Lightweight epilepsy electroencephalogram signal four-classification method

Abstract

The invention discloses a lightweight epilepsy electroencephalogram signal four-classification method, and relates to the technical field of electroencephalogram signal processing. Integrating short-time Fourier transform, a spectrum reconstruction strategy, a one-dimensional convolutional neural network and a long-short term memory network, and constructing an electroencephalogram signal four-classification model; based on the trained electroencephalogram signal four-classification model, the electroencephalogram signals of the user serve as input, and the probability value that the electroencephalogram signals belong to each category is output; comparing the probability values of the four categories, taking the category with the maximum probability value as the category to which the electroencephalogram signal belongs, and sending a corresponding alarm according to the category to which the electroencephalogram signal belongs. Compared with traditional dichotomous and trichotomous models, the electroencephalogram signal four-classification model of the application brings features in the later period of attack into the range of recognition, the accuracy of the model is improved, and based on the lightweight design of the spectrum reconstruction strategy, the reliability of the model is improved. The lightweight epilepsy electroencephalogram signal four-classification method provided by the invention can be applied to edge wearable equipment scenes.

Description

Technical Field

[0001] The present application relates to the technical field of electroencephalogram (EEG) signal processing, and in particular to a lightweight four-classification method for epileptic EEG signals. Background Art

[0002] As a neurological disease with a wide range of impacts worldwide, epilepsy has a complex and unpredictable pathogenesis, which poses a severe challenge to patients' daily lives. In recent years, epilepsy seizure monitoring methods based on EEG signals have gradually become a research hotspot, aiming to achieve early warning and accurate classification of seizures through intelligent means. Researchers have proposed a large number of epilepsy prediction and detection methods. For example, some researchers have tried a stacked one-dimensional convolutional neural network model that combines random selection and data enhancement strategies. Other researchers have achieved automatic prediction of epileptic seizures through a bidirectional long short-term memory network model based on spectral features. Many researchers have also used the fast Fourier transform method to extract frequency domain information from the patient's EEG signal, but the EEG signal is a non-stationary signal, and the fast Fourier transform has limitations in processing such signals. To this end, some researchers have proposed using discrete wavelet transform, short-time Fourier transform, etc. to convert the patient's EEG signal from the time domain to the time-frequency domain, which can not only capture the time and frequency characteristics of the signal at the same time, but also enhance the applicability of the signal characteristics to the convolutional neural network.

[0003] However, since the convolution kernel cannot extend to areas beyond the edge, the edge pixels cannot always be at the center of the kernel function, resulting in significant attenuation of information at the edge of the image in the output feature map. To compensate for this edge effect, the conventional approach is to introduce a zero-padding strategy to expand the effective area that the convolution kernel can reach. However, zero-padding increases the complexity of hardware design, especially for customized accelerators, which require additional consideration of edge filling logic; at the same time, the zero-padding operation increases the amount of computation and inevitably increases hardware energy consumption, which is obviously not friendly to wearable device application scenarios that pursue energy efficiency.

[0004] In actual situations, portable epilepsy monitoring equipment can effectively assist patients in avoiding possible safety threats. Seizure prediction methods can remind patients to move to a safe environment in time. Seizure detection methods can provide patients' relatives or doctors with information about the patient's condition, allowing them to take appropriate rescue measures and therapeutic interventions when the patient has an attack. However, given that the EEG activity of epilepsy patients shows four typical time period characteristics, including pre-ictal, ictal, post-ictal and interictal. The existing three-classification model simply classifies the EEG signals of the post-ictal period as interictal, ignoring the significant differences between the post-ictal and interictal EEGs. This simplified processing will lead to a significant increase in the false alarm rate in practical operations, thereby affecting the reliability of the monitoring system. Summary of the invention

[0005] The present application aims to solve one of the technical problems in the related art at least to some extent. To this end, one purpose of the present application is to propose a lightweight four-classification method for epileptic EEG signals, which improves the high reliability of monitoring patients in practical applications.

[0006] One aspect of the present application provides a lightweight four-classification method for epileptic EEG signals, comprising:

[0007] Step S100: collecting the user's EEG signal;

[0008] Step S200: Integrate short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network to construct a four-classification model of EEG signals;

[0009] The construction method of the four-classification model of EEG signals is:

[0010] Obtaining original EEG signals, preprocessing the original EEG signals, marking four categories of EEG signal states of epileptic patients, wherein the four categories of EEG signal states of epileptic patients include interictal period, preictal period, ictal period and postictal period, dividing the original EEG signals into four categories with a time length t as a slice window length, dividing the original EEG signals of each category into m data slices, and constructing a data set containing n data samples using the data slices, wherein each data sample contains data slices of four categories;

[0011] Using short-time Fourier transform to map each data sample to the time-frequency domain, obtaining the time-frequency domain signal of the original EEG signal, and applying the spectrum reconstruction strategy to filter the noise frequency band in the time-frequency domain signal of the original EEG signal, moving the low-frequency part to the central position of the spectrum dimension, and obtaining the optimized feature representation of the time-frequency domain signal of the original EEG signal; the dimensions of the time-frequency domain signal include the spectrum dimension and the time series dimension;

[0012] The specific implementation method of the spectrum reconstruction strategy is as follows: setting a noise threshold λ, filtering the noise frequency band greater than or equal to the noise threshold in the [0, A1Hz] frequency band of the original EEG signal by filtering, retaining the [0, A2Hz) part, where A2<λ, cropping the [0, A2Hz) part to obtain the [0, A3Hz] part and the (A3Hz, A2Hz) part, and moving the [0, A3Hz] part to the central position of the spectrum dimension by translation and splicing;

[0013] Construct a fusion neural network model, including an input layer, a one-dimensional convolutional neural network, a long short-term memory network, a fully connected layer, a softmax activation function and an output layer; the one-dimensional convolutional neural network is used to perform a convolution operation on the time-frequency domain signals of the optimized original EEG signal in the spectrum dimension to extract the frequency domain features of the original EEG signal; the long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network in the time series dimension to obtain the time domain features of the frequency domain features of the original EEG signal in the time series; the fully connected layer and the softmax activation function are used to calculate the probability value of the data sample belonging to each category, and the output layer is used to output the classification of the data sample; the fusion neural network model is trained using the data set to construct a trained four-classification model of EEG signals;

[0014] Step S300: Based on the trained EEG signal four-classification model, the user's EEG signal is used as input, and the probability value of the EEG signal belonging to each category is output;

[0015] The specific process of taking the user's EEG signal as input and outputting the probability value of the EEG signal belonging to each category based on the trained EEG signal four-classification model is as follows:

[0016] Step S310: Input the user's EEG signal into the trained EEG signal four-classification model, divide the EEG signal into a number of EEG signal segments according to the preset time window length, and use short-time Fourier transform to map each EEG signal segment to the time-frequency domain to obtain a time-frequency domain signal;

[0017] Step S320: applying a spectrum reconstruction strategy, using a translation and re-splicing method, moving the low-frequency part of the time-frequency domain signal to the central position of the spectrum dimension, and filtering the noise frequency band to obtain an optimized time-frequency domain signal;

[0018] Step S330: In the frequency spectrum dimension, a one-dimensional convolutional neural network is used to perform a convolution operation on the optimized time-frequency domain signal to extract frequency domain features;

[0019] Step S340: In the time series dimension, the frequency domain features extracted by the one-dimensional convolutional neural network are modeled using a long short-term memory network to obtain the time domain features of the frequency domain features in the time series;

[0020] Step S350: Input the frequency domain features and the time domain features into the fully connected layer and the softmax activation function, classify the EEG signal segments, and output the probability values ​​of the EEG signal segments belonging to the four categories;

[0021] Step S400: comparing the probability values ​​of the four categories, taking the category with the largest probability value as the category to which the EEG signal belongs, and sending a corresponding alarm according to the category to which it belongs; wherein, determining the category to which the EEG signal belongs to realize the prediction and detection of the seizure of the condition of the epilepsy patient by the four-category model of the EEG signal, realizing the prediction of the seizure of the condition of the epilepsy patient when the category to which it belongs is the pre-ictal period, realizing the detection of the seizure of the condition of the epilepsy patient when the category to which it belongs is the ictal period, the post-ictal period or the interictal period;

[0022] The specific method of comparing the probability values ​​of the four categories, taking the category with the largest probability value as the category to which the EEG signal belongs, and sending the corresponding alarm according to the category is: classifying through the fully connected layer and the softmax function, outputting the probability value of the EEG signal segment belonging to each category, comparing the sizes of the four probability values, and taking the category with the largest probability value as the category to which the EEG signal segment belongs; if the category is pre-ictal, the user is warned, and if the category is ictal, post-ictal or interictal, the doctor is notified.

[0023] One aspect of the present application provides a lightweight four-classification system for epileptic EEG signals, comprising:

[0024] A sensor module for collecting the user's EEG signals;

[0025] The processing unit module is used to integrate short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network to construct a four-category model of EEG signals; the construction method of the four-category model of EEG signals is as follows: obtaining the original EEG signals, preprocessing the original EEG signals, marking the four categories of EEG signal states of epileptic patients, the four categories of EEG signal states of epileptic patients include interictal period, preictal period, ictal period and postictal period, dividing the four categories in the original EEG signals with a time length t as the slice window length, dividing the original EEG signals of each category into m data slices, and constructing a data set containing n data samples using the data slices, each data sample containing data slices of four categories; using short-time Fourier transform to map each data sample to the time-frequency domain to obtain the time-frequency domain signal of the original EEG signals, and applying the spectrum reconstruction strategy to filter the noise frequency band in the time-frequency domain signal of the original EEG signals, and moving the low-frequency part to The central position of the spectrum dimension is used to obtain the characteristic representation of the time-frequency domain signal of the optimized original EEG signal; the dimensions of the time-frequency domain signal include the spectrum dimension and the time series dimension; a fusion neural network model is constructed, including an input layer, a one-dimensional convolutional neural network, a long short-term memory network, a fully connected layer, a softmax activation function and an output layer; the one-dimensional convolutional neural network is used to perform a convolution operation on the time-frequency domain signal of the optimized original EEG signal in the spectrum dimension to extract the frequency domain features of the original EEG signal; the long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network in the time series dimension to obtain the time domain features of the frequency domain features of the original EEG signal in the time series; the fully connected layer and the softmax activation function are used to calculate the probability value of the data sample belonging to each category, and the output layer is used to output the classification of the data sample; the fusion neural network model is trained using the data set to construct a trained four-classification model of EEG signals;

[0026] The output interface module is used to take the user's EEG signal as input based on the trained EEG signal four-classification model and output the probability value of the EEG signal belonging to each category;

[0027] The communication module is used to compare the probability values ​​of the four categories, take the category with the largest probability value as the category to which the EEG signal belongs, and send a corresponding alarm according to the category; wherein, the category to which the EEG signal belongs is determined to realize the EEG signal four-classification model for the prediction and detection of epileptic seizures. When the category is pre-ictal, the prediction of the epileptic seizure is realized; when the category is ictal period, post-ictal period or interictal period, the detection of the epileptic seizure is realized.

[0028] One aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in a lightweight four-classification method for epileptic EEG signals are implemented.

[0029] One aspect of the present application provides a readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor to execute steps in a lightweight four-classification method for epileptic EEG signals.

[0030] Compared with the prior art, the lightweight four-classification method of epilepsy EEG signals proposed in this application has the following advantages:

[0031] The lightweight four-classification method of epilepsy EEG signals provided in this application completely covers all stages of epilepsy patients, and meets the functional requirements of epilepsy prediction and detection. The feature recognition of the late stage of the seizure is included in the scope of model prediction and detection, eliminating the false alarm problem caused by the traditional two-classification and three-classification methods that do not consider the late stage of the seizure and are easily identified as other periods, thereby improving the recognition accuracy of the model and ensuring the high reliability of monitoring patients in practical applications;

[0032] The EEG signal four-classification model proposed in this application integrates short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network. The spectrum reconstruction strategy reduces the impact of noise, so that the low-frequency part is concentrated in the central area of ​​the spectrum dimension, so that the one-dimensional convolutional neural network can directly perform convolution operations on these key frequency parts without using padding operations. The omission of padding operations significantly reduces the complexity of hardware design, making the model proposed in this application more suitable for deployment on hardware devices;

[0033] The spectrum reconstruction strategy optimizes the time-frequency domain signal through two steps: noise band filtering and low-frequency part movement. Noise band filtering suppresses background noise and improves signal quality; low-frequency part movement enhances the concentration of the spectrum, which is conducive to the feature extraction of one-dimensional convolutional neural network. These two steps work together to improve the optimization effect of time-frequency domain feature representation, laying the foundation for one-dimensional convolutional neural network feature extraction and four-classification of epileptic EEG signals. At the same time, the spectrum reconstruction strategy has low computational complexity and is easy to implement, which helps to improve the operating efficiency of the entire system and realize the lightweight design of the model.

[0034] The combined use and collaborative work of the one-dimensional convolutional neural network and the long short-term memory network ensure that the time domain and frequency domain information of the EEG signal can be fully captured. At the same time, the one-dimensional convolutional neural network and the long short-term memory network are respectively suitable for identifying the frequency domain and the time domain, so that each network module only recognizes the information it is suitable for, and can achieve excellent recognition accuracy at a lower parameter amount. This design effectively reduces the total amount of calculation and the amount of parameters, making the lightweight epilepsy EEG signal four-classification method of this application highly lightweight and with extremely low hardware overhead;

[0035] Compared with traditional classification models, a lightweight epileptic EEG signal four-classification method provided in the present application can simultaneously realize seizure prediction and seizure detection for epileptic patients. When the category result output by the EEG signal four-classification model is the pre-ictal stage, the prediction of the patient's disease attack is realized, so that the patient can take preventive measures in advance based on the early warning. When the category result output by the EEG signal four-classification model is the seizure period, post-ictal stage or inter-ictal stage, it indicates that the patient is already in the process of disease attack, and the specific seizure stage can be detected to facilitate medical staff to carry out corresponding treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A method flow chart of a lightweight four-classification method of epileptic EEG signals provided in this application;

[0037] Figure 2 A schematic diagram of a method for preprocessing EEG signals of a lightweight four-classification method for epilepsy EEG signals provided in this application;

[0038] Figure 3 A schematic diagram of a method for short-time Fourier transform of a lightweight four-classification method of epileptic EEG signals provided in this application;

[0039] Figure 4 A schematic diagram of a spectrum reconstruction strategy for a lightweight four-classification method of epileptic EEG signals provided in this application;

[0040] Figure 5 A schematic diagram of a one-dimensional convolutional neural network and a long short-term memory network for a lightweight four-classification method of epileptic EEG signals provided in this application;

[0041] Figure 6 Schematic diagram of experimental results provided for this application;

[0042] Figure 7 Schematic diagram of the four-class confusion matrix of the experimental results provided for this application;

[0043] Figure 8 Schematic diagram of the effect of the postictal phase on specificity provided for this application;

[0044] Fig. 9 A functional module diagram of a lightweight four-classification system for epileptic EEG signals provided in this application;

[0045] Fig.10 A schematic diagram of the structure of an electronic device provided in this application;

[0046] Fig.11 It is a schematic diagram of the structure of a readable storage medium provided by this application. DETAILED DESCRIPTION

[0047] In order to better understand the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application and do not limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0048] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0049] It should also be understood that expressions such as "including", "comprising", "having", "containing" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0050] Unless otherwise specified, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that, unless clearly stated in this application, words defined in common dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0051] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0052] Example 1

[0053] like Figure 1 As shown, a lightweight four-classification method of epilepsy EEG signals provided by this application includes:

[0054] Step S100: collecting the user's EEG signal;

[0055] The EEG signal is a non-stationary signal, which indicates the change of the electrical activity of neurons in the cerebral cortex over time and contains relevant information of epileptic seizures.

[0056] Step S200: Integrate short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network to construct a four-classification model of EEG signals;

[0057] The construction method of the four-classification model of EEG signals is:

[0058] Obtaining original EEG signals, preprocessing the original EEG signals, marking four categories of EEG signal states of epileptic patients, wherein the four categories of EEG signal states of epileptic patients include interictal period, preictal period, ictal period and postictal period, dividing the original EEG signals into four categories with a time length t as a slice window length, dividing the original EEG signals of each category into m data slices, and constructing a data set containing n data samples using the data slices, wherein each data sample contains data slices of four categories;

[0059] Using short-time Fourier transform to map each data sample to the time-frequency domain, obtaining the time-frequency domain signal of the original EEG signal, and applying the spectrum reconstruction strategy to filter the noise frequency band in the time-frequency domain signal of the original EEG signal, moving the low-frequency part to the central position of the spectrum dimension, and obtaining the optimized feature representation of the time-frequency domain signal of the original EEG signal; the dimensions of the time-frequency domain signal include the spectrum dimension and the time series dimension;

[0060] The time-frequency domain signal is a two-dimensional representation obtained by performing a short-time Fourier transform on the EEG signal segment;

[0061] The low-frequency part refers to the part of the time-frequency domain signal with a frequency of 0 to bHz; the value of b is set by those skilled in the art according to actual needs;

[0062] Construct a fusion neural network model, including an input layer, a one-dimensional convolutional neural network, a long short-term memory network, a fully connected layer, a softmax activation function and an output layer; the one-dimensional convolutional neural network is used to perform a convolution operation on the time-frequency domain signals of the optimized original EEG signal in the spectrum dimension to extract the frequency domain features of the original EEG signal; the long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network in the time series dimension to obtain the time domain features of the frequency domain features of the original EEG signal in the time series; the fully connected layer and the softmax activation function are used to calculate the probability value of the data sample belonging to each category, and the output layer is used to output the classification of the data sample; the fusion neural network model is trained using the data set to construct a trained four-classification model of EEG signals;

[0063] The specific implementation method of the spectrum reconstruction strategy is as follows: setting a noise threshold λ, filtering the noise frequency band greater than or equal to the noise threshold in the [0, A1Hz] frequency band of the original EEG signal by filtering, retaining the [0, A2Hz) part, where A2<λ, cropping the [0, A2Hz) part to obtain the [0, A3Hz] part and the (A3Hz, A2Hz) part, and moving the [0, A3Hz] part to the central position of the spectrum dimension by translation and splicing;

[0064] The values ​​of the noise threshold λ and A3 are set by those skilled in the art according to actual needs and experience;

[0065] The spectrum reconstruction strategy is used to optimize the feature representation of the time-frequency domain signals of the electroencephalogram (EEG) signals of epileptic patients. The strategy effectively suppresses background noise and enhances the spectrum concentration of the signal through two main steps: noise frequency band filtering and low-frequency part movement, thereby improving the accuracy of subsequent feature extraction and classification.

[0066] Figure 2 A schematic diagram of a method for preprocessing EEG signals of a lightweight four-classification method for epilepsy EEG signals provided in this application; Figure 2 As shown, the preprocessing of the original EEG signal includes data labeling, data slicing and data set division. In the data labeling stage, the original EEG signal is labeled with four categories of the EEG signal state of epileptic patients, and the parts that do not belong to the four categories are discarded; each category of the labeled original EEG signal is divided into m data slices with a time length t as the slice window length, t is 10s, and a data set is constructed. Each data sample of the data set contains data slices of the interictal period, preictal period, ictal period, and postictal period;

[0067] In the above step S200, the EEG signal state of the epileptic patient is divided into the interictal period, the preictal period, the ictal period and the postictal period, and the postictal period is innovatively included in the scope of model recognition, which greatly improves the accuracy of the model;

[0068] Short-time Fourier transform is used to extract the time-frequency domain signals of the EEG signal. The time-frequency domain signals facilitate feature extraction by the subsequent EEG signal four-classification model. The noise frequency band in the time-frequency domain signal is filtered out using a spectrum reconstruction strategy, and the low-frequency part is moved to the center of the spectrum dimension. A one-dimensional convolutional neural network is then used to extract frequency domain features. The advantage of a one-dimensional convolutional neural network is that it has a small number of parameters, which makes the EEG signal four-classification model lightweight and can be used in edge wearable device scenarios that are sensitive to power consumption.

[0069] Step S300: Based on the trained EEG signal four-classification model, the user's EEG signal is used as input, and the probability value of the EEG signal belonging to each category is output;

[0070] The specific process of taking the user's EEG signal as input and outputting the probability value of the EEG signal belonging to each category based on the trained EEG signal four-classification model is as follows:

[0071] Step S310: Input the user's EEG signal into the trained EEG signal four-classification model, divide the EEG signal into a number of EEG signal segments according to the preset time window length, and use short-time Fourier transform to map each EEG signal segment to the time-frequency domain to obtain a time-frequency domain signal;

[0072] The length of the time window is set by those skilled in the art according to actual needs;

[0073] Figure 3 A schematic diagram of a short-time Fourier transform method for a lightweight four-classification method of epilepsy EEG signals provided in this application is provided, in which EEG signal segments with a time window length of 10s are short-time Fourier transformed to obtain the time characteristics and frequency characteristics of the EEG signal segments on each electrode channel.

[0074] The frequency spectrum dimension represents the amplitude of different frequency components, and the time series dimension represents different time windows in the time series;

[0075] The time-frequency domain signal reveals the changes in the frequency components of the EEG signal at different times;

[0076] Step S320: applying a spectrum reconstruction strategy, using a translation and re-splicing method, moving the low-frequency part of the time-frequency domain signal to the central position of the spectrum dimension, and filtering the noise frequency band to obtain an optimized time-frequency domain signal;

[0077] Figure 4A schematic diagram of a method for spectrum reconstruction strategy of a lightweight four-classification method of epileptic EEG signals provided in the present application, in which the noise frequency band is filtered out in the range of 0 to 120 Hz, the 0 to 59 Hz part is retained, the 0 to 59 Hz part is cropped to obtain the 0 to 45 Hz part and the 46 to 59 Hz part, and the 0 to 45 Hz part is moved to the central position of the spectrum dimension by translation and splicing. The spectrum reconstruction strategy aims to selectively emphasize the key frequency bands and place the key frequency bands in a prominent position that is easily recognized by a one-dimensional convolutional neural network, thereby increasing the significance of the key frequency bands and reducing the impact of noise.

[0078] Step S330: In the frequency spectrum dimension, a one-dimensional convolutional neural network is used to perform a convolution operation on the optimized time-frequency domain signal to extract frequency domain features;

[0079] Step S340: In the time series dimension, the frequency domain features extracted by the one-dimensional convolutional neural network are modeled using a long short-term memory network to obtain the time domain features of the frequency domain features in the time series;

[0080] Figure 5 A schematic diagram of a one-dimensional convolutional neural network and a long short-term memory network for a lightweight four-classification method of epileptic EEG signals provided in this application. The one-dimensional convolutional neural network and long short-term memory network of this application only need to recognize the information that they are suitable for recognition, and they are still sufficient to complete the recognition task under a smaller network size. The theoretical calculation amount and parameter optimization design make it particularly suitable for resource-constrained edge computing environments, such as wearable devices.

[0081] Step S350: Input the frequency domain features and the time domain features into the fully connected layer and the softmax activation function, classify the EEG signal segments, and output the probability values ​​of the EEG signal segments belonging to the four categories;

[0082] Step S400: comparing the probability values ​​of the four categories, taking the category with the largest probability value as the category to which the EEG signal belongs, and sending a corresponding alarm according to the category to which it belongs; wherein, determining the category to which the EEG signal belongs to realize the prediction and detection of the seizure of the condition of the epilepsy patient by the four-category model of the EEG signal, realizing the prediction of the seizure of the condition of the epilepsy patient when the category to which it belongs is the pre-ictal period, realizing the detection of the seizure of the condition of the epilepsy patient when the category to which it belongs is the ictal period, the post-ictal period or the interictal period;

[0083] The specific method of comparing the probability values ​​of the four categories, taking the category with the largest probability value as the category to which the EEG signal belongs, and sending the corresponding alarm according to the category is: classifying through the fully connected layer and the softmax function, outputting the probability value of the EEG signal segment belonging to each category, comparing the sizes of the four probability values, and taking the category with the largest probability value as the category to which the EEG signal segment belongs; if the category is pre-ictal, the user is warned, and if the category is ictal, post-ictal or interictal, the doctor is notified.

[0084] The warning threshold is set by those skilled in the art and is set and adjusted according to actual needs and classification results.

[0085] Example 2

[0086] In order to evaluate the generalization performance of the model, this application uses a 5-fold cross-validation technique to randomly divide the data set into five equal parts. In each iteration, one of the subsets is used as a test set, and the remaining four subsets are used as training sets, and the number of training rounds for each experiment is 300. In order to evaluate the classification performance of the model, this application uses total accuracy, specificity, and sensitivity as evaluation indicators. Sensitivity measures the accuracy of the method provided in this application in identifying positive samples to ensure that no cases are missed; specificity measures the ability of the method provided in this application to correctly identify negative samples to avoid misdiagnosis.

[0087] The four-classification network model used in this application can handle epileptic seizure detection and prediction tasks at the same time. In order to evaluate the epileptic seizure prediction performance of the model, this application designates the ictal, interictal, and postictal stages as negative examples, and distinguishes the preictal stage as a positive example, so as to facilitate a detailed evaluation of the specificity and sensitivity of the model in predicting epileptic seizures. When evaluating the epileptic seizure detection performance of the model, the preictal, interictal, and postictal stages are used as negative examples, and the seizure stage is set as a positive example.

[0088] Figure 6 The schematic diagram of the experimental results provided for this application shows the model accuracy of the seizure prediction sensitivity (SENS-P), seizure detection sensitivity (SENS-D), seizure prediction specificity (SPEC-P), seizure detection specificity (SPEC-D) and four-classification accuracy of 10 cases selected from the CHB-MIT data set, including chb01, chb02, chb03, chb04, chb05, chb07, chb08, chb09, chb10, and chb22. The EEG signal four-classification model proposed in this application has achieved excellent classification results in most patients, with an accuracy rate of more than 99% in cases such as chb03, chb04, chb07, chb08, and chb09. Figure 7The schematic diagram of the four-class confusion matrix of the experimental results provided for this application shows the confusion matrix of the four-classification of epileptic EEG signals. The average accuracy of SENS-P, SENS-D, SPEC-P, SPEC-D and four-classification is 97.90%, 99.89%, 99.28%, 100% and 98.44% respectively.

[0089] The EEG signal four-classification model proposed in this application can not only complete the tasks of epileptic seizure prediction and detection at the same time, but also achieve a highly competitive classification accuracy with fewer parameters. The EEG signal four-classification model proposed in this application uses only 3.7K parameters, which is a significant reduction in parameters compared to newer models in recent years, ranging from 1.7 times to 60.7 times.

[0090] Traditional two-class and three-class models cannot cover the late stage of seizures during training. In order to evaluate the impact of the late stage of seizures on recognition under realistic conditions, this application conducts two sets of experiments on the two-class and three-class models: one set is under ideal conditions and excludes late stage samples from the test set, and the other set includes these samples to simulate realistic scenarios. The experiment shows the seizure prediction and detection performance of the three-class model. The two-class model does not have the seizure detection function, so only the seizure prediction performance is obtained. Figure 8 As shown, it is a schematic diagram of the effect of the late seizure on specificity provided in this application. After incorporating the late seizure samples, the specificity of the two-class seizure prediction model and the three-class seizure prediction model both dropped by more than 20%, while the specificity of the three-class seizure detection model dropped relatively little, only about 5%. An important reason for the significant drop in seizure prediction specificity is that the similarity between the late seizure features and the pre-seizure features is higher, which makes it easier for the model to misclassify the late seizure samples as pre-seizure samples.

[0091] The model proposed in this application performs well even in real-life scenarios involving postictal samples, maintaining a specificity of 99.28% for epileptic seizure prediction and 100% for detection. This finding highlights the great advantage of the four-classification model in improving the specificity of epileptic seizure prediction and detection tasks in real-life scenarios, demonstrating its effectiveness compared to traditional methods.

[0092] Example 3

[0093] like Fig. 9 As shown, a lightweight four-classification system for epilepsy EEG signals provided by the present application includes:

[0094] A sensor module for collecting the user's EEG signals;

[0095] The processing unit module is used to integrate short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network to construct a four-category model of EEG signals; the construction method of the four-category model of EEG signals is as follows: obtaining the original EEG signals, preprocessing the original EEG signals, marking the four categories of EEG signal states of epileptic patients, the four categories of EEG signal states of epileptic patients include interictal period, preictal period, ictal period and postictal period, dividing the four categories in the original EEG signals with a time length t as the slice window length, dividing the original EEG signals of each category into m data slices, and constructing a data set containing n data samples using the data slices, each data sample containing data slices of four categories; using short-time Fourier transform to map each data sample to the time-frequency domain to obtain the time-frequency domain signal of the original EEG signals, and applying the spectrum reconstruction strategy to filter the noise frequency band in the time-frequency domain signal of the original EEG signals, and moving the low-frequency part to The central position of the spectrum dimension is used to obtain the characteristic representation of the time-frequency domain signal of the optimized original EEG signal; the dimensions of the time-frequency domain signal include the spectrum dimension and the time series dimension; a fusion neural network model is constructed, including an input layer, a one-dimensional convolutional neural network, a long short-term memory network, a fully connected layer, a softmax activation function and an output layer; the one-dimensional convolutional neural network is used to perform a convolution operation on the time-frequency domain signal of the optimized original EEG signal in the spectrum dimension to extract the frequency domain features of the original EEG signal; the long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network in the time series dimension to obtain the time domain features of the frequency domain features of the original EEG signal in the time series; the fully connected layer and the softmax activation function are used to calculate the probability value of the data sample belonging to each category, and the output layer is used to output the classification of the data sample; the fusion neural network model is trained using the data set to construct a trained four-classification model of EEG signals;

[0096] The output interface module is used to take the user's EEG signal as input based on the trained EEG signal four-classification model and output the probability value of the EEG signal belonging to each category;

[0097] A communication module is used to compare the probability values ​​of the four categories, take the category with the largest probability value as the category to which the EEG signal belongs, and send a corresponding alarm according to the category to which it belongs; wherein, the category to which the EEG signal belongs is determined to realize the prediction and detection of the seizure of the condition of the epilepsy patient by the four-category model of the EEG signal, and when the category to which it belongs is the pre-ictal period, the prediction of the seizure of the condition of the epilepsy patient is realized, and when the category to which it belongs is the ictal period, the post-ictal period or the interictal period, the detection of the seizure of the condition of the epilepsy patient is realized;

[0098] Optionally, the communication module also includes a wireless communication means for ensuring that the user can communicate in a timely manner even when the user is in a remote or inconvenient operating environment;

[0099] Optionally, the lightweight epilepsy EEG signal four-classification system is designed to be portable or wearable, integrated with low-power components, and adapted to long-term continuous monitoring of the EEG signal status of epilepsy patients;

[0100] Optionally, the lightweight epileptic EEG signal four-classification system is connected to a remote monitoring platform via wireless communication technology to achieve real-time data transmission and remote medical support functions.

[0101] Example 4

[0102] Fig.10 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Fig.10 As shown, according to another aspect of the present application, an electronic device is also provided. The electronic device may include one or more processors and one or more memories. The memory stores a computer readable code, and when the computer readable code is run by one or more processors, it can execute the above-mentioned lightweight epileptic EEG signal four-classification method.

[0103] The method or system according to the embodiment of the present application can also be used by Fig.10 The electronic device architecture shown in FIG. Fig.10As shown, the electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, an input / output component, a hard disk, etc. The storage device in the electronic device, such as a ROM or a hard disk, can store a lightweight four-classification method for epilepsy EEG signals provided in the present application. A lightweight four-classification method for epilepsy EEG signals may, for example, include: collecting the user's EEG signals; integrating short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network to construct an EEG signal four-classification model; the method for constructing the EEG signal four-classification model is: obtaining the original EEG signal, pre-processing the original EEG signal, and marking the four categories of the EEG signal state of the epilepsy patient, the four categories of the EEG signal state of the epilepsy patient include interictal period, pre-ictal period, ictal period and post-ictal period, and dividing the four categories in the original EEG signal with a slice window length of time t, and dividing the original EEG signal of each category into The signal is divided into m data slices, and a data set containing n data samples is constructed using the data slices, each data sample contains four categories of data slices; each data sample is mapped to the time-frequency domain using short-time Fourier transform to obtain the time-frequency domain signal of the original EEG signal, and the spectrum reconstruction strategy is applied to filter the noise frequency band in the time-frequency domain signal of the original EEG signal, and the low-frequency part is moved to the central position of the spectrum dimension to obtain the feature representation of the optimized time-frequency domain signal of the original EEG signal; the dimensions of the time-frequency domain signal include the spectrum dimension and the time series dimension; a fusion neural network model is constructed, including an input layer, a one-dimensional convolutional neural network, a long and short The LSTM network is a convolutional neural network with a time-domain memory, a fully connected layer, a softmax activation function, and an output layer. The one-dimensional convolutional neural network is used to perform convolution operations on the time-frequency domain signals of the optimized original EEG signals in the spectrum dimension to extract the frequency domain features of the original EEG signals. The long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network in the time series dimension to obtain the time domain features of the frequency domain features of the original EEG signals in the time series. The fully connected layer and the softmax activation function are used to calculate the probability value of the data sample belonging to each category, and the output layer is used to output the classification of the data sample. The fusion neural network model is trained using the data set to construct a A trained four-category model of EEG signals is constructed; based on the trained four-category model of EEG signals, the user's EEG signals are used as input, and the probability value of the EEG signals belonging to each category is output; the probability values ​​of the four categories are compared, and the category with the largest probability value is used as the category to which the EEG signal belongs, and a corresponding alarm is sent according to the category; wherein, the category to which the EEG signal belongs is determined to realize the EEG signal four-category model for the prediction and detection of epileptic seizures, and when the category is pre-ictal, the prediction of epileptic seizures is realized, and when the category is ictal, post-ictal or interictal, the detection of epileptic seizures is realized. Furthermore, the electronic device may also include a user interface. Of course, Fig.10 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Fig.10 One or more components of an electronic device are shown.

[0104] Example 5

[0105] Fig.11 Schematic diagram of a readable storage medium structure provided by an embodiment of the present application. Fig.11 As shown, it is a readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, a lightweight four-classification method of epilepsy EEG signals according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0106] In addition, according to the implementation mode of the present application, the process described in the above reference flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, such as: collecting the user's EEG signal; integrating short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network to construct a four-category model of EEG signals; the method for constructing the four-category model of EEG signals is: obtaining the original EEG signal, pre-processing the original EEG signal, and marking the four categories of the EEG signal state of the epileptic patient, the four categories of the EEG signal state of the epileptic patient include interictal period, preictal period, During the seizure period and the post-seizure period, the original EEG signal is divided into four categories with a slice window length of time t, and the original EEG signal of each category is divided into m data slices. The data slices are used to construct a data set containing n data samples, and each data sample contains data slices of four categories; each data sample is mapped to the time-frequency domain using a short-time Fourier transform to obtain the time-frequency domain signal of the original EEG signal, and the spectrum reconstruction strategy is applied to filter the noise frequency band in the time-frequency domain signal of the original EEG signal, and the low-frequency part is moved to the central position of the spectrum dimension to obtain the feature representation of the optimized time-frequency domain signal of the original EEG signal; the dimensions of the time-frequency domain signal include the spectrum dimension and the time series dimension degree; construct a fusion neural network model, including input layer, one-dimensional convolutional neural network, long short-term memory network, fully connected layer, softmax activation function and output layer; the one-dimensional convolutional neural network is used to perform convolution operation on the time-frequency domain signal of the optimized original EEG signal in the spectrum dimension to extract the frequency domain features of the original EEG signal; the long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network in the time series dimension to obtain the time domain features of the frequency domain features of the original EEG signal in the time series; the fully connected layer and the softmax activation function are used to calculate the probability value of the data sample belonging to each category, and the output layer is used to output the classification of the data sample; use the data The fusion neural network model is trained to construct a trained EEG signal four-classification model; based on the trained EEG signal four-classification model, the user's EEG signal is used as input, and the probability value of the EEG signal belonging to each category is output; the probability values ​​of the four categories are compared, and the category with the largest probability value is used as the category to which the EEG signal belongs, and a corresponding alarm is sent according to the category; wherein, the category to which the EEG signal belongs is determined to realize the EEG signal four-classification model for the onset prediction and onset detection of the epileptic patient's condition, when the category belongs to the pre-ictal period, the onset prediction of the epileptic patient's condition is realized, and when the category belongs to the ictal period, the post-ictal period or the interictal period, the onset detection of the epileptic patient's condition is realized.When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are performed.

[0107] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0108] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0109] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A lightweight four-classification method for epileptic EEG signals, characterized in that: include: Collecting the user's EEG signals; Integrate short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network to build a four-classification model of EEG signals; The method for constructing the four-classification model of the electroencephalogram signal is as follows: obtaining the original electroencephalogram signal, preprocessing the original electroencephalogram signal, marking four categories of electroencephalogram signal states of epileptic patients, wherein the four categories of electroencephalogram signal states of epileptic patients include interictal period, preictal period, ictal period and postictal period, dividing the four categories in the original electroencephalogram signal with a time length t as the slice window length, dividing the original electroencephalogram signal of each category into m data slices, and constructing a data set containing n data samples using the data slices, wherein each data sample contains data slices of four categories; Using short-time Fourier transform to map each data sample to the time-frequency domain, obtaining the time-frequency domain signal of the original EEG signal, and applying the spectrum reconstruction strategy to filter the noise frequency band in the time-frequency domain signal of the original EEG signal, moving the low-frequency part to the central position of the spectrum dimension, and obtaining the optimized feature representation of the time-frequency domain signal of the original EEG signal; the dimensions of the time-frequency domain signal include the spectrum dimension and the time series dimension; Construct a fusion neural network model, including an input layer, a one-dimensional convolutional neural network, a long short-term memory network, a fully connected layer, a softmax activation function, and an output layer; the one-dimensional convolutional neural network is used to perform a convolution operation on the time-frequency domain signal of the optimized original EEG signal in the spectrum dimension to extract the frequency domain features of the original EEG signal; The long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network in the time series dimension, and obtain the time domain features of the frequency domain features of the original EEG signal in the time series; the fully connected layer and the softmax activation function are used to calculate the probability value of the data sample belonging to each category, and the output layer is used to output the classification of the data sample; the fusion neural network model is trained using the data set to construct a trained EEG signal four-classification model; Based on the trained EEG signal four-classification model, the user's EEG signal is taken as input and the probability value of the EEG signal belonging to each category is output; The probability values ​​of the four categories are compared, and the category with the largest probability value is taken as the category to which the EEG signal belongs, and a corresponding alarm is sent according to the category. The category to which the EEG signal belongs is determined to realize the EEG signal four-classification model for the prediction and detection of epileptic seizures. When the category is pre-ictal, the prediction of the epileptic seizure is realized, and when the category is ictal, post-ictal or interictal, the detection of the epileptic seizure is realized.

2. A lightweight four-classification method for epileptic EEG signals as claimed in claim 1, characterized in that: The specific implementation method of the spectrum reconstruction strategy is: set the noise threshold λ, filter the noise frequency band greater than or equal to the noise threshold in the [0, A1Hz] frequency band of the original EEG signal by filtering, retain the [0, A2Hz) part, where A2<λ, crop the [0, A2Hz) part to obtain the [0, A3Hz] part and the (A3Hz, A2Hz) part, and move the [0, A3Hz] part to the central position of the spectrum dimension by translation and splicing.

3. A lightweight four-classification method for epileptic EEG signals as claimed in claim 2, characterized in that: The specific process of taking the user's EEG signal as input and outputting the probability value of the EEG signal belonging to each category based on the trained EEG signal four-classification model is as follows: Input the user's EEG signal into the trained EEG signal four-classification model, divide the EEG signal into a EEG signal segments according to the preset time window length, and use short-time Fourier transform to map each EEG signal segment to the time-frequency domain to obtain a time-frequency domain signal; Apply the spectrum reconstruction strategy, use the translation and re-splicing method to move the low-frequency part of the time-frequency domain signal to the central position of the spectrum dimension, and filter the noise frequency band to obtain the optimized time-frequency domain signal; In the spectrum dimension, a one-dimensional convolutional neural network is used to perform convolution operations on the optimized time-frequency domain signals to extract frequency domain features; In the time series dimension, the long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network to obtain the time domain features of the frequency domain features in the time series; The frequency domain features and time domain features are input into the fully connected layer and the softmax activation function to classify the EEG signal segments and output the probability values ​​of the EEG signal segments belonging to the four categories.

4. A lightweight four-classification method for epileptic EEG signals as claimed in claim 3, characterized in that: The specific method of comparing the probability values ​​of the four categories, taking the category with the largest probability value as the category to which the EEG signal belongs, and sending the corresponding alarm according to the category is: classifying through the fully connected layer and the softmax function, outputting the probability value of the EEG signal segment belonging to each category, comparing the sizes of the four probability values, and taking the category with the largest probability value as the category to which the EEG signal segment belongs; if the category is pre-ictal, the user is warned, and if the category is ictal, post-ictal or interictal, the doctor is notified.

5. A lightweight four-classification system for epilepsy EEG signals, which is implemented based on a lightweight four-classification method for epilepsy EEG signals according to any one of claims 1 to 4, characterized in that: include: A sensor module for collecting the user's EEG signals; A processing unit module is used to integrate short-time Fourier transform, spectrum reconstruction strategy, one-dimensional convolutional neural network and long short-term memory network to construct a four-category model of EEG signals; the method for constructing the four-category model of EEG signals is as follows: obtaining original EEG signals, preprocessing the original EEG signals, marking four categories of EEG signal states of epileptic patients, the four categories of EEG signal states of epileptic patients include interictal period, preictal period, ictal period and postictal period, dividing the original EEG signals into four categories with a time length t as a slice window length, dividing the original EEG signals of each category into m data slices, and using the data slices to construct a data set containing n data samples, each data sample containing data slices of four categories; Using short-time Fourier transform to map each data sample to the time-frequency domain, the time-frequency domain signal of the original EEG signal is obtained, and the spectrum reconstruction strategy is applied to filter the noise frequency band in the time-frequency domain signal of the original EEG signal, and the low-frequency part is moved to the central position of the spectrum dimension to obtain the feature representation of the optimized time-frequency domain signal of the original EEG signal; the dimension of the time-frequency domain signal includes the spectrum dimension and the time series dimension; a fusion neural network model is constructed, including an input layer, a one-dimensional convolutional neural network, a long short-term memory network, a fully connected layer, a softmax activation function and an output layer; the one-dimensional convolutional neural network is used to perform a convolution operation on the optimized time-frequency domain signal of the original EEG signal in the spectrum dimension to extract the frequency domain features of the original EEG signal; The long short-term memory network is used to model the frequency domain features extracted by the one-dimensional convolutional neural network in the time series dimension, and obtain the time domain features of the frequency domain features of the original EEG signal in the time series; the fully connected layer and the softmax activation function are used to calculate the probability value of the data sample belonging to each category, and the output layer is used to output the classification of the data sample; the fusion neural network model is trained using the data set to construct a trained EEG signal four-classification model; The output interface module is used to take the user's EEG signal as input based on the trained EEG signal four-classification model and output the probability value of the EEG signal belonging to each category; The communication module is used to compare the probability values ​​of the four categories, take the category with the largest probability value as the category to which the EEG signal belongs, and send a corresponding alarm according to the category; wherein, the category to which the EEG signal belongs is determined to realize the EEG signal four-classification model for the prediction and detection of epileptic seizures. When the category is pre-ictal, the prediction of the epileptic seizure is realized; when the category is ictal period, post-ictal period or interictal period, the detection of the epileptic seizure is realized.

6. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the lightweight four-classification method of epileptic EEG signals as claimed in any one of claims 1 to 4 are implemented.

7. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps in the lightweight four-classification method for epileptic EEG signals as described in any one of claims 1 to 4.

Images