20 results about "Neurophysiology" patented technology

The invention discloses a rehabilitation training evaluation system for dealing with schizophrenia patients, and relates to the technical field of data processing, the evaluation system comprises a multi-modal sensing module, an edge intelligent processing module and a dynamic graph network evaluation module; according to the technical key points, neurophysiology, behavior tracks, cognitive functions and environmental parameters are fused to form a'microscopic neural activity-mesoscopic behavior performance-macroscopic environment interaction 'full-dimension evaluation network, for example, the recessive decoupling phenomenon of'reduced brain oxygen metabolism but normal autonomic nerve function' of a negative symptom patient can be synchronously captured, and the accuracy of the evaluation network is improved. The method comprises the following steps of: firstly, quantifying the coordination and causality of data of different dimensions through a dynamic graph network, disclosing a dynamic association path of insufficient activation of a forehead cortex, social attention distraction and cognitive task error rate increase, and providing a visual basis for mechanism research and intervention target selection.

According to the three-dimensional electric field coupling modeling method for analgesia provided by the invention, the propagation process of an electric field in each physiological tissue is accurately simulated by constructing a multi-layer bionic tissue model, so that the accuracy and effect of analgesia treatment are improved; calculating the conductivity and dielectric constant of each layer of tissue, performing numerical simulation on electric field distribution by using a finite element analysis technology, optimizing electrode configuration and electrical stimulation parameters, and ensuring the uniformity and stability of the electric field of a target area; a neurophysiology model is integrated, the conduction law of nerve fiber action potential is dynamically simulated, the stimulation effect of electric field intensity on nerve fibers is quantitatively analyzed, analgesia parameters are further optimized, and accurate control over pain signal transmission is achieved. The problems that in an existing electrical stimulation technology, electric field distribution is not uniform, electrode contact is not stable, and the stimulation effect is difficult to last are effectively solved, wide clinical application prospects are achieved, and an efficient, stable and accurate solution is provided especially in non-invasive treatment of chronic pain.

The invention discloses an event-driven electroencephalogram pulse diagram-based emotion recognition and interpretation method and device, and belongs to the field of artificial intelligence and biomedical engineering cross technologies, and the method comprises the following steps: S1, determining coordinates of electroencephalogram leads in a three-dimensional space, and establishing an initial electroencephalogram topological graph; s2, forming complete electroencephalogram pulse diagram data through training; s3, processing the electroencephalogram pulse diagram data from the S2 to obtain fusion features; s4, performing pulse time sequence dependency modeling on the fusion features, and using the model to complete classification decision; and S5, verifying the physiological rationality of the classification decision. According to the emotion recognition and interpretation method and device based on the event-driven electroencephalogram pulse diagram, brain dynamic characteristics are accurately captured, objective and accurate evaluation and decision making of the emotional state of a testee are achieved, a physiological interpretability analysis mechanism is introduced, and the reliability of a model is verified from the perspective of neurophysiology.

The present invention discloses a rehabilitation training evaluation system for schizophrenia patients, which relates to the field of data processing technology. The evaluation system includes a multimodal perception module, an edge intelligent processing module, and a dynamic graph network evaluation module. The technical key points are: integrating neurophysiology, behavioral trajectories, cognitive functions and environmental parameters to form a full-dimensional evaluation network of "micro-neural activity-meso-behavioral performance-macro-environment interaction". For example, it can simultaneously capture the implicit decoupling phenomenon of "reduced brain oxygen metabolism but normal autonomic nervous function" in patients with negative symptoms, avoiding the missed diagnosis of complex pathological mechanisms by traditional scales. Secondly, through the dynamic graph network, the synergy and causality of data of different dimensions are quantified, revealing the dynamic association path of "insufficient prefrontal cortex activation → social attention distraction → increased cognitive task error rate", providing a visual basis for mechanism research and intervention target selection.

The present invention belongs to the fields of artificial intelligence and neurobiology, and particularly relates to a method for learning the constraints of a deep neural network topology. First, the rs-fMRI data of the subject is collected and preprocessed, the correlation coefficients between different brain regions are calculated to obtain the biological brain topology matrix, and a deep neural network model is constructed; then, the learning process of the neural network is constrained by the biological brain topology to train the model, and the backpropagation algorithm is used to update the neural network parameters. The loss function of the backpropagation algorithm simultaneously includes the negative log-likelihood loss and the topology matrix similarity loss. Therefore, after the model is trained, the topology matrix of the neural network will tend to be the biological topology matrix, thereby realizing the technology of directly integrating neurophysiological recordings into artificial neural networks. The present invention fills the technical gap in directly converting neurophysiological recordings into improvements in artificial neural networks, thereby improving the engineering performance of neural networks.

The application relates to a motor imagery electroencephalogram channel selection and classification method based on average energy difference, which takes the channel mean energy of two types of motor imagery signals as a voting threshold, counts the number of obvious energy difference trials on each channel according to the voting difference value, selects appropriate channels based on the number, normalizes the energy features of the channels, combines the CSP spatial features, and classifies by using an SVM. The selected channels have certain neurophysiological significance, which helps to improve the performance of the brain-computer interface, and the selected channels also include some channels which have energy distinction but are not in the motor imagery area, and the channels also help the motor imagery classification. In addition, the application extracts energy features from the selected channels, the energy features become more distinctive with the increase of the number of selected channels, which can make up for the precision reduction problem caused by the multiple channels to a certain extent, and has certain feasibility and superiority.

Disclosed in the present invention are a motor-related electroencephalographic signal source localization method and system based on an MNE-GAN. The method comprises the following steps: synthesizing virtual multi-channel electroencephalographic data; constructing a brain electrical source data generation network based on minimum norm estimation (MNE); constructing a brain electrical source data discriminator; preprocessing the virtual electroencephalographic data; training an MNE-GAN model on the basis of the virtual electroencephalographic data; and using the trained model to perform source localization on real electroencephalographic data. In the present invention, an MNE-based generative adversarial network (GAN) is used to provide a new brain electrical source localization method. A minimum norm constraint is added to restrict generated brain electrical source data to satisfy physical prior knowledge, thereby facilitating the research into non-invasive neurophysiological mechanisms and the improvement of the electroencephalographic decoding accuracy.

The present invention discloses a method for EEG recognition of natural hand movements based on a time-frequency multi-layer brain network, comprising: (1) collecting multi-channel EEG signals of natural hand movements; (2) preprocessing the multi-channel EEG signals to extract the delta wave, theta wave, alpha wave, beta wave, and gamma wave at each time point; (3) constructing a time-domain multi-layer brain network using a wSAR model; (4) calculating a frequency-domain multi-layer brain network using cross-frequency coupling; (5) combining and standardizing the time-domain and frequency-domain multi-layer brain networks; (6) calculating the multi-layer network metric and the decomposed super-adjacency matrix of the multi-layer brain network, and inputting them into a two-layer graph convolutional network (GCN) to fuse artificial, shallow, and deep features for classification. The present invention proposes a new time-frequency fusion multi-layer brain network using the wSAR model and cross-frequency coupling (CFC), and uses two layers of GCN to comprehensively extract the feature information of the multi-layer brain network, which is conducive to revealing the neurophysiological mechanism of the brain and improving the decoding accuracy of natural movement EEG.

The invention discloses a motion-related electroencephalogram signal source positioning method and system based on MNE-GAN. The method comprises the following steps: synthesizing virtual multichannel electroencephalogram data; constructing a brain power data generation network based on minimum norm estimation MNE; constructing a brain power source data discriminator; preprocessing the virtual electroencephalogram data; training an MNE-GAN model based on the virtual electroencephalogram data; and carrying out source positioning on the real electroencephalogram data by utilizing the trained model. According to the method, a new brain power source positioning method is provided by using the MNE-based generative adversarial network, and the brain power source data generated by adding minimum norm constraint limitation meets physical prior knowledge, so that the research of a noninvasive neurophysiology mechanism and the improvement of electroencephalogram decoding precision are facilitated.

A method of reducing stimulation artifact when performing electrical stimulation, in which a stimulation pulse is generated by an electrical stimulator connected to a stimulation electrode. A closed equipotential surface is created around the electrical stimulator by complete electrical shielding of the electrical stimulator from the rest of the electrical stimulator and from the surroundings, a low capacitive coupling is ensured between the electrical stimulator itself and the rest of the device structure, the shielding of the stimulation electrode is connected to the closed equipotential surface of the electrical stimulator and to the closed equipotential surface electrical stimulator and / or a collection electrode designed to be placed on the patient is connected to the shielding of the stimulation electrode. The stimulation artifact reducing electrical stimulation device comprises an electrical stimulator (1) designed to connect to a stimulation electrode. The electrical stimulator (1) is provided with a shield (3) with an electrically shielding surface for shielding the electrical stimulator by creating an equipotential conductive surface surrounding this electrical stimulator (1), wherein the shielding is provided with a connection connector for connection to the shielding of the stimulation electrode or is directly connected to this shielding, and that the shielding (3) of the electrical stimulator (1) and / or to the shielding of the stimulating electrode is designed to be connected to the collecting electrode (6) or is connected to the collecting electrode (6), and that at least between the electrical stimulator (1) and the remaining parts of the device create a low capacitive coupling.

The invention discloses a neurophysiology heuristic electroencephalogram emotion recognition method based on deep learning, and the method comprises the steps: firstly carrying out the preprocessing of an EEG signal, constructing potential feature input representing an emotional state, inputting the potential feature input to an emotional response adjacent embedded module, and forming an emotional state space-time view; secondly, inputting the emotional state space-time view into a layered space-time Transform module, and outputting enhanced emotional channel representation; and then inputting the emotion channel representation into a channel independent time sequence embedding module to generate a cross-time-scale multi-view time sequence representation, and inputting the cross-time-scale multi-view time sequence representation into a hierarchical dual attention Transform module to obtain time representation. And finally, based on the time characterization, the electroencephalogram emotional state is judged, and a corresponding emotion recognition result is output. According to the method, the extracted emotion features have higher separability among different emotion categories, and the stability and accuracy of emotion recognition are improved.

The application discloses a kind of MNE-GAN-based motion-related electroencephalogram signal source positioning method and system.Method includes the following steps: virtual multi-channel electroencephalogram data synthesis;Electroencephalogram source data generation network construction based on minimum norm estimation MNE;Electroencephalogram source data discriminator construction;Virtual electroencephalogram data preprocessing;MNE-GAN model training based on virtual electroencephalogram data;The source positioning of real electroencephalogram data is carried out using the trained model.The application uses the generative adversarial network based on MNE to propose a new electroencephalogram source positioning method, by adding minimum norm constraint limit generated electroencephalogram source data meets physical prior knowledge, is conducive to non-invasive neurophysiological mechanism research and electroencephalogram decoding precision promotion.

The invention discloses an ecological healing model system and method based on natural connection and consciousness expansion. The ecological healing model system comprises an evaluation module, a natural activity module, a technical intervention module and a data analysis module. The influence of multi-sensory stimulation in the natural environment on the neural mechanism of the teenagers and family members of the teenagers is systematically discussed for the first time, the brain-computer interface technology and the psychological evaluation tool are combined, the internal relation between natural healing and consciousness expansion is revealed from the two aspects of neurophysiology and psychology, and the limitation of traditional psychological treatment is broken through. Through case research and multi-channel psychological evaluation verification, 12 weeks of intervention shows that the natural connection degree of participants is remarkably improved, the psychological pressure is remarkably reduced, and the psychological toughness is remarkably enhanced, which shows that the model has a remarkable effect on promoting the psychological health of teenagers.

The invention discloses a production and teaching integrated lamp professional skill assessment system and method, and relates to the technical field of professional skill assessment, and the method comprises the steps: calculating the local conductance change amplitude of each time point in a uniform conductance sequence, taking the maximum value of the difference value of front and back points, defining the maximum value as a micro-crack transition value, calculating composite indexes in a window, and carrying out the screening. Obtaining a transition point set; calculating ghosting intensity, constructing a time-intensity trajectory curve according to a time sequence, screening the time-intensity trajectory curve, generating a ghosting point group, calculating a single-point stability index based on instantaneous frequency and phase synchronization intensity, and calculating a mean value to obtain a comprehensive score; and skill grade judgment is carried out on the comprehensive score. According to the method, the maximum stress peak and the rollback index are combined, the accuracy and robustness of stress point recognition are enhanced, the comprehensiveness and accuracy of evaluation are improved through deep coupling of neurophysiology and phase synchronization, and errors of static analysis are avoided.

The invention belongs to the technical field of rehabilitation training, and discloses a self-adaptive VR rehabilitation training method and system driven by a mirror neuron system. The system comprises a neurophysiology and motion behavior feature enhancement module, a VR scene adaptive control module, a neurophysiology and motion behavior coupling analysis module and a diagnosis interpretation early warning report processing module, and is used for cleaning a multi-modal time sequence data set to obtain cleaned multi-modal data; the method comprises the following steps of: obtaining neurophysiology and motion behavior characteristics after related brain region characteristics of a mirroring neuron system are enhanced, obtaining a parameter dynamic adjustment record report, obtaining a neurophysiology and motion behavior coupling map, and performing analysis based on the neurophysiology and motion behavior coupling map to obtain an interpretable diagnosis report and an early warning report. The method has the remarkable advantages of high multi-modal fusion data quality, good self-adaptive mechanism optimization effect and great transformation effect from the system to clinical use.

The Smart Interactive Shirt System is an advanced wearable biosensing platform engineered for real-time, multi-modal monitoring and predictive management of pain, fatigue, and physiological stress. Embedded within a flexible textile, the system integrates 15 specialized IoT sensors—spanning biochemical, biomechanical, thermal, and neurophysiological domains—to deliver continuous high-resolution insight into the wearer's physiological state. Key innovations include plasmonic nano-optical modules for real-time cortisol and CRP detection, EMG-based neuromuscular sensing, and thermopile arrays for deep-tissue inflammation mapping. A hybrid AI engine combining convolutional and recurrent neural networks (CNN-LSTM) processes incoming data locally, enabling early prediction of acute fatigue and pain episodes 10–15 minutes before physiological onset. The system incorporates triboelectric nanogenerators (TENGs) that harvest kinetic energy from body motion, minimizing reliance on external power sources and supporting extended autonomous operation. Validated through pilot deployments in elite European sports organizations, the shirt also features screen-printed electronic circuits, vibrotactile feedback mechanisms, and seamless Bluetooth Low Energy (BLE) integration with mobile interfaces. This invention marks a significant advancement over conventional wearables by offering proactive, data-driven physiological management, setting a new benchmark in intelligent, AI-powered textile systems.

The present invention discloses a bionic modeling method for the sense of smell and hippocampus based on the theory of neural clusters and anatomical structure. Based on the theory of neural clusters and anatomical structure, the method first starts with the sense of smell, which has a relatively clear structure and function, and improves on existing neurophysiological research results to construct an olfactory-entorhinal cortex bionic model. It then gradually moves deeper into the more complex hippocampal structure to construct an entorhinal cortex-hippocampus bionic model. Finally, by fusing the two constructed bionic models, with the entorhinal cortex as the core, the method connects the sense of smell, the entorhinal cortex, and the hippocampus, creating an olfactory-hippocampus neural network model that is as realistic as possible, providing an effective research object for the study of the nervous system in the brain.

The present invention discloses an EEG signal decoding method based on an orthogonal experiment. The method steps adopted by the present invention are: (1) using a motor imagery dataset as the EEG signal to be analyzed; (2) extracting and designing EEG signal parameters; (3) designing an orthogonal experiment based on the EEG signal parameters; (4) generating optimized parameters based on the orthogonal experiment; (5) extracting features from the EEG signal parameters selected by the orthogonal experiment; and (5) classifying the extracted features to achieve EEG signal decoding. The method of the present invention can overcome the problems of the prior art, such as high computational complexity, inaccurate preprocessing, and reliance on neurophysiological cognition.

The invention relates to a method and device for analyzing visual and neural function changes after visual training, and relates to the technical field of visual neural function evaluation.The method comprises the steps that in the visual training process of a target object, visual brain physiological data of different training groups and trained binocular visual functions are synchronously collected through EEG-fNIRS, and the visual brain physiological data are obtained; the method comprises the following steps of: acquiring physiological data signals, performing preprocessing and feature extraction on the acquired physiological data signals to obtain corresponding signal features, performing analysis based on the extracted signal features to determine a first analysis result and a second analysis result, and finally analyzing dynamic interaction of electroencephalogram and brain oxygen by utilizing EEG-fNIRS in combination with the two analysis results and binocular visual functions. According to the method, the change analysis result of the visual and neurological functions after visual training is obtained, the examination of organically combining the traditional visual function with the neurological function is realized, the improvement of the visual function is analyzed, and the influence of the visual function on the brain function can be revealed from the neurophysiology level.