110 results about "Brain model" patented technology

The invention relates to the technical field of large language models, in particular to a reservoir dam safety evaluation report multi-dimensional examination method based on a large language model. A reservoir dam safety evaluation report is processed by constructing a multi-dimensional insight brain-assisting model; using the risk preview to output a risk early warning text; performing scene verification, extracting parameters to drive external simulation, and outputting a comparison analysis report; a natural language processing technology is adopted, a traceable data link is constructed, and a semantic link traceability set is generated; and the multi-dimensional insight auxiliary brain model performs comprehensive review on the semantic link traceability set, records review difficult points, and generates a multi-dimensional review report through a man-machine common intelligence report engine. At present, a review method of a reservoir dam safety evaluation report has the problem of single review dimension. Therefore, the invention provides a reservoir dam safety evaluation report multi-dimensional examination method based on a large language model.

The invention discloses a functional connection and dynamic model-based anatomical connection prediction method, which comprises the following steps of: firstly, constructing a neurodynamic model, taking a random matrix as initial input, combining functional connection data and the neurodynamic model, and generating a coupling matrix which is more in line with neurodynamic characteristics by iteratively optimizing the random matrix; and the coupling matrix is used for predicting anatomical connection and replacing anatomical connection data to construct a high-precision brain model. According to the method, the initial random matrix is iteratively optimized, so that the generated coupling matrix gradually approaches real anatomical connection, non-intrusive anatomical connection prediction is realized, dependence on intrusive structure connection data is remarkably reduced, and compared with an existing neurodynamics modeling method depending on dMRI data, the method has the advantages that the modeling efficiency is improved, and the modeling cost is reduced. The used DMF model achieves higher fitting degree in structure and function, has higher flexibility and adaptability, is beneficial to revealing deep connection between functional connection and anatomical connection, and provides more efficient technical support for brain network research.

The invention provides a multi-robot collaborative operation method and system, and the method comprises the steps: receiving an input instruction through a global agent, and uploading the input instruction to a cloud brain model; task-level disassembly is carried out on the instruction through the cloud brain model, a task topological graph comprising a plurality of sub-tasks is generated, and a robot body for executing each sub-task is determined; respectively transmitting each sub-task to a corresponding end-side cerebellum model through the global agent by a cloud brain model; after each end-side cerebellum model receives the subtask, continuing to call the cloud brain model to disassemble the subtask into a skill sequence, and controlling the corresponding robot body to execute the skill sequence through the end-side cerebellum model, the intelligent distribution mechanism solves the problem of uneven robot load caused by task distribution based on simple rules in a traditional system, and improves the overall efficiency of multi-robot collaborative operation.

The invention relates to a transcranial magnetic stimulation high-precision positioning method, device and equipment based on optical navigation. Comprising the steps of selecting non-coplanar reference points based on a three-dimensional brain model of a patient, obtaining image coordinates and physical coordinates of all the reference points, carrying out corresponding point matching through the image coordinates and the physical coordinates, calculating and generating an optimal rigid transformation matrix, carrying out target registration error calculation, and realizing registration of an image coordinate system and a physical coordinate system. And according to the registered brain tissue conductivity parameters, calculating electric field space distribution induced by the transcranial magnetic stimulation coil in a target brain area, dynamically correcting stimulation target point coordinates of the virtual coil, and according to a completed coordinate system registration result, dynamically displaying the position and direction of the virtual coil corresponding to the transcranial magnetic stimulation coil on the three-dimensional brain model. And synchronously updating the brain slice view based on the corrected target point coordinates, and highlighting the actually stimulated brain region boundary. According to the method, adaptive neural navigation is driven through electric field remapping, and compensation target point correction is achieved.

The invention discloses a brain inspiration-based multi-modal data-driven driver emotion recognition method and system. Feature extraction is performed on the face video data and the multi-source heterogeneous driving behavior data after pulse processing through a constructed pulse neural network brain-like model of a driver face video feature extraction network, a multi-source heterogeneous driving behavior feature extraction network and a multi-modal feature fusion network; and outputting a cross-modal pulse attention feature fusion result, and identifying the emotion of the driver. Experiments show that the method is remarkably superior to an existing method in the aspects of accuracy, real-time performance and robustness, and the problems that single-modal recognition accuracy is insufficient, facial video and multi-source heterogeneous driving behavior modal feature extraction is insufficient, and a modal fusion strategy is low in efficiency are effectively solved. In addition, the pulse neural network brain-like method significantly accelerates the calculation speed, enhances the anti-interference capability of the model, and provides an efficient emotion recognition solution for an intelligent driving system.

A method of enabling a user to visualize, review and analyze a patient's EEG data, pre-surgical data and post-surgical data, includes generating a unified viewing environment, wherein the unified viewing environment has at least a first view area and a second view area; importing, using the unified viewing environment, pre-surgical data and post-surgical data; acquiring EEG data of the patient; displaying, simultaneously, the EEG data in the first view area and the post-surgical data in the second view area of the unified viewing environment, wherein the EEG data is displayed as a vertical stack of a plurality of EEG traces, and wherein the post-surgical data is displayed without a need to pre-process and co-register with a three-dimensional coordinate system; and automatically associating visual representation of each of one or more electrodes and contacts in the post-surgical data with an EEG trace of the plurality of EEG traces.

Anatomically accurate rodent brain models and phantoms, processes for constructing an anatomically correct computer simulation model of a rodent head, and fabricating the accurate rodent brain models and phantoms, and methods for leveraging the accurate rodent brain models and phantoms production are disclosed, and which may be used for simulated and experimental verification of induced electric fields and for experimentally testing neuromodulation and neuroimaging procedures.

The invention discloses a transcranial stimulation magnetic therapy coil navigation method, a transcranial stimulation magnetic therapy coil navigation system, a storage medium and equipment. The method comprises the following steps: acquiring three-dimensional structure information of the head of a target object, magnetic resonance imaging (MRI) data of an individual target object, or three-dimensional model data obtained by matching from a general MRI template library; real-time surface geometric information of the head of the target object is collected through an infrared optical tracking system; performing registration fusion on the three-dimensional structure information and the real-time surface geometric information, and generating an individualized three-dimensional brain model synchronized with a real space coordinate system on a navigation interface; the spatial position and posture of the optical marker fixed on the magnetic therapy coil are tracked in real time through an infrared optical tracking system and correspondingly mapped to the individualized three-dimensional brain model, and visual navigation of the magnetic therapy coil relative to the brain anatomical structure is achieved. Through the individualized three-dimensional navigation and real-time visualization technology, the problems that a traditional TMS is low in positioning precision, invisible in operation and poor in treatment repeatability are solved.

The invention discloses an electroencephalogram transformation simulation system and method for different brain states based on a Hopv model, and the electroencephalogram transformation simulation system constructs a virtual brain model by using an objective nonlinear dynamic model, carries out the quantitative description of the brain states, and achieves the accurate simulation of the transformation between different brain states and the prediction of a target spot. According to the method, the weighted phase lag index and the similarity of the network attributes of the weighted phase lag index are used as a parameter optimization target when the virtual brain signal is constructed, the electroencephalogram simulation level of the virtual signal is improved, and the target spot in the brain state transition process can be recognized and predicted by extracting the co-activation brain area of the co-activation mode and combining virtual stimulation. According to the method, a quantitative basis is provided for virtual brain model construction and brain state regulation and control, and an individualized nerve regulation and control strategy can be formulated.

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 discloses an optical and neural feedback multi-modal data analysis method for a nerve regulation target, and belongs to the technical field of cranial nerve treatment, and the method specifically comprises the steps: receiving a head movement instruction of a patient through an interactive interface, pausing transcranial magnetic stimulation after receiving the instruction, and switching to a head movement monitoring state; an infrared optical navigation device is combined with a magnetic resonance image to construct an individualized brain three-dimensional model, head position changes are tracked in real time, and autonomic nerve feedback signals are collected at the same time; synchronously aligning the head coordinates with the neural feedback signals to generate a multi-modal data set, and analyzing relevance to obtain real-time regulation and control parameters; the positioning and stimulation intensity of the transcranial magnetic stimulation coil are adaptively adjusted according to the parameters, and related information is displayed on a treatment interface; after the head of the patient finishes moving and is stable, a rapid re-calibration process is automatically triggered, high-precision monitoring is recovered, and magnetic stimulation output is reactivated; according to the invention, the treatment stability and adaptability are improved.

The invention discloses a fast incremental learning technology based on a pulse brain-like model, and belongs to the technical field of computer vision. According to the invention, a Yolov3-tiny model is selected as a basic model of SpikingYolov3 of the spiking neural network, and the adaptability of the Yolov3-tiny model is improved; an IF neuron model is used as a neuron model of SpikingYolov3; carrying out incremental learning training on the Yolov3-tiny by adopting a method based on network expansion; the weight of the trained model is assigned to the newly constructed SpikingYolov3 through a method of converting ANN into SNN; according to the method, a test image is subjected to coding operation in a Poisson coding mode, so that the test image is converted into an asynchronous pulse sequence, the asynchronous pulse sequence is sent into a Spiking Yolov3 model to be tested and is subjected to comparative analysis with corresponding Yolov3-tiny, and a conclusion that the detection performance of the Spiking Yolov3 model is better is obtained. The SpikingYolov3 is applied to a battlefield environment, so that accurate detection of different types of targets is realized. The problem that a traditional network model needs to be retrained when encountering a new task is solved, and a new solution is provided for a detection task of a complex target.

A method for performing artificial intelligence (AI) alignment on a generative AI model (GAIM), the method includes receiving a content item, which is generated by the GAIM. A computerized brain model, which has been trained to simulate responses of at least one human to content items generated by the GAIM, is applied to the content item. The AI alignment is performed on the GAIM based on a simulated response of the computerized brain model to the content item.

The embodiment of the invention discloses program control equipment and a medical system. The program control equipment is in communication connection with a stimulator implanted into a target object, and comprises a display interface and a processor, the display interface comprises a display unit for at least displaying a postoperative brain model of a target object, an operation unit for an operation object to execute parameter selection, and a program control unit for delivering a stimulation instruction to the stimulator; wherein the processor is configured to select and generate a target electric field model displayed on the postoperative brain model displayed on the display unit in an overlapping manner based on target stimulation parameters of an operation object on the operation unit, so that the operation object adjusts the target stimulation parameters on the operation unit based on the target electric field model displayed on the display unit; and under the condition that the operation object triggers the program control unit, the target stimulation parameter is sent to the stimulator in a soft output mode. According to the technical scheme, the accuracy of the adopted stimulation parameters can be improved.

The invention provides a multi-frequency time-domain interference stimulation simulation optimization method and device. The method comprises the following steps: constructing a corresponding Gaussian function according to time-domain interference stimulation parameters for a target clinical user, and obtaining Fourier series of each channel of a transcranial electrical stimulator; generating a brain model based on the brain T1 weighted imaging data, and setting corresponding target spot position information to optimize the target spot electric field direction in any direction; determining an effective electrode arrangement area of each axial section of the craniocerebral model and arranging electrodes; and optimizing the electrodes arranged on each axial section so as to determine each grid of the craniocerebral model and the intensity amplitude of the time domain interference stimulation electric field, and optimizing the input current of each channel. According to the invention, multi-frequency stimulation simulation optimization for each channel of the transcranial electrical stimulator can be realized, the focusing performance of time domain interference stimulation can be improved, the calculation complexity of time domain interference stimulation parameter configuration can be reduced, and personalized time domain interference stimulation simulation can be effectively and quickly realized in combination with clinical data.

The invention belongs to the technical field of image target recognition, and particularly relates to an anti-interference target recognition method combining a pulse neural network and a capsule network, a program, equipment and a storage medium. A capsule structure is introduced into a pulse brain-like model, a self-attention mechanism is introduced, the protocol degree between capsules can be learned in single forward propagation, a capsule attention map is generated through a self-attention layer, and then the capsule attention map is mapped to a classification layer through a one-dimensional convolution layer, so that the model structure and the calculation complexity are simplified, and the accuracy of the model is improved. And irrelevant capsule voting can be selected and inhibited by utilizing a self-attention mechanism, so that information useful for entity recognition is reserved, and the capabilities of long-distance dependence and feature selection are improved. The method has good robustness under the conditions of different noises and different intensities, has good generalization and invariance for affine transformation, and improves the anti-interference capability of target identification.

The invention provides a SEEG electrode positioning epileptic focus method and a processing device, and the method comprises the steps: constructing an individualized digital twin brain model based on multi-modal imaging data and physiological signal data; based on the digital twin brain model, obtaining a possible epilepsy region; obtaining an optimal SEEG electrode distribution scheme based on the possible epilepsy region; based on the optimal SEEG electrode distribution scheme, the epilepsy focus is positioned; according to the method, the possible epilepsy region is positioned by constructing the digital twin brain model, the association between the brain structure abnormality and the physiological signal abnormality is comprehensively considered, and the optimal SEEG electrode distribution scheme is determined according to the possible epilepsy region, so that the SEEG electrodes cover the suspicious region more accurately, the number of the SEEG electrodes is reduced, the cost burden of a patient is reduced, and the accuracy of the SEEG electrode distribution scheme is improved. And the monitoring effectiveness and the data processing efficiency are improved.

The invention discloses a transcranial magnetic stimulation coil based on a magnetic negative metamaterial and a method of the transcranial magnetic stimulation coil. The transcranial magnetic stimulation coil comprises a flat plate magnetic core located above an 8-shaped coil, the 8-shaped coil and the resonance type magnetic negative metamaterial located below the 8-shaped coil. On the basis of the 8-shaped coil, the flat plate magnetic core with high magnetic conductivity and the electromagnetic metamaterial with negative equivalent magnetic conductivity are introduced at the same time, and the magnetic field in the space is regulated and controlled by the flat plate magnetic core and the electromagnetic metamaterial on the basis of not changing the driving source and the 8-shaped coil winding structure; and the stimulation intensity and the stimulation precision of the stimulation coil on the brain model are greatly improved.

The present application relates to a kind of brain stimulation target point fast positioning method based on facial recognition and AI neural navigation, by obtaining the MRI data of user's head, construct the three-dimensional digital brain model including brain function partition information;Acquisition facial three-dimensional point cloud, with the head surface model reconstructed by MRI registration, establish the space mapping of actual head and brain model;Based on this mapping, determine stimulation target point on model.In treatment, real-time tracking head pose using optical system, and in navigation interface fusion display brain model, target point and the real-time position and angle of magnetic stimulation coil.Determine the best target stimulation angle of coil according to the gyri and sulci orientation of target point, guide operator to adjust coil pose by comparing the difference between real-time angle and target angle.The present application realizes the fast, accurate, visual positioning and dynamic maintenance of target point in transcranial magnetic stimulation treatment, and upgrades the traditional experience-dependent operation to individualized, real-time feedback precision navigation treatment.

A self-acting computer system (110) IS configured with a computational brain model, CBM,(102) comprising at least one self-learning artificial neural network, SL-ANN, (200), where the SL-ANN (200) comprises: a plurality of nodes (216), at least one of the nodes (216) comprising a directly self-acting node (400) configured to autonomously generate on-going perpetual BF internal activity, PBFIA, (406) and cause spontaneously output node activity, SONA, (412) to be output to the SL-ANN (200) which is driven by both: incoming activity input (302) received by the self-acting node (400); and the PBFIA (406) generated by the self-acting node (400), wherein the incoming activity input (302) is driven by activity propagating within the SL-ANN (200) derived from or comprising primary input (214) to the SL-ANN (200) and / or by SONA (412) output by other DSA nodes (400) or IDSA nodes (600) of the SL-ANN, wherein the primary input (214) to the SL-ANN (200) comprises data representing a sensed state of an entity, wherein the SL-ANN (200) is configured over time at least in part by SONA (412) generated by one or more self-acting nodes (400) and zero or more IDSA nodes (600) to adopt a network state space configuring the SL-ANN (200) as a self-acting ANN which is capable of spontaneously generating ANN output (220) The SL-ANN has a time-varying spatial region comprising a dynamic core where SONA (412) is dominant over node output activity comprising or driven from primary input (214) to the SL-ANN (200), and responsive to receiving spontaneously generated ANN output (220), the self-acting computer system (110) spontaneously generates computer system output (112) which causes an update to a sensed state of the entity.

Aspects provide systems and methods for utilizing quantum computing systems for processing of data generated by quantum sensor. For example, magnetic field data may be captured from a brain using a quantum sensor array. This magnetic field data may then be processed using a quantum computing apparatus including a plurality of qubits in order to generate a model of the brain.

A method of enabling a user to visualize, review and analyze a patient's EEG data, pre-surgical data and post-surgical data, includes generating a unified viewing environment, wherein the unified viewing environment has at least a first view area and a second view area; importing, using the unified viewing environment, pre-surgical data and post-surgical data; acquiring EEG data of the patient; displaying, simultaneously, the EEG data in the first view area and the post-surgical data in the second view area of the unified viewing environment, wherein the EEG data is displayed as a vertical stack of a plurality of EEG traces, and wherein the post-surgical data is displayed without a need to pre-process and co-register with a three-dimensional coordinate system; and automatically associating visual representation of each of one or more electrodes and contacts in the post-surgical data with an EEG trace of the plurality of EEG traces.

The invention discloses a positioning and delimiting method and system for a cortex pathological focus based on an intracranial electroencephalogram signal. The method comprises the following steps: constructing an individualized three-dimensional navigation model; obtaining an original intracranial electroencephalogram signal; generating a plurality of representative segments according to the original intracranial electroencephalogram signals; analyzing the original intracranial electroencephalogram signal and the plurality of representative segments so as to obtain a network analysis core index; generating a fusion type three-dimensional brain model according to the network analysis core index and the individualized three-dimensional navigation model; generating a space-time three-dimensional electroencephalogram model and an electrophysiology functional area distribution diagram according to the fused three-dimensional brain model and the network analysis core indexes; and according to the space-time three-dimensional electroencephalogram model and the electrophysiology functional area distribution map, generating accurate electrophysiology positioning and delimiting information of the cortical pathological focus. According to the invention, accurate electrophysiological delimitation of intra-operative cortical pathological lesions (glioma, hemangioma, focal cortical dysplasia and the like) is realized.

The present invention discloses an artificial intelligence multimodal medical image processing and diagnosis and treatment system, which relates to the field of medical image processing and diagnosis and treatment technology. It collects multimodal brain image data from multiple angles, extracts brain region features based on the multimodal brain images and formulates a normal brain model. The acquired brain region feature set is fused to generate a three-dimensional structural model of the brain region. The three-dimensional structural model is compensated using the patient's medical data to obtain patient characteristics, and the patient characteristics are analyzed to obtain a diagnosis report. The present invention constructs a three-dimensional brain structural model by fusing multimodal image features and patient medical data, simulates the pathophysiological process of brain diseases, thereby improving the accuracy and reliability of diagnosis, and providing technical support for early diagnosis and personalized treatment of brain diseases.

The present invention discloses an anatomical connection prediction method based on functional connectivity and kinetic models. First, a neural kinetic model is constructed, with a random matrix as the initial input. Combining functional connectivity data and the neural kinetic model, a coupling matrix that better conforms to neural kinetic characteristics is generated through iterative optimization of the random matrix, and this coupling matrix is used to predict anatomical connections, replacing anatomical connection data to construct a high-precision brain model. The method of the present invention realizes non-invasive anatomical connection prediction by iteratively optimizing the initial random matrix, enabling the generated coupling matrix to gradually approach the true anatomical connection, significantly reducing the dependence on invasive structural connection data. Compared with existing neural kinetic modeling methods that rely on dMRI data, the DMF model used has a higher degree of fit in terms of structure and function, stronger flexibility and adaptability, helps to reveal the deep connection between functional connectivity and anatomical connection, and provides more efficient technical support for brain network research.

The application belongs to the technical field of biomedical engineering and brain science, and particularly relates to a heterogeneous whole brain model construction method based on linearization theory and fusing connection-nonconnection effects, which constructs a heterogeneous whole brain model, uses real structural connections obtained through fiber bundle tracking as model input, compresses heterogeneous parameters based on real neural image data, introduces the influence of nonconnection effects on the whole brain model after completing parameter optimization, and solves the nonconnection effects through mathematical simplification, thereby providing a specific method for constructing individual-level heterogeneous whole brain models. The application introduces real neural image data, overcomes the difficulty of high-dimensional parameter optimization, and enhances the biological rationality of heterogeneous parameters, and simultaneously significantly improves the speed and stability of parameter optimization through the linearization method.

The application relates to a control method for dynamic walking of a biped robot and the biped robot, and belongs to the technical field of robot control, which comprises the following steps: 1, a self-recurrent cerebellar model neural network is used to establish a dynamic model of the biped robot with a disturbance term, and dynamic robust walking of the biped robot is converted into a problem of realizing stability of a multi-input multi-output nonlinear system with a bounded uncertain term; 2, an adaptive self-recurrent cerebellar model neural network error observer is designed to estimate an error upper limit; 3, an adaptive law of network weight is designed to realize real-time updating of the network weight space and to adjust parameters of each learning factor; and 4, a boundary value estimation algorithm is used to compensate for an estimation error and feedback to a robot walking system, so that the biped robot can realize asymptotic stable walking. The application enables the control system to adapt to time-varying characteristics of the biped walking system on line, and has continuous learning and adaptive capacity for unknown dynamics.

The invention relates to a method for inferring epileptogenicity of a brain region not observed to be recovered or not observed to be not recovered in a seizure activity of a brain of an epilepsy patient, comprising the steps of: providing a computerized model modeling individual regions of a primate brain and connectivity between said regions; providing said computerized model with a model capable of reproducing the dynamics of a seizure in a primate brain; providing structural data of a brain of an epilepsy patient and using said structural data to individualize the computerized model in order to obtain a virtual epilepsy patient (VEP) brain model; translating a state space representation of the virtual epilepsy patient (VEP) brain model into a probabilistic programming language (PPL) using probabilistic state transitions in order to obtain a probabilistic virtual epilepsy patient brain model (BVEP); and acquiring electroencephalogram or magnetoencephalogram data of the brain of the patient and fitting the probabilistic virtual epilepsy patient brain model against said data in order to infer the epileptogenicity of said brain region not observed.

The application discloses an individualized transcranial electrical stimulation system and method based on a multi-scale fusion brain model, which comprises the following modules: a large-scale brain model construction module, which is used for reconstructing an individualized brain function connection matrix by using electroencephalogram (EEG) data, then constructing an individualized large-scale brain model based on an average field model, and equivalent transcranial electrical stimulation to an external current input of the large-scale brain model, and constructing a large-scale brain model under the action of external stimulation; a microscopic neural circuit dynamics model construction module, which is used for fusing single neuron dynamics and synaptic plasticity, adopting a coupled leaky integrate-and-fire model and a spike-timing-dependent plasticity model to establish long-term plasticity between synapses, and then establishing a local neural circuit model through a stimulation target and downstream brain areas; an individualized multi-scale fusion brain model construction module, which is used for replacing corresponding nodes in the large-scale brain model with the local neural circuit model, and constructing an individualized multi-scale fusion brain model; and a stimulation response simulation module, which is used for adjusting transcranial electrical stimulation parameters by using the constructed individualized multi-scale fusion brain model, and obtaining EEG activity and short-term response and long-term effect. The application can more accurately describe the complexity of brain activity by establishing an individualized multi-scale fusion brain model.

Techniques for automatically detecting a seizure of a patient are presented. The techniques include: obtaining patient EEG data, where the patient EEG data represents an EEG of the patient for a plurality of channels, each channel representing a respective location in or on a brain of the patient; evaluating a tendency to act as a sink for each channel; determining, for each tendency to act as a sink, a respective energy distribution according to frequency; assessing an entropy of each energy distribution according to frequency; measuring, from at least one of the plurality of entropy quantifications, at least one sink tendency entropy drop value; identifying, based on the sink tendency entropy drop value, a presence of a patient seizure proximate to a time of a sink tendency entropy drop; and outputting an indication of the patient seizure.