120 results about "Network classification" patented technology

The invention discloses an expandable category guide anomaly detection method and device for multiple categories of targets, and relates to the field of computer vision. The method comprises the following steps: carrying out abnormal region guided adaptive enhancement preprocessing on an industrial image to obtain a target image; judging the category of the target image according to a pre-constructed lightweight neural network classifier; activating at least one anomaly detection model according to the category of the target image; and performing anomaly prediction on the target image by using the activated anomaly detection model, and fusing with the confidence corresponding to the anomaly detection model to realize adaptive anomaly discrimination of the industrial image. According to the method, the sample category is quickly judged through the lightweight classifier, the pre-screening and path guidance of the anomaly detection model are realized, the category guidance weight is generated by using a confidence coefficient mechanism, the subsequent model fusion strategy is endowed with higher adaptability, and the structural clarity, the model selection accuracy and the overall calculation efficiency of the system are effectively improved.

The invention provides an intelligent early warning method and system for physiological fatigue of a construction equipment operator, and the method comprises the steps: synchronously collecting the limb movement and equipment trajectory data of the operator through an inertial sensor and a construction equipment control terminal, carrying out the parallel prediction of an operation sequence through a two-channel time convolution network TCN, and recognizing a redundant and fatigue movement mode; dynamic structure features of the construction equipment track are extracted in combination with an improved ConvNeXt network, and the abnormal level of the track is judged based on a graph neural network classifier; a soft behavior-reviewer algorithm is introduced, the physiological fatigue index, the trajectory deviation rate and the trajectory control fluctuation degree are used as state input, and optimization operation suggestions are dynamically output; a diagnosis result is transmitted to an operator in real time through a voice and tactile feedback mechanism, and a sustainable closed-loop regulation and control system is formed. According to the invention, the fatigue identification accuracy and the intelligent intervention capability of the operator in the construction process are obviously improved, and the construction safety and the operation efficiency are improved.

The invention discloses a network traffic large model construction method based on heterogeneous federated learning, which comprises the following steps: analyzing, cleaning and formatting network traffic data, and constructing question and answer pairs; performing semantic equivalence reappearing on the public data set by using a large language model to generate an enhanced data set; performing architecture optimization on the generative basic model to replace an original output layer with a customizable network classification head; decoupling the teacher model into a simulator and an adapter; initializing a LoRA module for a simulator and an adapter of the student model; the client adaptively adjusts the LoRA rank according to local resources; the client only finely adjusts parameters of the LoRA module of the adapter and freezes other parameters; the server adopts a weighted stacking algorithm to aggregate the LoRA modules uploaded by the client; the method has good universality and expandability.

The invention discloses a dementia identification method based on brain computer network space cross attention fusion. The dementia identification method comprises the steps that resting-state electroencephalogram signals are acquired, preprocessing and brain network construction are carried out, the frequency band power ratio is calculated, and a training set and a test set are divided; the brain network fuses the spatial information, and spatial features are obtained through an isotropic graph neural network and a local feature enhancement module; the frequency band power ratio is coded by a multi-layer perceptron to obtain frequency spectrum statistical characteristics; a bidirectional cross attention module is input, and complementary fusion features are extracted; and performing mixed pooling and splicing on the complementary fusion features, then sending the fused features to a Chebyshev Kolmogorov-Arnold network classifier, and outputting an Alzheimer's disease / frontotemporal dementia / health control (AD / FTD / HC) classification result and a cognitive scale evaluation score (MMSE). According to the method, the multi-feature complementary information is effectively integrated through joint modeling of the spatial diagram features and the global spectrum features, and the accuracy, stability and generalization ability of AD and FTD classification in a complex brain network are improved.

The invention discloses a deep learning prediction method fused with multi-modal features, which can accurately identify protein hidden binding sites in a ligand-free (apoo) state. The method comprises the following steps of: firstly, constructing a protein graph by taking residues as nodes and taking C alpha distance less than or equal to 14 as edges, wherein node feature sets comprise amino acid one-hot, secondary structures, atomic attributes, protein language model embedding and BLOSUM62 evolutionary information, and edge features comprise distance and angle similarity; then capturing three-dimensional geometric equivariant features by adopting an equivariant graph neural network (EGNN), and modeling a chemical topological relation by using a graph isomorphic network (GINE) with edge features; eGNN and GINE double-branch feature fusion and global dependence integration are realized through gating cross attention and gating multi-head attention; and finally, inputting the fusion features into a Kolmogorov-Arnold network (KAN) classifier, and predicting whether each residue belongs to a hidden binding site or not. The method can adapt to large-scale conformation change without coordinate alignment, AUC and F1 on a standard data set are remarkably superior to those of an existing method, high robustness and generalization are kept for multi-chain protein and complex conformation, and the method can be widely applied to drug target discovery and structure-driven drug design.

The invention relates to a paper archive digital processing method and device, equipment and a medium. The method comprises the following steps: extracting image quality characteristics of a paper archive image, identifying a flaw region based on the image quality characteristics, and classifying flaw types through a pre-trained neural network; according to a preset defect type-image restoration algorithm mapping rule, restoring the defect area by adopting a corresponding algorithm to obtain a finished image; extracting a character sequence from the trimmed image by using an optical character recognition algorithm, encoding the character sequence into a semantic vector, and determining a document theme label in a pre-established archive theme library through vector similarity matching; and a multi-dimensional index structure is generated by combining the original image, the trimmed image and the character sequence, so that efficient retrieval and management of archive contents are realized. According to the method, the accuracy of defect repair and the recognition rate of optical character recognition are improved, and the automation level of digital processing is enhanced.

There is provided a computer-implemented method for verifying the robustness of a neural network classifier with respect to one or more parameterised transformations applied to an input, the classifier comprising one or more convolutional layers, the method comprising: encoding each layer of the classifier as one or more algebraic classifier constraints; encoding each transformation as one or more algebraic transformation constraints; encoding a change in an output classifier label from the classifier as an algebraic output constraint; determining whether a solution exists which satisfies the classifier constraints, transformation constraints and output constraints, and determining the classifier as robust to the local transformations if no such solution exists. A perception system and a computer readable medium are also provided.

The invention belongs to the technical field of image processing, and discloses a schizophrenia classification method based on connection gradient, which comprises the following steps: acquiring magnetic resonance imaging data, and preprocessing the magnetic resonance imaging data; performing brain region division on the preprocessed magnetic resonance imaging data, and constructing a functional connection network and a morphological similarity network; constructing a function connection gradient and a form similarity gradient by using a connection gradient algorithm based on the function connection network and the form similarity network; performing threshold processing on the function connection network and the morphological similarity network to serve as edge features, taking the bimodal connection gradient as node features, and constructing a graph convolutional network classification model; and training and testing the graph convolutional network classification model. According to the schizophrenia classification method based on the connection gradient, schizophrenia classification identification is realized by using the graph convolutional network classification model, the classification accuracy is improved, and the application value is higher.

The invention discloses a washing machine motor detection method, and relates to the field of electric digital data processing, and the method comprises the following steps: S1, collecting signals of a plurality of sensors when a motor operates; s2, performing feature extraction on the signal of each sensor by using a multi-head self-attention feature extraction module fused with a Transform block to obtain a feature vector reflecting the running state of the motor; s3, constructing a residual network classification model, inputting the extracted feature vector into the model, and outputting a prediction type of a motor fault; s4, based on a sample set training model composed of normal operation data and fault data of the washing machine motor, a cross entropy loss function quantification model is adopted to predict the difference between a fault type and an actual fault type; and S5, minimizing a loss function by adjusting model parameters until the model prediction precision reaches a preset standard, processing a real-time operation signal of the motor by using the trained model, and carrying out fault detection. The optimal sensor configuration and high-precision fault detection of the motor power system of the washing machine are realized.

The invention discloses a superheat degree identification method based on self-supervised pre-training and feature fusion, and the method comprises the steps: the first stage is self-supervised pre-training based on a priori guidance learnable mask, and the second stage is supervised fine tuning based on feature fusion and a KAN network. The first stage comprises video slicing and space-time embedding, learnable masks guided by priori knowledge, and asymmetric encoder-decoder training; and the second stage comprises double-flow feature extraction, cross attention-based feature fusion, KAN network classification and supervised fine tuning. The invention relates to the technical field of industrial process intelligent perception and computer vision, and solves the problems of strong dependence on labeled data, weak generalization ability under small samples, incomplete feature expression and insufficient interpretability in the prior art.

The invention relates to the technical field of data transmission, in particular to a transmission efficiency improvement system based on big data, which comprises a parameter acquisition module for periodically acquiring the transmission rate of each network, bandwidth occupation information in different time periods and transmission delay information, the efficiency evaluation module evaluates the efficiency level of each network bandwidth according to the transmission rate, the bandwidth occupation information and the transmission delay information; the classification module monitors time periods in a period for classification and classifies each network; the transmission optimization module determines network adjustment modes in different time periods based on a time period classification result and a network classification result, the dynamic adjustment module dynamically adjusts the data sending rate through a back pressure mechanism in the transmission process, and transmission fault tolerance and rapid recovery are achieved based on the asynchronous check point technology. According to the method, the network communication delay is reduced, the transmission efficiency is improved, and overload of a receiver is avoided; business pause is reduced, and the fault recovery speed is improved.

The application provides a multi-modal brain network classification method based on feature decoupling and dynamic graph construction, and relates to the technical field of artificial intelligence, and the method comprises the following steps: acquiring functional magnetic resonance imaging (fMRI) data and structural magnetic resonance imaging (sMRI) data of a to-be-tested person, obtaining multi-modal brain network data according to the fMRI data and the sMRI data, processing the multi-modal brain network data based on a preset multi-modal brain network classification model, and obtaining the brain network state of the to-be-tested person. The application can fully utilize the advantages of the two modalities by combining the fMRI data and the sMRI data, thereby improving the accuracy and comprehensiveness of the brain network state classification, and the dynamic graph attention module based on a graph attention network (GAT) can capture the dynamic change characteristics of the brain network, construct a dynamic graph representation, and enhance the sensitivity of the model to the dynamic connection relationship between brain regions.

The invention provides a dual confidence calibration method and system for a neural network classifier, equipment and a medium, and effectively solves the problems that an existing single-stage calibration method is difficult to give consideration to excessive confidence, under confidence, class imbalance sensitivity and the like. A mixed loss function fusing bifocus loss and difference between multi-class confidence and accuracy is introduced in a training stage, so that a neural network classifier is promoted to generate well-calibrated prediction distribution; a class-by-class multi-partition temperature scaling model optimized based on a coupling simulated annealing method is adopted in the reasoning stage, and calibration requirements of different classes and different confidence intervals are more accurately met compared with a traditional temperature scaling technology of a single temperature coefficient; in the training process, classifiers of different rounds are stored, multi-model calibration results are averaged class by class in the test stage, the calibration stability is effectively improved, prediction confidence errors are reduced, and the method is particularly suitable for the safety key fields such as medical diagnosis and automatic driving which have extremely high requirements for prediction reliability.

The embodiment of the application relates to the technical field of digital medical treatment, and specifically provides a text classification model training method, a classification method, a terminal and a storage medium. The method comprises the following steps: inputting a training sample into a text coding network to obtain a first text vector corresponding to the training sample; inputting the first text vector into a context coding network to obtain a second text vector corresponding to the first text vector; inputting the second text vector into a first classification network and a second classification network respectively to obtain a first category probability distribution of the training sample classified by the first classification network and a second category probability distribution of the training sample classified by the second classification network, constructing a first loss function according to the first category probability distribution and constructing a second loss function according to the second category probability distribution, and determining a fusion loss function according to the first loss function and the second loss function; and iteratively updating a text classification model based on the training sample and the fusion loss function to obtain a target text classification model.

The invention discloses a buried pipeline leakage signal collaborative classification system based on a twin neural network. The system comprises a data acquisition module, a signal preprocessing module, a twin neural network classification module, an intelligent decision module and a man-machine interaction module. The twin neural network comprises two sub-networks sharing weights, and the two sub-networks respectively process multi-modal fusion signals of the same pipe section at different moments, so that intelligent detection of pipeline state changes is realized. According to the method, the leakage detection precision can be effectively improved, the false alarm rate is reduced, accurate classification of different leakage types is realized, and reliable guarantee is provided for safe operation of buried pipelines. According to the system, the DTS is matched with the DAS technology, and intelligent identification and classification of pipeline leakage signals are realized by utilizing a laying mode that an optical cable is attached to a buried pipeline in an accompanying manner.

Provided are a method for regulating a wind-photovoltaic-storage power station based on electricity, green certificate, and carbon price prediction, a device, a medium, and a product. The method includes: inputting acquired historical price data into a price prediction model, and outputting a predicted price; determining a deviation vector of price data based on the historical price data and the predicted price, and generating an uncertainty set of the predicted price by using a multi-kernel-based one-class support vector machine algorithm; classifying the uncertainty set of the predicted price by using a neural network classifier, to obtain multiple types of price scenarios; solving, based on predicted prices under the multiple types of price scenarios, a joint clearing model by using a Pied Kingfisher Optimization (PKO) algorithm, to obtain an operation strategy for the wind-photovoltaic-storage power station; and regulating the wind-photovoltaic-storage power station based on the operation strategy for the wind-photovoltaic-storage power station.

The application relates to the technical field of artificial intelligence, and provides a classification prediction method based on table data, which comprises the following steps: inputting a characteristic value, a characteristic type corresponding to the characteristic value and statistical information corresponding to the characteristic value into an embedding layer of a neural network classification model to obtain an embedding representation corresponding to the characteristic value; then determining an embedding representation sequence according to the embedding representation; inputting the embedding representation sequence into an encoding layer of the neural network classification model to obtain a semantic vector sequence; inputting the semantic vector sequence into an output layer of the neural network classification model to obtain a prediction result; determining a loss value according to the prediction result and a labeled label, and training the neural network classification model according to the loss value to obtain a target neural network classification model. Through the above scheme, the neural network model can understand the global statistical information of the characteristics like a tree model, the performance and accuracy of the neural network model in performing a classification prediction task based on table data are improved, and the satisfaction of users in the experience of financial products is improved.

The application provides a light diffraction neural network classification method and system based on ensemble learning, aiming to improve the object classification accuracy in a scattering medium environment, comprising the following steps: step 1, constructing and generating a simulation dataset suitable for light diffraction neural network training, the dataset containing a target object dataset and a scattering medium dataset; step 2, building multiple differentiated light diffraction neural network forward propagation models, and training each model based on the above simulation dataset; step 3, using a preset ensemble learning strategy to fuse the classification results output by the multiple light diffraction neural networks to improve the overall classification accuracy; step 4, driving the optical system to run, and outputting the classification result of the target object in real time according to the light field intensity data collected by the detector. The application introduces an ensemble learning mechanism to construct an anti-scattering classification strategy, effectively improving the object classification accuracy and robustness under the interference condition of static or dynamic scattering medium.

A system and method for measuring and assessing cognitive abilities of a user are disclosed. The method includes generating an individualized assessment protocol comprising a plurality of tasks each configured to evaluate cognitive mental specification. The method also includes the user selecting at least one task tasks using a semi-random process. The method further includes displaying a task-specific interface to present the selected task to user. The method includes receiving user responses to the task along with associated parameters. The method includes transmitting an individualized performance score table to a server. The method also includes processing the individualized performance scores using a population database, a neural network classifier, and regression models, which adjust their parameters based on the received scores. The method further includes computing individualized assessment scores to generate a profile of cognitive mental abilities. The method also includes transmitting profile of cognitive mental abilities to user device.

The invention discloses a predictive maintenance method for a hammer head and a hammer handle of an impact crusher, which comprises the following steps: (1) at least two paths of high-precision position sensors are mounted on the periphery of a rotor of the crusher, and the mounting angles of the sensors are arbitrary and different from each other; (2) collecting a pulse sequence through no-load rotation, calculating phase deviation of each path by adopting a least square method, and generating a phase mapping table; (3) synchronously collecting position pulses and multi-mode sensing signals, and resolving a rotor phase in real time by adopting majority voting and time tolerance redundancy check; the rotor phase is solved in real time through time redundancy fault-tolerant logic; (4) performing delta A (theta) coarse positioning, VMD-game mapping feature selection and graph convolutional network classification on the basis of the resolving phase to obtain an abnormal wear phase and an end type; (5) calculating a counterweight according to an ISO1940 standard and a multi-objective optimization algorithm, verifying the residual unbalance amount and stress compliance by using three-dimensional virtual simulation, and completing dynamic balance compensation at one time; and (6) generating a predictive maintenance plan by adopting the wear integral model and the bearing degradation model.

The present application belongs to the technical field of radar detection, and particularly relates to a biological migration monitoring system based on weather radar network IQ data edge computing processing. The system comprises an edge computing platform and a data center processing server, and the edge processing platform is arranged at a weather radar site. The edge computing platform is used for receiving and processing original IQ data of a weather radar at the site, so as to obtain a range Doppler mask that suppresses weather echoes and retains biological echoes. After frequency domain processing of the range Doppler mask, a multi-peak spectrum structured representation method is used to calculate spectrum characteristic parameters, and the calculation results are transmitted to the data center processing server. The data center processing server stores a network classification and identification model, receives the spectrum characteristic parameters to train the network classification and identification model, and the trained network classification and identification model is used to realize biological classification and output.

The application discloses a gear forming defect recognition method and belongs to the technical field of image processing. The gear forming image is collected first, and the background is separated to obtain a gear image, and then the gear image is converted to a gear polar diagram with a center point as an origin. Based on gear tooth number periodicity, radial gray scale profiles at various angles in the polar diagram are extracted and normalized, and a standard tooth profile is constructed. Residual profile diagrams are obtained by calculating the difference between the normalized profile and the standard profile, and after separating positive and negative deviation profile diagrams, defect skeleton points are extracted and merged into a profile skeleton diagram. At the same time, according to the normalized profile, polar radius mutation characteristic values are calculated under the same polar radius, and a polar radius mutation characteristic diagram is constructed. Finally, the gear defect classification network processes the above four types of images, and outputs the gear forming defect type. The application combines multi-dimensional feature extraction and network classification, and improves the precision of gear forming defect recognition.

This invention provides a method for identifying transient processes in traction networks based on phase space reconstruction and neural networks. The method includes: acquiring transient current signals; calculating the maximum Lyapunov exponent of the transient current signals; if the exponent is greater than zero, proceeding to the next step; for transient current signals that meet the phase space analysis conditions, adaptively determining the optimal delay time using the average mutual information method and adaptively determining the optimal embedding dimension using the pseudo-nearest neighbor method; reconstructing the phase space of the transient current signals to obtain a reconstructed phase space vector; extracting dynamic attribute features reflecting the dynamic characteristics of the transient process and constructing a joint feature vector; inputting the joint feature vector into a pre-established and trained radial basis function neural network classification model, and outputting the category identification result of the transient process through the model. This invention can solve the problems of poor identification ability, difficulty in fully revealing the deep dynamic characteristics of transient signals, and limited adaptability to complex scenarios in existing technologies.

The application discloses a human body falling detection method and system based on acoustic signals. The method comprises the following steps: controlling a loudspeaker to generate ultrasonic waves at a set frequency, and collecting acoustic signals generated when a human body falls by using a microphone; performing shunting and denoising on the acoustic signals to obtain low-frequency signals generated by human body collision and high-frequency signals of human body reflected ultrasonic waves; detecting the starting point and ending point of human body activity in the low-frequency signals, and detecting the starting point and ending point of human body activity in the high-frequency signals, and then determining the starting point and ending point of the acoustic signals; performing feature extraction on the low-frequency signals and the high-frequency signals respectively to obtain low-frequency signal features and high-frequency signal features; inputting the low-frequency signal features and the high-frequency signal features into a pre-trained double-flow long short-term memory network classification model to obtain a falling detection result. The application can realize real-time falling monitoring, and has high recognition accuracy and low false alarm rate.

A method implemented on a UE includes determining an application class of an application, and permitting or barring access by the application to a communication network according to a comparison of the determined application with a rule to provide application class based access control. The application is classified into the determined application class. The application is classified into the determined application class by a home network. The application is classified into the determined application class by a 3GPP layer. The application is classified into the determined application class by a visited network. The visited network classifies the application into a further application class. The rule includes a list of applications for permitting or barring access by the applications according to the comparison of the determined application class with the rule.

This invention relates to an intelligent classification device for skin lesion images based on self-supervised learning, belonging to the field of image processing technology. The device includes a basic module, an image acquisition module, an image processing module, a neural network training module, a neural network classification module, and an output display module. The neural network training module applies a multi-channel self-supervised learning training method to obtain a neural network suitable for skin feature extraction. This addresses the overfitting problem of existing neural networks caused by insufficient numbers of skin lesion images. Ultimately, this invention provides a skin lesion image classification method and device suitable for rapid detection in clinical settings, reducing the burden on dermatologists and improving service efficiency.

The invention discloses a brain function network classification method and system based on adversarial graph comparative learning, and the method comprises the steps: obtaining resting-state functional magnetic resonance image data, and carrying out the preprocessing of the data, and constructing a functional connection matrix X; and inputting the X into an adversarial graph comparison learning classification model for classification. The model comprises an image augmentor, a feature extraction layer, a projection head and a classifier. A trainable encoder is arranged in the image augmentation device, and an edge deletion probability matrix P and an augmentation image X 'are generated through the encoder; the feature extraction layer extracts X and X 'feature representations; the projection head maps the feature representation to a contrast learning space to obtain an optimal weight parameter; the classifier performs brain function classification based on the feature representation. The method has the advantages that data driving and task-oriented dynamic augmentation are achieved, classification related function connection is reserved, redundant connection is deleted, the model can distinguish different brain region function specificity, and the problems that a traditional model cannot distinguish different brain region function differences due to node replacement invariance, so that classification performance is poor, and explanatory performance loses practical significance are solved.

This invention discloses a hypergraph representation method for brain functional networks. The steps include: preprocessing resting-state functional magnetic resonance imaging (fMRI) to obtain time series data for all brain regions; dividing the entire time series into multiple overlapping sub-sequence segments using a sliding window; constructing a dynamic brain functional network and transforming it into an optimization model; constructing a hypergraph of the dynamic brain functional network using the nearest neighbor algorithm; dynamically modifying the hypergraph structure through convolution operations and extracting features to obtain a new dynamic hypergraph; extracting the Laplacian matrix of the dynamic hypergraph; constructing the manifold regularization term of the Laplacian matrix and simultaneously introducing the manifold regularization term and the L1 norm regularization term into the optimization model to obtain the hypergraph representation of the brain functional network. This invention is used to represent functional interactions and higher-order relationships between multiple brain regions, determine discriminative brain functional network classification features, and effectively improve the classification performance of brain disease features.

The invention discloses a spacecraft complex service damage high-precision classification method based on multi-modal fusion, and the method comprises the steps: collecting a vibration response signal under ultrasonic excitation through a sensor, and constructing a vibration data set Dvib after the vibration response signal is processed; the method comprises the following steps: acquiring a temperature distribution sequence under photo-thermal excitation through an infrared thermal imager, and processing by adopting a distance interval division and partition enhancement algorithm to construct an infrared data set Dir; based on the multi-modal data Dmul, constructing and training a deep residual network classification model of a vibration mode and an infrared mode; and further constructing a multi-modal fusion test set Dmultest, performing evidence synthesis and decision fusion on an output result of the bimodal classification model by adopting a D-S evidence theory, and finally outputting a high-confidence damage type and grade classification result. Through a targeted data enhancement strategy and a deep fusion mechanism, the limitation of single-mode detection is effectively overcome, and the accuracy and robustness of spacecraft complex service damage classification are remarkably improved.

The application discloses a diatom image classification system and method driven by data and knowledge, which comprises a generative adversarial network module, a knowledge learning module and a deep residual network module; the generative adversarial network module designs a generative adversarial network model suitable for diatom image generation to expand a diatom image dataset; the knowledge learning module embeds diatom knowledge into a knowledge vector space; and the deep residual network module embeds diatom images into a feature vector space; in order to overcome the semantic gap between the knowledge domain and the feature domain, a knowledge-assisted deep residual network classification is utilized, a multilayer perceptron is adopted to project the knowledge domain into the feature domain, and a least mean square error loss function is used to minimize the distance between the knowledge embedding and the feature embedding in the feature domain; compared with a traditional classification model without the generative adversarial network and the knowledge attribute, the method of the application improves the precision by 8.6%, the recall by 9.7% and the loss by 31.6%.