49 results about "Neural function" patented technology

The invention relates to the technical field of cognitive disease risk assessment, and discloses a cognitive disease intelligent risk management method based on multi-modal voiceprint data analysis, the method comprises multi-modal feature fusion, dynamic risk assessment and real-time intervention linkage, by setting a multi-modal feature fusion module, when cognitive disease risk assessment is carried out, a multi-modal voiceprint data analysis module is set, the risk of the cognitive disease is evaluated, and the risk of the cognitive disease is evaluated. The recognition specificity of different cognitive impairment types is guaranteed by fusing acoustic characteristics, rhythm rules and multi-dimensional voiceprint characteristics of semantic logic, meanwhile, a comprehensive feature vector is constructed based on depth feature extraction, neural function degeneration signals implied in voiceprint data can be captured in real time, the misjudgment risk caused by traditional single-mode analysis is reduced, and the recognition accuracy of the cognitive impairment types is improved. According to the method, the reliability of early cognitive impairment screening is improved, a dynamic risk assessment mechanism is constructed, a cognitive state score and an adaptive threshold are compared in real time during individualized cognitive tracking, and abnormal fluctuation of a cognitive function is recognized in time.

The invention relates to the technical field of ophthalmology informatization, in particular to an intelligent optic nerve function evaluation method and system based on visual evoked potential, and the method comprises the steps: obtaining an electroencephalogram signal, an eye movement track and an auditory reaction signal of a subject; obtaining visual stimulation parameters, wherein the visual stimulation parameters comprise stimulation frequency, stimulation intensity and stimulation duration; on the basis of the electroencephalogram signals, the eye movement tracks and the auditory reaction signals, signal preprocessing operation is executed, and preprocessed multi-modal physiological signals are obtained; extracting features by adopting an improved space-time convolutional neural network based on the preprocessed multi-modal physiological signals to obtain optic nerve function features; according to the optic nerve function features and the visual stimulation parameters, establishing an optic nerve conduction pathway model; evaluating the optic nerve function state based on the optic nerve conduction pathway model to obtain an optic nerve function evaluation result; generating an evaluation report containing the optic nerve function evaluation result; predicting the optic nerve function change trend, and generating a prediction report.

The invention discloses a neural function detection balancing system and method based on artificial intelligence, the system comprises a detection unit, a signal processing unit, an intelligent analysis unit, a treatment unit and a control unit, the detection unit comprises a multi-mode sensor array and is used for collecting neural signals of a human nervous system; the signal processing unit is used for filtering, amplifying and digitalizing the neural signal acquired by the detection module; the intelligent analysis unit is used for establishing a neural function evaluation model and analyzing the abnormal condition of the neural signal to obtain an analysis result; the treatment unit comprises an electromagnetic pulse generator, an ultrasonic generator and a phototherapy device and is used for performing forward stimulation treatment on the ganglion according to an analysis result; and the control unit is used for controlling and adjusting the treatment parameters of the treatment unit. According to the invention, the integration of neural function detection and treatment is realized, and the accuracy and objectivity of neural function evaluation are remarkably improved through multi-modal signal acquisition and artificial intelligence analysis.

The invention provides an elbow joint exoskeleton control system based on myoelectricity angle prediction and a use method thereof, the elbow joint exoskeleton control system comprises a dual-channel surface myoelectricity signal acquisition device and an advanced one-step prediction model OSA: the dual-channel surface myoelectricity signal acquisition device acquires myoelectricity signals and provides input data for the system; establishing an advanced one-step prediction model OSA based on a non-linear autoregressive model NARX with exogenous input, performing offline training, and determining a mapping relation between the electromyographic signals and the actions; and realizing online intention estimation and real-time control of the upper limb elbow joint exoskeleton system by using an advanced one-step prediction model OSA. By means of the technical scheme, the electromyographic signals can be detected in real time, the exoskeleton is driven to assist in completing elbow joint flexion and extension movement, neural function reconstruction and motor ability recovery are promoted, and the risk of muscle disuse atrophy is reduced.

The invention relates to a neural function detection and regulation method and system for a magnetic stimulation coil, and the method comprises the steps: driving a capacitor through a control circuit to discharge to a dual-path stimulation coil, and generating a millisecond pulse magnetic field; utilizing the pulsed magnetic field to act on nervous tissue to generate a nerve regulation effect comprising suprathreshold stimulation and subthreshold stimulation; acquiring evoked potential signals generated by stimulation and induction of the pulsed magnetic field in real time; the evoked potential signal is analyzed, and the nerve conduction time and excitation inhibition ratio is calculated; according to the nerve conduction time and the excitement inhibition ratio, a double-path stimulation time sequence and / or a capacitor discharge parameter are / is adjusted, detection and cooperative regulation and control of the nerve function are carried out, and the purposes of real-time detection, quantitative evaluation and self-adaptive precise regulation and control of the nerve function are achieved.

A system for estimating a subject's functional brain age using non-invasive electroencephalography (EEG), the system includes: an EEG acquisition module (101) configured to record multichannel EEG signals from the subject; a stimulation control module (102) configured to present a predefined sequence of cognitive and sensory tasks that specifically target the frontal, temporal, parietal and occipital brain regions, and to generate synchronized event markers; a data processing module (103) configured to prepare the recorded EEG signals by filtering, artifact removal, normalization and segmentation into task-oriented time windows; a machine learning module (104) comprising one or more self-monitoring contrastive learning encoders configured to transform the preprocessed EEG signals into latent feature representations; and a brain age estimation module (105) configured to process the latent feature representations to generate a BrainAge Score indicating a difference between a predicted biological brain age and the subject's chronological age.

The application provides a personalized rehabilitation path making method and system based on amygdala function evaluation. First, the application obtains multi-modal neural function data of an individual. Second, the amygdala function lateralization mode is determined based on amygdala sub-region functional connection data. Third, the amygdala function lateralization mode is cooperatively analyzed with preset target individual behavior representation data. Finally, the personalized rehabilitation path is generated according to the cooperative analysis result obtained by the analysis. The technical scheme provided by the application not only realizes sub-region level accurate evaluation of amygdala function by integrating multi-modal neural function data and individual behavior representation data, but also generates a highly individualized rehabilitation path with precise coupling of neural activity and rehabilitation training, thereby effectively improving the pertinence and effect of intervention.

The application discloses a high-fidelity three-dimensional face reconstruction and generation method based on an implicit neural function, and proposes a high-fidelity parameterized face model which can be semantically decoupled and edited, and simultaneously introduces new identity, expression representation and semantic segmentation networks. With the aid of the implicit neural representation, the method can perform high-fidelity reconstruction and synthesis on face details, difficult expressions and large-angle camera poses, so that the generated face pictures have good reality and clarity.

The invention discloses a fusion oligopeptide. The fusion oligopeptide is formed by fusing a cell-penetrating peptide and an oligopeptide for inhibiting combination of MD2 and CIRP. The invention also discloses an application of the fusion oligopeptide in preparation of a medicine for treating central nervous cell diseases mediated by an MD2-TLR4 signal channel. The fusion oligopeptide provided by the invention only has 15 amino acids, not only reduces immunological rejection of an organism, but also is relatively low in synthesis cost, and is used as a bioactive molecule to effectively block central nervous cell disease injury mediated by an MD2-TLR4 signal channel, relieve post-stroke nerve injury caused by nerve excitation toxicity and reduce infarct area, so that the fusion oligopeptide can be used as a biologically active molecule to effectively inhibit apoplexy. The nerve function is effectively recovered.

The invention provides a personalized rehabilitation path making method and system based on amygdala kernel function evaluation. The method comprises the following steps: firstly, acquiring multi-modal neural function data of an individual; secondly, determining an amygdala function bias mode based on the amygdala subregion function connection data; then carrying out collaborative analysis on the amygdaloid nucleus function bias mode and preset target individual behavior characterization data; and finally, generating a personalized rehabilitation path according to a collaborative analysis result obtained by analysis. According to the technical scheme provided by the invention, the subregion-level accurate evaluation of the amygdala kernel function is realized by integrating the multi-modal neural function data and the individual behavior characterization data, and a highly individualized rehabilitation path in which neural activity and rehabilitation training are precisely coupled is generated accordingly, so that the pertinence and effect of intervention are effectively improved.

The invention discloses a wind power AC / DC system transient stability evaluation method based on a positive definite structure neural Lyapunov function. The method comprises the following steps: constructing a state space physical model containing a wind power AC / DC system, and collecting real-time operation data; determining a candidate Lyapunov function based on the neural network; updating parameters of the Lyapunov function based on a gradient method; generating a counter example set based on a projection gradient descent algorithm, and verifying a Lyapunov function based on an SMT solver; the method comprises the following steps: acquiring the operation state of a wind power-containing AC / DC system to obtain a training set, constructing a total training set based on the training set, a counter-example set and a verification set, and training based on the total training set to obtain a trained neural Lyapunov network; and evaluating the transient stability state of the wind power AC / DC system based on the trained neural Lyapunov network. According to the method, the local Lyapunov function of the complex power system can be effectively learned, and the transient stability of the alternating-current and direct-current hybrid system containing wind power can be quickly and accurately evaluated.

The invention discloses an emotion recognition, consciousness evaluation and auxiliary rehabilitation method and device based on closed-loop olfactory stimulation, and a medium, and relates to the technical field of neural function diagnosis and artificial intelligence, and the method comprises the steps: obtaining a first face image sequence of a patient under odor stimulation; inputting the first facial image into a facial action unit intensity estimation model, and obtaining a plurality of facial action unit recognition results output by the model online; determining the facial expression change intensity of the patient based on the recognition results of the plurality of facial action units; and under the condition that the facial expression change is lower than a preset threshold value, adjusting the concentration and the type of the odor stimulation in real time based on a preset concentration gradient, and re-collecting the image for evaluation. Through multiple expression intensity results, the consciousness level of the patient is determined, the olfactory consciousness brain network remaining condition is judged, a rehabilitation training scheme is formulated, and longitudinal tracking is implemented. The emotion and consciousness level of the patient can be accurately evaluated in real time, and the method is applied to olfactory stimulation assisted rehabilitation.

Presented herein are techniques that make use of objective measurements obtained in response to acoustic stimulation signals. More specifically, at least one measure of outer hair cell function and at least one measure of auditory nerve function are obtained from a tonotopic region of an inner ear of a recipient of a hearing prosthesis. The at least one measure of auditory nerve function and the least one measure of outer hair cell function are then analyzed relative to one another.

The invention belongs to the field of medical rehabilitation, and particularly relates to a post-stroke functional rehabilitation training system which comprises a multi-mode biological signal acquisition device, and the multi-mode biological signal acquisition device comprises an sEMG electrode array, an IMU sensor and a pressure sensor matrix; the self-adaptive game engine is used for receiving the physiological feature vectors in real time and dynamically adjusting game parameters; and the neural function evaluation matrix generator outputs a quantitative rehabilitation progress report. The physiological state of a patient is monitored in real time through an sEMG / IMU / pressure / fNIRS sensor network, difficulty parameters are dynamically adjusted through a game engine to maintain the optimal training intensity, and a quantitative rehabilitation report is automatically generated through a neural function evaluation matrix. The problem that interestingness and effectiveness are difficult to consider in traditional rehabilitation is solved, and training compliance and neural function reconstruction efficiency are remarkably improved.

The application discloses a construction method and application of a post-cardiopulmonary resuscitation neural function prognosis prediction model, and a method, which comprises the following steps: acquiring clinical data of patients who have achieved spontaneous circulation recovery after cardiopulmonary resuscitation, and screening clinical patients meeting the inclusion criteria; taking brain function classification as a dependent variable, respectively adopting LASSO regression analysis and Boruta feature screening to screen characteristic variables, and selecting common characteristic variables; based on the common characteristic variables, constructing multiple machine learning models, and drawing a ROC curve and a decision curve corresponding to each machine learning model; adopting AUC to evaluate the discrimination of the machine learning models, adopting the decision curve to evaluate the clinical benefits of the machine learning models, and screening an optimal prediction model; and adopting SHAP tools to explain the optimal prediction model and the common characteristic variables. The prediction model constructed by the application can conveniently and quickly predict the neural function prognosis within 24 hours after cardiopulmonary resuscitation.

The invention relates to a self-adaptive closed-loop exoskeleton system based on a multi-modal brain-computer interface. The self-adaptive closed-loop exoskeleton system comprises a) a multi-modal signal acquisition unit; b) an adaptive neural decoding algorithm module; c) the three-joint exoskeleton follows the motion intention in real time through a hierarchical control strategy to control exoskeleton joints to move, and gait parameters are dynamically adjusted; d) a redundancy switching unit which is switched to an EEG full-function mode within 200ms when the ECoG signal is abnormal; and e) a spinal cord electrical stimulation module which is used for providing closed-loop auxiliary stimulation when the electroencephalogram signal is weak. High-precision and high-reliability motion control can be provided, the self-adaptive complex environment interaction capability is achieved, nerve function remodeling and rehabilitation can be promoted, and a safe solution is provided for motion control of a spinal cord injury patient.

The invention discloses a preparation method and application of neural stem cells capable of being used for in-vivo visual neural circuit connection. The method comprises the following steps: constructing a tool virus vector which is driven by a broad-spectrum promoter EF1 alpha, is optimized by a mammal codon and is expressed by a fusion reporter gene of wheat germ lectin and tyrosinase, and transfecting the vector into neural stem cells. TYR catalyzes tyrosine in cells to synthesize melanin through a multi-step reaction, and the in-vivo visualization of a brain region connected with a neural circuit formed by transplanted neural stem cells can be realized by utilizing a nuclide labeling probe of targeted melanin. According to the method, the neural stem cells for in-vivo tracing of neural circuit connection of the neural stem cells are established for the first time, and when and where the neural stem cells are dynamically and visually traced to establish connection with the host neural network in a living body; and a powerful research tool is provided for exploring a specific brain region in which the neural stem cells form loop connection in vivo and an action mechanism of the neural stem cells in neural function repair.

This invention provides a head-mounted intelligent wearable neuromodulation and sleep state regulation device and method based on neural coupling tuning and state transfer induction, including a flexible contact array, a state recognition module, a state transfer induction module, a neural coupling modulation module, a stimulation output module, and a feedback optimization module. The system acquires brain state feature vectors and, based on sleep stages and state regulation goals, divides the head into multiple neural functional node regions. Based on the brain state feature vectors, it dynamically generates node combination relationships, node activation sequences, and node collaborative paths. The state transfer induction module controls multimodal stimulation signals to form rhythmic synchronization, phase coupling, and node collaborative regulation, and outputs the signals to the probes corresponding to the target nodes. Simultaneously, it collects feedback signals in real time and dynamically optimizes the topological relationships between nodes and stimulation parameters to achieve closed-loop transfer regulation of brain states between different sleep stages. This invention can improve the individual adaptability, regulation accuracy, and safety of sleep state regulation.

Presented herein are techniques that make use of objective measurements obtained in response to acoustic stimulation signals. More specifically, at least one measure of outer hair cell function and at least one measure of auditory nerve function are obtained from a tonotopic region of an inner ear of a recipient of a hearing prosthesis. The at least one measure of auditory nerve function and the least one measure of outer hair cell function are then analyzed relative to one another.

A method of designing a component includes the steps of 1) inputting operator desired performance of a final component into a neural function-learning based module, and utilizing the neural function-learning based module to reach desired structural features for the component, 2) generating a physically realizable design in a design realization module based on the structural features and 3) evaluating the physically realizable design in an evaluation module, and utilizing evaluation module output to determine performance results for the physically realizable design. A system is also disclosed.

The application relates to the technical field of a brain-computer interface driven wearable adaptive brain-spinal cord synergistic neural regulation system, and particularly discloses a brain-computer interface driven wearable adaptive brain-spinal cord synergistic neural regulation system, which aims to solve the problems of brain and spinal cord regulation device synergistic stimulation, brain signal decoding based on a brain-computer interface, and a closed-loop adaptive neural regulation mechanism. The system comprises a brain-computer interface signal acquisition and decoding module, a multi-modal physiological state sensing module, and an adaptive brain-spinal cord synergistic neural regulation decision and execution module. The system realizes closed-loop adaptive neural intervention by collecting electroencephalogram and electromyogram signals in real time and dynamically generating brain and spinal cord synergistic regulation parameters. The application improves the individualization, precision and continuity of neural function repair, and has wearable integration and safety monitoring capabilities.

The invention discloses a novel porous microgel cell delivery system with high-throughput preparation capability, the system is composed of three parts, namely an aqueous two-phase system, a gas-assisted microfluidic device and a microporous microgel support, and can realize rapid and large-scale preparation of homogenized microgel, and the natural microporous structure in the microgel can be used for preparing a cell with high throughput. The survival and proliferation of various stem cells and somatic cells are facilitated, and high cell loading capacity and long-term activity maintenance are realized; the composite hydrogel between the microgels provides support for migration of endothelial cells and lumen formation, has good injectability and biocompatibility, and is matched with various tissue repair applications, and animal experiments find that in an ischemic stroke rat model, the composite hydrogel has a good application prospect. The microporous microgel loaded with the primary rat neural progenitor cells is injected, so that long-term neural function recovery of stroke rats can be effectively improved; the invention establishes a porous microgel delivery system with high throughput, high cell loading capacity and multiple vascularization functions, and the porous microgel delivery system is suitable for various tissue engineering applications.

The application discloses a kind of based on proprioception guide's brain-computer interface closed loop rehabilitation training system and method, it is related to brain-computer interface technical field, to solve the problem that existing fusion stimulation's brain-computer interface system lacks the individualized rehabilitation training method of stage, guiding, and with promoting central nervous remodeling as basic goal in rehabilitation training, system includes stimulation module and the central control module being connected with stimulation module, the stimulation module applies external stimulation to target muscle group;The central control module is respectively connected with intention decoding module and multi-modal feedback module, the intention decoding module judges whether motion intention characteristic meets standard according to built-in algorithm model;The intention decoding module is connected with electroencephalogram acquisition and processing module, and the electroencephalogram acquisition and processing module real-time acquisition and pre-processes electroencephalogram signal;The technical scheme of the application can enhance the authenticity and effectiveness of motor imagination, promote neural function remodeling.

The invention discloses a low-toxicity condition-dependent recombinant pseudorabies virus traced by a reverse neural circuit as well as a preparation method and application of the low-toxicity condition-dependent recombinant pseudorabies virus. The recombinant pseudorabies virus is obtained by packaging a polygene expression module containing a pseudorabies virus PRV Bartha homologous arm, a Ubc promoter and a 2A peptide sequence and a carrier plasmid of an expression cassette for expressing blue fluorescent protein; the 2A peptide sequence is a combination of P2A, F2A and T2A sequences. The recombinant pseudorabies virus PRV911 disclosed by the invention has remarkable low toxicity and can be used for efficiently tracing for a long time (more than 10 days). Besides, the PRV911 can realize accurate neuron type selective marking through conditional start (Cre-loxP system), so that an upstream input neural circuit is accurately tracked, the specificity and accuracy of neural circuit tracing are greatly improved, and a brand-new tool is provided for research of neural functions and disease mechanisms.

The embodiment of the invention discloses an electroencephalogram feature extraction method combining ABR and ERP waveform, comprising: acquiring left and right brain wave shapes from the same test, the brain wave shapes including ABR waveform and ERP waveform; for the left and right ABR waveforms and the left and right ERP waveforms, time features, amplitude features, density features and fatigue features between single-side waveforms and double-side waveforms are extracted; and fusing time features, amplitude features, density features and fatigue features of the left and right ABR waveforms and the left and right ERP waveforms as electroencephalogram features for reflecting neural activity. According to the embodiment of the invention, multi-dimensional effective signal features can be extracted from the ABR and ERP brain wave shapes to comprehensively reflect the neural function states of the brain and the brainstem.

The invention discloses a clinical application-oriented cloud edge hybrid AI artificial spinal cord system and a control method, and relates to the technical field of neural engineering and brain-computer interfaces. The system comprises a neural signal acquisition module, a multi-mode perception fusion module, an edge real-time control unit, a cloud intelligent training unit, a nerve stimulation output module, a somatosensory feedback module, a clinical-level safety fusion module and a wireless communication module. According to the invention, a core architecture of low-delay real-time control at an edge end less than or equal to 15ms, cloud individualized AI model training, rehabilitation process dynamic adaptation and networking non-inductive upgrading is adopted, the motion intention decoding accuracy is improved through multi-modal sensing fusion, and the use security and data privacy are guaranteed through a clinical-level security compliance system; the motion function of the patient with the spinal cord transection injury can be reconstructed, the control strategy can be dynamically optimized according to the rehabilitation process of the patient, and the lifelong iteration upgrading of the system is realized. The problems that in the prior art, pure edge computing power is insufficient, pure cloud delay is too high, individual adaptation and clinical compliance core pain points are lacked are solved, the motion intention recognition accuracy is larger than or equal to 98%, clinical conversion can be directly achieved, the method is suitable for rehabilitation of diseases such as spinal cord injury, cerebral apoplexy and cerebral palsy and nerve function replacement, and the commercialized application prospect is wide.

The invention belongs to the technical field of biomedical engineering, and particularly relates to a biological electromagnetic stimulation system based on an extremely-low-frequency magnetic field. The system comprises a control host, an integrated stimulation coil and an air cooling system, the integrated stimulation coil is composed of two Helmholtz coils which are arranged in parallel and is used for generating a uniform magnetic field; the air cooling system is integrated in the Helmholtz coil and is used for reducing the working temperature of the coil; the control host comprises an operation panel, a single-chip microcomputer circuit, a power supply circuit, a sine wave control circuit, a pulse control circuit and an upper computer serial interface. The operation panel is provided with a mode selection button, an intensity adjustment button and a timing setting button. The single-chip microcomputer circuit is responsible for controlling the whole system, the sine wave control circuit is used for outputting sine wave waveforms, and the pulse control circuit is used for outputting pulse waveforms. An alternating magnetic field noninvasively penetrates through the brain barrier, induced current is generated in intracranial tissue and directly acts on a focus area, and the purposes of improving blood circulation, repairing the neurological function and adjusting brain magnetic balance are achieved.

The invention discloses a pre-hospital stroke face recognition method and system based on a hybrid deep learning model, and belongs to the field of medical artificial intelligence. The method comprises the following steps: processing multi-modal baseline data when a user executes a standardized challenge in a healthy state by adopting a hybrid deep learning model so as to construct a personalized baseline response model; when the suspected stroke occurs, processing multi-modal instantaneous data when the user executes the same challenge by adopting a hybrid deep learning model to generate an instantaneous response trajectory; the hybrid deep learning model calculates a potential function failure potential representing a neural function instability degree based on a dynamic difference between the transient response trajectory and the baseline response model, and determines a time change trend of the potential function failure potential to obtain a failure potential accumulation rate; and finally, the model generates a face recognition result representing the stroke risk level based on the potential function failure potential and the failure potential accumulation rate. According to the invention, early and fine stroke-related face and speech abnormalities can be recognized with high sensitivity.

The invention provides a heat stroke early warning device and method based on zero heat flux and multi-parameter perception, and relates to the technical field of military operation medical protection. A zero-heat-flux core body temperature monitoring technology, a high-precision heart rate sensor and a three-axis acceleration sensor are integrated, key indexes such as core body temperature, heart rate and gait stability of heat stroke forebodes are monitored in real time, the neural function state is accurately judged in combination with an intelligent algorithm, and a multi-stage early warning system is constructed; early warning of labor heat stroke can be effectively achieved, and reliable protection is provided for people who work and exercise in the high-temperature environment.