density estimation method to obtain a second probability density function, and the kernel density estimation comprises a linear kernel density estimation method, a Gaussian kernel density estimation method and a cosine kernel density estimation method;
The signal judging module is used for calculating the information divergence between the first probability density function and the second probability density function, judging whether the first nerve electric pulse signal sample belongs to nerve electric pulses or not according to the information divergence, and outputting a judging result;
calculating probability densities of the first probability density function and the second probability density function between the first nerve electrical pulse signal sample value and a second nerve electrical pulse signal sample value, respectively;
calculating an information divergence between the first probability density function and the second probability density function according to the probability density between the first nerve electric pulse signal sample value and the second nerve electric pulse signal sample value;
the calculation formula of the information divergence is as follows:；
wherein,representing a first probability density function, +.>Representing a second probability density function->Representing information divergence;
judging whether the first nerve electric pulse signal sample belongs to nerve electric pulses or not, and outputting a judging result;
if the information divergence is smaller than or equal to a preset threshold value, the judgment result is that the first nerve electric pulse signal sample belongs to nerve electric pulses.
7. A terminal, the terminal comprising: a memory, a processor and a nerve electrical pulse detection program stored on the memory and executable on the processor, which when executed by the processor, performs the steps of the nerve electrical pulse detection method of any one of claims 1-5.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a nerve electrical pulse detection program, which when executed by a processor, implements the steps of the nerve electrical pulse detection method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311675784.3A CN117357134B (en) | 2023-12-08 | 2023-12-08 | Nerve electric pulse detection method, system and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311675784.3A CN117357134B (en) | 2023-12-08 | 2023-12-08 | Nerve electric pulse detection method, system and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117357134A CN117357134A (en) | 2024-01-09 |
| CN117357134B true CN117357134B (en) | 2024-02-09 |
Family
ID=89400692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311675784.3A Active CN117357134B (en) | 2023-12-08 | 2023-12-08 | Nerve electric pulse detection method, system and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117357134B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110088138A (en) * | 2010-01-28 | 2011-08-03 | 충북대학교 산학협력단 | Device and method to detect sleep apnea and classify its type |
| WO2016029590A1 (en) * | 2014-08-28 | 2016-03-03 | 北京交通大学 | Fault prediction and condition-based maintenance method for urban rail train bogie |
| CN106203628A (en) * | 2016-07-11 | 2016-12-07 | 深圳先进技术研究院 | A kind of optimization method strengthening degree of depth learning algorithm robustness and system |
| CN107273688A (en) * | 2017-06-16 | 2017-10-20 | 山东万腾电子科技有限公司 | Equipment life and health degree monitoring method and system based on primary fault data |
| JP2020048838A (en) * | 2018-09-26 | 2020-04-02 | 株式会社国際電気通信基礎技術研究所 | Estimation device, estimation program, and estimation method |
| CN114564814A (en) * | 2022-01-12 | 2022-05-31 | 云南电网有限责任公司信息中心 | Dynamic threshold Gaussian kernel density estimation system and method for sparse data |
| CN115438312A (en) * | 2022-10-21 | 2022-12-06 | 国网四川省电力公司成都供电公司 | Probability distribution model establishment and application method and medium for new energy output |
| CN116807496A (en) * | 2023-08-25 | 2023-09-29 | 北京大学 | Method, device, equipment and medium for positioning epileptic interval brain wave abnormal signals |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10694946B2 (en) * | 2016-07-05 | 2020-06-30 | Freer Logic, Inc. | Dual EEG non-contact monitor with personal EEG monitor for concurrent brain monitoring and communication |
| CN114364318A (en) * | 2019-07-12 | 2022-04-15 | 萨鲁达医疗有限公司 | Monitoring the quality of a neural recording |
-
2023
- 2023-12-08 CN CN202311675784.3A patent/CN117357134B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110088138A (en) * | 2010-01-28 | 2011-08-03 | 충북대학교 산학협력단 | Device and method to detect sleep apnea and classify its type |
| WO2016029590A1 (en) * | 2014-08-28 | 2016-03-03 | 北京交通大学 | Fault prediction and condition-based maintenance method for urban rail train bogie |
| CN106203628A (en) * | 2016-07-11 | 2016-12-07 | 深圳先进技术研究院 | A kind of optimization method strengthening degree of depth learning algorithm robustness and system |
| CN107273688A (en) * | 2017-06-16 | 2017-10-20 | 山东万腾电子科技有限公司 | Equipment life and health degree monitoring method and system based on primary fault data |
| JP2020048838A (en) * | 2018-09-26 | 2020-04-02 | 株式会社国際電気通信基礎技術研究所 | Estimation device, estimation program, and estimation method |
| CN114564814A (en) * | 2022-01-12 | 2022-05-31 | 云南电网有限责任公司信息中心 | Dynamic threshold Gaussian kernel density estimation system and method for sparse data |
| CN115438312A (en) * | 2022-10-21 | 2022-12-06 | 国网四川省电力公司成都供电公司 | Probability distribution model establishment and application method and medium for new energy output |
| CN116807496A (en) * | 2023-08-25 | 2023-09-29 | 北京大学 | Method, device, equipment and medium for positioning epileptic interval brain wave abnormal signals |
Non-Patent Citations (1)
| Title |
|---|
| 基于单站探空资料的不同强度短时强降水预报指标研究;李文娟等;暴雨灾害;20170430;第36卷(第2期);第132-138页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117357134A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112102237A (en) | Brain tumor recognition model training method and device based on semi-supervised learning | |
| Naga Srinivasu et al. | A comparative review of optimisation techniques in segmentation of brain MR images | |
| CN107657209B (en) | Template image registration mechanism based on finger vein image quality | |
| CN111345817B (en) | QRS complex position determination method, device, equipment and storage medium | |
| US11119091B2 (en) | Method and device for automatically tracking urine | |
| CN111986183A (en) | Chromosome scattergram image automatic segmentation and identification system and device | |
| CN104679967B (en) | A kind of method for judging psychological test reliability | |
| CN116386120A (en) | Noninductive monitoring management system | |
| CN117357134B (en) | Nerve electric pulse detection method, system and terminal | |
| Zhang et al. | A robust spike sorting method based on the joint optimization of linear discrimination analysis and density peaks | |
| CN112843425B (en) | Sleeping posture detection method and device based on sleeping pillow, electronic equipment and storage medium | |
| CN107212882A (en) | The real-time detection method and system of a kind of EEG signals state change | |
| CN113255802A (en) | Intelligent skin tendering system based on infrared laser | |
| EP3176726A1 (en) | Method and device for positioning human eyes | |
| CN108470182A (en) | A kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification | |
| CN115670397B (en) | PPG artifact identification method and device, storage medium and electronic equipment | |
| CN114356074B (en) | Animal brain-computer interface implementation method and system based on in-vivo fluorescence signals | |
| CN116362782A (en) | User interest point identification method and system based on big data analysis | |
| CN114997229A (en) | Electroencephalogram signal-based motor imagery classification method and system | |
| CN110647870B (en) | Method for calculating approximate entropy of resting state fMRI data based on sliding window | |
| CN113538396B (en) | Counting prompting method and device based on injection needle processing | |
| CN113421643B (en) | AI model reliability judging method, device, equipment and storage medium | |
| CN111488844B (en) | Eye state detection method, device, equipment and storage medium | |
| CN117253096B (en) | Finger-adaptive health index monitoring method, device, equipment and storage medium | |
| CN116982993B (en) | Electroencephalogram signal classification method and system based on high-dimensional random matrix theory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |