A Brain-Computer Interface Control System and Method Based on Multi-Mode Fusion

Abstract

The present invention discloses a brain-computer interface control system and method based on multi-mode fusion, which relates to the technical field of brain-computer interface control. It includes a microelectrode array management module responsible for the arrangement of the microelectrode array and initial signal acquisition, and real-time monitoring of electroencephalogram signal characteristics; a parameter optimization module for dynamically adjusting the sampling parameters of the microelectrode array to optimize the signal quality; a multi-channel signal processing module for weighted fusion and noise suppression of signals from multiple electrode channels; a self-calibration feedback module for self-calibrating electrode parameters according to feedback and optimizing the acquisition parameters of the microelectrode array; a control instruction generation module for generating instructions; and an output adjustment module for dynamically adjusting the output. The present invention realizes the accurate acquisition and processing of electroencephalogram signals, thereby improving the flexibility and accuracy of the system in real-time applications.

Description

Technical Field

[0001] The present invention relates to the technical field of brain-computer interface control, and particularly to a brain-computer interface control system and method based on multi-mode fusion. Background Art

[0002] Brain-Computer Interface (BCI), as a cutting-edge technology, has achieved rapid development in recent years. Traditional BCI technologies mainly rely on one-way information transfer between the brain and external devices. By collecting electroencephalogram (EEG) signals and converting them into control instructions, BCI technologies can achieve the control of devices such as computers, robotic arms, and wheelchairs. The development of these technologies began with early studies on EEG signal detection and neuronal activities, and gradually evolved into the use of more complex algorithms and signal processing methods for real-time control.

[0003] Although existing BCI technologies can already achieve the control of external devices by collecting EEG signals, signal processing still poses significant challenges. Existing microelectrode array signal acquisition technologies are insufficient in automatically adjusting and optimizing sampling parameters, unable to adaptively adjust in real time according to signal characteristics, resulting in significant fluctuations in signal quality. In addition, there is also room for optimization in the fusion and noise suppression of EEG signals. The signal fusion algorithms for multiple channels are relatively simple, making it difficult to effectively suppress noise and enhance the reliability of signals. Summary of the Invention

[0004] In view of the problems existing in existing BCI technologies, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention lies in how to solve the problems of signal acquisition stability, real-time performance, and signal processing.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a brain-computer interface control system based on multi-mode fusion, which includes a microelectrode array management module responsible for the arrangement and initial signal acquisition of the microelectrode array and real-time monitoring of electroencephalogram signal characteristics; a parameter optimization module for dynamically adjusting the sampling parameters of the microelectrode array to optimize the signal quality; a multi-channel signal processing module for weighted fusion and noise suppression of multiple electrode channel signals; a self-calibration feedback module for self-calibrating electrode parameters according to feedback and optimizing the acquisition parameters of the microelectrode array; a control instruction generation module for generating instructions; and an output adjustment module for dynamically adjusting the output. The microelectrode array management module is connected to the parameter optimization module, the parameter optimization module is connected to the multi-channel signal processing module; the multi-channel signal processing module is connected to the self-calibration feedback module; the self-calibration feedback module is connected to the control instruction generation module; and the control instruction generation module is connected to the output adjustment module.

[0008] In a second aspect, an embodiment of the present invention provides a brain-computer interface control method based on multi-mode fusion, which includes: arranging a microelectrode array in a target area, initializing the microelectrode array and performing initial microelectrode array signal acquisition, and real-time monitoring of the electroencephalogram signal characteristics; automatically adjusting the microelectrode array signal acquisition parameters according to the signal characteristics to optimize the signal quality of the electrode channels; processing multiple electrode channel signals to enhance the reliability and output stability of the signals; performing self-calibration based on a feedback mechanism to optimize the microelectrode array signal acquisition parameters; generating control instructions, and dynamically adjusting the output according to the actual scenario requirements.

[0009] As a preferred solution of the brain-computer interface control method based on multi-mode fusion of the present invention, wherein: the automatically adjusting the microelectrode array signal acquisition parameters according to the signal characteristics includes the following steps: dynamically optimizing the sampling frequency of the microelectrode array according to the monitored signal characteristics; automatically adjusting the gain and impedance matching of the microelectrode array according to different neural signal frequency bands and modes.

[0010] As a preferred solution of the brain-computer interface control method based on multi-mode fusion of the present invention, wherein: the dynamically optimizing the sampling parameters of the microelectrode array includes: the dynamic adjustment of the sampling frequency is adaptively optimized according to the frequency characteristics of the signal, and a formula is designed based on the Nyquist criterion combined with an adaptive adjustment mechanism, specifically as follows:

[0011] ;

[0012] wherein, is the sampling frequency at the current time t, is the signal frequency detected at the current time t, is the frequency compensation amount dynamically adjusted according to the signal frequency band and noise level at time t, is the set minimum sampling frequency; for low-frequency signals, the sampling frequency is reduced to reduce data redundancy; for high-frequency signals, the sampling frequency is increased to capture rapidly changing signals.

[0013] As a preferred solution of the brain-computer interface control method based on multi-mode fusion according to the present invention, wherein: the automatic adjustment of the gain and impedance matching of the microelectrode array includes the following: the adjustment of the microelectrode array gain is adaptively optimized according to the amplitude characteristics of the signal, and the adjustment process is as follows:

[0014] ;

[0015] wherein, is the gain at time t, is the initial gain value, is the ideal amplitude of the target signal, is the amplitude of the signal monitored in real time, is the adjustment factor; the optimization of the microelectrode array impedance matching is achieved by monitoring the impedance between the electrode and the skin or brain tissue in real time and dynamically adjusting the contact conditions, and the formula is as follows:

[0016] ;

[0017] wherein, is the effective impedance of the current electrode contact, is the initial impedance value, is the target contact resistance, is the contact resistance value measured in real time, is the adjustment factor for impedance matching.

[0018] As a preferred solution of the brain-computer interface control method based on multi-mode fusion according to the present invention, wherein: the self-calibration based on the feedback mechanism and the optimization of the microelectrode array signal acquisition parameters include: evaluating the acquisition results after each signal adjustment, performing signal quality evaluation under the new parameters, and comparing with the initial setting: if the signal quality continues to improve, the system will automatically maintain the current microelectrode array signal acquisition parameters and save the current state as the new benchmark; if the signal quality deteriorates or fluctuates, it will be restored to the previous stable parameter state through the rollback mechanism; gradually optimize the microelectrode array signal acquisition parameters according to the trend of signal change, and find the optimal microelectrode array signal acquisition conditions through continuous small adjustments; the result of each self-calibration adjustment will be fed back to the signal quality evaluation to form a closed-loop feedback loop, and the optimal microelectrode array signal acquisition parameter setting will be found through multiple rounds of feedback and self-calibration adjustments.

[0019] As a preferred solution of the brain-computer interface control method based on multi-mode fusion according to the present invention, wherein: the calculation formula of the signal quality evaluation is as follows:

[0020] ;

[0021] Wherein, ~ are signal quality weight factors respectively; is the signal strength, is the frequency response, is the signal-to-noise ratio.

[0022] As a preferred solution of the brain-computer interface control method based on multi-mode fusion according to the present invention, wherein: the processing of multiple electrode channel signals includes weighted fusion and noise suppression.

[0023] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and wherein: when the computer program instructions are executed by the processor, the steps of the brain-computer interface control method based on multi-mode fusion as described in the second aspect of the present invention are implemented.

[0024] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and wherein: when the computer program instructions are executed by the processor, the steps of the brain-computer interface control method based on multi-mode fusion as described in the second aspect of the present invention are implemented.

[0025] The beneficial effects of the present invention are as follows: By arranging a microelectrode array on the cerebral cortex or the scalp surface, the present invention monitors the characteristics of electroencephalogram (EEG) signals in real time, and realizes the adaptive adjustment of signal acquisition by using dynamically optimized sampling parameters, ensuring the accurate capture of different EEG signal frequency bands. At the same time, through weighted fusion and noise suppression technologies, the reliability and output stability of the signals are enhanced, and problems such as unstable signal acquisition, inflexible parameter adjustment, and poor noise suppression effect in the existing brain-computer interface technologies are solved, realizing the accurate acquisition and processing of EEG signals, and further improving the flexibility and accuracy of the system in real-time applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings according to these drawings without creative efforts.

[0027] Figure 1 It is a structural diagram of a brain-computer interface control system based on multi-mode fusion.

[0028] Figure 2 It is a flowchart of a brain-computer interface control method based on multi-mode fusion. Detailed Implementation Modes

[0029] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific implementation modes of the present invention in conjunction with the accompanying drawings of the specification.

[0030] In the following description, many specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0031] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation mode of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an individual or alternative embodiment that excludes other embodiments.

[0032] Embodiment 1

[0033] Referring to Figures 1 to 2 , this is the first embodiment of the present invention. This embodiment provides a brain-computer interface control system based on multi-mode fusion, including

[0034] A microelectrode array management module, which is responsible for the arrangement and initial signal acquisition of the microelectrode array and real-time monitoring of the electroencephalogram signal characteristics; a parameter optimization module, which is used to dynamically adjust the microelectrode array signal acquisition to optimize the signal quality; a multi-channel signal processing module, which is used to enhance the reliability and stability of the electrode channel signals; a self-calibration feedback module, which self-calibrates the electrode parameters according to the feedback; a control instruction generation module, which is used to generate instructions; and an output adjustment module, which is used to dynamically adjust the output.

[0035] Furthermore, this embodiment also provides a brain-computer interface control method based on multi-mode fusion, including

[0036] S1: Arrange a microelectrode array in the target area (cerebral cortex or scalp surface), initialize the microelectrode array and perform initial microelectrode array signal acquisition, and real-time monitor the electroencephalogram signal characteristics.

[0037] Specifically, using standard initial microelectrode array signal parameters, such as sampling frequency, gain, and electrode contact quality, start the acquisition system, record the neuronal activities in the target brain area. During the acquisition process, the system records the electroencephalogram signals in real-time to generate initial electroencephalogram signal data.

[0038] Furthermore, the collected signals are analyzed in real time to detect signal characteristics (such as amplitude, frequency, and noise level). The main frequency bands (such as alpha waves, beta waves, etc.) in the EEG signals are identified through frequency domain analysis techniques (such as FFT), and the changing trend of the signals is observed using time domain analysis methods (such as the sliding window method). The signal stability and noise interference conditions are detected, including signal strength, signal-to-noise ratio (SNR), etc.

[0039] S2: Automatically adjust the sampling parameters of the microelectrode array according to the signal characteristics to optimize the signal quality.

[0040] S2.1: Dynamically optimize the sampling frequency of the microelectrode array according to the signal characteristics monitored and collected.

[0041] Preferably, based on the collected signal characteristics, analyze whether the current acquisition parameters need to be optimized. Among them, analyze the signal quality through a feedback mechanism to identify the deviation between the acquisition parameters and the signal characteristics; according to the dynamic changes of the signal, decide whether to adjust the parameters of the acquisition device in real time, such as sampling frequency, gain, and impedance, etc.

[0042] Specifically, the dynamic adjustment of the sampling frequency is adaptively optimized according to the frequency characteristics of the signal (such as alpha waves, beta waves, etc.). A formula is designed based on the Nyquist criterion combined with an adaptive adjustment mechanism, as follows:

[0043] ;

[0044] Among them, is the sampling frequency at the current time t (changing dynamically with time), is the signal frequency detected at the current time t (such as the frequency range of alpha waves), is the frequency compensation amount dynamically adjusted according to the signal frequency band and noise level at time t, is the set minimum sampling frequency.

[0045] According to the EEG signals of different frequency bands (such as alpha waves, beta waves, etc.), dynamically adjust the sampling frequency of the microelectrode array to ensure accurate signal acquisition: for low-frequency signals (such as delta waves), the sampling frequency can be reduced to reduce data redundancy; for high-frequency signals (such as beta waves), the sampling frequency is increased to capture rapidly changing signals. For example, for beta waves (13 - 30 Hz), the sampling frequency should be set above 500 Hz, while for delta waves (0.5 - 4 Hz), it can be reduced to about 250 Hz.

[0046] S2.2: Automatically adjust parameters such as the sampling gain and impedance matching of the microelectrode array according to different neural signal frequency bands and modes to ensure the sensitivity and accuracy of signal acquisition.

[0047] Specifically, the gain parameter is automatically adjusted according to the signal amplitude to ensure that the amplitude of the acquired signal is within the range that the device can process. If the signal strength is weak, the gain will be automatically increased (e.g., from 10,000 times to 50,000 times) to enhance the signal strength and prevent small signals from being masked by noise. If the signal strength is too large, the gain will be automatically decreased to avoid signal overload or device saturation. Among them, the adjustment of the gain is adaptively optimized according to the amplitude characteristics of the signal to avoid signal overload or small signals being masked by noise. The adjustment process is as follows:

[0048] ;

[0049] Among them, is the gain at time t, is the initial gain value, is the ideal amplitude of the target signal, is the amplitude of the signal monitored in real time, is the adjustment factor used to control the dynamic response speed of the gain (generally taking values from 0.5 to 1.5, specifically adjusted according to different signals).

[0050] Check the impedance between the electrode and the skin or brain tissue to ensure the stability of signal conduction. If the electrode impedance is too high (e.g., greater than 10 kΩ), the system will prompt or automatically adjust the electrode contact quality or use an impedance matching circuit to reduce the impedance; automatically optimize the impedance matching parameters of the electrode to avoid signal distortion or noise increase caused by too high impedance.

[0051] The optimization of impedance matching can be achieved by real-time monitoring of the impedance between the electrode and the skin or brain tissue and dynamically adjusting the contact conditions. The formula is as follows:

[0052] ;

[0053] Among them, is the effective impedance of the current electrode contact, is the initial impedance value, is the target contact resistance (such as the ideal contact resistance value between the electrode and the skin), is the contact resistance value measured in real time, is the adjustment factor for impedance matching, which controls the speed and sensitivity of the adjustment.

[0054] It can be seen that by automatically adjusting the gain parameter according to the signal amplitude, the adaptive optimization of signal acquisition is realized. The current brain-computer interface technology usually relies on static settings, which may lead to a decrease in signal quality in the face of environmental changes. However, the present invention overcomes this deficiency by adopting a dynamic adjustment mechanism to ensure the sensitivity and accuracy during the signal acquisition process. Dynamic gain adjustment can effectively handle the processing requirements of signals with different intensities, avoiding the situation where weak signals are masked by noise or distortion caused by signal overload. For example, when it is detected that the signal intensity is weak, the automatic increase in gain ensures that effective signals can still be captured even in a high-noise environment.

[0055] S3: Perform weighted fusion and noise suppression on the signals of multiple electrode channels to enhance the reliability and output stability of the signals.

[0056] For each electrode channel in the microelectrode array, electroencephalogram (EEG) signals are collected to obtain independent signal data of multiple channels. The signals captured by each channel may contain different noises and distortions, so subsequent processing is required to enhance the signal quality.

[0057] For the signals of multiple electrode channels, a weighted fusion algorithm is applied. Different weight coefficients are set for the signals of each channel. Through weighted average processing, multiple signals can be effectively fused to reduce the noises and interferences that may exist in the signals of certain channels.

[0058] Specifically, the formula of the weighted fusion algorithm is as follows:

[0059] ;

[0060] Wherein, is the fused signal, is the weight of electrode channel i, is the acquired signal of electrode channel i, and N is the total number of electrode channels.

[0061] Furthermore, during the signal fusion process, noise suppression processing is performed on the signals of each electrode channel, and an adaptive filter (such as an LMS filter or a Kalman filter) is used to reduce the influence of high-frequency noise or environmental interference. By performing weighted average or noise suppression on the signals from multiple electrodes, the stability of the output signal is ensured.

[0062] S4: Perform self-calibration based on the feedback mechanism to gradually optimize the acquisition parameters of the microelectrode array.

[0063] Evaluate the acquisition results after each signal adjustment, assess the signal quality under the new parameters, and compare it with the initial settings: If it is found that the signal quality continues to improve (for example, both the SNR and signal strength are better than the previous settings), the system will automatically maintain the acquisition parameters of the current microelectrode array and save the current state as the new benchmark; if the signal quality deteriorates or fluctuates, the rollback mechanism will be used to restore to the previous stable parameter state to avoid long-term signal degradation. This mechanism allows the system to make tentative adjustments in a short period of time and quickly roll back to a safe state when anomalies occur.

[0064] Among them, the calculation formula for evaluating the signal quality under the new parameters is as follows:

[0065] ;

[0066] Among them, ~ are the signal quality weight factors respectively; is the signal strength, is the frequency response, is the signal-to-noise ratio.

[0067] The system will gradually optimize the signal acquisition of the microelectrode array according to the trend of signal changes, and find the optimal signal acquisition conditions of the microelectrode array through continuous small adjustments. To avoid signal fluctuations caused by frequent adjustments, the system sets limits on the adjustment frequency and range to ensure the stability of the microelectrode array signal acquisition during long-term operation; the result of each self-calibration adjustment will be fed back to the signal evaluation of the system to form a closed-loop feedback loop. Through multiple rounds of feedback and self-calibration adjustments, the system gradually finds the optimal acquisition parameter settings of the microelectrode array.

[0068] Among them, the feedback loop update formula is:

[0069] ;

[0070] Among them, is the updated set of electrode acquisition parameters, is the set of acquisition parameters in the previous round, is the learning rate, which is used to control the step size of parameter adjustment, is the gradient of the signal quality with respect to the acquisition parameters, and P is the set of acquisition parameters.

[0071] Through the self-calibration mechanism, the system can continuously adjust the acquisition parameters of the microelectrode array according to the acquired signal quality, ensure the stability and accuracy of signal acquisition, and avoid signal degradation during long-term operation.

[0072] S5: Generate control instructions and dynamically adjust the output according to the actual scenario requirements to ensure real-time response.

[0073] The processed high-quality EEG signals will be transmitted to the control instruction generation module, which receives signals from multiple electrode channels and generates output instructions according to a predetermined control model. The control model will identify corresponding signal patterns based on the characteristics of the collected EEG signals and convert them into specific operation commands, such as physical operations like moving a robotic arm, a robot, or an exoskeleton, or virtual controls like manipulating objects, characters in a virtual environment, or performing computer tasks.

[0074] To adapt to the changing requirements of the actual scenario, the system will dynamically adjust the output of control instructions according to the scenario feedback. For example, when the change frequency of EEG signals is relatively high (such as in a fast movement control scenario), the system needs to increase the output frequency to ensure timely response to EEG instructions; on the contrary, in a stable or slow task, the frequency can be appropriately reduced to save computing resources; in a scenario requiring fine control (such as precision operation, medical instrument control), the system will improve the output accuracy of instructions; while in a scenario with lower task accuracy requirements (such as rough operation or navigation tasks), the accuracy can be reduced to improve the system response speed.

[0075] This embodiment also provides a computer device applicable to the case of the brain-computer interface control method based on multi-mode fusion, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the brain-computer interface control method based on multi-mode fusion as proposed in the above embodiment.

[0076] This computer device can be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be achieved through WIFI, operator networks, NFC (Near Field Communication), or other technologies. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad set on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0077] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the brain-computer interface control method based on multi-mode fusion as proposed in the above embodiment.

[0078] In summary, the present invention arranges a microelectrode array on the cerebral cortex or the scalp surface to monitor the characteristics of electroencephalogram (EEG) signals in real time. By using dynamically optimized sampling parameters, it realizes the adaptive adjustment of signal acquisition, ensuring the precise capture of different EEG signal frequency bands. At the same time, through weighted fusion and noise suppression techniques, it enhances the reliability and output stability of the signals, solves the problems of unstable signal acquisition, inflexible parameter adjustment, and poor noise suppression effect in the existing brain-computer interface technology, realizes the precise acquisition and processing of EEG signals, and further improves the flexibility and accuracy of the system in real-time applications.

[0079] Embodiment 2

[0080] Referring to Table 1, this is the second embodiment of the present invention. This embodiment provides a brain-computer interface control method based on multi-mode fusion. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0081] The experiment is carried out in a standardized laboratory environment, and the participants are professional-trained volunteers. The experimental equipment includes a high-precision microelectrode array, a signal acquisition system, a real-time signal analysis module, and a control instruction generation module. First, the microelectrode array is precisely arranged in the target area (cerebral cortex) to ensure good contact between the electrodes and the brain tissue. After the arrangement is completed, the microelectrode array is initialized, the initial sampling frequency is set to 500 Hz, the gain is set to 20,000 times, and the impedance matching parameter is adjusted to the ideal value. The acquisition system is started to begin the initial signal acquisition, continuously recording the activity signals of brain neurons.

[0082] During the signal acquisition process, the system monitors the characteristics of EEG signals in real time, including amplitude, frequency, and noise level. The fast Fourier transform (FFT) is used to perform frequency-domain analysis on the signals to identify the main EEG frequency bands, such as alpha waves (8 - 12 Hz), beta waves (13 - 30 Hz), etc. At the same time, the sliding window method is used to observe the change trend of the signals in the time domain to evaluate the signal stability and noise interference situation. Based on the acquired signal characteristics, the system automatically adjusts the sampling parameters.

[0083] The weighted fusion algorithm is used to perform weighted average processing on the signals from different electrodes. At the same time, an adaptive filter (such as an LMS filter) is applied to perform noise suppression processing on the fused signals to further improve the reliability and stability of the signals.

[0084] The processed high-quality EEG signals are transmitted to the control instruction generation module. Based on a predetermined control model, this module converts the EEG signal features into specific operation commands, such as controlling the movement of a robotic arm or manipulating objects in a virtual environment. To adapt to the requirements of different scenarios, the system dynamically adjusts the frequency and accuracy of the output instructions according to real-time feedback. The following table records the experimental data comparison between the method of the present invention and traditional brain-computer interface methods under different parameters:

[0085] Table 1 Experimental Comparison Table of EEG Signal Processing

[0086]

[0087] It can be clearly seen from the above experimental data table that the multi-mode fusion brain-computer interface control method based on the present invention shows significant advantages in multiple key parameters. First, in terms of the sampling frequency, traditional methods generally adopt a fixed sampling frequency of 500Hz, while the method of the present invention dynamically adjusts the sampling frequency according to different EEG signal frequency bands. For example, Method 1 and Method 2 of the present invention increase the sampling frequency to 1000Hz and 750Hz when processing high-frequency β waves, ensuring the accurate capture of fast signals; while when processing low-frequency δ waves, the sampling frequency is appropriately reduced to 250Hz, effectively reducing data redundancy. This dynamic adjustment mechanism not only optimizes the data acquisition efficiency but also improves the system's response speed, significantly reducing the signal distortion and data processing burden caused by the fixed sampling frequency in traditional methods.

[0088] The signal-to-noise ratio (SNR) is an important indicator for measuring signal quality. The SNR values of Traditional Method 1 and Traditional Method 2 are 15dB and 16dB respectively, while the SNR values of the method of the present invention are significantly improved under different configurations, reaching a maximum of 25dB. This improvement is mainly due to the multi-mode fusion and adaptive parameter adjustment mechanisms introduced in the signal acquisition and processing process of the present invention, which effectively suppresses noise interference and enhances the intensity of useful signals. In addition, through the weighted fusion algorithm and adaptive filtering technology, the method of the present invention further improves the reliability and stability of the signals, enabling the system to more accurately decode EEG signals in practical applications and improving the accuracy and response efficiency of control instructions.

[0089] In summary, the brain-computer interface control method based on multi-mode fusion shows obvious innovation and superiority in multiple key parameters such as sampling frequency, signal-to-noise ratio, gain adjustment, impedance matching, signal stability, and response time. Compared with traditional methods, the present invention significantly improves the efficiency and quality of signal acquisition and processing through dynamic optimization and adaptive adjustment, enhances the reliability and real-time performance of the system, and solves the problems of signal distortion, noise interference, and slow response existing in the prior art.

[0090] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A brain-computer interface control system based on multi-mode fusion, characterized in that: including a microelectrode array management module, responsible for the layout of the microelectrode array and initial signal acquisition, and real-time monitoring of electroencephalogram signal characteristics; a parameter optimization module, used to dynamically adjust the sampling parameters of the microelectrode array to optimize the signal quality; a multi-channel signal processing module, which performs weighted fusion and noise suppression on signals of multiple electrode channels; a self-calibration feedback module, which self-calibrates electrode parameters according to the feedback and optimizes the acquisition parameters of the microelectrode array; a control instruction generation module, used to generate instructions; an output adjustment module, used to dynamically adjust the output; the microelectrode array management module is connected to the parameter optimization module, the parameter optimization module is connected to the multi-channel signal processing module; the multi-channel signal processing module is connected to the self-calibration feedback module; the self-calibration feedback module is connected to the control instruction generation module; the control instruction generation module is connected to the output adjustment module; Automatically adjusting the microelectrode array signal acquisition parameters according to the signal characteristics includes the following steps: dynamically optimizing the sampling frequency of the microelectrode array according to the monitored signal characteristics; automatically adjusting the gain and impedance matching of the microelectrode array according to different neural signal frequency bands and modes; The dynamic optimization of the sampling frequency of the microelectrode array includes: the dynamic adjustment of the sampling frequency is adaptively optimized according to the frequency characteristics of the signal, and a formula is designed based on the Nyquist criterion combined with an adaptive adjustment mechanism; For low-frequency signals, the sampling frequency is reduced to reduce data redundancy; for high-frequency signals, the sampling frequency is increased to capture rapidly changing signals; The automatic adjustment of the gain and impedance matching of the microelectrode array includes the following: the adjustment of the microelectrode array gain is adaptively optimized according to the amplitude characteristics of the signal; the optimization of the microelectrode array impedance matching is achieved by real-time monitoring of the impedance between the electrode and the skin or brain tissue and dynamically adjusting the contact conditions; Self-calibration based on a feedback mechanism to optimize the microelectrode array signal acquisition parameters includes: Evaluating the acquisition results after each signal adjustment, performing signal quality assessment under new parameters, and comparing with the initial settings: if the signal quality continues to improve, the system will automatically maintain the current microelectrode array signal acquisition parameters and save the current state as a new benchmark; if the signal quality deteriorates or fluctuates, it will be restored to the previous stable parameter state through a rollback mechanism; Gradually optimize the microelectrode array signal acquisition parameters according to the trend of signal changes, and find the optimal microelectrode array signal acquisition conditions through continuous small adjustments; The results of each self-calibration adjustment will be fed back to the signal quality assessment to form a closed-loop feedback loop. Through multiple rounds of feedback and self-calibration adjustments, the optimal microelectrode array signal acquisition parameter settings are found; The calculation formula for the signal quality assessment is as follows: ； Among them, ~ are signal quality weight factors respectively; is the signal strength, is the frequency response, is the signal-to-noise ratio; Among them, the feedback loop update formula is: ； Among them, is the updated electrode acquisition parameter set, is the acquisition parameter set of the previous round, is the learning rate, which is used to control the step size of parameter adjustment, is the gradient of the signal quality with respect to the acquisition parameters, and P is the acquisition parameter set.

2. A brain-computer interface control method based on multi-modal fusion, based on the brain-computer interface control system based on multi-modal fusion described in claim 1, characterized in that: also including arranging a microelectrode array in the target area, initializing the microelectrode array and performing initial microelectrode array signal acquisition, and real-time monitoring of electroencephalogram signal characteristics; automatically adjusting the microelectrode array signal acquisition parameters according to the signal characteristics to optimize the signal quality of the electrode channels; processing signals of multiple electrode channels to enhance the reliability and output stability of the signals; Self-calibration is performed based on a feedback mechanism to optimize the signal acquisition parameters of the microelectrode array; Generate control instructions and dynamically adjust the output according to the actual scenario requirements.

3. The brain-computer interface control method based on multi-modal fusion according to claim 2, characterized in that: The formula is designed based on the Nyquist criterion combined with an adaptive adjustment mechanism, as follows: ； Among them, is the sampling frequency at the current time t, is the signal frequency detected at the current time t, is the frequency compensation amount dynamically adjusted according to the signal frequency band and noise level at time t, is the set minimum sampling frequency.

4. The brain-computer interface control method based on multi-modal fusion according to claim 3, characterized in that: The adjustment of the microelectrode array gain is adaptively optimized according to the amplitude characteristics of the signal. The adjustment process is as follows: ； wherein, is the gain at time t, is the initial gain value, is the ideal amplitude of the target signal, is the signal amplitude monitored in real time, is the adjustment factor; The optimization of the impedance matching of the microelectrode array is achieved by real-time monitoring of the impedance between the electrode and the skin or brain tissue and dynamically adjusting the contact conditions. The formula is as follows: ； Among them, is the effective impedance of the current electrode contact, is the initial impedance value, is the target contact resistance, is the contact resistance value measured in real time, is the adjustment factor for impedance matching.

5. The brain-computer interface control method based on multi-modal fusion according to claim 4, characterized in that: The processing of the signals of multiple electrode channels includes weighted fusion and noise suppression.

Images