43 results about "Electrical brain activity" patented technology

The invention relates to an electroencephalogram classification method fusing phase amplitude coupling characteristics, and belongs to the field of electroencephalogram signal processing and deep learning. The method comprises the following steps: collecting electroencephalogram signal data, and carrying out channel selection and preprocessing; performing Hilbert transform on the EEG signal of each channel, and extracting instantaneous phase and amplitude information; calculating the coupling degree of phases and amplitudes between different frequency bands, and generating a phase-amplitude coupling characteristic matrix for representing the cross-frequency coupling strength; and the PAC features and the original EEG time sequence features are jointly input into an improved Transform classification network, a self-attention mechanism is utilized to effectively model a time sequence dependence and frequency coupling relationship, multi-scale time domain, frequency domain and space features are extracted, fusion calculation is performed, and a final classification result is output. According to the method, the dependence of a traditional electroencephalogram classification method on a single frequency spectrum feature is overcome, the modeling capability of an electroencephalogram activity cross-frequency cooperation mechanism is enhanced, and the accuracy and generalization performance of electroencephalogram classification are improved.

The invention discloses a disturbance of consciousness stimulation regulation and control system and method fused with electroencephalogram connection recognition. The system comprises a simulated electroencephalogram signal data acquisition stage, a connection recognition analysis stage, a stimulation parameter optimization stage and an executable stimulation instruction conversion stage. The method has the following advantages and effects that a whole-electroencephalogram activity distribution diagram is generated by simulating an electroencephalogram signal data acquisition stage, a key connection area is identified, and a brain function connection map is generated by utilizing a function connection analysis network and a phase synchronization algorithm in a connection identification analysis stage; in the stimulation parameter optimization stage, space-time correlation between a whole electroencephalogram activity distribution map and a brain function connection map is established, a multi-objective optimization algorithm is adopted to generate an optimized stimulation parameter set through a fusion network, and finally, in the executable stimulation instruction conversion stage, the optimized stimulation parameter set is converted into an executable stimulation instruction based on a self-adaptive control model. Therefore, the accuracy and the self-adaptive capability of electroencephalogram signal stimulation regulation and control are remarkably improved.

The embodiment of the present application provides a sports rehabilitation training method, electronic device and sports rehabilitation training system. The method includes: in the process of using a sports training device to perform rehabilitation training on the limbs of the training object, outputting the movement prompt information corresponding to the first training task of the sports training device in the current time period, so that the training object generates a movement intention according to the movement prompt information to actively follow the movement of the sports training device; obtaining the EEG activity information of multiple positions of the training object's brain in the current time period; according to the EEG activity information, determining the consistency information between the first movement intention of the training object in the current time period and the first training task and the consistency information between the first training task; according to the consistency information, determining the second training task of the sports training device in the next time period. The training effect of sports rehabilitation training can be significantly improved.

The invention discloses a brain-computer interface system based on audio-visual matching error monitoring, which is characterized in that: according to EEG data obtained by three feedback paradigms of audio-visual matching errors, important ERP components related to the audio-visual matching errors are extracted by applying ERP analysis, so that neural responses in a specific time window are interpreted; then, on the basis of time-frequency analysis, dynamic changes of the electroencephalogram signals in different wave bands are captured, and the reliability and stability of the electroencephalogram activity in different feedback modes are revealed by combining ITPC of the electroencephalogram activity; and finally, through an improved EEGNet model, automatic feature extraction and efficient classification of the signals are realized, and the robustness and generalization ability of the system are improved. The electroencephalogram signals have high nonlinearity and specificity, by combining ERP analysis, time-frequency analysis and a deep learning model, potential neural mechanisms of audio-visual matching errors can be more effectively understood, the performance of a brain-computer interface system is improved, and the method is applied to clinical research of error processing related obstacles.

According to the system for evaluating the treatment effect of the AUD patient through the electroencephalogram power spectrum characteristics, the electroencephalogram activity is captured through an electroencephalogram monitoring sensor, the electroencephalogram power spectrum characteristics in a resting state are calculated through a data processing unit, the electroencephalogram power spectrum characteristics are compared with a preset reference value or index modes in different psychological states, and the treatment effect of the AUD patient is evaluated. To identify features of brain activity of the patient. The preset value is based on a classification of subconsciousness and consciousness reactions of the AUD patient and statistically validated. The system judges the brain activity state and the treatment effect of the AUD patient according to the analysis result of the electroencephalogram power spectrum characteristics, and the analysis and judgment result is displayed through an output unit. The system can accurately evaluate the treatment effect of the new treatment method of subconsciousness memory degradation on the AUD patient, so as to provide accurate treatment and prevention strategies for the AUD patient.

The invention discloses a closed-loop transcranial electrical stimulation method, a closed-loop transcranial electrical stimulation device, closed-loop transcranial electrical stimulation equipment and a storage medium. The closed-loop transcranial electrical stimulation method comprises the steps of electroencephalogram signal acquisition, autoregression model construction and prediction, phase extraction, phase difference calculation and adjustment, AM signal generation and TIS stimulation signal generation. According to the method, future electroencephalogram signals can be predicted by using the autoregression model, the phase extraction technology is combined, the electrical stimulation signals are ensured to be synchronous with the specific phase of the target electroencephalogram activity, nerve regulation is performed on the generated stimulation signals in a TIS mode, overlapping of stimulation signal interference frequency bands and electroencephalogram signal frequency spectrums is effectively avoided, and the accuracy of the electroencephalogram activity is improved. Therefore, the space-time precision and the individualized regulation capability of nerve regulation are greatly improved. In addition, the TIS signal can noninvasively adjust the deep brain area, and a better brain area stimulation effect is achieved. The invention relates to a nerve regulation technology.

Provides is a method for detecting a complex target in pedestrian re-identification video streams based on an event-related potential (ERP). According to the method, video streams of a complex target in different scenarios are collected, and are made into experimental paradigms, and electroencephalogram (EEG) data of a subject during watching of a video content is collected. Then brain electrical activity mapping (BEAM) is analyzed, and ERP features are marked, including P300 and P300-D, which correspond to target emergence and target disappearance respectively. Positive and negative sample pairs are constructed, and essential features between classes are obtained based on a method of contrastive representation learning and a method of spatial-temporal feature attention extraction, so as to solve the extreme class imbalance problem of samples and the problem of how to distinguish between two similar classes in a video paradigm.

The invention provides a cold start method of a brain-computer interface, which relates to the technical field of brain-computer interfaces, and comprises the following steps: collecting an initial signal of a target user by using brain-computer interface equipment; the initial signal comprises electroencephalogram data and magnetoencephalogram data; preprocessing the initial signal to obtain a preprocessed signal; performing feature extraction on the preprocessed signal to obtain a signal feature; inputting the signal features into a trained electroencephalogram activity classification model to obtain a classification result; and generating a feedback result according to the classification result, and sending the feedback result to the target user. The cold start method of the brain-computer interface effectively solves the problems that a system based on transfer learning is poor in adaptive capacity and slow in response in the cold start stage of a new user. According to the method, individuation, real-time feedback and online learning are emphasized, so that a more effective and flexible user adaptation scheme is provided, the interactive experience of the user is smoother, and the overall performance of the system and the user satisfaction degree are improved.

A user interface system enables communication through inaudible speech by detecting physiological signals associated with inner voice communication. The system includes a wearable device positioned in, on, or around a user's ear, housing one or more sensor modalities such as electromyography (EMG) sensors for detecting muscle movements, functional near-infrared spectroscopy (fNIR) sensors for brain activity, and / or detection-and-ranging systems using sonar or radar for micro-deformations. Pre-processing modules condition the sensor data, which is then analyzed by one or more machine learning models to reconstruct the content of the user's inaudible communication and produce output representations. The system enables high-bandwidth natural language interaction without audible vocalization, maintaining privacy while supporting applications including AI assistant interaction, real-time translation, secure authentication, and inter-party communication.

According to the system for evaluating the treatment effect of the AUD patient through the electroencephalogram microscopic state indexes, the electroencephalogram activity is captured through the electroencephalogram monitoring sensor, the electroencephalogram microscopic state indexes in the resting state are calculated through the data processing unit, the electroencephalogram microscopic state indexes are compared with a preset reference value or index modes in different psychological states, and the treatment effect of the AUD patient is evaluated. To identify features of brain activity of the patient. The preset value is based on a classification of subconsciousness and consciousness reactions of the AUD patient and statistically validated. And the system judges the brain activity state and the treatment effect of the AUD patient according to the analysis result of the electroencephalogram microscopic state index, and displays the analysis and judgment result through an output unit. The system can accurately evaluate the treatment effect of the AUD patient so as to provide accurate treatment and prevention strategies for the AUD patient.

Embodiments described herein relate to systems, devices, and methods for monitoring brain activity and delivering electrical brain stimulation to a patient. In some embodiments, a system can deliver responsive electrical stimulation in a closed-loop manner and can offer real-time or near real-time monitoring of induced neurophysiological effects. After detecting a targeted brain pattern (i.e., an epileptic seizure), the system may deliver high-intensity ultra-short electrical stimulation impulses non-invasively or minimal-invasively to diminish or stop the neural oscillations underlying the epileptic seizure. The stimuli are delivered in time and space, relative to the emerging seizure rhythm patterns, such that they diminish or terminate the seizure. The system may include an implantable device including one or more electrodes electrically coupled to one or more processors. The processor(s) may be operatively coupled to a memory, one or more communication modules, and may optionally be coupled to a battery and one or more additional sensor(s).

The invention provides an EEG (electroencephalogram)-based self-sensitivity quantitative evaluation method, and belongs to the field of physiological signal processing and mode recognition. The method comprises the following steps: collecting resting state and task state electroencephalogram signals of a subject, and obtaining a self-efficacy feeling score of the subject in combination with a scale; the electroencephalogram signals are preprocessed, window segmentation is carried out on the preprocessed signals, and multi-dimensional features such as a time domain, a frequency domain, a power spectrum entropy and a micro state are extracted; and inputting the features and the performance feeling score into a deep learning model based on LSTM-Attention for training, and constructing an evaluation model. The model can output a quantitative score according to the electroencephalogram signal, and the evaluation result continuously iterates and optimizes the model through continuous feedback data, so that the evaluation precision is improved. According to the method, objective and accurate quantification of self-effectiveness is achieved by combining the electroencephalogram signal features and the deep learning technology, the internal association between the self-effectiveness and electroencephalogram activity is revealed, and high practicability is achieved.

The present invention discloses a vibrating bed leg, an electric bed and a control method for an electric bed. A vibrating bed leg includes a fixing part, a supporting part, an elastic part, a pre-stressing mechanism and a vibrating device; the supporting part is used to support the ground and is arranged opposite to the fixing part in the longitudinal direction of the fixing part; the elastic part is arranged between the fixing part and the supporting part, and its two ends respectively abut against the fixing part and the supporting part; the pre-stressing mechanism is used to pre-stress the elastic part; the vibrating device is used to drive the fixing part to vibrate up and down through the elastic part. The vibrating bed leg, the electric bed and the control method for the electric bed of the present invention, driven by the vibrating device, the vibrating bed leg produces reciprocating extension and contraction, drives the bed body and the mattress to vibrate up and down, and makes the bed vibrate slightly at a certain frequency. These infrasonic vibrations can be felt by the balance receptors in the cochlea, and the tactile receptors can also be clearly felt, and finally affect the brain electrical activity, and pull the user into a corresponding sleep state. The elastic part can also obtain a shock-absorbing buffering effect to improve the sleep experience.

To solve the problem that seizure detection is sometimes difficult because of the absence of visible indication that a patient is experiencing a seizure.SOLUTION: A seizure detection system includes one or more circuits configured to receive an electroencephalogram (EEG) signal generated based on electrical brain activity of a patient. The one or more circuits are configured to determine metrics based on the EEG signal, the metrics indicating non-linear features of the EEG signal, determine that the EEG signal indicates a candidate seizure by determining, based at least in part on the metrics, a change in the non-linear features of the EEG signal over time, and generate a seizure alert indicating that the EEG signal indicates the candidate seizure. The change in the non-linear features indicates a physiological force that gives rise to the candidate seizure.SELECTED DRAWING: Figure 1

A method of seizure detection, the method comprising: receiving an EEG signal generated based on electrical brain activity of a patient; determining a plurality of metrics based on the EEG signal, the plurality of metrics indicating non-linear features of the EEG signal; performing a preliminary analysis with one of the plurality of metrics, wherein the preliminary analysis indicates that the EEG signal is significant or that the EEG signal is insignificant, the one of the plurality of metrics being eigenvalues of the EEG signal, and the preliminary analysis comprising monitoring a moving window of eigenvalues of the EEG signal, and determining whether the eigenvalues are decreasing; responsive to a determination in the preliminary analysis that the eigenvalues are decreasing, performing a secondary analysis with one or more other metrics of the plurality of metrics to determine whether the EEG signal indicates a candidate seizure; and generating a seizure alert indicating that the EEG signal indicates the candidate seizure responsive to a determination in the secondary analysis that the EEG signal indicates the candidate seizure.

The present invention belongs to the technical field of EEG feature analysis, and specifically relates to an EEG feedback training method and system based on multi-lead EEG feature analysis. The invention can effectively classify and evaluate the state of EEG activities through an EEG feedback training method based on multi-lead EEG feature analysis, and when collecting EEG feature spectra, it is not determined according to the collection position, but classified according to the actual collected EEG feature spectra. Specifically, it can be classified into a baseline feature subset and an edge feature subset. The EEG spectrum features in the edge feature subset may correspond to any of the adjacent brain regions, and in practical applications, it can more accurately identify and locate abnormal EEG activity areas. In addition, through the feedback mechanism, the present invention can adjust EEG activities in real time, provide personalized EEG activity adjustment strategies for training subjects, and help training subjects adjust EEG activities in time when abnormal brain regions appear through real-time monitoring and feedback adjustment.

EEG cap for recording electrical brain activity, comprising: a) a textile basic structure, b) a plurality of defined electrode positions, c) a central sensor module with amplifier, analog-digital converter and wireless data transmission unit, d) a mechanically and electrically contactable connection system between electrodes and module, e) an integrated energy supply using a lithium polymer cell.

Specifically, this invention relates to an acoustic stimulation electrophysiological system and control method based on real-time EEG feedback, comprising: an EEG acquisition module that acquires the user's raw EEG signals in real time via an electrode array, and transmits them to an EEG preprocessing and feature extraction module for filtering and noise reduction, extracting multi-frequency power feature data, and sending it to a sleep state recognition and safety monitoring module. The sleep state module identifies the user's state and transmits the result to an acoustic stimulation parameter decision module. This module generates acoustic stimulation control parameters based on the state recognition result and sends them to a sound field synthesis and rendering module via a communication module to generate multi-channel acoustic stimulation signal waveform data, which is then transmitted to an acoustic stimulation output module to be converted into analog signals to drive an acoustic device to generate a specific sound field. The safety monitoring module continuously monitors abnormal EEG activity. The advantage of this invention is that the entire system forms a closed-loop feedback path from signal acquisition to acoustic stimulation output and safety monitoring.

The invention discloses a vehicle-mounted system for providing emotional value based on AI, and particularly relates to the field of artificial intelligence, which comprises a driver facial expression acquisition module, an emotion diagnosis module, a vehicle-mounted AI control system and an emotion regulation module, facial expressions of a driver are captured through a camera, electroencephalogram activities are detected through a wireless EEG sensor, eyebrow challenge, eye expression, lip radian and facial muscle changes are analyzed, and the emotion of the driver is preliminarily judged; the system combines facial expressions and electroencephalogram data, utilizes a Bayesian network algorithm to comprehensively judge emotional states, and divides the emotional states into positive emotional states and negative emotional states; under the positive emotion, the system is kept silent; in case of negative emotion, relaxed music is played, positive voice prompts are provided through the bone conduction audio unit, and the environment in the vehicle is adjusted to improve the driving experience.

In some embodiments, the present invention provides an exemplary inventive system that includes: an apparatus to record: individual's brain electrical activity, a physiological parameter of the individual, and iii) an environmental parameter; a computer processor configured to perform: obtaining a recording of the electrical signal data; projecting the obtained recording of electrical signal data onto a pre-determined ordering of a denoised optimal set wavelet packet atoms to obtain a set of projections; normalizing the particular set of projections of the individual using a pre-determined set of normalization factors to form a set of normalized projections; determining a personalized mental state of the individual by assigning a brain state; determining a relationship between: the physiological parameter, the environmental parameter, and the personalized mental state; generating an output, including: a visual indication, representative of the personalized mental state, and) a feedback output configured to affect the personalized mental state of the individual.

The invention discloses an emotion recognition method, device and equipment based on brain waves and a storage medium, belongs to the technical field of artificial intelligence, and is applied to a production insurance renewal or old-age health detection scene. The method comprises the following steps of: acquiring an electroencephalogram signal of a user, accurately extracting key wave bands including an active wave band and a relaxed wave band in the electroencephalogram signal in combination with a spectrum analysis method, further calculating a power proportion, forming a representative key wave band proportion index, and further realizing accurate identification of an emotional state of the user. Firstly, the accuracy and timeliness of electroencephalogram signal processing are improved through spectral analysis, and subtle differences of electroencephalogram activities in different emotional states are effectively captured; secondly, the key wave band proportion serves as a core index, the physiological mechanism of dynamic change of brain waves of a user can be reflected, and the discrimination ability and personalized adaptability of an emotion recognition model are enhanced; and thirdly, the pre-training model is combined with large-scale diversified data, so that the generalization performance and robustness of recognition are improved, and the method is suitable for different users and environment conditions.

The invention discloses an electroencephalogram signal-based method for evaluating attention of wine products after drinking. The method comprises the following steps of: determining a plurality of testees under the same condition and different types of to-be-evaluated wine samples; collecting behavior data and electroencephalogram data when each testee executes the Stroop color word task before and after drinking the Baijiu sample; the behavior data and the electroencephalogram data of all the subjects are subjected to statistical analysis, the expression in the Stroop task before and after drinking and the change of the electroencephalogram signals are compared, and the potential influence of the wine products on the attention of the subjects is evaluated. According to the method, the electroencephalogram signals and the behavior data are combined, so that evaluation on the attention of the wine products after drinking is more comprehensive, and physiological and behavior changes can be reflected at the same time. In addition, through the electroencephalogram technology, the electroencephalogram activity of the subject can be monitored in real time, the instantaneous change of attention can be captured in time, and a more dynamic analysis result is provided.

The invention belongs to the technical field of electroencephalogram feature analysis, and particularly relates to an electroencephalogram feedback training method and system based on multi-lead electroencephalogram feature analysis. According to the electroencephalogram feedback training method based on multi-lead electroencephalogram characteristic analysis, electroencephalogram activity can be effectively classified and subjected to state evaluation, electroencephalogram characteristic frequency spectrums are not determined according to the collection position when collected, classification is carried out according to actually collected electroencephalogram characteristic frequency spectrums, and therefore the accuracy of electroencephalogram characteristic frequency spectrums is improved. The method can be specifically classified into a reference feature subset and an edge feature subset, electroencephalogram spectrum features in the edge feature subset may correspond to any one of adjacent brain regions, an electroencephalogram activity abnormal region can be identified and positioned more accurately in practical application, in addition, through a feedback mechanism, the electroencephalogram activity can be adjusted in real time, and the accuracy of the electroencephalogram activity abnormal region is improved. A personalized electroencephalogram activity adjustment strategy is provided for the training object, and the training object can adjust the electroencephalogram activity in time when the abnormal brain region appears through real-time monitoring and feedback adjustment.

The invention discloses an Alzheimer's disease classification system based on multi-modal data and cranial-like nerve calculation, and the system comprises a first construction module which is used for constructing an electroencephalogram network based on preprocessed EEG data; the second construction module is used for constructing a functional network based on the preprocessed fMRI data; the node embedding module is used for learning node embedding of the electroencephalogram network and the function network through the graph convolutional neural network; the feature extraction module is used for embedding nodes corresponding to the same ROI of a plurality of subjects for extraction and splicing to form a feature vector of each subject; and the model training module is used for training a classification model based on the plurality of tested feature vectors obtained by splicing. According to the Alzheimer's disease classification system based on multi-modal data and cranial nerve-like calculation, EEG and fMRI data are fused, the time-frequency characteristics of electroencephalogram activities and the functional connectivity between brain regions are comprehensively considered, the feature extraction capacity is enhanced, and comprehensive understanding of the disease state is improved.

The invention provides an experimental method for verifying the curative effect of retinoic acid on schizophrenia, which comprises the following steps: step 1, selecting two groups of pregnant SD rats, injecting Poly I: C into tail veins of one group of SD rats after 9.5 days of pregnancy according to the standard of 10 mg / kg, and taking male offspring rats as schizophrenia model group rats; the other group of SD rats are intravenously injected with equal-volume normal saline at the tail after pregnancy 9.5 days, and the male offspring rats are the control group; 2, the model components are divided into two groups, retinoic acid is fed to one group 45 days after birth according to the standard of 3 mg / kg / day, an equal amount of placebo is injected to the other group, and an equal amount of placebo is injected to the control group; step 3, carrying out behavioral detection experiments on the three groups of rats in the step 2; and 4, implanting electrodes into hippocampal CA1 regions of the three groups of rats in the step 2, and recording and analyzing electroencephalogram activities of the three groups of rats. The experimental method provided by the invention proves that the retinoic acid has good application value in preparation of the schizophrenia medicine.

This invention provides an electroencephalogram (EEG) simulation device, comprising an interaction module for receiving and displaying user input information and feedback signals from a processing module, converting the input information into input signals and sending them to the processing module; a processing module for generating corresponding modulation control signals, power control signals, and feedback signals based on the input signals; a signal generation module for generating waveform signals; a signal modulation module for modulating the waveform signals according to the modulation control signals to generate simulated EEG signals for output; and a power supply module for supplying power to other modules according to the power control signals. The beneficial effects of this invention are that the precise modulation of the waveform signals and the application of bias voltage make the output simulated EEG signals more closely resemble real brain activity, which is beneficial for scientific research and clinical applications; and the design of common-mode filters and capacitors in the power supply module effectively reduces the impact of environmental noise on system performance.

A method of determining a type of a brain dysfunction is discloses. The method may include: receiving an electroencephalogram (EEG) signal from an electrode placed on the head; calculating a regularity index for an electric activity of the brain based on EEG signal; detecting a temporal change in the regularity index; receiving a medical related input; and determining the type of brain dysfunction based on the temporal change in the regularity index and the medical related input.

The embodiment of the invention provides a nerve regulation and control device and system based on a deep electrode, and relates to the technical field of nerve regulation and control. The stimulator is used for being electrically connected with at least one deep electrode, and the stimulator is configured to determine electroencephalogram activity distribution information based on an electroencephalogram signal of a target area acquired by at least one contact of the deep electrode; determining target stimulation information based on the electroencephalogram activity distribution information and the position information of each contact; based on the target stimulation information, controlling at least two target contacts to output stimulation signals to form a target envelope waveform so as to perform nerve regulation on the target area; the electroencephalogram activity distribution information is used for representing the activity degree of the electroencephalogram activity of the target area, and the target stimulation information comprises target contact information and stimulation parameter information corresponding to each target contact. According to the embodiment of the invention, the target stimulation information can be determined according to the real-time electroencephalogram signal of the patient, and the accuracy and treatment effect of nerve regulation and control are improved.

A medical device system is configured to sense electrical brain activity and sense electrical cardiac activity. The system may detect a concerning heart rate from the electrical cardiac activity and determine that the concerning heart rate is a hemodynamically unstable cardiac rhythm based on the sensed electrical brain activity. The medical device system may generate an output for providing a response to determining that the concerning heart rate is a hemodynamically unstable rhythm.

The invention discloses a depression assessment method based on multi-view subgraph construction, which is applied to the field of electroencephalogram data processing and aims at solving the problem that the accuracy and reliability of emotion recognition are limited due to the fact that comprehensive brain function structure features cannot be effectively extracted from multiple dimensions in the prior art. According to the method, firstly, a graph construction mode based on Euclidean distance, time-frequency analysis and nonlinear features is introduced, and the model can perform deep abstraction on signals of the brain from multiple angles, so that feature loss possibly caused by a single-view-angle analysis method is effectively avoided, and the adaptability to the complexity and diversity of brain activities is improved. Wherein the nonlinear analysis helps to excavate a potential complex dynamic relationship in the signal, and helps to reveal the nonlinear change of the brain in a specific mental state. Finally, the construction of a multi-view image not only enhances the recognition of functional connection between brain areas, but also improves the sensitivity to different electroencephalogram activity states.