Multi-channel electroencephalogram signal fusion method and system, storage medium and terminal

Abstract

The invention provides a multi-channel electroencephalogram signal fusion method and system, a storage medium and a terminal.The method comprises the following steps that when electroencephalogram signals are collected, the contact impedance between an electrode on each channel and the skin is obtained; obtaining an effective signal-to-noise ratio of each channel based on the contact impedance; generating a fusion weight of each channel based on the effective signal-to-noise ratio; and based on the fusion weight, realizing the fusion of the electroencephalogram signals on each channel. According to the multi-channel electroencephalogram signal fusion method and system, the storage medium and the terminal, multi-channel electroencephalogram signal fusion is achieved based on electrode contact impedance self-adaptive adjustment, and the signal accuracy is effectively improved.

Description

Technical Field

[0001] This invention relates to the technical field of brain-computer interface (BCI) signal processing, and in particular to a multi-channel EEG signal fusion method, system, storage medium, and terminal. Background Technology

[0002] Brain-computer interface systems rely on multichannel electroencephalograms (EEGs) acquired from the scalp to decode a user's intentions or cognitive states. To improve system performance, researchers commonly employ multichannel fusion strategies, weighting and combining signals from different electrode locations to enhance target neural responses and suppress noise interference.

[0003] In existing technologies, typical fusion algorithms include: Canonical Correlation Analysis (CCA), Filter Bank Canonical Correlation Analysis (FBCCA), Task-Related Component Analysis (TRCA), and its extended form eTRCA, all used for Steady-State Visual Evoked Potential (SSVEP) identification. These methods typically assume that all channels have similar signal-to-noise ratios (SNR) and employ fixed weights (such as equal-weighted averaging) or static weights learned from offline training data for fusion.

[0004] However, in real-world online applications, EEG signal quality is highly dependent on the physical contact between the electrodes and the scalp. Poor contact (such as hair obstruction, insufficient perspiration, or loose electrodes) leads to increased local contact impedance, introducing additional thermal noise, power frequency interference, and signal attenuation, significantly reducing the effective signal-to-noise ratio of that channel. Assigning the same fusion weight to this high-impedance channel as to other low-impedance channels not only fails to improve overall performance but also introduces noise pollution, resulting in decreased classification accuracy or even system failure.

[0005] Some studies have attempted to screen for "good channels" offline or manually eliminate high-impedance electrodes, but these methods cannot handle dynamic impedance changes caused by user movement, sweating, or prolonged wear during online use. Furthermore, while some commercial EEG devices possess impedance detection capabilities (such as Neuroscan, Brainstorm, and OpenBCI), their results are only used to prompt users to adjust electrodes and have not yet been effectively integrated into real-time signal processing as a basis for adaptive fusion.

[0006] Therefore, the existing multi-channel EEG signal fusion technology has the following key drawbacks:

[0007] (1) The fusion weights are static and cannot be dynamically adjusted according to the channel quality;

[0008] (2) The impedance-signal-noise ratio correlation is ignored and no quantitative mapping between contact impedance and channel contribution is established;

[0009] (3) The lack of a closed-loop feedback mechanism means that impedance information is not involved in online decoding decisions, resulting in wasted resources and performance loss. Summary of the Invention

[0010] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a multi-channel EEG signal fusion method, system, storage medium and terminal, which realizes multi-channel EEG signal fusion based on adaptive adjustment of electrode contact impedance, effectively improving signal accuracy.

[0011] In a first aspect, the present invention provides a method for fusing multi-channel electroencephalogram (EEG) signals, the method comprising the following steps: when acquiring EEG signals, obtaining the contact impedance between the electrodes and the skin on each channel; obtaining the effective signal-to-noise ratio (SNR) of each channel based on the contact impedance; generating a fusion weight for each channel based on the effective SNR; and realizing the fusion of EEG signals on each channel based on the fusion weight.

[0012] In one implementation of the first aspect, obtaining the effective signal-to-noise ratio of each channel based on the contact impedance includes the following steps:

[0013] Construct a mapping function from contact impedance to effective signal-to-noise ratio;

[0014] The effective signal-to-noise ratio corresponding to the contact impedance is obtained based on the mapping function.

[0015] In one implementation of the first aspect, the mapping function is a monotonically decreasing exponential decay function, a power function, or a piecewise linear function.

[0016] In one implementation of the first aspect, according to Obtain the effective signal-to-noise ratio (SNR) of the i-th channel. iWhere a, b, and c all represent adjustable parameters, Z i This indicates the contact resistance.

[0017] In one implementation of the first aspect, according to Generate the fusion weight ω of the i-th channel i SNR i Let N represent the effective signal-to-noise ratio of the i-th channel, and N represent the total number of channels.

[0018] In one implementation of the first aspect, according to Generate the fusion weight ω of the i-th channel i Where α represents the control parameter, Z i Z represents the contact resistance. th This indicates the preset impedance threshold.

[0019] In one implementation of the first aspect, the fusion weights are used to fuse multi-channel EEG signals through a weighted covariance matrix, a weighted signal matrix, or a weighted spatial filter.

[0020] In a second aspect, the present invention provides a multi-channel EEG signal fusion system, the system comprising a first acquisition module, a second acquisition module, a generation module and a fusion module;

[0021] The first acquisition module is used to acquire the contact impedance between the electrodes and the skin on each channel when acquiring EEG signals;

[0022] The second acquisition module is used to acquire the effective signal-to-noise ratio of each channel based on the contact impedance;

[0023] The generation module is used to generate fusion weights for each channel based on the effective signal-to-noise ratio;

[0024] The fusion module is used to fuse EEG signals from each channel based on the fusion weights.

[0025] Thirdly, the present invention provides a storage medium on which a computer program is stored, which, when executed by a processor, implements the above-described multichannel EEG signal fusion method.

[0026] Fourthly, the present invention provides a terminal, comprising: a processor and a memory;

[0027] The memory is used to store computer programs;

[0028] The processor is used to execute the computer program stored in the memory, so that the terminal performs the above-described multi-channel EEG signal fusion method.

[0029] As described above, the multi-channel EEG signal fusion method, system, storage medium, and terminal of the present invention have the following beneficial effects:

[0030] (1) Multi-channel EEG signal fusion is achieved based on adaptive adjustment of electrode contact impedance, effectively improving signal accuracy. For example, in the SSVEP-BCI experiment, compared with fixed-weight CCA, the average recognition accuracy of this invention was improved by 5.2% (from 87.3% to 92.5%) in 12 subjects, and the gain was more significant in high-noise environments (such as motion artifacts).

[0031] (2) Even if some channels fail due to poor contact, they can still maintain stable output by automatically reducing weight, thus avoiding the problem of "bad channels dragging down overall performance" and enhancing robustness;

[0032] (3) The weights are directly derived from the physical impedance, without relying on a large amount of labeled data, and are suitable for zero-training or small sample scenarios;

[0033] (4) It can be seamlessly integrated into the existing BCI framework and is applicable to various algorithms such as CCA, TRCA, xDAWN, and Common Spatial Pattern (CSP). It can improve the online performance without changing the original algorithm structure and has strong compatibility.

[0034] (5) Reduces interruptions caused by electrode adjustment, supports more natural and longer-term interaction, and is particularly suitable for consumer-grade wearable BCI devices, especially for mobile scenarios, long-term monitoring and non-professional user environments.

[0035] (6) It can intelligently compensate for hardware contact defects through software, and can achieve near-wet electrode performance on low-cost dry electrode systems. Attached Figure Description

[0036] Figure 1 The flowchart shown is an embodiment of the multi-channel EEG signal fusion method of the present invention;

[0037] Figure 2 The diagram shown is a structural schematic of the multi-channel EEG signal fusion system of the present invention in one embodiment.

[0038] Figure 3 The diagram shown is a structural schematic of the terminal of the present invention in one embodiment. Detailed Implementation

[0039] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0040] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0041] The technical solutions of the present invention will now be described in detail with reference to the accompanying drawings.

[0042] The multi-channel EEG signal fusion method, system, storage medium, and terminal of this invention achieve adaptive channel fusion driven by effective signal-to-noise ratio by detecting the contact impedance between the scalp electrodes and the skin in real time online and dynamically adjusting the weighting coefficients of each channel in the feature extraction or classification stage accordingly. It is applicable to various mainstream BCI paradigms such as steady-state visual evoked potentials (SSVEP), event-related potentials (ERP), and motor imagery (MI). In particular, it can significantly enhance the robustness and accuracy of multi-channel fusion algorithms based on canonical correlation analysis (CCA) and task-related component analysis (TRCA).

[0043] like Figure 1 As shown, in one embodiment, the multi-channel EEG signal fusion method of the present invention includes steps S1-S4.

[0044] Step S1: When collecting EEG signals, obtain the contact impedance between the electrodes and the skin on each channel.

[0045] Specifically, during the operation of the brain-computer interface system, the contact impedance between the electrodes and the skin of each channel is acquired in real time. This is achieved through a built-in impedance measurement circuit (such as a small-amplitude AC excitation method or a DC bias method) to measure the contact impedance between the electrodes and the skin of each channel in real time. This process can be completed in milliseconds without affecting the acquisition of the main signal.

[0046] Step S2: Obtain the effective signal-to-noise ratio of each channel based on the contact impedance.

[0047] Specifically, firstly, a mapping function from contact impedance to effective signal-to-noise ratio (SNR) is constructed; then, the effective SNR corresponding to the contact impedance is obtained based on the mapping function. The mapping function employs a monotonically decreasing exponential decay function, a power function, or a piecewise linear function.

[0048] In one embodiment, according to Obtain the effective signal-to-noise ratio (SNR) of the i-th channel. i , where a, b, and c are all adjustable parameters that can be obtained by fitting a small amount of calibration data. Z i This indicates the contact resistance.

[0049] Step S3: Generate the fusion weights for each channel based on the effective signal-to-noise ratio.

[0050] Specifically, based on the effective signal-to-noise ratio, the fusion weights of the channels are dynamically generated, so that the high signal-to-noise ratio (low impedance) channels are given higher weights, while the low signal-to-noise ratio (high impedance) channels are automatically suppressed or reduced in weight.

[0051] In one embodiment, the effective signal-to-noise ratio of each channel is normalized and used as the fusion weight. That is, according to... Generate the fusion weight ω of the i-th channel i SNR i Let N represent the effective signal-to-noise ratio of the i-th channel, and N represent the total number of channels.

[0052] In another embodiment, according to Generate the fusion weight ω of the i-th channel i , where α represents a control parameter used to control the sensitivity of the fusion weight to contact impedance. Z i Z represents the contact resistance. th This indicates a preset impedance threshold. In other words, when the contact impedance of a channel exceeds the preset threshold, its fusion weight is reset to zero.

[0053] Step S4: Based on the fusion weights, the EEG signals on each channel are fused.

[0054] Specifically, the fusion weights are applied to the weighted combination of multi-channel EEG signals, and the weighted signals are input into a decoding algorithm to achieve EEG signal recognition. The decoding algorithms include canonical correlation analysis (CCA), filter bank CCA (FBCCA), task-related component analysis (TRCA), or variations thereof. The fusion weights are used to fuse multi-channel EEG signals through weighted covariance matrices, weighted signal matrices, or weighted spatial filters. For example, for CCA-type methods, channel weighting (i.e., weighting the covariance matrix) is applied when calculating the correlation between the reference signal and the EEG signal. For TRCA / eTRCA-type methods, the weights ω are applied during template construction or spatial filter solving. iIntroducing an objective function is equivalent to assigning greater importance to high signal-to-noise ratio channels. In general, the original multi-channel signal X∈R is... N*T Transformed into a weighted signal X w =diag(ω)X, and then input to the subsequent decoder. It should be noted that the channel EEG signal fusion method of the present invention can be implemented in real time on an embedded BCI platform (such as an ARM or FPGA-based system), and can also provide visual feedback (such as impedance heatmap) to help users optimize wearing.

[0055] The following section uses the SSVEP-BCI system as an example to further illustrate the multi-channel EEG signal fusion method of the present invention.

[0056] In this embodiment, a 24-channel EEG signal amplifier with impedance detection function (such as OpenBCI Cyton+Daisy) is used, with a sampling rate of 1000Hz, and the electrodes are arranged according to the international 10–20 system (focusing on covering the O1, Oz, O2 and other regions of the occipital lobe).

[0057] Before each test, a weak AC current of 1kHz and 10nA is injected into each channel, the voltage response is measured, and the contact impedance Z is calculated. i The entire process took less than 200ms.

[0058] Set the preset impedance threshold Z th =50kΩ, α=1, for Z i Calculate ω for channels <50 i =1 / Z i The rest are set to 0 and normalized.

[0059] Acquire 2 seconds of SSVEP data, apply bandpass filtering (5–90Hz) to the original signal X, and construct a weighted signal X. w =diag(ω)X. The FBCCA algorithm is executed using the weighted signal to calculate the maximum correlation coefficient with each frequency reference signal. The stimulus frequency corresponding to the maximum correlation coefficient is output as the recognition result. Testing showed that in a simulated daily use scenario including slight head movements, the traditional FBCCA method achieved an average accuracy of 81.6%, while the method of this invention reached 89.4%, with a smaller standard deviation, indicating significantly improved stability.

[0060] The scope of protection of the multi-channel EEG signal fusion method described in this embodiment is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principle of this invention is included within the scope of protection of this invention.

[0061] This invention also provides a multi-channel EEG signal fusion system, which can implement the multi-channel EEG signal fusion method described in this invention. However, the implementation device of the multi-channel EEG signal fusion system described in this invention includes, but is not limited to, the structure of the multi-channel EEG signal fusion system listed in this embodiment. All structural modifications and substitutions of the prior art made according to the principles of this invention are included within the protection scope of this invention.

[0062] like Figure 2 As shown, in one embodiment, the multi-channel EEG signal fusion system of the present invention includes a first acquisition module 21, a second acquisition module 22, a generation module 23, and a fusion module 24.

[0063] The first acquisition module 21 is used to acquire the contact impedance between the electrodes and the skin on each channel when acquiring EEG signals.

[0064] The second acquisition module 22 is connected to the first acquisition module 21 and is used to acquire the effective signal-to-noise ratio of each channel based on the contact impedance.

[0065] The generation module 23 is connected to the second acquisition module 22 and is used to generate the fusion weights of each channel based on the effective signal-to-noise ratio.

[0066] The fusion module 24 is connected to the generation module 23 and is used to fuse the EEG signals on each channel based on the fusion weight.

[0067] The structure and principle of the first acquisition module 21, the second acquisition module 22, the generation module 23 and the fusion module 24 correspond one-to-one with the steps in the above-mentioned multi-channel EEG signal fusion method, so they will not be described again here.

[0068] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0069] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of the present invention, depending on actual needs. For example, the functional modules / units in the various embodiments of the present invention may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0070] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0071] This invention also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the multi-channel EEG signal fusion method of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. This available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0072] This invention also provides a terminal. The terminal includes a processor and a memory.

[0073] The memory is used to store computer programs.

[0074] The memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0075] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the terminal performs the above-described multi-channel EEG signal fusion method.

[0076] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0077] like Figure 3 As shown, the terminal of the present invention is presented in the form of a general-purpose computing device. The components of the terminal may include, but are not limited to: one or more processors or processing units 31, a memory 32, and a bus 33 connecting different system components (including the memory 32 and the processing unit 31).

[0078] Bus 33 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0079] Terminals typically include various computer system-readable media. These media can be any available media that can be accessed by the terminal, including volatile and non-volatile media, and removable and non-removable media.

[0080] Memory 32 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 321 and / or cache memory 322. The terminal may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 323 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 3Not shown; usually referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 33 via one or more data media interfaces. Memory 32 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0081] A program / utility 324 having a set (at least one) of program modules 3241 may be stored, for example, in memory 32. Such program modules 3241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 3241 typically perform the functions and / or methods described in the embodiments of the present invention.

[0082] The terminal can also communicate with one or more external devices (e.g., keyboard, pointing device, display, etc.), one or more devices that enable user interaction with the terminal, and / or any device that enables the terminal to communicate with one or more other computing devices (e.g., network interface card, modem, etc.). This communication can be performed through input / output (I / O) interface 34. Furthermore, the terminal can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) through network adapter 35. Figure 3 As shown, network adapter 35 communicates with other modules of the terminal via bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the terminal, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0083] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for fusing multi-channel electroencephalogram (EEG) signals, characterized in that, The method includes the following steps: When collecting EEG signals, the contact impedance between the electrodes and the skin on each channel is obtained; The effective signal-to-noise ratio of each channel is obtained based on the contact impedance. The fusion weights for each channel are generated based on the effective signal-to-noise ratio. The fusion weights are used to fuse the EEG signals from each channel.

2. The multi-channel EEG signal fusion method according to claim 1, characterized in that, Obtaining the effective signal-to-noise ratio of each channel based on the contact impedance includes the following steps: Construct a mapping function from contact impedance to effective signal-to-noise ratio; The effective signal-to-noise ratio corresponding to the contact impedance is obtained based on the mapping function.

3. The multi-channel EEG signal fusion method according to claim 2, characterized in that, The mapping function is a monotonically decreasing exponential decay function, a power function, or a piecewise linear function.

4. The multi-channel EEG signal fusion method according to claim 1, characterized in that, according to Obtain the effective signal-to-noise ratio (SNR) of the i-th channel. i Where a, b, and c all represent adjustable parameters, Z i This indicates the contact resistance.

5. The multi-channel EEG signal fusion method according to claim 1, characterized in that, according to Generate the fusion weight ω of the i-th channel i SNR i Let N represent the effective signal-to-noise ratio of the i-th channel, and N represent the total number of channels.

6. The multi-channel EEG signal fusion method according to claim 1, characterized in that, according to Generate the fusion weight ω of the i-th channel i Where α represents the control parameter, Z i Z represents the contact resistance. th This indicates the preset impedance threshold.

7. The multi-channel EEG signal fusion method according to claim 1, characterized in that, The fusion weights are achieved by using a weighted covariance matrix, a weighted signal matrix, or a weighted spatial filter to fuse multi-channel EEG signals.

8. A multi-channel EEG signal fusion system, characterized in that, The system includes a first acquisition module, a second acquisition module, a generation module, and a fusion module; The first acquisition module is used to acquire the contact impedance between the electrodes and the skin on each channel when acquiring EEG signals; The second acquisition module is used to acquire the effective signal-to-noise ratio of each channel based on the contact impedance; The generation module is used to generate fusion weights for each channel based on the effective signal-to-noise ratio; The fusion module is used to fuse EEG signals from each channel based on the fusion weights.

9. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the multichannel EEG signal fusion method according to any one of claims 1 to 7.

10. A terminal, characterized in that, include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to cause the terminal to perform the multichannel EEG signal fusion method according to any one of claims 1 to 7.

Images