Energy decoding method, system, device and program for electroencephalogram signal classification

Abstract

The invention discloses an energy decoding method, system, device and program for electroencephalogram signal classification. The method comprises the steps that electroencephalogram signals are divided into signals of five frequency bands; constructing a sub-network matrix of electroencephalogram signals under the same frequency band; constructing a sub-network matrix of the electroencephalogram signals under the cross-band; splicing the sub-network matrix of the electroencephalogram signals under the same frequency band and the sub-network matrix of the electroencephalogram signals under the cross-frequency band into a multi-layer brain network matrix; constructing a primary function of the multilayer brain network matrix; splicing the signals of the five frequency bands into a new electroencephalogram signal along the vertical direction; performing cross projection and splicing on the primary function and the new electroencephalogram signal; and expanding energy differences and features under different tasks by using a common spatial pattern algorithm, and performing classification. Through the processing scheme disclosed by the invention, local and global energy change characteristics of the brain can be captured, and classification of the motor imagery electroencephalogram signals can be effectively realized.

Description

Technical Field

[0001] The present invention relates to the technical field of electroencephalogram (EEG) signal feature extraction, and in particular to an energy decoding method, system, device and program for EEG signal classification. Background Art

[0002] Brain-computer interface technology is an emerging technology that collects brain electrophysiological signals to convey user status and control intentions. The key step of this technology is to efficiently and stably identify the collected EEG signals to accurately "translate" the user's exact thoughts and achieve the purpose of communicating with the outside world. Among them, motion-related brain-computer interfaces are the most widely used. This type of system can allow users to control external devices to assist in the grasping of objects in daily life, and assist patients with movement disorders in limb rehabilitation.

[0003] At present, the signals of the brain-computer interface related to movement are mainly generated through motor imagery, which has weak characteristics and is not easy to identify. Moreover, motor imagery is different from actual movement and is a kind of mental rehearsal activity. In addition to motor-related EEG signals, this activity also involves cognition-related EEG signals. Therefore, extracting the signal of a single frequency band or a single brain area alone cannot effectively and comprehensively represent the user's movement intention during motor imagery.

[0004] It can be seen that the above existing EEG signal extraction methods still have inconveniences and defects in use, and are in urgent need of further improvement. How to create a new energy decoding method for EEG signal classification has become a goal that the industry urgently needs to improve. Summary of the invention

[0005] In view of this, an embodiment of the present disclosure provides an energy decoding method for EEG signal classification, which at least partially solves the problems existing in the prior art.

[0006] In a first aspect, an embodiment of the present disclosure provides an energy decoding method for EEG signal classification, the method comprising the following steps:

[0007] The EEG signal is divided into five frequency bands;

[0008] Construct a sub-network matrix of EEG signals in the same frequency band;

[0009] Construct a sub-network matrix of EEG signals across frequency bands;

[0010] splicing the sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band into a multi-layer brain network matrix;

[0011] constructing basis functions of the multi-layer brain network matrix;

[0012] splicing the signals of the five frequency bands into a new EEG signal in a vertical direction;

[0013] Cross-projecting and splicing the basis function and the new EEG signal;

[0014] The common space pattern algorithm is used to expand the energy differences and features under different tasks and classify them.

[0015] According to a specific implementation of the embodiment of the present disclosure, dividing the EEG signal into five frequency bands includes:

[0016] The preprocessed motor imagery EEG signals of different movement types were filtered through a fourth-order Butterworth filter to obtain signals in five different frequency bands: δ, θ, α, β, and γ.

[0017] According to a specific implementation of the embodiment of the present disclosure, a sub-network matrix of EEG signals in the same frequency band is constructed based on the following formula, including:

[0018]

[0019]

[0020] in, is the analytical signal of the mth single channel at frequency f; is the mth single-channel signal at frequency f; HT[.] represents Hilbert transform; is the instantaneous amplitude of the mth single-channel signal at frequency f; φ f (t) is the instantaneous phase at frequency f; is the analytical signal of the nth single channel at frequency f; is the nth single-channel signal at frequency f; is the instantaneous amplitude of the nth single-channel signal at frequency f; f is any one of the five different frequency bands of δ, θ, α, β, and γ;

[0021] The instantaneous amplitude envelope coefficient ρ of two signals at the same frequency is calculated based on the following formula:

[0022]

[0023] Among them, 0<ρ<1; is the amplitude envelope correlation coefficient of channel m and channel n at frequency f;

[0024] Based on the coefficient values ​​between different channels in the same frequency band, and arranged in sequence according to the channel order, the matrix format is the number of channels * the number of channels, and u is obtained. δ 、u θ 、u α 、u β 、uγ The matrix of five sub-networks in the same frequency band.

[0025] According to a specific implementation of the embodiment of the present disclosure, a sub-network matrix of cross-band EEG signals is constructed based on the following formula, including:

[0026]

[0027]

[0028] in, is the analytical signal of the mth single channel at frequency f1; is the mth single-channel signal at frequency f1; HT[.] represents Hilbert transform; is the instantaneous amplitude of the mth single-channel signal at frequency f1; is the instantaneous phase at frequency f1; is the analytical signal of the nth single channel at frequency f2; is the nth single-channel signal at frequency f2; is the instantaneous amplitude of the nth single-channel signal at frequency f2; is the instantaneous phase at frequency f2;

[0029] The results of calculating the amplitude-amplitude coupling using the Pearson correlation coefficient are obtained based on the following formula:

[0030]

[0031] in, is the amplitude-amplitude coupling correlation coefficient of channel m at frequency f1 and channel n at frequency f2; corr(.) is the formula for calculating the Pearson correlation coefficient; f1 and f2 are any of the five different frequency bands of δ, θ, α, β, and γ;

[0032] Based on the coefficient values ​​between different channels in the same frequency band, and arranged in sequence according to the channel order, the matrix format is the number of channels * the number of channels, and v is obtained. δ-α 、v δ-β 、v δ-γ 、v θ-α 、v θ-β 、v θ-γ 、v α-β 、v α-γ 、v β-γ Ten sub-network matrices across frequencies.

[0033] According to a specific implementation of the embodiment of the present disclosure, the sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band are spliced ​​into a multi-layer brain network matrix:

[0034]

[0035] Among them, Z is a multi-layer brain network matrix.

[0036] According to a specific implementation of the embodiment of the present disclosure, cross-projecting and splicing the basis function and the new EEG signal include:

[0037] The basis functions of the multi-layer brain network matrix are constructed using the graph Laplace method:

[0038] L=DZ

[0039] Where D is the degree matrix and L is the Laplace matrix;

[0040] The basis function and the new EEG signal are cross-projected and spliced ​​based on the following formula:

[0041]

[0042] in, It is the energy signal of the signal type 1 after cross-projection and concatenation of different basis functions; is the basis function of signal type 1; The new EEG signal is formed by sequentially splicing the signal of signal type 1 according to the five frequency bands of δ, θ, α, β, and γ; It is the energy signal of the signal type 2 after cross-projection and concatenation of different basis functions; is the basis function of signal type 2; It is a new EEG signal formed by sequentially splicing the signal of signal type 2 according to the five frequency bands of δ, θ, α, β, and γ.

[0043] In a second aspect, an embodiment of the present disclosure provides an energy decoding system for EEG signal classification, the system comprising:

[0044] A filtering module configured to separate the EEG signal into signals of five frequency bands;

[0045] A building module, configured to build a sub-network matrix of EEG signals in the same frequency band;

[0046] Construct a sub-network matrix of EEG signals across frequency bands;

[0047] splicing the sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band into a multi-layer brain network matrix;

[0048] constructing basis functions of the multi-layer brain network matrix;

[0049] splicing the signals of the five frequency bands into a new EEG signal in a vertical direction;

[0050] A splicing module, configured to cross-project and splice the basis function and the new EEG signal;

[0051] The classification module is configured to utilize the common spatial pattern algorithm to expand the energy differences and features under different tasks and perform classification.

[0052] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0053] at least one processor; and,

[0054] a memory communicatively connected to the at least one processor; wherein,

[0055] The memory stores instructions that can be executed by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor implements the energy decoding method for EEG signal classification as described in any one of the first aspect or any one of the implementations of the first aspect.

[0056] In a fourth aspect, an embodiment of the present disclosure further provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions, and when the program instructions are executed by a computer, the computer executes the energy decoding method for EEG signal classification in the aforementioned first aspect or any implementation of the first aspect.

[0057] The energy decoding method for EEG signal classification in the disclosed embodiment can capture the local and global energy change characteristics of the brain by combining the multi-layer network features with the graph signal processing method, and can effectively realize the classification of motor imagery EEG signals. It can extract the change characteristics of brain information in different frequency bands and different brain regions to more comprehensively, fully and effectively identify user intentions and improve the utilization efficiency of the brain-computer interface system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The above is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0059] Figure 1 A schematic diagram of a flow chart of an energy decoding method for EEG signal classification provided in an embodiment of the present disclosure;

[0060] Figure 2 A schematic diagram of the structure of an energy decoding system for EEG signal classification provided by an embodiment of the present disclosure;

[0061] Figure 3A schematic diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0062] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0063] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0064] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement a device and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0065] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0066] An embodiment of the present invention provides an energy decoding method for EEG signal classification. For motor imagery EEG signals, in order to address the problems of low recognition accuracy and poor stability, the same-band and cross-band sub-network matrices are constructed by extracting the envelope correlation of the same-band and cross-band signals. The multi-layer brain network matrix constructed by the sub-network is used to effectively capture the rich local and global energy information of the brain. The energy matrix is ​​projected into a complex energy domain using the graph Laplace method. Finally, the common space pattern method is used to further amplify the energy differences under different tasks and classify them, thereby improving the classification accuracy of the motor imagery signal pattern.

[0067] Figure 1A schematic diagram of the energy decoding method flow for EEG signal classification provided in an embodiment of the present disclosure.

[0068] like Figure 1 As shown, at step S110, the EEG signal is divided into signals of five frequency bands.

[0069] In an embodiment of the present invention, dividing the EEG signal into five frequency bands includes: filtering the pre-processed motor imagery EEG signals of different movement types through a fourth-order Butterworth filter to obtain signals in five different frequency bands of δ, θ, α, β, and γ.

[0070] More specifically, the pre-processed motor imagery EEG signals of different movement types, such as X1 and X2, are filtered through a fourth-order Butterworth filter to obtain signals of five different frequency bands: δ (delta), θ (theta), α (alpha), β (beta), and γ (gamma).

[0071] More specifically, the process proceeds to step S120.

[0072] In step S120, a sub-network matrix of EEG signals in the same frequency band is constructed.

[0073] In an embodiment of the present invention, a sub-network matrix of EEG signals in the same frequency band is constructed based on the following formula, including:

[0074]

[0075]

[0076] in, is the analytical signal of the mth single channel at frequency f; is the mth single-channel signal at frequency f; HT[.] represents Hilbert transform; is the instantaneous amplitude of the mth single-channel signal at frequency f; φ f (t) is the instantaneous phase at frequency f; is the analytical signal of the nth single channel at frequency f; is the nth single-channel signal at frequency f; is the instantaneous amplitude of the nth single-channel signal at frequency f; f is any one of the five different frequency bands of δ, θ, α, β, and γ;

[0077] The instantaneous amplitude envelope coefficient ρ of two signals at the same frequency is calculated based on the following formula:

[0078]

[0079] Among them, 0<ρ<1; is the amplitude envelope correlation coefficient of channel m and channel n at frequency f;

[0080] Based on the coefficient values ​​between different channels in the same frequency band, and arranged in sequence according to the channel order, the matrix format is the number of channels * the number of channels, and u is obtained. δ 、u θ 、u α 、u β 、u γ The matrix of five sub-networks in the same frequency band.

[0081] More specifically, Hilbert transform is used to extract EEG signal envelope information, and the Pearson correlation coefficient method is used to solve the correlation coefficient between different electrodes of EEG signals to construct a network matrix, and the matrix dimension is the number of electrodes * the number of electrodes. The above frequency f can represent any of the five different frequency bands of δ, θ, α, β, and γ. This method can be used to obtain the correlation coefficient values ​​between different channels in the same frequency band and arrange them in sequence according to the channel order to obtain the correlation coefficient sub-network matrix u f , the matrix format is the number of channels * the number of channels, and so on to get u δ 、u θ 、u α 、u β 、u γ The matrix of five sub-networks in the same frequency band.

[0082] Different from the EEG signal under cross-frequency, the single-channel signal of the same frequency band of multi-channel EEG signal after filtering can be expressed as and The signal obtained after Hilbert transform is shown as follows:

[0083]

[0084]

[0085] Then the correlation coefficient ρ of the instantaneous amplitude / envelope of two signals at the same frequency can be obtained by the following formula:

[0086]

[0087] The same result as the cross-frequency coupling is obtained, and the value of the amplitude envelope coefficient is also between 0 and 1. This method can be used to obtain u δ 、u θ 、u α 、u β 、u γ The matrix of five sub-networks in the same frequency band.

[0088] Next, go to step S130.

[0089] In step S130, a sub-network matrix of cross-band EEG signals is constructed.

[0090] In an embodiment of the present invention, a sub-network matrix of cross-band EEG signals is constructed based on the following formula, including:

[0091]

[0092]

[0093] in, is the analytical signal of the mth single channel at frequency f1; is the mth single-channel signal at frequency f1; HT[.] represents Hilbert transform; is the instantaneous amplitude of the mth single-channel signal at frequency f1; is the instantaneous phase at frequency f1; is the analytical signal of the nth single channel at frequency f2; is the nth single-channel signal at frequency f2; is the instantaneous amplitude of the nth single-channel signal at frequency f2; is the instantaneous phase at frequency f2;

[0094] The results of calculating the amplitude-amplitude coupling using the Pearson correlation coefficient are obtained based on the following formula:

[0095]

[0096] in, is the amplitude-amplitude coupling correlation coefficient of channel m at frequency f1 and channel n at frequency f2; corr(.) is the formula for calculating the Pearson correlation coefficient; f1 and f2 are any of the five different frequency bands of δ, θ, α, β, and γ;

[0097] Based on the coefficient values ​​between different channels in the same frequency band, and arranged in sequence according to the channel order, the matrix format is the number of channels * the number of channels, and v is obtained. δ-α 、v δ-β 、v δ-γ 、v θ-α 、v θ-β 、v θ-γ 、v α-β 、v α-γ 、v β-γ Ten sub-network matrices across frequencies.

[0098] More specifically, the amplitude-amplitude coupling method in cross-frequency coupling is used to solve the correlation coefficient between different electrodes of cross-frequency EEG signals to construct a network matrix, and the matrix dimension is the number of electrodes*the number of electrodes.

[0099] For each filtered single-channel signal in different frequency bands of the multi-channel EEG signal, it can be expressed as and The filtered signal is transformed using Hilber transform and After transformation, we can obtain the following formula:

[0100]

[0101]

[0102] Among them, A(t) and φ(t) represent the instantaneous amplitude / envelope and instantaneous phase of the signal.

[0103] According to the instantaneous envelope of different signals, the Pearson correlation coefficient can be used to calculate the result of amplitude-amplitude coupling. The specific formula is as follows:

[0104]

[0105] Where corr(.) is the formula for calculating the Pearson correlation coefficient, the absolute value ρ is between 0 and 1, and also represents the value of the amplitude-amplitude coupling.

[0106] The above frequencies f1 and f2 can represent any one of the five different frequency bands of δ, θ, α, β, and γ. This method can be used to obtain the correlation coefficient values ​​between different channels in different frequency bands and arrange them in sequence according to the channel order to obtain the correlation coefficient subnetwork matrix The matrix format is the number of channels * the number of channels, and so on to get v δ-θ 、v δ-α 、v δ-β 、v δ-γ 、v θ-α 、v θ-β 、v θ-γ 、v α-β 、v α-γ 、v β-γ Ten sub-network matrices across frequencies.

[0107] Next, go to step S140.

[0108] In step S140, the sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band are spliced ​​into a multi-layer brain network matrix.

[0109] In an embodiment of the present invention, the sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band are spliced ​​into a multi-layer brain network matrix:

[0110]

[0111] Among them, Z is a multi-layer brain network matrix.

[0112] Next, go to step S150.

[0113] In step S150, the basis functions of the multi-layer brain network matrix are constructed.

[0114] Next, go to step S160.

[0115] In step S160, the signals of the five frequency bands are spliced ​​vertically into a new EEG signal.

[0116] Next, go to step S170.

[0117] In step S170, the basis function and the new EEG signal are cross-projected and spliced.

[0118] In an embodiment of the present invention, cross-projecting and splicing the basis function and the new EEG signal includes:

[0119] The basis functions of the multi-layer brain network matrix are constructed using the graph Laplace method:

[0120] L=DZ

[0121] Where D is the degree matrix and L is the Laplace matrix;

[0122] The basis function and the new EEG signal are cross-projected and spliced ​​based on the following formula:

[0123]

[0124] in, It is the energy signal of the signal type 1 after cross-projection and concatenation of different basis functions; is the basis function of signal type 1; The new EEG signal is formed by sequentially splicing the signal of signal type 1 according to the five frequency bands of δ, θ, α, β, and γ; It is the energy signal of the signal type 2 after cross-projection and concatenation of different basis functions; is the basis function of signal type 2; It is a new EEG signal formed by sequentially splicing the signal of signal type 2 according to the five frequency bands of δ, θ, α, β, and γ.

[0125] More specifically, the graph Laplace method is used to construct the multi-layer brain network matrix basis functions under different tasks, and the basis functions of all trials obtained after the solution are superimposed and averaged to obtain the final template. The EEG signals filtered according to the frequency band range are spliced ​​vertically into new EEG signals A two-dimensional matrix with the dimension of (number of frequency bands * number of electrodes) * time points. Cross-project and splice the EEG signal with the basis function to obtain a new signal containing complex energy.

[0126] The graph Laplace method is used to construct the matrix basis functions of multi-layer brain networks under different tasks. This method can transform matrix signals into complex energy domain signals, as shown in formula (8):

[0127] L=DZ (8)

[0128] Where D is the degree matrix and L is the Laplace matrix. This method can be used to obtain basis functions for different types of motion tasks. The basis functions calculated from all trials are superimposed and averaged to obtain a stable basis function template with representative characteristics for the corresponding task.

[0129] The EEG signal filtered according to the frequency band range Splice vertically to form a new EEG signal A two-dimensional matrix with dimensions (number of frequency bands * number of electrodes) * time points.

[0130] The reassembled EEG signal is cross-projected and spliced ​​with the basis function to obtain a new signal containing complex energy.

[0131] After the above steps, the EEG signal in a single frequency band can be expanded to multiple frequency bands, and the brain network can be used to capture the energy changes between different levels.

[0132] Next, go to step S180.

[0133] In step S180, the energy differences and features under different tasks are enlarged and classified using a common space pattern algorithm.

[0134] More specifically, the co-spatial pattern algorithm is a widely used method for extracting features of motor imagery EEG signals, which constructs a variance matrix to expand the differences between different types of signals. Difference amplification is performed and the obtained features are sent to the classifier for classification and recognition.

[0135] Decoding of EEG signals based on motor imagery is an important link in rehabilitation brain-computer interface systems or sports brain-computer interface systems. The decoding accuracy and stability will directly affect the performance of the system. The method proposed in the present invention can effectively extract the local and global performance of motor imagery signals, is highly sensitive to changes in brain energy during motor imagery, can be effectively applied to sports-related brain-computer interface systems, and has reliable and practical application value for controlling external devices and medical rehabilitation.

[0136] Figure 2 The energy decoding system 200 for EEG signal classification provided by the present invention includes a filtering module 210 , a building module 220 , a splicing module 230 and a classification module 240 .

[0137] The filtering module 210 is used to divide the EEG signal into signals of five frequency bands;

[0138] The construction module 220 is used to construct a sub-network matrix of EEG signals in the same frequency band;

[0139] Construct a sub-network matrix of EEG signals across frequency bands;

[0140] splicing the sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band into a multi-layer brain network matrix;

[0141] constructing basis functions of the multi-layer brain network matrix;

[0142] splicing the signals of the five frequency bands into a new EEG signal in a vertical direction;

[0143] The splicing module 230 is used to cross-project and splice the basis function and the new EEG signal;

[0144] The classification module 240 is used to utilize the common space pattern algorithm to expand the energy differences and features under different tasks and perform classification.

[0145] See also Figure 3 The embodiment of the present disclosure further provides an electronic device 30, the electronic device comprising:

[0146] at least one processor; and,

[0147] a memory communicatively connected to the at least one processor; wherein,

[0148] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the energy decoding method for EEG signal classification in the aforementioned method embodiment.

[0149] The disclosed embodiment also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the energy decoding method for EEG signal classification in the aforementioned method embodiment.

[0150] The embodiments of the present disclosure also provide a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the energy decoding method for EEG signal classification in the aforementioned method embodiment.

[0151] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 30 suitable for implementing the embodiment of the present disclosure. The electronic device in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0152] like Figure 3 As shown, the electronic device 30 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 30 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0153] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication device 309 may allow the electronic device 30 to communicate with other devices wirelessly or by wire to exchange data. Although the electronic device 30 with various devices is shown in the figure, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0154] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0155] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0156] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0157] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains at least two Internet Protocol addresses; sends a node evaluation request including the at least two Internet Protocol addresses to a node evaluation device, wherein the node evaluation device selects an Internet Protocol address from the at least two Internet Protocol addresses and returns it; receives the Internet Protocol address returned by the node evaluation device; wherein the obtained Internet Protocol address indicates an edge node in a content distribution network.

[0158] Alternatively, the computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; selects an Internet Protocol address from the at least two Internet Protocol addresses; and returns the selected Internet Protocol address; wherein the received Internet Protocol address indicates an edge node in a content distribution network.

[0159] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0160] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0161] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0162] It should be understood that various parts of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof.

[0163] The above is only a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. An energy decoding method for EEG signal classification, characterized in that: The method comprises the following steps: The EEG signal is divided into five frequency bands; Construct a sub-network matrix of EEG signals in the same frequency band; Construct a sub-network matrix of EEG signals across frequency bands; splicing the sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band into a multi-layer brain network matrix; constructing basis functions of the multi-layer brain network matrix; splicing the signals of the five frequency bands into a new EEG signal in a vertical direction; Cross-projecting and splicing the basis function and the new EEG signal; The common space pattern algorithm is used to expand the energy differences and features under different tasks and classify them.

2. The energy decoding method for EEG signal classification according to claim 1, characterized in that: The EEG signal is divided into five frequency bands, including: The preprocessed motor imagery EEG signals of different movement types were filtered through a fourth-order Butterworth filter to obtain signals in five different frequency bands: δ, θ, α, β, and γ.

3. The energy decoding method for EEG signal classification according to claim 1, characterized in that: The sub-network matrix of EEG signals in the same frequency band is constructed based on the following formula, including: in, is the analytical signal of the mth single channel at frequency f; is the mth single-channel signal at frequency f; HT[.] represents Hilbert transform; is the instantaneous amplitude of the mth single-channel signal at frequency f; φ f (t) is the instantaneous phase at frequency f; is the analytical signal of the nth single channel at frequency f; is the nth single-channel signal at frequency f; is the instantaneous amplitude of the nth single-channel signal at frequency f; f is any one of the five different frequency bands of δ, θ, α, β, and γ; The instantaneous amplitude envelope coefficient ρ of two signals at the same frequency is calculated based on the following formula: Among them, 0<ρ<1; is the amplitude envelope correlation coefficient of channel m and channel n at frequency f; Based on the coefficient values ​​between different channels in the same frequency band, and arranged in sequence according to the channel order, the matrix format is the number of channels * the number of channels, and u is obtained. δ 、u θ 、u α 、u β 、u γ The matrix of five sub-networks in the same frequency band.

4. The energy decoding method for EEG signal classification according to claim 1, characterized in that: The sub-network matrix of EEG signals across frequency bands is constructed based on the following formula, including: in, is the analytical signal of the mth single channel at frequency f1; is the mth single-channel signal at frequency f1; HT[.] represents Hilbert transform; is the instantaneous amplitude of the mth single-channel signal at frequency f1; is the instantaneous phase at frequency f1; is the analytical signal of the nth single channel at frequency f2; is the nth single-channel signal at frequency f2; is the instantaneous amplitude of the nth single-channel signal at frequency f2; φ f2 (t) is the instantaneous phase at frequency f2; The results of calculating the amplitude-amplitude coupling using the Pearson correlation coefficient are obtained based on the following formula: in, is the amplitude-amplitude coupling correlation coefficient of channel m at frequency f1 and channel n at frequency f2; corr(.) is the formula for calculating the Pearson correlation coefficient; f1 and f2 are any of the five different frequency bands of δ, θ, α, β, and γ; Based on the coefficient values ​​between different channels in the same frequency band, and arranged in sequence according to the channel order, the matrix format is the number of channels * the number of channels, and v is obtained. δ-θ 、v δ-α 、v δ-β 、v δ-γ 、v θ-α 、v θ-β 、v θ-γ 、v α-β 、v α-γ 、v β-γ Ten sub-network matrices across frequencies.

5. The energy decoding method for EEG signal classification according to claim 1, characterized in that: The sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band are spliced ​​into a multi-layer brain network matrix: Among them, Z is a multi-layer brain network matrix.

6. The energy decoding method for EEG signal classification according to claim 1, characterized in that: Cross-projecting and splicing the basis function and the new EEG signal include: The basis functions of the multi-layer brain network matrix are constructed using the graph Laplace method: L=DZ Where D is the degree matrix and L is the Laplace matrix; The basis function and the new EEG signal are cross-projected and spliced ​​based on the following formula: in, It is the energy signal of the signal type 1 after cross-projection and concatenation of different basis functions; is the basis function of signal type 1; The new EEG signal is formed by sequentially splicing the signal of signal type 1 according to the five frequency bands of δ, θ, α, β, and γ; It is the energy signal of the signal type 2 after cross-projection and concatenation of different basis functions; is the basis function of signal type 2; It is a new EEG signal formed by sequentially splicing the signal of signal type 2 according to the five frequency bands of δ, θ, α, β, and γ.

7. An energy decoding system for EEG signal classification, characterized in that: The system comprises: A filtering module configured to separate the EEG signal into signals of five frequency bands; A building module, configured to build a sub-network matrix of EEG signals in the same frequency band; Construct a sub-network matrix of EEG signals across frequency bands; splicing the sub-network matrix of the EEG signal in the same frequency band and the sub-network matrix of the EEG signal in the cross-frequency band into a multi-layer brain network matrix; constructing basis functions of the multi-layer brain network matrix; splicing the signals of the five frequency bands into a new EEG signal in a vertical direction; A splicing module, configured to cross-project and splice the basis function and the new EEG signal; The classification module is configured to utilize the common spatial pattern algorithm to expand the energy differences and features under different tasks and perform classification.

8. An electronic device, characterized in that: The electronic device includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor executes the energy decoding method for EEG signal classification as described in any one of claims 1 to 6.

9. A computer program product, characterized in that The computer program product comprises a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions, which, when executed by a computer, cause the computer to execute the energy decoding method for EEG signal classification as described in any one of claims 1 to 6.

Images