Method, device and terminal for generating microstate template of EEG signal based on compressed domain

Abstract

The present application is applicable to the field of EEG signal processing technology, and provides a method, device and terminal for generating EEG signal microstate templates based on a compressed domain. The method includes: converting and transforming the EEG signal to obtain a compressed summary consisting of a low-frequency component and a high-frequency component; segmenting the low-frequency component data to form multiple test sequences; band-pass filtering the test sequence and calculating the global field power of each filtered test sequence; searching for the local extreme point of the global field power GFP of each test sequence, forming a new sequence with the test sequence data at the local extreme point position, clustering the new sequence using a clustering algorithm, and generating microstate templates corresponding to various types of users. The embodiment of the present application can not only realize data compression of EEG signals, but also generate microstate templates based on the compressed data, which can reduce the pressure of data storage and transmission, and the generated EEG microstate template can meet the subsequent analysis requirements.

Description

Technical Field

[0001] The present application belongs to the technical field of electroencephalogram (EEG) signal processing, and in particular relates to a method, device, and terminal for generating an EEG signal microstate template based on a compressed domain. Background Art

[0002] Among EEG analysis methods, EEG microstates are defined using the topological structure of multi-channel electrode topography. These microstates reflect transient brain states generated by the synchronized activity of dominant brain networks, making them an important tool for analyzing EEG data. For different populations, EEG data can be clustered to form microstate templates. For example, for people with Alzheimer's disease (AD), mild cognitive impairment (MCI), and healthy individuals, microstate clustering results, or microstate templates, can be calculated for the AD, MCI, and healthy groups, respectively.

[0003] EEG data is a typical example of unstructured streaming data. It is significantly larger than text-based medical data, making efficient processing challenging. Currently, EEG microstate templates are generated based on raw data, which places significant pressure on data storage, transmission, and analysis. Summary of the Invention

[0004] In order to overcome the problems existing in the related art, the embodiments of the present application provide a method, device and terminal for generating an EEG signal microstate template based on a compressed domain.

[0005] This application is achieved through the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for generating an EEG signal microstate template based on a compressed domain, comprising:

[0007] Converting the EEG signal to obtain a compressed summary consisting of low-frequency components and high-frequency components; wherein the EEG signal includes multiple categories, each category of EEG signal corresponding to a category of user;

[0008] Performing data segmentation on the low-frequency component data to form multiple test sequences;

[0009] performing bandpass filtering on the plurality of test sequences and calculating a global field power of each filtered test sequence;

[0010] The local extreme point of the global field power GFP of each test sequence is searched, the test sequence data at the local extreme point position is combined into a new sequence, the new sequence is clustered using a clustering algorithm, and microstate templates corresponding to various types of users are generated.

[0011] In combination with the first aspect, in some embodiments, converting the EEG signal to obtain a compressed summary consisting of a low-frequency component and a high-frequency component includes:

[0012] Step A1: For a given original vector D = {d1, d2, d3, ... d n}, n = 2 t , according to the preset error Δ, each original data is represented as a data interval

[0013] Step A2: Assume that the adjacent interval is and i is an odd number, and the calculation is performed on two adjacent intervals in turn to obtain the updated low-frequency component of the data interval And the conversion coefficient high frequency component b, the updated data interval Stored in the original row vector At , the conversion coefficient b is stored in the original row vector Department, l1 represents the current decomposition level; hour, when When b=0, φ represents the empty set,

[0014] Step A3: the newly generated low-frequency component Perform the calculation in step A1 again to obtain new low-frequency components and high-frequency components;

[0015] Step A4: Calculate step by step until the Lth level is reached, at which point the average value of the endpoints of the data interval is selected as the approximate value of the low-frequency component;

[0016] Step A5: Set the Lth-order low-frequency component to 0.

[0017] In combination with the first aspect, in some embodiments, before segmenting the low-frequency component data, the compressed domain-based EEG signal microstate template generation method further includes:

[0018] By refactoring the model

[0019]

[0020]

[0021] Reconstructing the compressed summary to the L-1th level to obtain reconstructed low-frequency components and high-frequency components;

[0022] in, is the reconstructed data stored at position i in the l2-th level reconstruction component, is the reconstructed data stored at position i+1 in the l2-th level reconstruction component; when l2=1, The compressed summary is stored in The data at; when l2>1, The storage location in the l2-1 level reconstruction component is The data at; when l2=1, The compressed summary is stored in The data at; when l2>1, The storage location in the l2-1 level reconstruction component is Data at l2 represents the current reconstruction level, l2 = 1, 2, ..., L-1, i = 1, 3, 5, ..., m2-1 at each level of reconstruction, and L is the decomposition level.

[0023] In combination with the first aspect, in some embodiments, segmenting the low-frequency component data to form multiple test sequences includes:

[0024] The low-frequency component data is segmented according to a preset duration to form multiple test sequences, each of which is two seconds long.

[0025] In combination with the first aspect, in some embodiments, before bandpass filtering the multiple test sequences, the compressed domain-based EEG signal microstate template generation method further includes:

[0026] Test sequences with electrode voltage amplitudes greater than a threshold value of 100 μV were removed.

[0027] In combination with the first aspect, in some embodiments, calculating the global field power of each filtered test sequence includes:

[0028] pass The global field power of each test sequence after filtering is calculated, where t represents the time point, i represents the electrode position, and v represents the electrode voltage amplitude.

[0029] In conjunction with the first aspect, in some embodiments, clustering the new sequence using a clustering algorithm to generate microstate templates corresponding to various types of users includes:

[0030] The new sequences are clustered using the AAHC clustering algorithm to generate four microstate templates corresponding to each type of user. The four microstate templates are microstate category A, microstate category B, microstate category C, and microstate category D.

[0031] In a second aspect, an embodiment of the present application provides a device for generating an EEG signal microstate template based on a compressed domain, comprising:

[0032] a transformation module, configured to transform the EEG signal to obtain a compressed summary consisting of a low-frequency component and a high-frequency component; wherein the EEG signal includes multiple categories, each category of EEG signal corresponding to a category of user;

[0033] a segmentation module, configured to segment the low-frequency component data to form a plurality of test sequences;

[0034] a filtering calculation module, configured to perform bandpass filtering on the plurality of test sequences and calculate the global field power of each filtered test sequence;

[0035] The generation module is used to search for the local extreme point of the global field power GFP of each test sequence, compose the test sequence data at the position of the local extreme point into a new sequence, cluster the new sequence using a clustering algorithm, and generate microstate templates corresponding to various types of users.

[0036] In a third aspect, an embodiment of the present application provides a terminal comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the method for generating an EEG signal microstate template based on the compressed domain as described in any one of the first aspects.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method for generating an EEG signal microstate template based on the compressed domain as described in any one of the first aspects.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal, the terminal executes the compressed domain-based EEG signal microstate template generation method described in any one of the first aspects above.

[0039] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0040] In the embodiment of the present application, the EEG signal is converted and transformed to obtain a compressed summary consisting of low-frequency components and high-frequency components; the low-frequency component data is segmented to form multiple test sequences; the test sequences are band-pass filtered, and the global field power of each filtered test sequence is calculated; the local extreme point of the global field power GFP of each test sequence is searched, and the test sequence data at the local extreme point position is combined into a new sequence, and the new sequence is clustered using a clustering algorithm to generate microstate templates corresponding to various types of users. The embodiment of the present application can not only realize data compression of EEG signals, but also generate microstate templates based on the compressed data, which can reduce the pressure of data storage and transmission, and the generated EEG microstate templates can meet the subsequent analysis requirements.

[0041] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 1 is a flow chart of a method for generating an EEG signal microstate template based on a compressed domain according to an embodiment of the present application;

[0044] Figure 2 Schematic diagram of the structure of the device for generating microstate templates of EEG signals based on compressed domain provided in an embodiment of the present application;

[0045] Figure 3 It is a schematic diagram of the structure of the terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0047] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0048] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0049] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0050] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0051] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0052] Figure 1 This is a schematic flow chart of a method for generating an EEG signal microstate template based on a compressed domain according to an embodiment of the present application. Figure 1 , the detailed description of the EEG signal microstate template generation method based on the compressed domain is as follows:

[0053] Step 101: convert the EEG signal to obtain a compressed summary consisting of low-frequency components and high-frequency components.

[0054] Among them, the EEG signals may include multiple categories, and each category of EEG signals corresponds to a category of users.

[0055] For example, the EEG signals of people with Alzheimer's disease (AD), mild cognitive impairment (MCI), and normal subjects are transformed to produce compressed summaries consisting of low-frequency and high-frequency components, respectively. Setting an error Δ in the transformation compresses the data while removing high-frequency noise. The number of decomposition levels, L, is determined based on the relationship between baseline drift and the sampling frequency. The low-frequency components of the Lth level are set to zero to remove baseline drift.

[0056] Since the frequency range of EEG signals is mainly within 0.5-35Hz, and baseline drift is a slowly varying signal, the signal frequency is usually less than 1Hz. For EEG signals with a sampling frequency of F, according to the Nyquist sampling theorem, the EEG signal frequency range it contains is 0-F / 2. With each level of conversion and decomposition, the signal frequency of the low-frequency component obtained is halved. When the low-frequency component signal frequency is lower than the baseline drift frequency, that is, 1Hz, this low-frequency component reflects the overview of the baseline drift. Therefore, the low-frequency component at this level can be set to zero to remove the baseline drift. However, there is a certain amount of high-frequency noise in the EEG signal, so it can be removed by setting the error.

[0057] First determine the decomposition level L: When it is established, the minimum value of i is the decomposition level L, and i is an integer greater than or equal to 1. For example, assuming that the EEG signal sampling frequency is 500Hz, when i=8, It holds, so the decomposition level L = 8.

[0058] Based on the above, in step 101, the raw data of each channel of the EEG data is converted. The specific implementation process may include:

[0059] Step A1: For a given original vector D = {d1, d2, d3, ... d n}, n = 2 t , according to the preset error Δ, each original data is represented as a data interval

[0060] In order not to affect the accuracy of subsequent data analysis in the EEG signal, the value range of the preset error Δ can be 0-0.1.

[0061] Step A2: Assume that the adjacent interval is and i is an odd number, and the calculation is performed on two adjacent intervals in turn to obtain the updated low-frequency component of the data interval And the conversion coefficient high frequency component b, the updated data interval Stored in the original row vector At , the conversion coefficient b is stored in the original row vector Department, l1 represents the current decomposition level.

[0062] Among them, when hour, when When b=0, φ represents the empty set,

[0063] Step A3: the newly generated low-frequency component The calculation in step A1 is performed again to obtain new low-frequency components and high-frequency components.

[0064] Step A4: Calculate step by step until the Lth level is reached, at which point the average value of the endpoints of the data interval is selected as the approximate value of the low-frequency component.

[0065] Step A5: Set the Lth-order low-frequency component to 0.

[0066] In order to remove the baseline drift, the Lth-order low-frequency component can be set to 0.

[0067] In some embodiments, before step 102 , the compressed summary obtained in step 101 may be reconstructed so that the amount of data obtained after reconstruction is smaller than the original data, thereby reducing data analysis time.

[0068] Specifically, the above method may further include: reconstructing the model

[0069]

[0070]

[0071] The compressed summary is reconstructed to the L-1th level to obtain reconstructed low-frequency components and high-frequency components.

[0072] in, is the reconstructed data stored at position i in the l2-th level reconstruction component, is the reconstructed data stored at position i+1 in the l2-th level reconstruction component; when l2=1, The compressed summary is stored in The data at; when l2>1, The storage location in the l2-1 level reconstruction component is The data at; when l2=1, The compressed summary is stored in The data at; when l2>1, The storage location in the l2-1 level reconstruction component is Data at l2 represents the current reconstruction level, l2 = 1, 2, ..., L-1, i = 1, 3, 5, ..., m2-1 at each level of reconstruction, and L is the decomposition level.

[0073] In this embodiment, it is only necessary to reconstruct to the L-1th level. At this time, the low-frequency component obtained is half of the original data volume, and the data volume is greatly reduced, thereby reducing the data analysis time.

[0074] Step 102: segment the low-frequency component data to form multiple test sequences.

[0075] For example, the low-frequency component data can be segmented according to a preset duration to form multiple test sequences, each of which lasts from one to two seconds. For example, since each EEG microstate often remains stable within 1 to 2 seconds, the data is segmented into 2-second segments.

[0076] In some embodiments, before step 103, the compressed domain-based EEG signal microstate template generation method may further include removing test sequences with electrode voltage amplitudes greater than a threshold value, where the threshold value is 100 μV. By removing test sequences with electrode voltage amplitudes greater than 100 μV, artifacts such as eye and muscle artifacts can be removed.

[0077] Step 103: band-pass filter the multiple test sequences, and calculate the global field power of each filtered test sequence.

[0078] In this step, the test sequence obtained in step 102 is bandpass filtered. Here, the microstate template is produced by bandpass filtering the data in a specific frequency range. For example, when studying the EEG of patients with Alzheimer's disease, 2Hz-20Hz FIR bandpass filtering is preferred.

[0079] For example, it can be achieved by The global field power of each test sequence after filtering is calculated, where t represents the time point, i represents the electrode position, and v represents the electrode voltage amplitude.

[0080] Step 104 , searching for the local extreme point of the global field power GFP of each test sequence, composing the test sequence data at the local extreme point position into a new sequence, clustering the new sequence using a clustering algorithm, and generating microstate templates corresponding to each type of user.

[0081] Among them, the number of clusters is set to four, and after clustering, each group of people can obtain four EEG microstates A, B, C and D.

[0082] For example, the new sequence can be clustered using the AAHC clustering algorithm to generate four microstate templates corresponding to each type of user. The four microstate templates are microstate category A, microstate category B, microstate category C, and microstate category D.

[0083] For example, the new sequence can be clustered using the K-means clustering algorithm to generate four microstate templates corresponding to each type of user. The four microstate templates are microstate category A, microstate category B, microstate category C, and microstate category D.

[0084] Among them, Microstate Class A was found to be associated with negative BOLD activation in the bilateral superior and middle temporal gyri, which play a key role in speech processing. Microstate Class B was associated with negative BOLD activation in the bilateral extrastriate visual cortex. Microstate Class C was associated with positive BOLD activation in the posterior anterior cingulate gyrus, bilateral inferior frontal gyri, right anterior insula, and left claustrum, which play an extremely important role in executive control function. Microstate Class D was associated with negative BOLD activation in the right dorsal and ventral regions of the frontal and parietal lobes.

[0085] The above-mentioned method for generating microstate templates of EEG signals based on the compression domain converts and transforms the EEG signals to obtain a compressed summary consisting of low-frequency components and high-frequency components. The low-frequency component data is segmented to form multiple test sequences. Afterwards, the test sequence is band-pass filtered, and the global field power of each filtered test sequence is calculated. Next, the local extreme point of the global field power GFP of each test sequence is searched, and the test sequence data at the local extreme point position is combined into a new sequence. The new sequence is clustered using a clustering algorithm to generate microstate templates corresponding to various types of users. The embodiment of the present application can not only realize data compression of EEG signals, but also generate microstate templates based on compressed data, which can reduce the pressure of data storage and transmission, and the generated EEG microstate template can meet subsequent analysis requirements.

[0086] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0087] Corresponding to the method for generating EEG signal microstate template based on compressed domain described in the above embodiment, Figure 2 A structural block diagram of a compressed domain-based EEG signal microstate template generation device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0088] See also Figure 2 The compressed domain-based EEG signal microstate template generation device in the embodiment of the present application may include a transformation module 201, a segmentation module 202, a filtering calculation module 203 and a generation module 204.

[0089] The transformation module 201 is used to transform the EEG signal to obtain a compressed summary consisting of low-frequency components and high-frequency components; wherein the EEG signal includes multiple categories, and each category of EEG signal corresponds to a category of users.

[0090] The segmentation module 202 is used to segment the low-frequency component data to form multiple test sequences.

[0091] The filtering calculation module 203 is configured to perform bandpass filtering on the multiple test sequences and calculate the global field power of each filtered test sequence.

[0092] The generation module 204 is used to search for the local extreme point of the global field power GFP of each test sequence, compose the test sequence data at the local extreme point position into a new sequence, cluster the new sequence using a clustering algorithm, and generate microstate templates corresponding to various types of users.

[0093] Optionally, the transformation module 201 specifically performs the following steps:

[0094] Step A1: For a given original vector D = {d1, d2, d3, ... d n}, n = 2 t , according to the preset error Δ, each original data is represented as a data interval

[0095] Step A2: Assume that the adjacent interval is and i is an odd number, and the calculation is performed on two adjacent intervals in turn to obtain the updated low-frequency component of the data interval And the conversion coefficient high frequency component b, the updated data interval Stored in the original row vector At , the conversion coefficient b is stored in the original row vector Department, l1 represents the current decomposition level; hour, when When b=0, φ represents the empty set,

[0096] Step A3: the newly generated low-frequency component Perform the calculation in step A1 again to obtain new low-frequency components and high-frequency components;

[0097] Step A4: Calculate step by step until the Lth level is reached, at which point the average value of the endpoints of the data interval is selected as the approximate value of the low-frequency component;

[0098] Step A5: Set the Lth-order low-frequency component to 0.

[0099] Optionally, the device for generating an EEG signal microstate template based on the compressed domain further includes a reconstruction module, which is specifically used to:

[0100]

[0101]

[0102] The compression summary is reconstructed to the L-1th level to obtain reconstructed low-frequency components and high-frequency components. Correspondingly, the segmentation module 202 is used to perform data segmentation on the reconstructed low-frequency components to form multiple test sequences.

[0103] in, is the reconstructed data stored at position i in the l2-th level reconstruction component, is the reconstructed data stored at position i+1 in the l2-th level reconstruction component; when l2=1, The compressed summary is stored in The data at; when l2>1, The storage location in the l2-1 level reconstruction component is The data at; when l2=1, The compressed summary is stored in The data at; when l2>1, The storage location in the l2-1 level reconstruction component is Data at l2 represents the current reconstruction level, l2 = 1, 2, ..., L-1, i = 1, 3, 5, ..., m2-1 at each level of reconstruction, and L is the decomposition level.

[0104] Optionally, the segmentation module 202 is specifically configured to segment the low-frequency component data according to a preset duration to form a plurality of test sequences, each of which has a duration of two seconds.

[0105] Optionally, the compressed domain-based EEG signal microstate template generation device may further include a removal module configured to remove test sequences with electrode voltage amplitudes greater than a threshold value of 100 μV. Correspondingly, a filter calculation module 203 is configured to perform bandpass filtering on the multiple test sequences processed by the removal module and calculate the global field power of each filtered test sequence.

[0106] Optionally, the filtering calculation module 203 is specifically used to: The global field power of each test sequence after filtering is calculated, where t represents the time point, i represents the electrode position, and v represents the electrode voltage amplitude.

[0107] Optionally, the generating module 204 is specifically configured to cluster the new sequence using the AAHC clustering algorithm to generate four microstate templates corresponding to each type of user, where the four microstate templates are microstate category A, microstate category B, microstate category C, and microstate category D.

[0108] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0110] The present application also provides a terminal. Figure 3 The terminal 300 may include: at least one processor 310 and a memory 320, wherein the memory 320 stores a computer program that can be run on the at least one processor 310, and when the processor 310 executes the computer program, the steps in any of the above-mentioned method embodiments are implemented, for example Figure 1 Steps 101 to 104 in the embodiment shown. Alternatively, when the processor 310 executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, for example Figure 2 Functions of modules 201 to 204 are shown.

[0111] For example, the computer program may be divided into one or more modules / units, one or more modules / units being stored in the memory 320 and executed by the processor 310 to complete the present application. The one or more modules / units may be a series of computer program segments capable of completing specific functions, and the program segments are used to describe the execution process of the computer program in the terminal 300.

[0112] Those skilled in the art will understand that Figure 3 These are merely examples of terminals and do not constitute a limitation on the terminals. The terminals may include more or fewer components than shown in the figures, or a combination of certain components, or different components, such as input and output devices, network access devices, buses, etc.

[0113] The processor 310 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0114] The memory 320 can be an internal storage unit of the terminal or 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, etc. The memory 320 is used to store the computer program and other programs and data required by the terminal. The memory 320 can also be used to temporarily store data that has been output or is about to be output.

[0115] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified into address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0116] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement the steps in each embodiment of the above-mentioned method for generating an EEG signal microstate template based on the compressed domain.

[0117] An embodiment of the present application provides a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal can implement the steps in each embodiment of the above-mentioned method for generating an EEG signal microstate template based on compression domain.

[0118] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include at least: any entity or device capable of carrying the computer program code to the camera device / terminal, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0119] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0122] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0123] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for generating microstate templates of EEG signals based on compressed domain, characterized in that: include: Converting the EEG signal to obtain a compressed summary consisting of low-frequency components and high-frequency components; wherein the EEG signal includes multiple categories, each category of EEG signal corresponding to a category of user; Performing data segmentation on the low-frequency component data to form multiple test sequences; performing bandpass filtering on the plurality of test sequences and calculating a global field power of each filtered test sequence; Search for the local extreme point of the global field power GFP of each test sequence, compose the test sequence data at the position of the local extreme point into a new sequence, cluster the new sequence using a clustering algorithm, and generate microstate templates corresponding to each type of user; The step of converting the EEG signal to obtain a compressed summary consisting of low-frequency components and high-frequency components includes: Step A1: For a given original vector , , according to the preset error , each original data is represented as a data interval ; Step A2: Assume that the adjacent interval is and , i is an odd number, and the two adjacent intervals are calculated in turn to obtain the updated data interval low-frequency component And the conversion coefficient high frequency component b, the updated data interval Stored in the original row vector At , the conversion coefficient b is stored in the original row vector Department, , Indicates the current decomposition level; when hour, ;when hour, , represents the empty set, ; Step A3: For the newly generated low-frequency component Perform the calculation in step A1 again to obtain new low-frequency components and high-frequency components; Step A4: Calculate step by step until the Lth level is reached, at which point the average value of the endpoints of the data interval is selected as the approximate value of the low-frequency component; Step A5: Set the Lth-order low-frequency component to 0.

2. The method for generating EEG signal microstate templates based on compressed domain according to claim 1, wherein: Before segmenting the low-frequency component data, the compressed domain-based EEG signal microstate template generation method further includes: By refactoring the model The compression summary is reconstructed to the L -1 level obtains the reconstructed low-frequency and high-frequency components; in, For the l The storage location in the 2nd level reconstruction component is i The reconstructed data, For the l The storage location in the 2nd level reconstruction component is i +1 reconstructed data; when l When 2=1, The compressed summary is stored in The data at l When 2>1, For the l The storage location in the 2-1 level reconstruction component is The data at l When 2=1, The compressed summary is stored in The data at l When 2>1, For the l The storage location in the 2-1 level reconstruction component is Data at , l 2 represents the current reconstruction level, l 2=1,2,..., L-1 , each level of reconstruction i =1,3,5,..., m 2-1, L is the decomposition series.

3. The method for generating EEG signal microstate templates based on compressed domain according to claim 1, characterized in that: The step of segmenting the low-frequency component data to form a plurality of test sequences includes: The low-frequency component data is segmented according to a preset duration to form multiple test sequences, and the duration of each test sequence is one to two seconds.

4. The method for generating an EEG signal microstate template based on a compressed domain according to claim 1, wherein: Before performing bandpass filtering on the multiple test sequences, the compressed domain-based EEG signal microstate template generation method further includes: Test sequences with electrode voltage amplitudes greater than a threshold value of 100 μV were removed.

5. The method for generating EEG signal microstate templates based on compressed domain according to claim 1, characterized in that: The calculating of the global field power of each filtered test sequence comprises: pass Calculate the global field power for each test sequence after filtering, t Represents a moment in time, i represents the electrode position, Represents the electrode voltage amplitude.

6. The method for generating EEG signal microstate templates based on compressed domain according to claim 1, characterized in that: The new sequence is clustered using a clustering algorithm to generate microstate templates corresponding to various types of users, including: The new sequences are clustered using the AAHC clustering algorithm to generate four microstate templates corresponding to each type of user. The four microstate templates are microstate category A, microstate category B, microstate category C, and microstate category D.

7. A device for generating microstate templates of EEG signals based on compressed domain, characterized in that: include: a transformation module, configured to transform the EEG signal to obtain a compressed summary consisting of a low-frequency component and a high-frequency component; wherein the EEG signal includes multiple categories, each category of EEG signal corresponding to a category of user; a segmentation module, configured to segment the low-frequency component data to form a plurality of test sequences; a filtering calculation module, configured to perform bandpass filtering on the plurality of test sequences and calculate the global field power of each filtered test sequence; A generation module is used to search for the local extreme point of the global field power GFP of each test sequence, compose the test sequence data at the position of the local extreme point into a new sequence, cluster the new sequence using a clustering algorithm, and generate microstate templates corresponding to each type of user; The transformation module specifically performs the following steps: Step A1: For a given original vector , , according to the preset error , each original data is represented as a data interval ; Step A2: Assume that the adjacent interval is and , i is an odd number, and the two adjacent intervals are calculated in turn to obtain the updated data interval low-frequency component And the conversion coefficient high frequency component b, the updated data interval Stored in the original row vector At , the conversion coefficient b is stored in the original row vector Department, , Indicates the current decomposition level; when hour, ;when hour, , represents the empty set, ; Step A3: For the newly generated low-frequency component Perform the calculation in step A1 again to obtain new low-frequency components and high-frequency components; Step A4: Calculate step by step until the Lth level is reached, at which point the average value of the endpoints of the data interval is selected as the approximate value of the low-frequency component; Step A5: Set the Lth-order low-frequency component to 0.

8. A terminal comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images