CN118797560B - A method for generating electrical stimulation signals based on brain-computer interface and related equipment - Google Patents
A method for generating electrical stimulation signals based on brain-computer interface and related equipment Download PDFInfo
- Publication number
- CN118797560B CN118797560B CN202411275729.XA CN202411275729A CN118797560B CN 118797560 B CN118797560 B CN 118797560B CN 202411275729 A CN202411275729 A CN 202411275729A CN 118797560 B CN118797560 B CN 118797560B
- Authority
- CN
- China
- Prior art keywords
- target user
- data
- target
- physiological
- generate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application provides a brain-computer interface-based method for generating an electrical stimulation signal and related equipment, which are applied to the technical field of data processing. The method comprises the steps of obtaining physiological data of a target user, medical use information of the target user, historical physiological parameter information of the target user and real-time somatosensory information of the target user, preprocessing the physiological data of the target user to generate multi-mode data of the target user, extracting characteristics of the multi-mode data of the target user based on the medical use information of the target user and the historical physiological parameter information of the target user to generate physiological characteristic risk influence factors, carrying out fusion processing on the physiological characteristic risk influence factors to generate target multi-mode data, processing the target multi-mode data and the real-time somatosensory information of the target user to generate autonomic nervous activity signal data of the target user, and processing the autonomic nervous activity signal data of the target user based on a target nervous regulation early warning model to generate an electric stimulation signal.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method for generating an electric stimulation signal based on a brain-computer interface and related equipment.
Background
Autonomic dysfunction, particularly overactivation of sympathetic nerves, can lead to functional and organic diseases in various organ systems of the human body, and current treatment modes include drug treatment such as beta blocker, and non-drug treatment includes stellate ganglion blocking, vagal nerve stimulation and the like. However, the traditional drug treatment has various limitations and disadvantages, such as that when a clinician applies a beta blocker, the dosage of the drug is mainly required to be adjusted according to the heart rate of a patient, subjective dependence exists, the acting time is slow after the dosage of the drug is adjusted, the treatment effect of the patient is influenced, and when the drug is excessive, the metabolism time of the drug is slow, and the safety of the patient is influenced.
Current measures in non-drug therapy are also very limited, and for example, the current clinical development of astroganglion block surgery requires invasive procedures on the neck, is not easily accepted by patients, and requires repeated visits to hospitals, thus limiting clinical development.
With the rapid development of the technical fields of artificial intelligence, brain-computer interface (Brain-computer interface, brain-computerinterfaces, BCI) and organoids in recent years, the theories of electroencephalogram signals, functional localization of corresponding Brain regions and the like are gradually clarified, and new hopes are brought for quantitative and qualitative assessment of noninvasive autonomic nervous system functions. Most traditional brain-computer interfaces are non-invasive, headgear-based, commercial products or microneedle-based invasive methods, but none of these methods are suitable for everyday use due to inconvenience, inflammation and even irreversible damage to human tissue.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The application aims to provide a brain-computer interface-based method and related equipment for generating an electrical stimulation signal, which at least overcome the problems existing in the prior art to a certain extent, and generate multi-mode data of a target user, including brain-computer signals, electrocardiosignals and heart sound signal data, by comprehensively analyzing physiological data, medical use information, historical physiological parameter information and real-time somatosensory information of the target user, wherein the physiological characteristic risk influencing factors can be formed after feature extraction and fusion processing of the data. And (3) carrying out deep analysis on the multi-modal data and the real-time somatosensory information of the user by using a target nerve regulation early warning model to generate autonomic nerve activity signal data. Finally, the model processes the signal data to generate an electric stimulation signal, so that the aim of regulating and controlling the autonomic nerves of the target user is fulfilled.
Other features and advantages of the application will be apparent from the following detailed description, or may be learned by the practice of the application.
According to one aspect of the application, the method for generating the electrical stimulation signal based on the brain-computer interface comprises the steps of obtaining physiological data of a target user, medical purpose information of the target user, historical physiological parameter information of the target user and real-time somatosensory information of the target user, preprocessing the physiological data of the target user to generate multi-mode data of the target user, wherein the multi-mode data of the target user comprise electroencephalogram signal data of the target user, electrocardiosignal data of the target user and heart sound signal data of the target user, extracting characteristics of the multi-mode data of the target user based on the medical purpose information of the target user and the historical physiological parameter information of the target user to generate physiological characteristic risk influencing factors, carrying out fusion processing on the physiological characteristic risk influencing factors to generate target multi-mode data, obtaining a target neural regulation early warning model, carrying out processing on the target multi-mode data and the real-time somatosensory information of the target user based on the target neural regulation early warning model to generate neural activity signal data of the target user, carrying out processing on the neural activity signal data of the target user based on the target neural regulation early warning model, and carrying out autonomous neural activity signal processing on the target user, and generating the autonomous neural activity signal for the electrical stimulation signal of the target user, wherein the autonomous electrical stimulation signal is used for regulating and controlling the electrical stimulation.
In one embodiment of the application, preprocessing the physiological data of the target user to generate the multi-modal data of the target user comprises denoising the physiological data of the target user to generate the physiological attribute information of the target user, wherein the physiological attribute information of the target user is the physiological data with the signal-to-noise ratio higher than a preset threshold value, and normalizing the physiological attribute information of the target user to generate the multi-modal data of the target user.
In one embodiment of the application, the method for generating the physiological feature risk influence factor comprises the steps of carrying out feature extraction on the multi-modal data of the target user to generate physiological feature classification information, processing the physiological feature classification information based on the medical use information of the target user to generate target physiological feature data, and processing the target physiological feature data based on the historical physiological parameter information of the target user to generate the physiological feature risk influence factor.
In one embodiment of the application, the method for generating the physiological characteristic classification information comprises the steps of processing the multi-mode data of the target user to generate the biological characteristic attribute information of the target user, performing characteristic extraction processing on the biological characteristic attribute information of the target user to generate a plurality of characteristic sample types, performing characteristic screening processing on the plurality of characteristic sample types to generate real-time characteristic sample data, and generating the physiological characteristic classification information based on the plurality of real-time characteristic sample data.
In one embodiment of the application, the physiological characteristic risk influence factors are fused to generate target multi-modal data, which comprises the steps of carrying out fusion processing on the physiological characteristic risk influence factors based on a preset long-short time memory network model to generate an initial physiological characteristic vector, wherein the initial physiological characteristic vector is formed by splicing physiological characteristic risk influence factors of a plurality of modes, carrying out processing on the initial physiological characteristic vector based on a preset weight characteristic processing rule to generate a target physiological characteristic vector, wherein the target physiological characteristic vector is obtained by adding physiological characteristic risk influence factors of different modes based on target weights, carrying out processing on the target physiological characteristic vector based on a preset long-short time memory network model to generate a prediction result of the multi-modal data, and carrying out processing on the prediction result of the multi-modal data to generate the target multi-modal data, wherein the method further comprises a calculation formula for acquiring the target physiological characteristic vector, and the calculation formula is as follows: Wherein, the method comprises the steps of, Is the vector of the physiological characteristics of the target,Is the weight of the i-th feature,Is the risk impact factor for the ith feature.
In one embodiment of the application, a target neuromodulation early-warning model is obtained, which comprises the steps of processing the physiological characteristic risk influence factors to generate identification information, wherein the identification information is used for representing that the physiological characteristic risk influence factors are in an abnormal state, obtaining an initial neuromodulation early-warning model matched with the identification information and a training sample set matched with the initial neuromodulation early-warning model, processing the training sample set based on a preset processing rule to generate a training set and a verification set, and processing the initial neuromodulation early-warning model based on the training set and the verification set to generate the target neuromodulation early-warning model.
In one embodiment of the application, the target multi-modal data and the real-time somatosensory information of the target user are processed based on the target nerve modulation early-warning model to generate the autonomous nerve activity signal data of the target user, and the autonomous nerve activity signal data of the target user is generated by processing the target multi-modal data based on the target nerve modulation early-warning model to generate skin conductance change information of the target user and skin temperature change information of the target user, processing the real-time somatosensory information of the target user based on the target nerve modulation early-warning model to generate skin contraction information of the target user, and processing the skin conductance change information of the target user and the skin temperature change information of the target user based on the skin contraction information of the target user.
The device for generating the electrical stimulation signals based on the brain-computer interface is characterized by comprising an acquisition module, a processing module, a target nerve regulation early warning model and an autonomous nerve activity signal processing module, wherein the acquisition module is used for acquiring physiological data of a target user, medical purpose information of the target user, historical physiological parameter information of the target user and real-time somatosensory information of the target user, the processing module is used for preprocessing the physiological data of the target user to generate multi-mode data of the target user, the multi-mode data of the target user comprises electroencephalogram signal data of the target user, electrocardio signal data of the target user and heart sound signal data of the target user, feature extraction is carried out on the multi-mode data of the target user based on the medical purpose information of the target user and the historical physiological parameter information of the target user to generate physiological feature risk influence factors, fusion processing is carried out on the physiological feature risk influence factors to generate the target multi-mode data, the autonomous nerve activity signal data of the target user is generated based on the target nerve regulation early warning model, the autonomous nerve activity signal data of the target user is processed based on the target nerve regulation early warning model, and the autonomous nerve activity signal data of the target user is stimulated by the autonomous nerve activity signal of the target user is generated.
According to yet another aspect of the application, an electronic device is characterized by comprising a first processor and a memory for storing executable instructions of the first processor, wherein the first processor is configured to perform a method of generating an electrical stimulation signal based on a brain-computer interface as described above via execution of the executable instructions.
According to yet another aspect of the present application, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a second processor, implements the above-described method of generating an electrical stimulation signal based on a brain-computer interface.
According to a further aspect of the present application, there is provided a computer program product comprising a computer program, characterized in that the computer program, when executed by a third processor, implements the above-mentioned method of generating an electrical stimulation signal based on a brain-computer interface.
According to the method and the related equipment for generating the electrical stimulation signals based on the brain-computer interface, the server generates the multi-mode data of the target user, including the brain electrical signals, the electrocardiosignals and the heart sound signal data, through comprehensively analyzing the physiological data, the medical use information, the historical physiological parameter information and the real-time somatosensory information of the target user, and the physiological characteristic risk influence factors can be formed after the data are subjected to characteristic extraction and fusion processing. And (3) carrying out deep analysis on the multi-modal data and the real-time somatosensory information of the user by using a target nerve regulation early warning model to generate autonomic nerve activity signal data. Finally, the model processes the signal data to generate an electric stimulation signal, so that the aim of regulating and controlling the autonomic nerves of the target user is fulfilled.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
FIG. 1 is a flow chart of a method for generating an electrical stimulation signal based on a brain-computer interface according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an apparatus for generating an electrical stimulation signal based on a brain-computer interface according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an electronic device according to an embodiment of the present application;
fig. 4 is a schematic diagram of a storage medium according to an embodiment of the present application.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
A method of generating an electrical stimulation signal based on a brain-computer interface according to an exemplary embodiment of the present application is described below with reference to fig. 1. It should be noted that the following application scenarios are only shown for facilitating understanding of the spirit and principles of the present application, and embodiments of the present application are not limited in this respect. Rather, embodiments of the application may be applied to any scenario where applicable.
In one embodiment, the application further provides a method and related equipment for generating the electrical stimulation signal based on the brain-computer interface. Fig. 1 schematically shows a flow diagram of a method of generating an electrical stimulation signal based on a brain-computer interface according to an embodiment of the application. As shown in fig. 1, the method is applied to a server, and includes:
S101, acquiring physiological data of a target user, medical purpose information of the target user, historical physiological parameter information of the target user and real-time somatosensory information of the target user.
In one embodiment, data such as Electrocardiography (ECG), electroencephalogram (EEG), myoelectricity (EMG), dermatology (EDA), blood volume and pulse, temperature, respiration, acceleration, etc. may be recorded using various physiological monitoring instruments, such as a wireless physiological analysis system PhysioLAB 291. The medical use information of the target user can be determined according to the specific requirements and symptoms of the target user, for example, the medical use information of the target user can be determined according to the specific requirements and symptoms of the target user, and the target user is an application scene of different symptoms, such as headache, insufficient sleep, palpitation, hypodynamia, insufficient memory and the like, and if the duration of onset of different symptoms and the current reserved time for treating the symptoms are different, different means are adopted to treat the different symptoms, and the target user is customized according to the specific health condition and requirements of the user, so that personalized health management, disease prevention and treatment solutions are provided.
Historical physiological parameter information of the target user is critical for personalized medicine and accurate treatment. By analyzing these historical data, a physician can better understand the patient's health, identify disease patterns, and formulate the most appropriate treatment plan. The doctor can analyze massive medical data including genome data, clinical examination results and medical image data of the historical physiological parameter information of the target user by utilizing the big data technology, and a more accurate and effective treatment plan is designed for the patient. By analyzing the historical medical history, physiological data and life habits of the patient, the big data technology is beneficial to predicting possible diseases of the patient in the future, optimizing the configuration of medical resources, ensuring that the patient can obtain the most suitable medical resources, and providing individualized risk prediction, diagnosis and treatment schemes for the patient through mining personal genome and other biological big data, and optimizing the configuration of the medical resources.
Real-time somatosensory information of the target user, particularly skin reactions and temperature changes, is critical to assess its acceptability to the current degree of treatment. Among them, the change of skin temperature is an expression of vascular reaction, and is influenced by external temperature and controlled by internal regulation mechanism. When the external temperature is reduced, the subcutaneous capillary blood vessel contracts to reduce heat dissipation, so that the skin temperature is reduced, otherwise, the heat dissipation is increased, and the skin temperature is increased. The regulation of skin temperature is mainly realized through vascular and sweat gland reactions, and is an important link of body temperature regulation. The change of the skin temperature can reflect the heat exchange condition between the human body and the environment, and has important significance for maintaining the stable body temperature. By monitoring the skin temperature and other physiological parameters of the target user in real time, the medical professional can more accurately determine whether the patient can accept the current treatment level and adjust the treatment scheme in time.
S102, preprocessing the physiological data of the target user to generate multi-mode data of the target user.
In one embodiment, denoising is performed on physiological data of a target user to generate physiological attribute information of the target user, wherein the physiological attribute information of the target user is physiological data with a signal-to-noise ratio higher than a preset threshold, normalization is performed on the physiological attribute information of the target user to generate multi-mode data of the target user, and the multi-mode data of the target user include but are not limited to electroencephalogram data of the target user, electrocardiograph data of the target user and heart sound signal data of the target user.
Specifically, physiological data of the user, such as signals of electrocardio, electroencephalogram, myoelectricity and the like, are collected through various sensors. Filtering, de-artifacting, etc. the collected physiological data to reduce noise components in the data. For example, in brain functional magnetic resonance imaging (fMRI) data, physiological disturbances of the heart and respiration signals have a significant impact on the data quality, and it is necessary to estimate and eliminate these noises using data-driven denoising methods or using filters (such as low-pass filtering, high-pass filtering and band-pass filtering), and to extract useful physiological features such as heart rate variability, brain wave shape features, etc. from the denoised signals. And (3) carrying out signal-to-noise ratio (SNR) evaluation on the denoised physiological data to ensure the data quality, wherein the SNR is the ratio of the useful signal intensity to the background noise intensity in the measured signal, the high SNR means that the signal quality is better, the physiological data with the SNR higher than a preset threshold value is regarded as effective data, and the physiological attribute information of the target user is further analyzed and generated.
And carrying out normalization processing on the physiological attribute information so that data of different sources or different dimensions can be compared and combined on the same scale, carrying out normalization processing on signals, eliminating scale differences among different data sources and ensuring consistency and comparability of input data. Normalization is the scaling of data to fall within a specific range, such as the [0,1] interval, while normalization is the centering and scale unification of data by subtracting the mean value and dividing by the standard deviation. The normalized physiological attribute information is subjected to multi-modal data generation, which may include brain electrical signal data, heart electrical signal data, and heart sound signal data. The generation of the multi-mode data is beneficial to comprehensively evaluating the health condition of the user from different angles, and in the process of recording the body electro-physiological signals, the signal quality is monitored in real time and adjusted according to feedback so as to ensure the high signal-to-noise ratio of the data. Through the steps, the physiological data of the target user can be effectively processed, high-quality physiological attribute information is extracted, and support is provided for subsequent analysis and evaluation.
And S103, carrying out feature extraction on the multi-mode data of the target user based on the medical use information of the target user and the historical physiological parameter information of the target user, and generating physiological feature risk influence factors.
In one embodiment, the multi-mode data of the target user is subjected to feature extraction to generate physiological feature classification information, wherein the physiological feature classification information comprises physiological feature data corresponding to a plurality of types, features such as R-R intervals, heart rate variability and the like are extracted from electrocardiosignals, S1 and S2 sound peak values, audio frequency spectrum features and the like are extracted from heart sound signals, and alpha wave and beta wave power spectrum features and the like are extracted from the electroencephalogram signals.
Specifically, for the feature extraction of the electroencephalogram signal, a Fast Fourier Transform (FFT) may be used to convert a time domain signal into a frequency domain signal, and extract a main frequency component, and the following calculation formula may be used to convert the time domain signal into the frequency domain signal: wherein X (n) is a time domain signal and X (f) is a frequency domain signal. The electroencephalogram signals are subjected to multi-scale decomposition by adopting Wavelet Transform (WT), characteristics of different frequency bands are extracted, and the wavelet transform can be used for performing multi-scale decomposition on the electroencephalogram signals and is realized by Continuous Wavelet Transform (CWT) or Discrete Wavelet Transform (DWT). The decomposed signals can be analyzed at different time and frequency resolutions, which helps to capture non-stationary characteristics and transient variations in the electroencephalogram signal. Various features such as energy, frequency distribution, statistical properties of wavelet coefficients, etc. can be extracted from the wavelet transformed signal. The characteristics reflect the activity intensity and distribution condition of the brain electrical signals in different frequency bands, and have important significance for understanding the working state and pattern recognition of the brain.
For feature extraction of electrocardiosignals, QRS complex detection can be performed by adopting a pan-thomson algorithm, heart rate and Heart Rate Variability (HRV) are extracted, time domain indexes of the heart rate variability, such as Standard Deviation (SDNN) and root mean square deviation (RMSSD), are calculated, and corresponding calculation formulas are respectively as follows:、。
For the feature extraction of the heart sound signals, the time-frequency features of the heart sound signals can be extracted by adopting Short Time Fourier Transform (STFT), and the features such as peak values, energy and frequency components of the heart sound can be extracted for the analysis of the heart sound signals.
And processing the physiological characteristic classification information based on the medical use information of the target user to generate target physiological characteristic data. Medical use information of the target user may be determined according to its specific needs and symptoms. For example, if the target user encounters a headache problem in the morning but needs to attend an important meeting in the afternoon, they may need a treatment regimen that can quickly relieve the symptoms. In this case, the selected physiological characteristic data will focus on those features that are able to react quickly and support temporary relief of headache, rather than the data required for a long-term treatment regimen.
In particular, if the goal is to completely cure a headache, a full range of physiological characteristic data may be required, including but not limited to blood pressure, heart rate, blood oxygen saturation, etc., which may be collected in real-time by various medical monitoring devices. However, if the goal is temporary relief, it may only be necessary to focus on several key physiological characteristic data directly related to the headache, such as heart rate variability or specific neural activity patterns.
Processing the target physiological characteristic data based on the historical physiological parameter information of the target user to generate physiological characteristic risk impact factors, wherein the physiological characteristic risk impact factors comprise, but are not limited to, heart rate variability, EEG spectrum characteristics and PCG audio characteristics. The abnormal deviation between physiological parameters is identified mainly by analyzing the physiological data of an individual, so that the health risk is estimated and positioned, and which physiological parameters are beyond the normal range or the deviation between the parameters is overlarge is identified by statistical analysis or a machine learning algorithm. For example, the Pan-Tompkins algorithm may be used to process the electrocardiogram signals, extract heart rate and Heart Rate Variability (HRV), and analyze the trend of these parameters, and when abnormal changes in physiological parameters are detected, timely issue early warning information to assist the user or doctor in taking preventive measures. Furthermore, there may be differences in physiological parameter baseline for different individuals, and thus individual specific conditions should be considered in risk assessment, providing personalized assessment results. The physiological characteristic data of the user can be effectively processed to generate risk influence factors with clinical significance, and scientific basis is provided for health management and disease prevention.
In another embodiment, the multi-modal data of the target user is subjected to feature extraction processing to generate physiological feature classification information, and the method specifically can refer to the following that the multi-modal data of the target user is processed to generate physical sign attribute information of the target user, and the multi-modal data of the target user is processed, which includes acquisition and preprocessing of signals such as electroencephalogram (EEG), myoelectricity (EMG) and heart rate (ECG). For example, EEG signals may be feature extracted through a deep learning network such as ResNets-50, and EOG and EMG signals processed using Mel Frequency Cepstrum Coefficients (MFCCs), where the vital sign attribute information of the target user is used to characterize the current physical state information of the target user, i.e., what symptoms, the response and duration of symptoms, etc. are currently present by the target user.
And carrying out feature extraction processing on the biological feature attribute information of the target user to generate a plurality of feature sample types. Specifically, corresponding physiological parameter information is selected based on the physical state of the target user, and when feature extraction processing is performed, corresponding feature extraction technology can be adopted for different types of physiological signals so as to generate feature sample types. The feature extraction of the electroencephalogram signal can be performed by adopting time domain features such as zero-crossing rate, standard deviation, maximum/minimum value, skewness, kurtosis and the like, frequency domain features such as Power Spectrum Density (PSD) obtained through Fourier transform, frequency band power, frequency peak and the like, time-frequency domain features such as time-frequency representation obtained through wavelet transform such as wavelet energy, wavelet entropy and the like, and nonlinear features such as approximate entropy, sample entropy, lyapunov index and the like. For the feature extraction of the electromyographic signals, the time domain features comprise mean value, variance, root mean square, waveform factor, skewness, kurtosis and the like, the frequency domain features comprise frequency distribution features obtained through Fourier transformation, such as mean value frequency, median frequency, frequency band energy and the like, the time-frequency domain features comprise time-varying features extracted through wavelet transformation, and the nonlinear dynamic features comprise Hjorth parameters, relevant dimensions and the like. For the feature extraction of the heart rate signal, time domain features such as standard deviation of heart rate and RR interval, maximum/minimum heart rate, etc., frequency domain features such as Heart Rate Variability (HRV) indexes such as SDNN, RMSSD, power spectrum density, etc., time-frequency domain features such as analysis of non-stationary features of the heart rate signal by wavelet transformation, morphological features such as width, amplitude, area, etc. of the QRS complex can be adopted. For feature extraction of galvanic skin activity, amplitude, rise time, recovery time, etc., event-related galvanic skin activity (PHASICEDA) and non-specific galvanic skin activity (tonicEDA) may be employed. The feature extraction of each physiological signal depends on the characteristics of the signal and the analysis purpose. After feature extraction, a plurality of feature sample types may be generated, each type containing a specific set of features that are capable of reflecting different aspects of the physiological signal. In practical applications, depending on the requirements of a specific task, a specific feature type may be selected for analysis to achieve optimal performance.
And performing feature screening processing on the plurality of feature sample types to generate real-time feature sample data, and generating physiological feature classification information based on the plurality of real-time feature sample data. Feature screening is a key step in the feature extraction process of processing multi-modal vital sign attribute information, which helps identify features that are most important to model performance from a large number of features, thereby generating real-time feature sample data, and generating physiological feature classification information based on these data. Feature screening can be accomplished by a variety of methods, including statistical-based methods (e.g., correlation analysis, mutual information methods), model-based methods (e.g., using random forests to evaluate feature importance), and embedded methods (e.g., automatically learning the importance of features during neural network training). These methods may help the applicant identify the features that have the most impact on predicting the target variables.
After feature screening, the applicant can obtain a simplified feature set, and the timeliness of the data needs to be considered in the generation of the real-time feature sample data, so that the feature can timely reflect the current state of the user. This process may involve the use of dimensionality reduction techniques such as Principal Component Analysis (PCA) to remove redundant information and preserve the most representative features. A classification model can be constructed to generate physiological feature classification information by using the filtered real-time feature sample data. The method may involve using a machine learning algorithm, such as a Support Vector Machine (SVM), random forest, deep learning, etc., to classify and identify feature data, and the classification result may provide basis for further health assessment and disease diagnosis, effectively process multi-modal vital sign attribute information, screen out key features, and generate real-time physiological feature classification information, providing scientific basis for health monitoring and disease prevention.
S104, fusion processing is carried out on the physiological characteristic risk influence factors, and target multi-mode data are generated.
In one embodiment, physiological characteristic risk influence factors are fused based on a preset long-short time memory network model, and an initial physiological characteristic vector is generated, wherein the initial physiological characteristic vector is formed by splicing physiological characteristic risk influence factors of a plurality of modes. After physiological feature risk influencing factors (such as electroencephalogram (EEG), electromyogram (EMG) and the like) are obtained, feature data of different modes are combined into a feature vector through feature level fusion, and then the feature vector is sent into a classifier. It should be noted that complementary information may exist between different modalities, and the recognition effect may be effectively improved by reasonably utilizing the information. Meanwhile, the feature fusion method can be fusion of a data level, a feature level, a decision level or a model layer, and the specific selection of which method depends on the characteristics of data and the requirements of the recognition task. Through these steps, the multimodal data can be efficiently processed and useful physiological characteristic classification information generated to support further health assessment and disease diagnosis.
Processing the initial physiological feature vector based on a preset weight feature processing rule to generate a target physiological feature vector, wherein the target physiological feature vector is obtained by adding physiological feature risk influence factors of different modes based on target weights. First, it is necessary to identify and determine which physiological characteristics are risk influencing factors, such as heart rate, blood pressure, respiratory rate, etc., each risk influencing factor is assigned a weight reflecting the importance of the respective factor in the overall risk assessment, and the assignment of weights may be based on expert knowledge, statistical analysis, or predictions of machine learning models.
Since the dimensions and magnitude ranges of different physiological features may be different, it is necessary to normalize the initial physiological feature vector to ensure that the contribution of each feature is comparable when weighted summation, multiply the risk impact factor of each physiological feature by its corresponding weight, and then add all the results to obtain the target physiological feature vector. This process can be expressed by the following mathematical formula: Wherein, the method comprises the steps of, Is the vector of the physiological characteristics of the target,Is the weight of the i-th feature,Is the risk impact factor for the ith feature.
The generated target physiological feature vector should be capable of reflecting the physiological state and health risk of the individual. The vector can be used for further analysis, such as classification, clustering or as input of a machine learning model, and in practical application, the weight distribution may need to be updated in real time according to new data and feedback, and the target physiological characteristic vector is adjusted to adapt to possible changes and new physiological characteristics, so that the multi-mode physiological data can be effectively integrated, a characteristic vector comprehensively reflecting the health condition of an individual is generated, and support is provided for health risk assessment and disease diagnosis.
Processing the target physiological feature vector based on a preset long-short time memory network model, generating a prediction result of the multi-mode data, and processing the prediction result of the multi-mode data to generate target multi-mode data. Long and short term memory networks (LSTM) are powerful recurrent neural networks capable of processing sequence data, especially for long-term dependence problems, and when processing target physiological feature vectors, LSTM can learn the time dependence in sequence data and generate predictive results for multi-modal data. The model may receive as input a target physiological feature vector. The model construction may include defining the number of neurons of the LSTM layer, selecting an activation function (e.g., tanh or ReLU), and determining the configuration of the output layer, training the LSTM model using historical physiological data. In the training process, the LSTM learns long-term and short-term dependency relationships between features, so that multi-modal data can be effectively predicted, wherein the target multi-modal data is generated based on symptoms which are needed to be solved by a target user currently.
S105, acquiring a target nerve regulation early warning model.
In one embodiment, physiological feature risk influence factors are processed to generate identification information, wherein the identification information is used for representing that the physiological feature risk influence factors are in an abnormal state, an initial neuromodulation early-warning model matched with the identification information and a training sample set matched with the initial neuromodulation early-warning model are obtained, the training sample set is processed based on a preset processing rule to generate a training set and a verification set, and the initial neuromodulation early-warning model is processed based on the training set and the verification set to generate a target neuromodulation early-warning model.
In another embodiment, a training data set is processed based on a preset processing rule to generate a training set and a verification set, specifically comprising the steps of obtaining physiological feature risk influence factors of other users matched with identification information, carrying out feature extraction on the physiological feature risk influence factors of the other users to generate a feature data set, obtaining any number of data features in the feature data set, generating adjacent features based on the distance between any number of data features and other numbers of data features in the same category, wherein the adjacent features comprise the preset number of any number of data features, determining a sampling proportion based on the number of data features in the training set, determining a sampling proportion based on the sampling proportion, sampling the adjacent features based on the sampling proportion to generate a preset number of sampling features, generating multiple groups of data sets based on any data feature and each sampling feature, wherein each group of data sets comprises the preset number of data samples, at least one data sample comprises identification information, processing the multiple groups to generate the training set and the verification set, and generating the training set and the verification set, wherein each of the training set and the verification set comprises the data features.
Specifically, in data analysis and machine learning, the sampling proportion and sampling ratio are determined based on the number of data features in the training set, the distribution situation of different features is known by counting the number of data features in the training set, and the sampling proportion is determined according to the number of data features and the size of the data set. The sampling ratio may help us decide how many samples to extract from each feature, from which a specific sampling ratio is calculated. The sampling ratio is a ratio of an actual number of samples to a total number of samples, and adjacent features are sampled using the sampling ratio to generate a preset number of sampled features. This process ensures the representativeness and diversity of the sample by generating a set of sampled features through the sampling process that will be used for subsequent data analysis and model training, constructing multiple sets of data sets based on any one data feature and each sampled feature. Each data set contains a predetermined number of data samples. Ensuring that the samples in each set of data sets are diverse, including at least one sample with identification information, facilitates model learning to feature representation under different conditions, model training using the data sets, evaluating contributions of different features to a prediction target, training a machine learning model using a set of sampled features, and evaluating performance of the model by a validation set, it may be necessary to adjust sampling proportions and ratios to optimize the predictive power of the model based on the results of model training and validation. By this method, large-scale data sets can be processed efficiently while maintaining the quality of the data and generalization ability of the model, helping to identify potential security risks and abnormal behavior.
S106, processing the target multi-modal data and the real-time somatosensory information of the target user based on the target nerve regulation early-warning model to generate the autonomous nerve activity signal data of the target user.
In one embodiment, the target multimodal data is processed based on a target neuromodulation early warning model to generate skin conductance change information of the target user and skin temperature change information of the target user. When target multimodal data is processed based on a target nerve regulation early warning model, skin conductance change information and skin temperature change information of a target user are generated as two key physiological parameters. Galvanic Skin Response (GSR) is a method of monitoring changes in skin conductance that reflects the state of sympathetic activity, and increases sweat gland activity when the human body experiences a change in emotion or physiological arousal, resulting in a measurable change in skin conductance. Whereas monitoring of skin temperature is typically accomplished by a contact temperature sensor, which can indirectly reflect the activity of the autonomic nerve, since the change in skin temperature is primarily dependent on the blood flow through the skin, the magnitude of which is affected by the excitability of the sympathetic nerve.
In practical application, the multi-mode data fusion technology can effectively integrate information from different modes, improve the performance of a model, and project single-mode features into a shared semantic subspace in different modes to realize feature fusion. These techniques may be applied to integrate multimodal physiological data such as skin conductance and skin temperature to generate more comprehensive physiological characteristic classification information. In the aspect of monitoring skin temperature change, research indicates that the rise of skin temperature can be used as an objective index for evaluating the blocking effect of an area, especially on hairless skin at the far end of limbs, the rise of skin temperature after sympathetic nerve blocking is particularly obvious, physiological parameters such as skin conductance, skin temperature and the like can be effectively processed and analyzed, and accurate physiological characteristic classification information is provided for a nerve regulation early warning model.
Processing real-time somatosensory information of the target user based on the target nerve regulation early-warning model, generating skin contraction information of the target user, processing skin conductance change information of the target user and skin temperature change information of the target user based on the skin contraction information of the target user, and generating autonomic nerve activity signal data of the target user. That is, since each user has a certain difference in the neural response, for example, the response to the same symptom, some people may have symptoms that are obvious just before the onset of the response, and some people may have the response after the symptoms continue to develop to a certain extent, at this time, the degree of the symptom of the user is judged by the skin conductance change information and the skin temperature change information of the target user, and the response condition of each user is judged by referring to the skin contraction information of each user, thereby generating autonomic nerve activity signal data conforming to each user.
And S107, processing the autonomic nervous activity signal data of the target user based on the target nerve regulation early warning model to generate an electric stimulation signal.
In one embodiment, the provision of direct targeting of electrical stimulation at start-up in the prior art is reduced so that the patient experiences intense stimulation without any sign, thereby affecting patient comfort. When the scheme receives the autonomic nerve activity signal data of the target user, the single stimulation consists of a plurality of pulse waveforms with fixed frequency, wherein the first pulse waveform is that the voltage of the first half section is rapidly increased from 0 to the target voltage value of the patient. The subsequent pulse waveforms are square wave pulses of the target voltage. The invention can effectively improve the adaptability of the patient to the voltage and effectively relieve the discomfort of the electric shock caused by the stimulation of the patient when the stimulator starts pulse stimulation each time.
In addition, the invention also comprises a calculation formula for generating the comfort voltage value, which is specifically shown as follows:
。
a is a pulse-issuing target voltage value, B is a rising rate constant, defaults to 100, and the rising speed of the voltage can be adjusted by changing the value of B.
The ear-entering brain-computer interface is used as a noninvasive brain-computer interface technology, is a mode which is easy to operate and is most easily accepted by a patient, can detect the brain-electrical activity condition of the patient, and can more accurately reflect the activity of the autonomic nerve function by carrying out multi-mode data fitting on data of the brain-electrical signal, the autonomic nerve activity signal and the electrocardiosignal, including heart rate variability analysis and other reaction autonomic nerve function states, thereby providing more effective and safer detection index references for the stimulation of the vagus nerve of the ear.
At the same time, the vagus nerve branches pass through the cartilage of auricle and are distributed in the concha cavity, the posterior muscle of the ear and the middle and upper part of the back of the ear (external auditory canal), and branch to the root of the auricular foot and the triangular fossa, the antitragus and the middle part of the auricular boat. The in-ear autonomic nerve regulation and control equipment not only can collect brain electrical signals through electrodes in ears, but also can activate vagus nerves through modes of electric stimulation, laser stimulation, millimeter wave stimulation, ultrasonic stimulation and the like through electrodes connected to the parts of the ear nails, and inhibit overactivation of sympathetic nerves, so that autonomic nerve rebalancing is regulated, and the nerve-body fluid-metabolism regulation steady state of an organism is restored.
Therefore, the application collects multi-mode data on the basis of the flexible electrode, carries out interactive integration analysis on the data through the brain-computer interface and the target nerve regulation early warning model, and regulates the autonomic nerve by utilizing different stimulation modes, thereby having good innovation and clinical application value.
By applying the technical scheme, the server acquires physiological data of the target user, medical purpose information of the target user, historical physiological parameter information of the target user and real-time somatosensory information of the target user, performs denoising processing on the physiological data of the target user to generate physiological attribute information of the target user, wherein the physiological attribute information of the target user is physiological data with signal-to-noise ratio higher than a preset threshold, performs normalization processing on the physiological attribute information of the target user to generate multi-mode data of the target user, wherein the multi-mode data of the target user comprises electroencephalogram signal data of the target user, electrocardio signal data of the target user and heart sound signal data of the target user, processes the multi-mode data of the target user to generate biological sign attribute information of the target user, performs feature extraction processing on the biological sign attribute information of the target user to generate a plurality of feature sample types, performs feature screening processing on the plurality of feature sample types to generate real-time feature sample data, generates physiological feature classification information based on the plurality of feature sample types, and the physiological feature classification information based on the real-time feature sample data, wherein the physiological feature classification information comprises physiological feature data corresponding to the plurality of types of the physiological feature information, and the physiological feature information is generated based on the medical purpose information of the target user.
The method comprises the steps of processing target physiological feature data based on historical physiological parameter information of a target user to generate physiological feature risk influence factors, carrying out fusion processing on the physiological feature risk influence factors based on a preset long-short time memory network model to generate initial physiological feature vectors, wherein the initial physiological feature vectors are formed by splicing physiological feature risk influence factors of a plurality of modes, processing the initial physiological feature vectors based on preset weight feature processing rules to generate target physiological feature vectors, wherein the target physiological feature vectors are obtained by adding physiological feature risk influence factors of different modes based on target weights, processing the target physiological feature vectors based on a preset long-short time memory network model to generate a prediction result of multi-mode data, processing the prediction result of the multi-mode data to generate target multi-mode data, processing the physiological feature risk influence factors to generate identification information, wherein the identification information is used for representing that the physiological feature risk influence factors are in an abnormal state, acquiring an initial neural adjustment model matched with the identification information and a training sample set matched with the initial neural adjustment model, processing the training sample set based on the preset processing rules to generate a training set and a verification set, and carrying out early warning processing on the initial neural adjustment model based on the training set and the verification set.
The method comprises the steps of processing target multi-mode data based on a target nerve regulation early-warning model to generate skin conductance change information of a target user and skin temperature change information of the target user, processing real-time somatosensory information of the target user based on the target nerve regulation early-warning model to generate skin contraction information of the target user, processing the skin conductance change information of the target user and the skin temperature change information of the target user based on the skin contraction information of the target user to generate autonomic nerve activity signal data of the target user, and processing the autonomic nerve activity signal data of the target user based on the target nerve regulation early-warning model to generate an electric stimulation signal, wherein the electric stimulation signal is used for regulating and controlling autonomic nerves of the target user. The physiological data, medical use information, historical physiological parameter information and real-time somatosensory information of the target user are comprehensively analyzed to generate multi-mode data of the target user, wherein the multi-mode data comprises brain electrical signals, electrocardiosignals and heart sound signal data, and the physiological characteristic risk influencing factors can be formed after the data are subjected to characteristic extraction and fusion processing. And (3) carrying out deep analysis on the multi-modal data and the real-time somatosensory information of the user by using a target nerve regulation early warning model to generate autonomic nerve activity signal data. Finally, the model processes the signal data to generate an electric stimulation signal, so that the aim of regulating and controlling the autonomic nerves of the target user is fulfilled.
In one embodiment, as shown in fig. 2, the present application further provides an apparatus for generating an electrical stimulation signal based on a brain-computer interface, including:
The acquisition module 201 is used for acquiring physiological data of a target user, medical use information of the target user, historical physiological parameter information of the target user and real-time somatosensory information of the target user;
The processing module 202 is configured to pre-process the physiological data of the target user to generate multi-modal data of the target user, where the multi-modal data of the target user includes brain electrical signal data of the target user, heart electrical signal data of the target user, and heart sound signal data of the target user, perform feature extraction on the multi-modal data of the target user based on medical use information of the target user and historical physiological parameter information of the target user to generate physiological feature risk influencing factors, perform fusion processing on the physiological feature risk influencing factors to generate target multi-modal data, process the real-time somatosensory information of the target user and the target multi-modal data based on the target nerve regulation pre-warning model to generate autonomous nerve activity signal data of the target user, and process the autonomous nerve activity signal data of the target user based on the target nerve regulation pre-warning model to generate an electrical stimulation signal, where the electrical stimulation signal is used for autonomous nerve regulation of the target user.
In another embodiment of the present application, the processing module 202 is configured to pre-process the physiological data of the target user to generate multi-modal data of the target user, and includes denoising the physiological data of the target user to generate physiological attribute information of the target user, where the physiological attribute information of the target user is physiological data with a signal-to-noise ratio higher than a preset threshold, and normalize the physiological attribute information of the target user to generate multi-modal data of the target user.
In another embodiment of the present application, the processing module 202 is configured to perform feature extraction on the multimodal data of the target user based on the medical use information of the target user and the historical physiological parameter information of the target user, and generate a physiological feature risk impact factor, including:
extracting features of the multi-mode data of the target user to generate physiological feature classification information, wherein the physiological feature classification information comprises physiological feature data corresponding to a plurality of types;
processing the physiological characteristic classification information based on the medical use information of the target user to generate target physiological characteristic data;
and processing the target physiological characteristic data based on the historical physiological parameter information of the target user to generate physiological characteristic risk influence factors.
In another embodiment of the present application, the processing module 202 is configured to perform feature extraction processing on the multimodal data of the target user, and generate physiological feature classification information, including:
Processing the multi-mode data of the target user to generate physical sign attribute information of the target user;
performing feature extraction processing on the biological feature attribute information of the target user to generate a plurality of feature sample types;
Performing feature screening processing on the plurality of feature sample types to generate real-time feature sample data;
physiological feature classification information is generated based on the number of real-time feature sample data.
In another embodiment of the present application, the processing module 202 is configured to perform fusion processing on the physiological characteristic risk impact factors to generate target multi-modal data, and includes:
Performing fusion processing on the physiological characteristic risk influence factors based on a preset long-short time memory network model to generate an initial physiological characteristic vector, wherein the initial physiological characteristic vector is formed by splicing physiological characteristic risk influence factors of a plurality of modes;
Processing the initial physiological feature vector based on a preset weight feature processing rule to generate a target physiological feature vector, wherein the target physiological feature vector is obtained by adding physiological feature risk influence factors of different modes based on target weights;
Processing the target physiological feature vector based on a preset long-short time memory network model to generate a prediction result of multi-mode data;
and processing the prediction result of the multi-mode data to generate target multi-mode data.
In another embodiment of the present application, the processing module 202 is configured to obtain a target neuromodulation early-warning model, including:
processing the physiological characteristic risk influence factors to generate identification information, wherein the identification information is used for representing that the physiological characteristic risk influence factors are in an abnormal state;
acquiring an initial neuromodulation early-warning model matched with the identification information and a training sample set matched with the initial neuromodulation early-warning model;
Processing the training sample set based on a preset processing rule to generate a training set and a verification set;
and processing the initial neuromodulation early-warning model based on the training set and the verification set to generate a target neuromodulation early-warning model.
In another embodiment of the present application, the processing module 202 is configured to process the target multimodal data and the real-time somatosensory information of the target user based on the target neuromodulation early-warning model, and generate the autonomic nervous activity signal data of the target user, including:
Processing the target multi-mode data based on the target nerve regulation early warning model to generate skin conductance change information of a target user and skin temperature change information of the target user;
processing the real-time somatosensory information of the target user based on the target nerve regulation early-warning model to generate skin contraction information of the target user;
and processing the skin conductance change information of the target user and the skin temperature change information of the target user based on the skin contraction information of the target user to generate autonomic nervous activity signal data of the target user.
The embodiment of the application provides an electronic device, as shown in fig. 3, the electronic device 3 comprises a first processor 300, a memory 301, a bus 302 and a communication interface 303, wherein the first processor 300, the communication interface 303 and the memory 301 are connected through the bus 302, a computer program capable of running on the first processor 300 is stored in the memory 301, and the method for generating an electrical stimulation signal based on a brain-computer interface provided by any one of the previous embodiments of the application is executed when the first processor 300 runs the computer program.
The memory 301 may include a high-speed Random Access Memory (RAM), and may further include a non-volatile memory (non-volatilememory), such as at least one disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 303 (which may be wired or wireless), the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.
Bus 302 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. The memory 301 is configured to store a program, and after receiving an execution instruction, the first processor 300 executes the program, and the method for generating an electrical stimulation signal based on a brain-computer interface disclosed in any of the foregoing embodiments of the present application may be applied to the first processor 300 or implemented by the first processor 300.
The first processor 300 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in software form in the first processor 300. The first processor 300 may be a general-purpose processor including a Central Processing Unit (CPU), a network processor (NetworkProcessor NP), etc., or may be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied as a hardware decoding processor executing or a combination of hardware and software modules executing in the decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 301 and the first processor 300 reads the information in the memory 301 and in combination with its hardware performs the steps of the above method.
The electronic device provided by the embodiment of the application and the method for generating the electrical stimulation signal based on the brain-computer interface provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the application program stored in the electronic device based on the brain-computer interface due to the same inventive concept.
An embodiment of the present application provides a computer readable storage medium, as shown in fig. 4, where the computer readable storage medium 401 stores a computer program, and when the computer program is read and executed by the second processor 402, the foregoing method for generating an electrical stimulation signal based on a brain-computer interface is implemented.
The technical solution of the embodiment of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method of the embodiment of the present application. The storage medium includes various media capable of storing program codes such as a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk.
The computer readable storage medium provided by the above embodiment of the present application has the same advantages as the method adopted, operated or implemented by the application program stored in the computer readable storage medium for generating the electrical stimulation signal based on the brain-computer interface provided by the embodiment of the present application, because the same inventive concept is adopted.
Embodiments of the present application provide a computer program product comprising a computer program for execution by a third processor to implement a method as described above.
The computer program product provided by the above embodiment of the present application and the method for generating an electrical stimulation signal based on a brain-computer interface provided by the embodiment of the present application are the same inventive concept, and have the same beneficial effects as the method adopted, operated or implemented by the application program stored therein.
It is noted that in the present application, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The embodiments of the present application are described in a related manner, and the same similar parts between the embodiments are all mutually referred, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the evaluation of the embodiment of the method of generating an electrical stimulation signal based on a brain-computer interface, the electronic device, the electronic apparatus, and the readable storage medium, the description is relatively simple, and the relevant point is only needed for a part of the description of the embodiment of the method of generating an electrical stimulation signal based on a brain-computer interface, since it is basically similar to the embodiment of the method of generating an electrical stimulation signal based on a brain-computer interface described above.
Although the present application is disclosed above, the present application is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the application, and the scope of the application should be assessed accordingly to that of the appended claims.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411275729.XA CN118797560B (en) | 2024-09-12 | 2024-09-12 | A method for generating electrical stimulation signals based on brain-computer interface and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411275729.XA CN118797560B (en) | 2024-09-12 | 2024-09-12 | A method for generating electrical stimulation signals based on brain-computer interface and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118797560A CN118797560A (en) | 2024-10-18 |
| CN118797560B true CN118797560B (en) | 2024-12-03 |
Family
ID=93023863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411275729.XA Active CN118797560B (en) | 2024-09-12 | 2024-09-12 | A method for generating electrical stimulation signals based on brain-computer interface and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118797560B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119092131B (en) * | 2024-11-07 | 2025-01-21 | 北京大学第三医院（北京大学第三临床医学院） | Target user health early warning method based on large language model and related equipment |
| CN119108113B (en) * | 2024-11-11 | 2025-02-11 | 吉林大学第一医院 | Early warning method and system for risk assessment of elderly puerpera |
| CN119424919B (en) * | 2025-01-10 | 2025-04-29 | 中国康复研究中心 | Control method for sacral nerve electrical stimulation and related equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200066A (en) * | 2020-10-09 | 2021-01-08 | 河北工业大学 | A Somatosensory Stimulation Brain-Computer Interface Paradigm and Implementation Method Combining Space and Frequency |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150142082A1 (en) * | 2013-11-15 | 2015-05-21 | ElectroCore, LLC | Systems and methods of biofeedback using nerve stimulation |
| US12515079B2 (en) * | 2021-06-30 | 2026-01-06 | Carnegie Mellon University | Systems and methods for personalized ultrasound neuromodulation |
-
2024
- 2024-09-12 CN CN202411275729.XA patent/CN118797560B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200066A (en) * | 2020-10-09 | 2021-01-08 | 河北工业大学 | A Somatosensory Stimulation Brain-Computer Interface Paradigm and Implementation Method Combining Space and Frequency |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118797560A (en) | 2024-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kaur et al. | Age and gender classification using brain–computer interface | |
| Kamble et al. | A comprehensive survey on emotion recognition based on electroencephalograph (EEG) signals | |
| Fernandez Rojas et al. | A systematic review of neurophysiological sensing for the assessment of acute pain | |
| CN111477299B (en) | Method and device for regulating and controlling sound-electricity stimulation nerves by combining electroencephalogram detection and analysis control | |
| CN118797560B (en) | A method for generating electrical stimulation signals based on brain-computer interface and related equipment | |
| US7269455B2 (en) | Method and system for predicting and preventing seizures | |
| Sharma et al. | Recent trends in EEG-based motor imagery signal analysis and recognition: a comprehensive review | |
| CA2801251C (en) | Cognitive function assessment in a patient | |
| CN117137500B (en) | Intelligent anesthesia depth monitoring instrument and feedback control system | |
| US20220199245A1 (en) | Systems and methods for signal based feature analysis to determine clinical outcomes | |
| Baghdadi et al. | Dasps: A database for anxious states based on a psychological stimulation | |
| Seal et al. | An EEG database and its initial benchmark emotion classification performance | |
| JP2025504414A (en) | Systems and methods for detection of delirium and other neurological conditions - Patents.com | |
| Hosseini et al. | Emotional stress recognition using a new fusion link between electroencephalogram and peripheral signals | |
| CN119454052A (en) | Intelligent sleep state monitoring method and device based on brain waves | |
| Munavalli et al. | Introduction to brain–computer interface: applications and challenges | |
| CN120412876A (en) | A personalized treatment for tinnitus based on artificial intelligence | |
| EP3850639A1 (en) | System and methods for consciousness evaluation in non-communcating subjects | |
| Mishra et al. | An emotionally intelligent haptic system–An efficient solution for anxiety detection and mitigation | |
| Hussain et al. | An interpretable tinnitus prediction framework using gap-prepulse inhibition in auditory late response and electroencephalogram | |
| CN120094067A (en) | Sleep-wake circadian rhythm disorder regulation method and device based on ultrasound stimulation | |
| Islam et al. | A review on emotion recognition with machine learning using EEG signals | |
| CN111760194B (en) | An intelligent closed-loop neural control system and method | |
| Yassin et al. | A FUSION OF A DISCRETE WAVELET TRANSFORM-BASED AND TIME-DOMAIN FEATURE EXTRACTION FOR MOTOR IMAGERY CLASSIFICATION. | |
| CN116570289A (en) | A Depression State Assessment System Based on Portable EEG |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |