Embedded electronic skull brain-computer interface device

Abstract

The invention provides an embedded electronic skull brain-computer interface device. The embedded electronic skull brain-computer interface device comprises a plurality of modules, wherein a stimulation module is used for presenting visual stimulation to induce an electroencephalogram signal and a multi-mode signal of a user; the processing module analyzes the accessed electroencephalogram signal and the multi-mode signal to generate an analysis result; the acquisition module receives and standardizes the analysis result and forwards the analysis result to the central communication platform; the data persistence module is used for storing standard data and system logs and simultaneously providing database query, modification and deletion functions; the peripheral control module generates a control instruction to operate peripheral equipment; the central communication platform is connected with all the modules and bears transmission of internal data and instructions. According to the device, through the embedded design, all modules are integrated in a miniaturized electronic device, the circuit layout is optimized, and miniaturized components are selected, so that the overall size is effectively reduced, the device is light and easy to wear, and the use requirements in daily life are met.

Description

Technical Field

[0001] The present invention relates to the technical field of brain-computer interface technology, and in particular to an embedded electronic skull brain-computer interface device. Background Art

[0002] With the rapid development of brain-computer interface technology (BCI), more and more research and applications are aimed at achieving direct communication between the human brain and computers or other electronic devices. This technology has shown great potential in the fields of medicine, rehabilitation, augmented reality, etc. For example, brain-computer interfaces can help paralyzed patients control prosthetic limbs, communicate or restore motor skills, and can also be used to control games, drones and other equipment. However, existing brain-computer interface devices still have the following major problems in practical applications:

[0003] Many brain-computer interface devices are often bulky and difficult to wear, and cannot be worn for long periods of time or implanted, which limits their use in daily life. Heavy or conspicuous devices may cause psychological burden on users, thus affecting their usage experience.

[0004] Most existing brain-computer interface systems consume high energy, especially during data acquisition and transmission, and are rarely able to achieve long battery life, which limits the usability and usage scenarios of the devices. Summary of the invention

[0005] In order to overcome the deficiencies of the prior art, an object of the present invention is to provide an embedded electronic skull brain-computer interface device.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] An embedded electronic skull brain-computer interface device, comprising:

[0008] Stimulation module: used to present visual stimulation to induce the generation of EEG signals and multimodal signals of the target user;

[0009] A processing module, used to process and analyze the received EEG signal and the multimodal signal to obtain an analysis result;

[0010] A collection module, used for receiving the analysis result from the processing module, standardizing the analysis result to obtain standard data, and forwarding the standard data to a central communication platform;

[0011] Data persistence module, used to store the standard data and system logs, and provide database query, modification and deletion functions;

[0012] A peripheral control module, used to generate control instructions for controlling the brain-computer interface external devices, and control the brain-computer interface external devices according to the control instructions;

[0013] The central communication platform is used to connect the stimulation module, the processing module, the acquisition module, the data persistence module and the peripheral control module to carry out internal data and interactive instruction transmission.

[0014] Preferably, the multimodal signal includes: electromyographic signal, visual stimulation signal, physiological signal and environmental signal.

[0015] Preferably, the processing module comprises:

[0016] A filtering unit, used for denoising and filtering the EEG signal and the multimodal signal to obtain a filtered signal;

[0017] A time synchronization unit, used for performing time synchronization on the filtered signal to obtain a time synchronization signal;

[0018] A feature extraction unit, used to extract features from the time synchronization signal to obtain a feature signal;

[0019] A fusion unit, used for performing modal fusion on the feature signal to obtain a comprehensive feature;

[0020] The analysis unit is used to analyze the comprehensive features using the trained support vector machine model to obtain the analysis results.

[0021] Preferably, the filtering unit comprises:

[0022] A decomposition subunit, used for decomposing the EEG signal and the multimodal signal into sub-signals of different frequencies using basis functions;

[0023] A coefficient sub-acquisition unit, used to obtain transform coefficients corresponding to sub-signals of different frequencies;

[0024] The variance subunit is used to calculate the variance of the transformation coefficients at each decomposition scale;

[0025] A model building unit, used for building a signal preprocessing model based on the variance of the transform coefficients;

[0026] The preprocessing subunit is used to preprocess the EEG signal and the multimodal signal using the signal preprocessing model to obtain the filtered signal.

[0027] Preferably, the model building unit comprises:

[0028] A standard deviation construction subunit is used to estimate the standard deviation of abnormal noise according to the variance of the transformation coefficients;

[0029] The threshold construction subunit is used to construct a coefficient removal threshold according to the standard deviation of the noise; wherein the coefficient removal threshold is: Among them, t represents the coefficient removal threshold, σ0 represents the variance of the transformation coefficient, σ p represents the standard deviation of abnormal noise, median(d p ) represents the median value of the transform coefficients at the pth decomposition scale;

[0030] The model building subunit is used to build a signal preprocessing model by using the coefficients to remove the threshold.

[0031] Preferably, the formula of the signal preprocessing model is:

[0032]

[0033] Among them, α represents the transformation coefficient, w j,k represents the transformation coefficient at the jth decomposition scale, m represents the convergence coefficient, sgn represents the sign function, and w j,k Represents the transformation coefficients for removing outliers.

[0034] Preferably, the feature extraction method is fast Fourier transform; the formula of the fast Fourier transform is: Wherein, X(k) is the kth component of the time synchronization signal, x(n) is the nth sample of the signal in the time domain, N is the total number of sampling points, and j is an imaginary unit.

[0035] Preferably, the central communication platform adopts a star network architecture communication platform based on Kafka message middleware.

[0036] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0037] The present invention provides an embedded electronic skull brain-computer interface device, comprising: a stimulation module: used to present visual stimulation to induce the generation of brain electrical signals and multimodal signals of a target user; a processing module, used to process and analyze the accessed brain electrical signals and multimodal signals to obtain analysis results; an acquisition module, used to receive the analysis results from the processing module, and standardize the analysis results to obtain standard data, and forward the standard data to a central communication platform; a data persistence module, used to store the standard data and system logs, and provide database query, modification and deletion functions; a peripheral control module, used to generate control instructions for controlling external devices of the brain-computer interface, and control the external devices of the brain-computer interface according to the control instructions; a central communication platform, used to connect the stimulation module, the processing module, the acquisition module, the data persistence module and the peripheral control module to carry internal data and interactive instruction transmission. The present invention adopts an embedded design to integrate the stimulation module, the processing module, the acquisition module, the data persistence module, the peripheral control module and the central communication platform into a miniaturized electronic device. By optimizing the circuit layout and selecting miniaturized components, the overall volume can be reduced, making the device lighter and easier to wear. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 A schematic diagram of the structure of a device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] Figure 1 A schematic diagram of the structure of the device provided in the embodiment of the present invention is shown in FIG. Figure 1 As shown, the present invention provides an embedded electronic skull brain-computer interface device, comprising:

[0043] Stimulation module: used to present visual stimulation to induce the generation of EEG signals and multimodal signals of the target user;

[0044] A processing module, used to process and analyze the received EEG signal and the multimodal signal to obtain an analysis result;

[0045] A collection module, used for receiving the analysis result from the processing module, standardizing the analysis result to obtain standard data, and forwarding the standard data to a central communication platform;

[0046] Data persistence module, used to store the standard data and system logs, and provide database query, modification and deletion functions;

[0047] A peripheral control module, used to generate control instructions for controlling the brain-computer interface external devices, and control the brain-computer interface external devices according to the control instructions;

[0048] The central communication platform is used to connect the stimulation module, the processing module, the acquisition module, the data persistence module and the peripheral control module to carry out internal data and interactive instruction transmission.

[0049] Specifically, this embodiment uses integrated circuit (IC) and system-on-chip (SoC) technologies to integrate multiple functions on one chip, further reducing the size and weight of the device.

[0050] Optionally, the acquisition module designs a unified data structure and standardizes the structure of the collected data. Other subsystems only need to parse the data according to the agreed structure for use; the acquisition subsystem sets an open preprocessing interface for application developers to write preprocessing programs according to their own needs; the acquisition subsystem also has the function of standby after the data acquisition device goes offline, and automatic reconnection after the data acquisition device is restarted.

[0051] Furthermore, the vertical architectures of the stimulation module, processing module, data persistence module, and peripheral control module are divided into an application layer, a platform framework layer, and a functional module layer, and the vertical architecture of the acquisition module is divided into a platform framework layer and a functional module layer.

[0052] Preferably, the multimodal signal includes: electromyographic signal, visual stimulation signal, physiological signal and environmental signal.

[0053] Specifically, the EEG activity recorded by the electrodes of this embodiment reflects the electrophysiological state of the brain. EEG signals are one of the main signal sources of brain-computer interfaces. This embodiment also records the electrical activity of muscles, which is usually used to monitor movement intentions or muscle states. EMG signals can be combined with EEG signals to provide richer user intention information. In addition, this embodiment also obtains signals from visual stimulation devices (such as displays or projectors) to present visual information to the user and induce corresponding EEG responses.

[0054] Furthermore, the physiological signals of this embodiment include physiological indicators such as heart rate, galvanic skin response (GSR), and breathing rate, which are used to reflect the user's emotional state and physiological response. Exemplarily, the environmental signals of this embodiment include environmental factors such as light, temperature, and sound, which can affect the user's attention and emotions, thereby affecting the generation of EEG signals.

[0055] Preferably, the processing module comprises:

[0056] A filtering unit, used for denoising and filtering the EEG signal and the multimodal signal to obtain a filtered signal;

[0057] A time synchronization unit, used for performing time synchronization on the filtered signal to obtain a time synchronization signal;

[0058] A feature extraction unit, used to extract features from the time synchronization signal to obtain a feature signal;

[0059] A fusion unit, used for performing modal fusion on the feature signal to obtain a comprehensive feature;

[0060] The analysis unit is used to analyze the comprehensive features using the trained support vector machine model to obtain the analysis results.

[0061] Specifically, this embodiment performs standardization processing on various signals to ensure that they are on the same scale for subsequent processing. Specific methods may use mean normalization, Z-score normalization, and other methods.

[0062] Furthermore, the time synchronization of this embodiment is to ensure that all signals are synchronized in time, so as to extract relevant time features from signals of different modalities.

[0063] Furthermore, the modality fusion of this embodiment is to fuse the features from different modalities (e.g., EEG signals, EMG signals, physiological signals, etc.) to form a unified feature vector. Commonly used methods include weighted averaging, feature concatenation, or dimensionality reduction techniques (such as PCA, t-SNE, etc.).

[0064] Preferably, the filtering unit comprises:

[0065] A decomposition subunit, used for decomposing the EEG signal and the multimodal signal into sub-signals of different frequencies using basis functions;

[0066] A coefficient sub-acquisition unit, used to obtain transform coefficients corresponding to sub-signals of different frequencies;

[0067] The variance subunit is used to calculate the variance of the transformation coefficients at each decomposition scale;

[0068] A model building unit, used for building a signal preprocessing model based on the variance of the transform coefficients;

[0069] The preprocessing subunit is used to preprocess the EEG signal and the multimodal signal using the signal preprocessing model to obtain the filtered signal.

[0070] Preferably, the model building unit comprises:

[0071] A standard deviation construction subunit is used to estimate the standard deviation of abnormal noise according to the variance of the transformation coefficients;

[0072] The threshold construction subunit is used to construct a coefficient removal threshold according to the standard deviation of the noise; wherein the coefficient removal threshold is: Among them, t represents the coefficient removal threshold, σ0 represents the variance of the transformation coefficient, σ p represents the standard deviation of abnormal noise, median(d p ) represents the median value of the transform coefficients at the pth decomposition scale;

[0073] The model building subunit is used to build a signal preprocessing model by using the coefficients to remove the threshold.

[0074] Preferably, the formula of the signal preprocessing model is:

[0075]

[0076] Among them, α represents the transformation coefficient, w j,k represents the transformation coefficient at the jth decomposition scale, m represents the convergence coefficient, sgn represents the sign function, and w j,k Represents the transformation coefficients for removing outliers.

[0077] Specifically, this embodiment transforms the original signal into sub-signals of different frequencies according to the principle of wavelet transform. The above sequence preprocessing model is continuous at t, the function value is (1-α)t, and it is first-order differentiable, and the derivative value at t is 1-α. The convergence speed can be adjusted by m, and the larger the m, the faster the convergence. The shrinkage degree of the wavelet coefficient within ±t can be adjusted by α, so that the above function can be transformed between the conventional hard threshold function and the soft threshold function, which can better reflect the characteristics of the original signal and perfectly remove the interference of noise.

[0078] Preferably, the feature extraction method is fast Fourier transform; the formula of the fast Fourier transform is: Wherein, X(k) is the kth component of the time synchronization signal, x(n) is the nth sample of the signal in the time domain, N is the total number of sampling points, and j is an imaginary unit.

[0079] Specifically, this embodiment sets an adaptive adjustment mechanism to change N according to the severity of signal fluctuations to improve calculation efficiency. For example, when the measured signal changes slightly, a smaller N is used, and when the change is large, a larger N is used to retain more spectrum information.

[0080] Preferably, the central communication platform adopts a star network architecture communication platform based on Kafka message middleware.

[0081] Specifically, Kafka can handle a large amount of data streams and has extremely high throughput, which can be regarded as the standard of modern data flow platforms, which means that real-time data from multiple modules can be processed without causing bottlenecks. Kafka supports low-latency data transmission and can realize real-time data processing, which is crucial for brain-computer interface systems because user reactions and feedback must be as rapid as possible. Kafka's architecture allows horizontal expansion, and more nodes can be added to cope with the increase in data volume, which is particularly important for application scenarios that need to support multiple users or multiple devices. Kafka can easily connect to multiple data sources and consumer ends, support different data modes, and is suitable for communication between various signal processing modules. Kafka can persist the received data to disk to ensure that the data is not lost. Even when the system fails, the data security can be guaranteed. And the star network architecture realizes loose coupling between modules through Kafka, and the modules can work independently, reducing the complexity of modification and expansion, and improving the flexibility and maintainability of the system. Kafka has a built-in replication mechanism that allows data to be redundantly stored between nodes to protect data from loss and enhance the reliability of the system. Kafka guarantees the order of messages, which is very important for some application scenarios (such as continuous EEG data analysis). As an open source project, Kafka has strong community support and a rich ecosystem, which can obtain various tools and services to facilitate system development and maintenance.

[0082] The beneficial effects of the present invention are as follows:

[0083] (1) The present invention adopts an embedded design, integrating the stimulation module, processing module, acquisition module, data persistence module, peripheral control module and central communication platform into a miniaturized electronic device. By optimizing the circuit layout and selecting miniaturized components, the overall volume is reduced, making the device lighter and easier to wear.

[0084] (2) The present invention places data processing on the device itself, reducing dependence on the central server, reducing the frequency of data transmission, and thus reducing energy consumption. The processing module analyzes EEG signals and multimodal signals locally in real time to reduce the amount of data transmission. In addition, a low-power wireless communication protocol (such as BLE or LoRa) is used to transmit data only when needed, further reducing energy consumption.

[0085] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0086] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An embedded electronic skull brain-computer interface device, characterized in that: include: Stimulation module: used to present visual stimulation to induce the generation of EEG signals and multimodal signals of the target user; A processing module, used to process and analyze the received EEG signal and the multimodal signal to obtain an analysis result; A collection module, used for receiving the analysis result from the processing module, standardizing the analysis result to obtain standard data, and forwarding the standard data to a central communication platform; Data persistence module, used to store the standard data and system logs, and provide database query, modification and deletion functions; A peripheral control module, used to generate control instructions for controlling the brain-computer interface external devices, and control the brain-computer interface external devices according to the control instructions; The central communication platform is used to connect the stimulation module, the processing module, the acquisition module, the data persistence module and the peripheral control module to carry out internal data and interactive instruction transmission.

2. The embedded electronic skull brain-computer interface device according to claim 1, characterized in that: The multimodal signal includes: electromyographic signal, visual stimulation signal, physiological signal and environmental signal.

3. The embedded electronic skull brain-computer interface device according to claim 1, characterized in that: The processing module comprises: A filtering unit, used for denoising and filtering the EEG signal and the multimodal signal to obtain a filtered signal; A time synchronization unit, used for performing time synchronization on the filtered signal to obtain a time synchronization signal; A feature extraction unit, used to extract features from the time synchronization signal to obtain a feature signal; A fusion unit, used for performing modal fusion on the feature signal to obtain a comprehensive feature; The analysis unit is used to analyze the comprehensive features using the trained support vector machine model to obtain the analysis results.

4. The embedded electronic skull brain-computer interface device according to claim 3, characterized in that: The filtering unit comprises: A decomposition subunit, used for decomposing the EEG signal and the multimodal signal into sub-signals of different frequencies using basis functions; A coefficient sub-acquisition unit, used to obtain transform coefficients corresponding to sub-signals of different frequencies; The variance subunit is used to calculate the variance of the transformation coefficients at each decomposition scale; A model building unit, used for building a signal preprocessing model based on the variance of the transform coefficients; The preprocessing subunit is used to preprocess the EEG signal and the multimodal signal using the signal preprocessing model to obtain the filtered signal.

5. The embedded electronic skull brain-computer interface device according to claim 4, characterized in that: The model building units include: A standard deviation construction subunit is used to estimate the standard deviation of abnormal noise according to the variance of the transformation coefficients; The threshold construction subunit is used to construct a coefficient removal threshold according to the standard deviation of the noise; wherein the coefficient removal threshold is: Among them, t represents the coefficient removal threshold, σ0 represents the variance of the transformation coefficient, σ p represents the standard deviation of abnormal noise, median(d p ) represents the median value of the transform coefficients at the pth decomposition scale; The model building subunit is used to build a signal preprocessing model by using the coefficients to remove the threshold.

6. The embedded electronic skull brain-computer interface device according to claim 5, characterized in that: The formula of the signal preprocessing model is: Among them, α represents the transformation coefficient, w j,k represents the transformation coefficient at the jth decomposition scale, m represents the convergence coefficient, sgn represents the sign function, and w j,k Represents the transformation coefficients for removing outliers.

7. The embedded electronic skull brain-computer interface device according to claim 3, characterized in that: The feature extraction method is fast Fourier transform; the formula of fast Fourier transform is: Wherein, X(k) is the kth component of the time synchronization signal, x(n) is the nth sample of the signal in the time domain, N is the total number of sampling points, and j is an imaginary unit.

8. The embedded electronic skull brain-computer interface device according to claim 1, characterized in that: The central communication platform adopts a star network architecture communication platform based on Kafka message middleware.

Images