351 results about "Human brain" patented technology

The invention provides an unmanned cluster brain-like navigation map fusion construction and cooperative positioning method. The method comprises the following steps: acquiring multi-modal perception data, respectively acquiring vision, sound wave and pose information through a binocular camera, a radar and an inertial sensor, simulating a human brain nerve coding mechanism, and generating a pulse sequence and a feature vector in combination with spatio-temporal information; constructing a multi-modal coding unit into a hypergraph node, and based on a dynamic hyperedge connection topological relation, aggregating spatial-temporal characteristics through a heterogeneous hypergraph convolutional network to generate a high-order brain-like semantic map of a single agent; sharing a local brain-like map by multiple agents through distributed communication, detecting geometric and semantic conflicts of an overlapped region, performing space-time alignment based on an anchor point reference, eliminating feature contradictions by utilizing probability distribution matching, and generating a global consistent high-confidence brain-like map; and outputting the optimal position estimation. Through bionic neural coding, heterogeneous hypergraph modeling and multi-agent collaborative optimization, establishment and positioning of a high-order brain-like map in a dynamic unknown environment are realized.

The invention relates to a multi-agent cooperation system based on a large model and a bionic human brain structure, and the method comprises the steps: an interaction layer is used for obtaining a natural language instruction inputted by a user side, and analyzing the natural language instruction into a structured task request; the application layer is used for generating a sub-task list according to the structured task request and determining a target resource demand; the support layer is used for dynamically allocating computing resources according to the sub-task list and target resource requirements and generating a resource allocation result; the cognitive layer is used for generating an environment state and a recommendation strategy according to the external environment data and the context of the natural language instruction; the decision-making layer generates a co-situation response and a task execution instruction according to the environment state, the recommendation strategy and the long-term portrait of the user; the execution layer is used for performing task execution according to the task execution instruction and generating a task execution result; and the model layer is used for determining a target model according to the task request and the model load state, and executing a task to generate a model processing result. According to the invention, the agent collaboration efficiency in a complex scene is improved.

The invention discloses a road target detection method based on brain-like dual-channel feature fusion, and belongs to the technical field of image recognition. According to the method, a target recognition and spatial positioning dual-channel mechanism based on a human brain vision system is provided, a traffic scene video stream is converted into a pulse density map, the pulse density map is input into a bionic dual-channel network, feature extraction is performed from a target recognition channel and a spatial positioning channel, then adaptive dynamic feature fusion is performed through a dynamic fusion module, and a traffic scene video stream is obtained. By strictly mapping a human brain visual path, enhancing the theoretical reliability of the technical scheme and introducing pulse convolution, high real-time performance and calculation efficiency are ensured, the precision, speed and power consumption of traffic target detection are balanced, and the method is suitable for a vehicle-mounted traffic target detection task and meets the requirement of an automatic driving system for target detection. Experiments prove that the mAP of the method for small target detection is improved by 15.8%, and the energy consumption is reduced by 40%.

The invention relates to the technical field of artificial intelligence, and discloses a brain-like multi-mode emotion recognition network, a brain-like multi-mode emotion recognition method and an emotion robot, and the brain-like multi-mode emotion recognition method comprises the steps: converting multi-mode emotion information into a pulse sequence; on the basis of the obtained pulse sequence, constructing a continuous pedigree emotion representation space, and realizing continuous representation of an emotional state; a continuous pedigree emotion representation space is utilized to generate pulse codes of mixed emotions, and a complex emotional state is represented; according to the pulse codes of the mixed emotions, establishing an emotional state conversion probability model, and describing a conversion relation between the emotions; based on an emotional state transition probability model, realizing prediction and processing of an emotional gradual change process, and capturing subtle emotional changes; according to the method, the working principle of human brain neurons can be used for reference, fine representation and accurate prediction of the human emotional state are achieved, and meanwhile high calculation efficiency and biological interpretability are achieved.

Belongs to the technical field of biomedical engineering, and discloses a method, a device, equipment, a product and a storage medium for identifying skull defects by constructing a characteristic spectrum through a nuclear magnetic image to solve the problem that a defect area is mistakenly divided into skull areas in existing automatic skull segmentation. Converting the human brain nuclear magnetic image to an anatomical space based on the plurality of anatomical points, and implementing preliminary segmentation to obtain a primary segmentation region of the skull; calculating coordinates of voxel points in the primary segmentation region in an anatomical point coordinate system, establishing a matrix, calculating a plurality of nuclear magnetic gray statistical characteristics of the primary segmentation region, and drawing a characteristic spectrum; and performing multi-condition feature threshold judgment on the feature map to obtain a logic binary map, and extracting a region of which a connected domain is greater than a specified threshold as a skull defect region. According to the method provided by the invention, a plurality of gray features are utilized, the misrecognition of the skull in the prior art is effectively corrected, the method can be further used for judging the filling tissue of the skull defect area, and the skull defect recognition capability can be improved.

The invention discloses a schizophrenia early warning and evaluation system based on human brain multi-region signals, and relates to the technical field of early warning and evaluation, and the system comprises a neural connection analysis unit which is used for recognizing neural connection characteristics of a brain network based on biomarker characteristics, comparing the neural connection characteristics with a database, and determining the neural connection characteristics of the brain network; clustering individuals with similar neural connection features according to a comparison result to generate a risk group; the emotion perception analysis unit is used for acquiring facial emotion states of the risk group in a preset time period and predicting evolution trends of neural connection features in different facial emotion states; and the early warning evaluation unit is used for inputting the evolution trend of the neural connection characteristics into a pre-constructed evaluation model, outputting a risk level evaluation result and formulating an early warning measure based on the risk level evaluation result. According to the method, neural connection features and emotion perception analysis are combined, so that early-stage neural connection abnormity and emotion turning intervals of schizophrenia can be accurately identified and positioned.

The invention provides a voice recognition method and device based on a brain-like model, electronic equipment and a storage medium, and the method comprises the steps: obtaining a whole-brain network topological structure according to a brain function network generated by human brain image data, and carrying out the recognition of a whole-brain network through employing a multi-class neuron model as a node and a synaptic plasticity model as an edge, constructing a multi-brain-region pulse neural network as a brain-like model; constructing a speech recognition framework of the brain-like model; electromagnetic intervention is applied to different brain areas of the brain-like model, optimal electromagnetic intervention parameters are determined by analyzing the voice recognition accuracy of the brain-like model before and after electromagnetic intervention, and brain-like model voice recognition is carried out according to the optimal electromagnetic intervention parameters. According to the invention, the speech recognition performance of the brain-like model can be effectively improved, the biological interpretability and neural information processing capability of the brain-like model are further improved, and the development of brain-like intelligence in the application of a mode recognition task is promoted.

The invention belongs to the field of food quality evaluation, and provides a delicate flavor synergistic effect evaluation method based on an electroencephalogram monitoring technology. Psychological or physiological factors such as subjective judgment, forced selection or scoring, individual umami cognition and umami sensitivity difference of sensory officers may affect the accuracy of sensory experiment results; the invention discloses methods such as umami sample selection and strength evaluation, electroencephalogram signal acquisition experiment normal form, quantitative evaluation and statistical analysis, feature extraction and response difference analysis, and the like, and the response mechanism of typical umami compounds in the human brain is explored by taking the response of people to umami signals as a research object and taking electroencephalogram signal detection analysis as a main method. A new theoretical basis is provided for quantitative evaluation based on the human palatable taste intensity, and the method is worthy of wide popularization.

Techniques are described for determining cognitive impairment, an example of which includes accessing a set of epochs of magnetoencephalography (MEG) data of responses of a brain of a test patient to a plurality of auditory stimulus events; processing the set of epochs to identify parameter values one or more of which is based on information from the individual epochs without averaging or otherwise collapsing the epoch data. The parameter values are input into a model that is trained based on the parameters to determine whether the test patient is cognitively impaired.

The invention discloses a method for detecting interpersonal nerve synchronization under audio-visual stimulation, which comprises the following steps of: designing a double-person super-scanning experiment normal form, collecting double-person electroencephalogram signals, and constructing a database of visual stimulation and auditory stimulation; preprocessing the data in the database to obtain electroencephalogram signals of four different frequency bands delta, theta, alpha and beta, extracting the electroencephalogram signals of the alpha frequency band, segmenting the electroencephalogram signals, and calculating a correlation ISC value between subjects of each segment; an intra-brain network and an inter-brain network are constructed by constructing a functional connection matrix, and the similarity of the intra-brain network and the global efficiency of the inter-brain network are calculated, so that the cooperation and synchronization degree between neural activities of subjects under visual stimulation and auditory stimulation is effectively evaluated. The invention further discloses a system for detecting interpersonal nerve synchronization under audiovisual stimulation. According to the method, the difference of subjects is reduced by standardizing experimental conditions, and the influence of single sensory stimulation on an intracerebral network activation mode is studied.

The basis of calculating memory capacity of modern computing is bit. Thus, the number of bits is the unit of information quantity of modern communication. The number of neurons (node number) in the neural networks in human brain is not the unit of the memory capacity of the human being. The complexity of neural network is much greater than the bit capacity. Hence, the current AI, which tries to imitate the human brain using computing with the basis on bits, performs inherently different processing of information from the human brain. In addition, computing based on bit number is always facing the limitation of integration. The present disclosure provides a system of information memory without relying on bits using three-dimensional neural networks. By replacing the electrical connection of non-volatile memory cells, which are distributed in a three-dimensional array, the mechanism of the information processing of the human brain can be imitated.

The invention relates to the technical field of transcranial electrical stimulation, and discloses a human brain transcranial stimulation circuit and a human brain transcranial stimulation method, and the method comprises the steps: obtaining the brain state data of a to-be-stimulated user; according to the brain state data, analyzing a connection relationship between brain regions, and constructing a brain network map; based on the relationship between the node degree value and the medium centrality value of each node in the brain network atlas and the corresponding preset value, analyzing an abnormal region in the brain network atlas in combination with a preset anomaly detection model to obtain a brain target region; generating a stimulation strategy according to the brain target area; optimizing the stimulation strategy in combination with the brain state data to realize closed-loop control of the stimulation strategy; by combining the real-time state of the user, dynamically generating the stimulation signal, accurately positioning the brain target area and optimizing the stimulation strategy, the brain target area can be stimulated more effectively, the treatment process is more scientific and reasonable, and the treatment effect and efficiency are improved.

The embodiment of the invention discloses a brain deep part electrical stimulation operation planning system and method based on a human brain network and a Lead-DBS technology, and the system and method are applied to operation planning of neuropsychiatric diseases. The data preprocessing module is used for denoising, correcting and standardizing the patient data to generate preprocessed data; the brain network model construction module is used for determining a functional connection matrix and a structural connection matrix based on the preprocessed data so as to construct an individualized brain network model; the electrode positioning module is used for generating an implantation target spot of a DBS electrode based on an individualized brain network model; the stimulation parameter optimization module optimizes stimulation parameters of the DBS based on the individualized brain network model and the electrophysiological data; the postoperative evaluation module compares the postoperative image with the preoperative plan to verify the actual implantation position and stimulation effect of the DBS electrode; the dynamic adjustment module is used for dynamically adjusting stimulation parameters.

The determination of the probability of gas hydrate formation using artificial neural network (ANN) and multilayer perceptrons (MLPs) models. ANN generally refers to a network of interconnected neurons (also referred to as “nodes”) that model the neurons in a human brain. An MLP refers to a feed-forward network having a specific arrangement of neurons and includes an input layer, one or more hidden layers, and an output layer. Input data such as temperature, pressure, gas mixture composition, and indicators of gas hydrate formation may be obtained and preprocessed for use in training and testing. The ANN and MLPs may be trained using a training set of the input to output a probability of gas hydrate formation. The trained ANN and MLP models may then be used to determine a gas hydrate formation probability for new data associated with a pipeline transporting a gas mixture.

The invention discloses a compound-target binding affinity prediction method based on multi-modal feature fusion, and relates to the technical field of compound activity prediction, and the technical key point is that the method comprises the steps of data acquisition, multi-modal feature characterization, multi-modal feature extraction and fusion, and affinity prediction to predict the compound activity. The problems of long time consumption, high cost, low efficiency and the like of compound activity prediction are solved through assistance of an artificial intelligence algorithm, and information can be processed in parallel in a self-adaptive and self-learning manner by referring to a multi-layered structure of a human brain and a layer-by-layer analysis processing mechanism of neuron information interaction. The intensity information of the interaction between the compound-target pair is provided by combining the affinity, the affinity between the compound and the target is predicted through a deep learning method, and the specific biological activity and key action target of the compound are analyzed.

The invention relates to a human brain extraction method and system for enhancing anatomical structure and surface information perception, electronic equipment and a storage medium, and belongs to the technical field of image processing. The anatomical structure sensing module aims to enhance understanding of global brain tissues, and the surface information sensing module emphasizes a local mode of a brain surface so as to solve challenges brought by low-level inter-class similarity of voxel intensity between brain tissues and non-brain tissues; furthermore, a novel local-global feature enhancement module is employed to enhance the association between local surface patterns and global brain tissue, providing a robust local-global representation that facilitates precise brain extraction. According to the method, the anatomical structure and surface information perception of the human brain is enhanced, so that accurate brain extraction is realized.

The invention discloses a large model real-time training system based on a human brain mechanism, and the system comprises an information input module which is used for receiving and processing various types of data, and carrying out the standardization processing; the temporary storage module is used for temporarily storing data for a certain time length; the importance evaluation module is used for evaluating the importance of the input data in the temporary storage module in real time; the memory classification storage module is used for classifying and storing the data into short-term, medium-term and long-term memories according to the importance of the data; the real-time fine tuning or training module is used for performing small-batch real-time training and updating model parameters by adopting a LoRA technology; and the model updating control module is used for monitoring the performance of the model in real time and automatically rolling back when abnormity occurs. According to the large model real-time training system based on the human brain mechanism, through a real-time fine tuning or training mechanism, the response speed and accuracy of the large model are remarkably improved, resource consumption is reduced, and meanwhile, the model can better adapt to a dynamic environment through an introduced memory and forgetting mechanism.

The invention discloses a result verification method for a transcranial magnetic stimulator calibration device, and relates to the technical field of medical equipment detection, and the method comprises the following steps: collecting pulse magnetic field parameters outputted by a TMS therapeutic instrument in real time through constructing a multipath parallel magnetic field distribution perception array composed of a plurality of coil type magnetic field sensors; designing a three-dimensional calibration platform to perform multi-dimensional dynamic calibration on the magnetic field distribution sensing array, calibrating the relationship between the induced electromotive force and the magnetic induction intensity of the sensor, and verifying whether the measurement error is less than + / -0.1% or not; and comparing the actually measured magnetic field data with the human brain magnetic field distribution data simulated by the finite element simulation model, analyzing the difference value between the simulation data and the actually measured data, and correcting the system according to the data deviation degree. According to the transcranial magnetic stimulator calibration device and the result verification method, real-time acquisition and high-precision calibration of dynamic parameters are realized through a multi-path synchronous magnetic field sensing array, and the calibration reliability is verified based on finite element simulation and actually measured data comparison.

The invention provides a diffusion magnetic resonance imaging method and system for multi-scale brain tissue microenvironment measurement, and the method comprises the steps: obtaining a spherical average signal of multi-b-value diffusion magnetic resonance data, carrying out the parameterization and normalization, and constructing a data training set; a microstructure dictionary comprising a feature extraction module and a multi-scale aggregation module is constructed, the feature extraction module is based on a visual Mangbar-convolution hybrid architecture and is used for extracting multi-scale structure information, and the multi-scale aggregation module is used for aggregating the extracted multi-scale structure information to obtain compact feature representation; and training the microstructure dictionary through the data training set, and carrying out joint characterization on the plurality of microstructure indexes by using the microstructure dictionary obtained by training to obtain a microenvironment measurement index. According to the method, the microenvironment parameters of multiple human brain tissues can be rapidly and quantitatively described in a cross-data acquisition protocol mode, and clinical application of dMRI microstructure imaging is promoted.

An integrated EEG-fNIRS neurofeedback system for interacting with participant's brain activity includes EEG electrodes, fNIRS detectors, at least one information receiver, a computation module, and a report generator. The EEG electrodes collect EEG signals. The fNIRS detectors collect fNIRS signals. The at least one information receiver receives and processes the collected EEG and fNIRS signals. The computation module executes an EEG and fNIRS signal processing pipeline with the EEG electrodes, the fNIRS detectors, and the information receiver. The computation module is further configured to: calculate score information based on received EEG and fNIRS signals; select a minimum score from the calculated score information; and discard an alternative score that is not selected as the minimum score, so as to enable the computation module to choose a single representative score for the shared target objective from both EEG and fNIRS signals. The report generator provides a report of the selection.

The invention discloses an audio feature extraction method based on a cranial nerve model, and the method comprises the steps: obtaining voice signal data, carrying out the preprocessing of a voice signal, and segmenting the voice signal into N voice segments; extracting acoustic features representing emotional conditions from each voice segment, normalizing the acoustic features, and synthesizing the acoustic features into a multi-channel voice spectrogram; and inputting the multi-channel speech spectrogram into the RBA-FE model, outputting a BDI score, carrying out depression degree prediction classification according to the BDI score, adjusting parameters of each network layer in the RBA-FE model according to the difference between prediction classification and actual classification, and obtaining an optimal RBA-FE model to carry out depression degree detection. According to the method, the cell selectivity in the auditory cortex of the human brain is simulated, the problems of overfitting and non-noise resistance of the LSTM are solved by adopting a self-adaptive activation mechanism, and precise recognition of the depression voice under different noise interferences is realized.

The invention discloses a photoelectric memristor based on a Ga2O3 / ITZO heterojunction, a preparation method and application. The photoelectric memristor comprises a bottom electrode layer, a Ga2O3 layer, an IZTO layer and a top electrode layer which are sequentially arranged from bottom to top. Wherein the Ga2O3 layer and the IZTO layer are used as heterostructure layers. And finally, a photoelectric memristor with a sandwich structure is formed. The preparation process is simple, large-scale preparation can be achieved, the performance is excellent and stable, the memristive effect is obvious under electric signals and multi-wavelength optical signals, the resistance value can change according to different voltage values or different illumination intensities, and the resistance value change is highly similar to nerve synapses of the human brain. Due to the characteristic, the photoelectric memristor can simulate the behavior of biological nerve synapse, and has the capability of a visual bionic system integrating perception and memory.

The invention discloses a human brain specific fluid flow direction identification method comprising the following steps: S1, multi-input network model construction: using a decoder to segment a task, and introducing a boundary detection task; high-density lesions and surrounding edema in the medical image are accurately segmented according to the Vi < T > and an attention mechanism; s2, fluid mechanics model construction and parameter setting, focus classification and risk quantification: optimizing time windows of two times of CT scanning; constructing a three-dimensional geometric model of high-density lesions, peripheral edema and normal brain tissue RO I; constructing initial physical field distribution; setting boundary conditions corresponding to a vascular rupture source and a focus drainage area; and dynamically adjusting the time step length based on the flow velocity and the diffusion coefficient. The invention provides a human brain specific fluid flow direction identification method, which combines image high-dimensional features with a multi-physics field coupling model, and reveals the heterogeneity of human brain specific fluid-blood conversion and contrast agent leakage in absorption and peripheral edema expansion modes.

The invention discloses a device and method for inducing sleep through a low-frequency changing magnetic field. The device comprises an electromagnetic unit, a sensing unit, an intelligent monitoring unit and a monitoring data platform, the method comprises the following steps: S1, acquiring state information of a human body through a sensing unit and transmitting the state information to an intelligent monitoring unit; s2, the intelligent monitoring system analyzes the acquired human body state information and controls an electromagnetic unit to be powered on, so that the electromagnetic unit generates an electromagnetic field and induces the brain of the human body to enter a sleep state; s3, the sensing unit continues to obtain the state information of the human body in real time and feeds back the state information, and the intelligent control unit optimizes and adjusts the magnetic field intensity and the magnetic field frequency generated by the electromagnetic unit; s4, the intelligent control unit uploads the human body state data and the magnetic field control data to a monitoring data platform, and the monitoring data platform generates a personal AI model and performs health state evaluation; and S5, the monitoring data platform feeds back a health state evaluation result to the intelligent control unit.

The invention discloses a depression subtype classification system based on a cross-species multi-mode brain image. The method comprises the following steps: firstly, obtaining cross-species multi-mode brain image data and depression brain image data and carrying out preprocessing; constructing a multi-modal mapping process between the human brain and the chimpanzee brain to obtain a homologous brain map of the human brain and the chimpanzee brain; the method comprises the following steps: constructing connection characteristics of a human brain and a chimpanzee brain by using whole-brain-based probability fiber tracking, and extracting specific connection characteristics of the human brain through cross-species comparison; constructing a depression typing model based on the specific connection characteristics of the human beings; and verifying the typing result based on the functional image data index and the brain function connection. According to the invention, from the perspective of species evolution, specific connection characteristics of human beings are constructed through cross-species comparison, depression subtype typing is realized, and a new perspective and a new method are provided for understanding depression subtypes and biological basis thereof.

Artificial neural networks (ANNs) are computing systems inspired by the human brain by learning to perform tasks by considering examples. These ANNs are typically created by connecting several layers of artificial neurons using connections, where each artificial neuron is connected to every other artificial neuron either directly or indirectly to create fully connected layers within the ANN. By substituting ternary matrices for one or more fully connected layers within the ANN, a complexity and resource usage of the ANN may be reduced, while improving the performance of the ANN.

The invention discloses an artificial intelligence model optimization method based on a brain-like artificial neural network, and the method comprises the steps: inputting a task data set into an artificial intelligence model, carrying out the forward propagation, and discriminating a corresponding dormancy neuron or an activation neuron of the artificial intelligence model in a process of executing an artificial intelligence task; a neuron dormancy matrix or activation matrix is generated as a mask matrix of the artificial intelligence model network weight, and a forward propagation path of the artificial intelligence model is reconstructed, so that dormancy neurons do not participate in the training and testing process of the artificial intelligence model network structure; or only enabling the activated neurons to participate in the training and testing process of the artificial intelligence model network structure; and loading the reconstructed artificial intelligence model at the computing device to execute the artificial intelligence task. According to the method, the working mode that only 0.5%-2.5% of neurons of the human brain are activated and most neurons are in a dormant state is effectively simulated, the calculation cost of the model is greatly reduced while the calculation performance of the model is not reduced, and the calculation efficiency of the model is improved.

The invention discloses a nerve coupling decoding method based on double electroencephalogram. The method comprises the following steps: S1, importing multiple groups of EEG data synchronously recorded by double persons and carrying out data preprocessing; s2, extracting features from the preprocessed electroencephalogram data, and calculating brain function connectivity across individual electrodes; s3, carrying out phase lag index analysis in combination with the frequency domain characteristics of each frequency band, and capturing the dynamic coupling characteristics of the double-brain signals in task execution; nonlinear coupling analysis is carried out by combining a calculated value of cross-individual electrode connectivity, and a nonlinear coupling relation between brain intervals is further quantified; and S4, integrating a phase lag index analysis result with the frequency domain features of each frequency band and the nonlinear time domain features of the single brain signal to form a high-dimensional feature matrix, performing dimension reduction, taking the features after dimension reduction as input, constructing an SVR model and calculating a double brain nerve synchronization index, and realizing decoding and prediction of the nerve coupling degree of the double brain signal.

A computer-implemented method for decoding speech, language and related semantic neural activity includes: collecting neural signals from an array of electrodes implanted in or on a brain; extracting features from the neural signals to detect distributed signatures of linguistic encoding using non-contiguous coverage of the electrode array; and decoding linguistic units, including phonemes and semantic embeddings from the extracted features. The decoding can utilize a custom neural language model for a limited or impaired brain adapted from a generalized neural language model trained on other human brains with intact speech, linguistic and cognitive regions.