337 results about "Neural network learning" patented technology

The invention relates to the technical field of mutual inductor tests, and provides a mutual inductor test abnormal data automatic filtering analysis method and system, and the method comprises the steps: obtaining magnetic field data, electric field data and thermal field data, respectively carrying out the feature extraction and weighted fusion, and obtaining a multi-physical field fusion feature vector; constructing an electromagnetic induction chain type propagation graph, calculating the weight of an edge in the graph, constructing a magnetic flux conservation constraint graph convolutional neural network, learning propagation and evolution modes of transformer test abnormity, and obtaining a coupling abnormity feature vector; the coupling anomaly feature vectors are classified, normal data, single physical field abnormal data and multi-physical field coupling abnormal data are recognized, and corresponding data are judged as abnormal data and filtered; and carrying out physical mechanism analysis on the filtered abnormal data to obtain an abnormal detection report. According to the invention, high-precision automatic identification, filtering analysis and physical mechanism traceability diagnosis of transformer test abnormal data are realized.

The invention discloses a molecular structure characterization-based drug-drug interaction prediction method, which comprises the following steps of: acquiring drug molecule data and drug-drug interaction data, performing standardized preprocessing on the data, and constructing a drug molecule map according to the drug molecule data; inputting the drug molecule map into a model, extracting drug molecule multi-scale features through a multi-scale map convolutional network, and fusing the drug molecule multi-scale features through a dynamic attention mechanism to obtain drug molecule features; based on the drug molecular characteristics, through a full-connection neural network, learning the relationship between the drug molecular characteristics and the drug-drug interaction, and obtaining the prediction probability of the drug-drug interaction; and training the model by adopting a joint loss function according to the drug-drug interaction data and the prediction probability, and applying the trained model to drug-drug interaction prediction. And through the multi-scale image convolutional network, dynamic attention fusion and joint optimization, the prediction accuracy is significantly improved.

The invention relates to an unmanned aerial vehicle track prediction method based on multi-feature LSTM, and belongs to the technical field of data processing, and the method comprises the following steps: 1, constructing a six-degree-of-freedom global motion state matrix of a target unmanned aerial vehicle; 2, performing joint estimation to obtain a three-dimensional wind field vector acting on the target unmanned aerial vehicle, and extracting the real-time speed direction of the target unmanned aerial vehicle; 3, fusing the historical state sequence, the three-dimensional wind field vector and the speed direction unit vector, and constructing a multi-dimensional time sequence feature vector; 4, the LSTM neural network learns a nonlinear maneuvering mode of the target unmanned aerial vehicle under the influence of the wind field through a door control mechanism of a forgetting door, an input door and an output door; and step 5, outputting the position probability distribution of the target unmanned aerial vehicle at a plurality of time points in the future through the LSTM neural network. The method has the advantages that the space-time cone representing the future trajectory is formed, and trajectory prediction of the target unmanned aerial vehicle is completed.

The invention relates to the field of intelligent control of marine navigation, and discloses a formation dynamic interception path planning method and device based on a differential game theory, and the method comprises the steps: constructing a differential game model comprising a formation and intercepted ships; designing revenue functions for the two parties; obtaining a Nash equilibrium strategy by solving a Hamiltonian-Jacobian-Bellman equation of the game, and solving an individual optimal control instruction of each formation member; and fusing state information among formation members through a consistency protocol, adjusting individual instructions to meet anti-collision and formation cooperative constraints, and generating a final control instruction. According to the method, historical adversarial data is learned by using the neural network, and the weight of the revenue function is adaptively and dynamically adjusted to cope with different tactical scenes; and the whole decision-making process is set under a model prediction control framework for rolling optimization, so that the real-time performance, the collaboration and the intelligent level of interception path planning are greatly improved, and the interception efficiency is effectively improved.

The invention relates to the technical field of electric vehicle charging pile planning, in particular to an intelligent charging pile layout optimization method based on a multi-scale space-time diagram neural network. Comprising the following steps: S1, constructing a heterogeneous dynamic graph which represents a potential charging pile position node set, epsilon t represents a time-varying edge set, At represents a time-varying adjacent matrix, and Xt represents a node feature matrix; s2, calculating a self-adaptive adjacency matrix with a specific relationship, and calculating a multi-type dynamic relationship between capture nodes of the self-adaptive adjacency matrix based on the constructed heterogeneous dynamic graph model; s3, updating a structure bias matrix, and capturing dynamic change characteristics of the network; s4, calculating distance measurement between nodes, and fusing geographic information and semantic information; s5, through graph neural network learning, based on the constructed heterogeneous dynamic graph and the calculated adaptive adjacency matrix, executing a graph neural network learning process, and extracting node space-time representation; and S6, predicting a future charging demand based on node representation obtained by graph neural network learning, and generating based on the future charging demand.

The invention discloses an electro-hydraulic system adaptive neural network preset time control method, which integrates a neural network real-time learning technology, innovatively introduces a preset time performance function, and designs an adaptive neural network preset time performance controller. For the electro-hydraulic system position tracking control problem, it can be ensured that system output transient performance and steady-state performance converge to a specified performance index range within a preset time, safe and reliable operation of the system is ensured, the unknown dynamic state of the system can be learned in real time through a neural network, high-precision motion control performance is achieved, and the control precision is improved. And the problem of differential explosion in traditional backstepping control of the electro-hydraulic system can be avoided, and the influence of measurement noise on the control precision is reduced.

The invention belongs to the field of track planning and intelligent control of a reusable vehicle, and relates to an intelligent track planning method for a cruise section of the reusable vehicle. The method comprises the following steps: constructing a three-degree-of-freedom centroid motion dynamics model of a cruise section vehicle, generating an offline optimal trajectory sample library covering wide working conditions based on a Gaussian pseudo-spectral method, designing a mapping relation between deep neural network learning task parameters and trajectory features, and outputting a high-quality trajectory planning initial value online. The distribution of collocation points is dynamically adjusted in combination with a self-adaptive collocation point method, a nonlinear programming problem is iteratively solved with a high-quality initial value as a starting point, and efficient and accurate optimization of the trajectory is achieved. Simulation results show that the method significantly reduces the sensitivity of online optimization to initial guess, still has fast response ability and high robustness under complex constraint and uncertainty working conditions, effectively improves the autonomous trajectory planning ability of the cruise section of the reusable vehicle, and ensures flight reliability and control precision.

The invention relates to the field of medical artificial intelligence, in particular to a laryngeal cancer early intelligent diagnosis system and method based on multi-modal deep learning, and the system comprises a multi-modal data collection module, a cross-modal feature extraction module, a cross-modal attention network module, an expert-level knowledge distillation network module, and a focus evolution prediction and diagnosis decision and visualization module. Endoscope images, acoustic features and clinical data are collected, a system extracts high-dimensional feature vectors, a cross-modal attention network is used for feature fusion, an expert-level knowledge distillation network is combined with pathology and expert experience, neural network learning is guided, a lesion evolution prediction module tracks lesion changes, risk prediction is generated, and finally, the lesion evolution prediction module is used for predicting the lesion change. And the diagnosis decision and visualization module generates a diagnosis result and explanation. The system improves the early detection rate of laryngeal cancer through multi-modal data fusion.

The invention provides an incinerator temperature field optimization method and system based on CFD numerical simulation, and the method comprises the steps: firstly recognizing a dynamic interference event in the operation of an incinerator, extracting the feature information of the event, constructing a hearth space association graph, learning the association relation between the interference feature and the temperature field abnormality through a graph neural network, and outputting a temperature abnormality association link; inputting the data into a CFD simulation system to generate and execute a target simulation task; acquiring dynamic response data of a temperature field; analyzing the data to determine a simulation correction direction; generating a parameter adjustment instruction to update simulation parameters; and finally, extracting a final simulation parameter as an optimization scheme, so that the temperature field of the incinerator can be accurately optimized.

The present invention discloses a drug-target prediction method based on a graph-attributed neural network, comprising the following steps: S1, constructing a multi-source heterogeneous biological network and uniquely identifying drugs, proteins, and diseases; S2, calculating the similarity between any two diseases based on the disease module theory of the human protein-protein interaction network; S3, using each biological entity pair and the corresponding similarity value as a training sample for the graph attention neural network representation learning phase; S4, using the training samples to drive the graph attention neural network learning to obtain a representation vector for each entity; and S5, using the trained drug-target prediction model to predict drug-target interactions. This invention reduces the dependence of deep learning models for drug-target interaction prediction on training samples, thereby improving prediction performance.

The invention provides a disease and pest epidemic prevention system based on image recognition, and the system comprises a data collection and preprocessing module which is used for collecting optical images, sound wave images and environment information of crops, and carrying out the preprocessing and feature extraction; the image enhancement module is used for processing the sound wave features, enhancing the optical features through a sound wave weight map obtained through processing, and marking the pest and disease region through a neural network to obtain an optical enhancement image; the image segmentation module is used for carrying out region division on the optical enhancement image and then carrying out pixel-level segmentation to obtain a to-be-identified region map; and the disease and pest recognition module is used for outputting a disease and pest recognition result graph through a disease and pest recognition model after learning a double mapping relation between the to-be-recognized area graph and the environment weight vector through a neural network. According to the invention, through comprehensive application of multi-modal information fusion and a deep learning technology, the efficiency and precision of crop disease and insect pest detection are significantly improved.

The invention relates to the field of electrical system fault detection, and provides a cable fault positioning method and system based on neural network learning. The method comprises the following steps: acquiring a cable traveling wave signal and preprocessing the cable traveling wave signal to obtain a preprocessed traveling wave signal; performing high-speed parallel acquisition on the preprocessed traveling wave signal to obtain multi-channel digital traveling wave data; performing multi-resolution decomposition on the multi-channel digital traveling wave data through a fast wavelet transform algorithm, and performing feature extraction on a wavelet coefficient obtained through decomposition to obtain a fault feature vector; and carrying out classification identification on the fault feature vector through a multilayer perceptron neural network, and carrying out fault position calculation on a classification result to obtain a fault positioning result. According to the invention, the cable fault positioning precision and reliability are improved.

The invention discloses a single cell space transcriptome data analysis method, device and system, and a storage medium. The method comprises the following steps: acquiring single cell space transcriptome data; the spatial transcriptome data comprises a gene expression map and spatial site coordinates; constructing a graph structure considering gene expression similarity and spatial position continuity on the basis of the data, and performing data representation on a gene expression graph by using an adversarial auto-encoder; in combination with a graph neural network, robust potential characterization is learned, training loss is constructed through reconstruction of a gene expression map, and meanwhile, a clustering prediction result of spatial sites is obtained in combination with mcluster clustering. By adopting the technical scheme of the invention, the spatial clustering analysis with higher precision can be realized, and the key spatial functional region in the biological tissue can be identified.

The invention provides a three-dimensional reconstruction method based on a structured Gaussian and neural kernel field, and the method comprises the steps: taking a multi-view image, internal and external parameters of a camera, and a point cloud as input, firstly constructing a structured Gaussian representation, optimizing the structured Gaussian representation, then constructing a neural kernel function field of a scene, taking a sparse voxel grid and an anchor point as a basic space structure of a kernel function, and carrying out the optimization of the neural kernel function field; and related features of the kernel function are predicted through neural network learning. According to the method, a mutual guidance mechanism between the structured Gaussian representation and the neural kernel function field is introduced to collaboratively optimize the two representations. And finally, performing efficient view rendering by using the structured Gaussian representation, and outputting a high-precision three-dimensional surface model. According to the method, high-quality rendering and reconstruction output can be realized by utilizing compactness and efficiency of structured Gaussian representation in processing a large-scale scene and combining scalability and robustness of a neural kernel function field in implicit surface learning, and the method is suitable for understanding and application of complex and large-scale three-dimensional scenes.

The invention discloses an air purification and temperature and humidity coordination control method and system for a central air conditioner, and the method comprises the steps: learning past and future environment change trends based on a Bi-LSTM bidirectional neural network, adding a one-dimensional CNN convolution layer before Bi-LSTM, and extracting a local space mode of sensor data; introducing an attention mechanism to dynamically weight a pollutant concentration peak value and a temperature and humidity sudden drop point in the input sequence; inputting the multi-modal data into the hybrid prediction model for prediction, and outputting a prediction result; establishing a dynamic optimization model by taking minimization of energy consumption, maximization of air cleanliness and maintenance of temperature and humidity stability as targets through an NSGA-II multi-objective optimization algorithm; and inputting the prediction result, the multi-modal data and a threshold value set by a user into a dynamic optimization model, and outputting an air purification adjustment parameter and a temperature and humidity adjustment parameter. The efficiency and accuracy of temperature and humidity control and air purification control are improved.

Various embodiments enable a robot, or other autonomous or semi-autonomous device or system, to receive data involving the performance of a task in the physical world. The data can be provided as input to a perception network to infer a set of percepts about the task, which can correspond to relationships between objects observed during the performance. The percepts can be provided as input to a plan generation network, which can infer a set of actions as part of a plan. Each action can correspond to one of the observed relationships. The plan can be reviewed and any corrections made, either manually or through another demonstration of the task. Once the plan is verified as correct, the plan (and any related data) can be provided as input to an execution network that can infer instructions to cause the robot, and / or another robot, to perform the task.

The invention belongs to the technical field of computers, and particularly relates to a personalized recommendation method and system based on a dynamic heterogeneous graph and reinforcement learning. The method comprises the following steps: firstly, constructing a global heterogeneous information graph of multiple types of nodes offline, and learning static embedding of the nodes by using a graph neural network; secondly, dynamically constructing a session history into a session graph in a real-time interaction process of the user, and aggregating by adopting a graph convolutional network to generate a dynamic state vector of the user; inputting the dynamic state vector into an actor and commentator reinforcement learning framework; and finally, using a dominant function calculated by the commentator network as a stable learning signal, and performing end-to-end joint training on the whole model to optimize long-term cumulative return. According to the method, by introducing the session graph volume accumulation device, the accuracy of dynamic state representation is remarkably improved; and an actor commentator framework is adopted, so that the problem of high variance of a traditional strategy gradient method is effectively solved, and the training stability and efficiency are improved.

The invention belongs to the technical field of six-axis robots, and discloses a method for predicting robot joint friction based on an improved PINN principle and a LuGre model, and the method specifically comprises the following steps: 1, generating a robot excitation track, and collecting the positions, speeds and currents of six joints of a robot; 2, current estimation torque of each joint of the robot is calculated according to the current, and a friction force-speed-displacement mapping of the joints of the robot is obtained; 3, constructing a friction model of the robot based on the improved PINN principle and the LuGre model; and 4, designing a double-neural network learning strategy of the robot friction model. According to the method, the improved physical information neural network PINN and the LuGre model are fused, the multi-joint coupling effect of the six-axis robot and the friction characteristic in the full-speed range can be considered at the same time, accurate prediction of the joint friction force of the six-axis robot is achieved, the prediction precision is improved, and the prediction efficiency is improved. And the problem of physical information loss caused by model simplification is also avoided.

The invention discloses a vehicle refitting scheme generation method and system based on a large model and a knowledge graph, and relates to the technical field of electric vehicle networking, and the method comprises the steps: inputting an obtained user refitting demand text into a cloud large model, analyzing the refitting demand text, extracting key information, converting the key information into a query vector, and sending the query vector to a cloud server; the method comprises the following steps: establishing a vehicle refitting knowledge graph, performing matching retrieval with entity embedding in the commercial vehicle refitting knowledge graph, constructing cue words according to the retrieved knowledge, generating a vehicle refitting scheme through cloud big model thinking chain reasoning, calling a 3D component to render a scheme effect graph, and feeding back the scheme effect graph to the local; vehicle data, accessory data, scene data, law and regulation data and historical modification case data are obtained in advance, after data preprocessing, entities and relationships are obtained through named entity recognition and relationship extraction, a commercial vehicle modification knowledge graph is constructed, and entity embedding in the knowledge graph is obtained through graph neural network learning. According to the invention, a refitting scheme which better meets user requirements can be obtained.

The invention relates to the technical field of energy conservation and carbon reduction in the high-energy-consumption industry, and discloses a system air leakage and carbon emission intelligent monitoring method in the high-energy-consumption industry, which comprises a data preprocessing link, a gas detection link, a carbon emission accounting link, a data fusion weight adjustment link and a carbon emission abnormity check link. The system innovatively develops a data deep processing mechanism, and adopts a multi-dimensional data calibration technology to carry out total factor correction on factors such as temperature and pressure fluctuation and humidity interference; the method comprises the following steps: measuring and calculating air leakage volume flow, calculating air leakage oxygen molar flow by combining with an oxygen proportion characteristic in air, carrying out cross validation on carbon emission through an oxygen balance and material balance double algorithm, learning historical working condition data by using an LSTM neural network, dynamically adjusting an algorithm weight built-in constant verification mechanism, and starting a retest and calibration program when the data is abnormal. According to the invention, through full-process intelligent cooperation, accurate monitoring of carbon emission and dynamic verification of abnormity are integrated, and a systematic solution is provided for low-carbon transformation in the high-energy-consumption industry.

The invention discloses a self-adaptive fuzzy PID flow field control method and device, and the method comprises the steps: generating an initial PID gain parameter in real time through a fuzzy reasoning module, introducing an RBF neural network module to carry out the dynamic optimization compensation of the initial parameter, and generating a correction gain. And a final PID parameter is dynamically synthesized by adopting a weighted fusion formula, and a weight coefficient is adjustable so as to balance the contribution of fuzzy rules and neural network learning. The nonlinear approximation capability of the RBF network is utilized, network parameters are updated in real time through a gradient descent method, a Jacobian matrix of a controlled system is output, and the sensitivity of the control quantity to input changes is accurately recognized. The parameter updating rate is dynamically adjusted through a momentum item and an exponential decay function in combination with environmental sensor data, flow feedback and historical deviation, and a closed-loop control loop of monitoring, fuzzy reasoning, RBF optimization, PID output and feedback is formed. The accuracy of flow field control is improved.

The invention provides a three-dimensional flow field acquisition method and system based on two-dimensional through-flow and a neural network, belongs to the field of fluid mechanics calculation, and can at least partially solve the problem that in the prior art, calculation efficiency is low, and two-dimensional through-flow cannot reflect three-dimensional features. Geometric parameters and working condition parameters of fluid machinery are input, and flow parameters on a two-dimensional flow surface are rapidly output; constructing and training a neural network model, wherein the neural network learns a mapping relation between a two-dimensional flow surface calculation result and a three-dimensional flow field; for the fluid machinery under the target working condition, a result is obtained through two-dimensional through-flow calculation, the result is preprocessed and then input into the trained neural network, the low-dimensional representation of the three-dimensional flow field is output, and complete three-dimensional flow field parameters are obtained through reconstruction. The calculation period is remarkably shortened, and rapid optimization of multiple schemes is supported.

The invention discloses a drug recommendation system based on causal co-occurrence enhancement, which fuses a co-occurrence relationship and a causal relationship between medical information to realize high-precision and high-safety personalized drug recommendation. Comprises: a medical information representation generation module based on a medical information co-occurrence relationship, used for constructing a medical entity co-occurrence graph and obtaining embedded representation through graph attention neural network learning; the patient treatment characterization generation module based on the medical information causal relationship constructs a treatment-level medical causal graph by using a causal discovery algorithm, and performs weighted fusion according to the causal roles (such as cause nodes and intermediate nodes) of entities to form patient treatment characterization; according to the drug recommendation module based on the co-occurrence causal relationship, co-occurrence enhancement factors and a causal effect matrix calibration mechanism are introduced on the basis of preliminary prediction, and it is ensured that a recommendation result has statistical rationality and causal interpretation at the same time. The accuracy, interpretability and clinical applicability of drug recommendation are remarkably improved.

The invention relates to the technical field of traffic safety research, in particular to a vehicle abnormal driving behavior recognition method and recognition system based on deep learning. The method comprises the steps of obtaining historical driving data and station environment data to construct an offline training data set, extracting a first type of time sequence features representing abnormal driving behaviors and a second type of time sequence features representing abnormal scenes, determining an optimal feature combination based on neural network learning, outputting a first feature vector representing the abnormal driving behaviors, and outputting a second feature vector representing the abnormal driving behaviors. And according to the first feature vector representing the abnormal scene and the second feature vector representing the abnormal scene, establishing an abnormal driving recognition model, inputting the driving data and the scene data acquired in real time into the abnormal driving recognition model, and outputting to obtain an abnormal driving behavior recognition result of the target operation vehicle. According to the invention, a dual-channel feature training mechanism is adopted, millisecond-level online identification is realized based on offline training, and a vehicle abnormal behavior result is output in real time.

The invention relates to the technical field of leather products, and particularly discloses a leather product feature recognition and authentication method and system based on deep neural network learning. According to the scheme, visible light, near-infrared reflection and polarized light interference images of leather are obtained through a multi-mode imaging technology, surface texture and color, internal fiber structure and section fiber arrangement features are extracted respectively and converted into standardized feature vectors, the three types of features are fused to construct a comprehensive leather feature vector, and the comprehensive leather feature vector is obtained. A deep neural network is input for authenticity identification, a confidence score is output, objective quantification of full-dimensional physical characteristics from the surface to the interior is realized by outputting the confidence score, subjectivity and one-sidedness of traditional artificial identification are overcome, and the method has efficient and large-scale accurate identification capability.

The invention discloses a spacecraft game control method and device under incomplete information based on adaptive dynamic programming, and belongs to the technical field of spaceflight. The method comprises the following steps: establishing a spacecraft pursuit game relative motion model, and estimating an unknown strategy and spatial disturbance of a non-cooperative target through a fixed time expansion state observer; constructing an incomplete information pursuit game model based on the estimation state, designing an adaptive dynamic programming game strategy, and approaching an optimal game strategy by using a neural network; an Ada-delta method is introduced to adaptively adjust the learning rate of the neural network, so that the convergence efficiency is improved; an escape spacecraft shape model is constructed based on a super-quadric surface, and collision avoidance is ensured in combination with a potential function; a time constraint problem is solved through a fixed time compensation item, and an approximate optimal game strategy in fixed time is realized. According to the method, the problems of time constraint and strategy optimization of spacecraft game control under incomplete information are effectively solved while the safety is ensured.

The invention relates to an online learning system based on a memristor cross array, and belongs to the technical field of machine learning. The system comprises a forward calculation subsystem, a memristor resistance value online adjustment subsystem and a visualization subsystem, the forward calculation subsystem comprises a memristor cross array simulation device and a computer module, and derivative calculation in neural network training and memristor resistance value dynamic adjustment are combined through a simulation platform. A memory resistor is used for achieving storage and calculation integration, a computer module completes derivative calculation in a differential mode, a differential derivative calculation mechanism of the computer module directly obtains a derivative through actual response of a physical device, the defect that a storage and calculation integration framework cannot store intermediate variables is overcome, and calculation autonomy and efficiency are remarkably improved. Meanwhile, an introduced resistance updating mechanism combining coarse adjustment and fine adjustment can realize efficient and accurate control of the resistance of the memristor. Finally, the neural network learning efficiency and performance based on the memristor cross array are improved.

The invention belongs to the technical field of spectrum reconstruction and machine learning, and particularly relates to a mapping relation model between a substance image and a spectrum thereof, a construction method and a substance spectrum reconstruction method. Preparing a plurality of groups of standard solutions with different substance types and different concentrations, and obtaining standard spectrums of the standard solutions by adopting a spectrograph; respectively placing each group of standard solutions in a transparent container, placing a colorimetric card on one side of the container, shooting from the other side to obtain an image containing the standard solutions and the colorimetric card, and constructing an image-spectrum sample pair; and constructing a nonlinear mapping relation model between the image and the spectrum through deep neural network learning. The method comprises the following steps: preparing a solution from an object to be detected, placing the solution in a transparent container, placing a colorimetric card on one side of the container, and taking a picture from the other side to obtain an image containing the solution and the colorimetric card; and obtaining a corresponding spectrum according to the obtained model. According to the method, non-contact and non-destructive spectrum reconstruction of an unknown solution can be finally realized.

This invention discloses a method for predicting and protecting the overheating risk of asynchronous motors, specifically relating to the field of motor control and protection technology. Based on an intelligent fusion model, it estimates temperature and thermal stress field, calculates the rate of change of thermal stress, non-uniformity, and hotspot trends, and calculates a dynamic health index using historical data. These parameters are then input into a multi-objective reinforcement learning controller to optimize long-term health and short-term performance, generating a thermal shaping control vector to regulate the motor. This invention combines physical mechanisms with data-driven approaches through an intelligent fusion model, utilizing a graph neural network to learn the structure of the heat conduction graph and verify physical laws, thereby improving the accuracy of thermal state estimation. It achieves a multi-dimensional risk characterization combining transient impact and cumulative effects through the rate of change of thermal stress, non-uniformity, hotspot trends, and dynamic health index. By optimizing long-term health and short-term performance losses, a thermal shaping control vector is generated to achieve regulation from passive protection to active prevention, extending the motor's service life.

The invention relates to the technical field of medical image recognition, in particular to an Alzheimer's disease MRI diagnosis method based on width neural network learning, and the method comprises the steps: 1, carrying out the adaptive ROI cutting of a brain MRI image; step 2, performing dynamic contrast compensation binaryzation; step 3, morphological optimization; step 4, gray scale returning; 5, density peak value guided K-means + + feature extraction is carried out; and step 6, obtaining a width neural network, inputting the final enhanced feature map into the width neural network for final classification prediction, and realizing diagnosis of the Alzheimer's disease MRI. According to the method, a binary segmentation method of dynamic contrast compensation and multi-scale feature enhancement of K-means + + driving are combined, the method is devoted to the hippocampus segmentation problem in image recognition for the Alzheimer's disease and the problem that subtle variation of an early-stage AD patient cannot be captured, and convenience is provided for doctors.