Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

59 results about "Multiple classifier" patented technology

Machine learning enhanced unit commitment problem optimization solving method and system and storage medium

The invention discloses a machine learning enhanced unit commitment problem optimization solving method, which establishes a probability fusion model, effectively combines the advantages of various classifiers, has stronger stability, higher accuracy and better generalization ability compared with a single model, and can more effectively guarantee the solving quality and improve the solving speed. In addition, a variable screening mechanism based on confidence ranking is designed, high-confidence integer variables are fixed preferentially, effective minimum start-stop time constraints are predicted, the variable and constraint scale of the mixed integer programming problem is remarkably reduced, and the solving efficiency is improved. The optimization solution model provided by the invention respectively realizes about 6 times and 11 times of acceleration effects in 96-period and 288-period scenes of the SG-126 system, which shows that the method has good universality, stability and expansibility.
Owner:NARI TECH CO LTD +2

Code risk identification method and system based on large language model

The invention discloses a code risk identification method and system based on a large language model. The method comprises the following steps: submitting a code of a current version on a code management platform, and triggering a submission event; a submission event is captured through Webhook in the code management platform, and an HTTP request is sent to the difference analysis system; analyzing the HTTP request according to a difference analysis system and obtaining a code of a previous version and a code of a current version; comparing the obtained code of the previous version with the code of the current version according to a difference analysis module of the difference analysis system to obtain a difference code of the current version and the previous version and a specific position of the difference code; according to the difference analysis system, the difference codes of the current version and the previous version and the specific positions of the difference codes can be quickly identified, the analysis efficiency is improved, and the accuracy of an analysis result is ensured; and the risk category and the risk level of the difference code can be accurately identified through multiple classifiers of a large language model and a context sensing module.
Owner:BEIJING THUNDERSTONE TECH CO LTD

RNA N4-acetylcytidine modification site prediction method and system based on RNAErnie pre-training model

The invention relates to an RNAN4-acetylcytidine modification site prediction method and an RNAN4-acetylcytidine modification site prediction system based on an RNAErnie pre-training model. The method comprises the following steps: collecting an RNA sequence data set, inputting the RNA sequence data set into an RNAErnie pre-training model, capturing a context dependency relationship, and extracting global features; performing feature coding through an RNAErnie pre-training model in combination with six traditional feature coding methods; and performing feature dimension reduction in the deep neural network model, inputting the feature dimension reduction result into a soft voting integration model, and integrating prediction results of different classifiers to obtain an RNAN4-acetylcytidine modification site prediction result. Multistage masking is carried out through an RNAErnie pre-training model, and details and physical and chemical attributes of the sequence can be captured in combination with six traditional feature coding modes; feature dimension reduction is automatically performed by using a deep neural network, so that the calculation complexity is reduced and key information is reserved; and the dimensionality-reduced features are input into a soft voting integrated model, and a final prediction result is obtained by integrating a plurality of classifiers, so that the prediction accuracy and robustness are remarkably improved.
Owner:HAINAN UNIV

Asset-level vulnerability and mitigation

Methods, systems, and apparatus for receiving a request for a damage propensity score for a parcel, receiving imaging data for the parcel, wherein the imaging data comprises street-view imaging data of the parcel, extracting, by a machine-learned model including multiple classifiers, characteristics of vulnerability features for the parcel from the imaging data, determining, by the machine-learned model and from the characteristics of the vulnerability features, a damage propensity score for the parcel, and providing a representation of the damage propensity score for display.
Owner:X DEVELOPMENT LLC

Rectangular channel two-phase flow pattern identification method, device and equipment, storage medium and product

The invention provides a rectangular channel two-phase flow pattern recognition method and device, equipment, a storage medium and a product. The method comprises the steps that a visual image of fluid in a rectangular channel of the heat exchange system is obtained; gray features in the visual image are extracted; inputting the visual image and the gray feature information into a plurality of classifiers of a preset ensemble learning model, performing classification through each classifier in the preset ensemble learning model, and determining a two-phase flow pattern prediction category corresponding to each classifier; counting the two-phase flow pattern prediction categories corresponding to the classifiers in the preset integrated learning model, and determining the two-phase flow pattern prediction category with the largest number in the statistical result; and the two-phase flow pattern prediction category with the largest number serves as the classification category of the two-phase flow patterns of the fluid in the rectangular channel of the heat exchange system. By combining the results of a plurality of classifiers, the sensitivity of the model to single error prediction is reduced, and the prediction precision of the model under different working conditions is enhanced.
Owner:NUCLEAR POWER INSTITUTE OF CHINA

Industrial equipment fault diagnosis method, system and storage medium based on multi-view expansion statistical features

The present invention provides an industrial equipment fault diagnosis method, system, and storage medium based on multi-view expansion statistical features, which relate to the technical field of industrial equipment fault diagnosis. The method aims to solve the problems that existing methods are easily contaminated by noise, and that the extracted features contain redundant and irrelevant features, resulting in long calculation time, low calculation efficiency, and high hardware computing power requirements. The method comprises the following steps: step 1, obtaining a time series data set of the operating fault status of the industrial equipment; step 2, preprocessing the time series data using an unsupervised differential expansion mapping preprocessor; step 3, constructing multiple filtering feature selectors at different storage ratios to obtain multi-view feature subset vectors and a combined feature selector; step 4, constructing multiple classifiers, training the multiple classifiers based on the multi-view feature subsets, and constructing a combined classifier; and step 5, using the combined feature selector and the combined classifier to perform fault diagnosis on the equipment operating status.
Owner:HARBIN INST OF TECH

Multi-endpoint reproductive toxicity prediction method and system based on large language model

The invention discloses a multi-endpoint reproductive toxicity prediction method and system based on a large language model, and belongs to the technical field of toxicity prediction. The method comprises the following steps: extracting phenotype information of text data in a candidate data set by using the large language model; performing multi-dimensional annotation processing on the phenotype level annotation data set; inputting the reproductive toxicity training set into a pre-constructed molecular representation learning model for training, and constructing a reproductive toxicity prediction model set with phenotype specificity; performing performance evaluation on the plurality of classifiers in the reproductive toxicity prediction model set by using the test data set, and screening according to preset performance indexes to obtain an optimal prediction model combination; performing toxicity prediction on the molecular structure of the chemical substance to be detected by using the optimal prediction model combination to obtain a multi-dimensional reproductive toxicity prediction result including cross-gender, cross-generation and cross-research types; according to the method, high-resolution and multi-dimensional reproductive toxicity phenotype prediction is carried out on the environmental chemical substances.
Owner:NANJING UNIV

Feature extraction device, image matching equipment and computer readable storage medium

The invention discloses a feature extraction device, an image matching apparatus and a medium. The feature extraction device comprises a feature extraction module which extracts features with a plurality of scales and a plurality of feature dimensions from an image to be matched; the feature fusion module is used for aligning all or part of the extracted features on the feature dimension, and then aligning the features aligned on the feature dimension in pairs on the scale dimension from small to large and from large to small so as to generate fused features; a classifier module comprising a plurality of classifiers, each classifier being assigned to a corresponding fusion feature and being trained such that a difference between a prediction result of each fusion feature drawn from small to large in a scale dimension and prediction results of all fusion features drawn from large to small is minimum, and vice versa; and the foreground enhancement module divides the fusion features into foreground features and background features according to a preset rule, and adds a class to the background features for another classifier during training.
Owner:FUJITSU LTD

Early failure diagnosis method for surge absorber based on acoustic characteristics

The invention discloses a surge absorber early failure diagnosis method based on acoustic characteristics. The surge absorber early failure diagnosis method comprises the steps of collecting acoustic signals generated by a surge absorber in an operation state; performing mixed feature extraction by fusing improved variational mode decomposition and frequency cepstrum coefficients, and constructing a high-dimensional initial feature set; pre-screening the high-dimensional feature set by using a minimum redundancy and maximum correlation algorithm, and then performing feature fine optimization by using a support vector machine package method optimized by a quantum behavior particle swarm algorithm to obtain an optimal feature subset; and finally, constructing a plurality of classifier groups based on self-service sampling, and performing decision-making layer fusion on the output of each classifier by using a D-S evidence theory to realize accurate diagnosis of the early failure state of the surge absorber. Through deep fusion of multiple levels and multiple algorithms, the sensitivity, robustness and accuracy of diagnosis are remarkably improved, and non-intrusive online monitoring and early warning of the surge absorber can be realized.
Owner:武汉京品电子科技有限公司

Small sample fault diagnosis method based on multi-scale integrated lightgbm

This invention discloses a small-sample fault diagnosis method based on multi-scale ensemble LightGBM, comprising the following steps: acquiring vibration acceleration signals of rotating machinery and extracting samples to obtain training and test sets; constructing a multi-scale ensemble model consisting of a data augmentation module, a label classification module, and an output weighting module; in the data augmentation module, resampling the original samples using a multi-scale sliding window to obtain multiple sub-sample training and sub-sample test sets; in the training phase, training multiple classifiers in the label classification module using the sub-sample training sets; in the testing phase, inputting the sub-sample test sets into the corresponding classifiers, and obtaining the test results of the label classification module on the original samples through ensemble; calculating the frequency domain similarity between the test set and the training set samples using a metric function, and using it as a weight; in the output weighting module, weighting the ensembled test results to obtain the final classification diagnosis result.
Owner:SOUTH CHINA UNIV OF TECH

Full-color bird target identification method and system

The invention discloses a full-color bird target recognition method and system. According to the method, a feature map is extracted from a full-color bird image through a convolutional neural network by using an SSD model, and a priori frame is set to determine the initial position and category information of a bird target. And target tracking is realized by means of a median flow tracking algorithm in combination with a failure detection mechanism and a forward-backward tracking algorithm. A cascade classifier comprising multiple classifiers is used to generate positive and negative samples, a P-N learning algorithm is used to iteratively train the classifiers, and then bird target position and category information is optimized. The problems of low recognition accuracy, insufficient tracking capability and backward data processing and model optimization means in the prior art are solved, accurate recognition and tracking of full-color bird targets are achieved, the bird repelling effect is improved, and safety and stability in related fields are guaranteed.
Owner:ZHONGKE RONGDA (TIANJIN) TECHNOLOGY CO LTD

Acoustic characterization method for deep-sea manganese nodule coverage based on multi-classifier decision fusion

The present application belongs to the technical field of deep-sea mineral resource exploration, and discloses a deep-sea manganese nodule coverage acoustic characterization method based on multi-classifier decision fusion. By extracting 14 backscattering texture features and 4 seabed topography features, and using Boruta algorithm to optimize the extracted features, a refined feature set for characterizing the seabed is constructed. An iterative robust estimation algorithm based on a sliding window is introduced to identify and suppress gross errors in the feature image by dynamically adjusting the observation weight through continuous smoothing of the data in different directions. In the model construction stage, the Stacking mechanism in ensemble learning is used to integrate the advantages of multiple classifiers for decision-level integration and generate a spatial distribution map of nodule coverage. The Boruta feature selection algorithm is introduced to screen out the key features with the strongest discrimination ability for nodule coverage from the original acoustic features, avoiding redundant interference and improving the accuracy and prediction discrimination ability of the model.
Owner:SHANDONG UNIV OF SCI & TECH +1

A waterlogged space distribution identification method and system based on multi-classifier cooperation

PendingCN122289976AAlgorithmMultiple classifier
This invention discloses a method and system for identifying the spatial distribution of accumulated water based on multi-classifier collaboration. The method includes: constructing a hierarchical classifier library comprising a preliminary screening layer, an arbitration layer, a re-identification layer, and a verification layer, with each layer containing multiple classifiers of different types. First, the preliminary screening layer performs coarse classification on UAV images, and the results of each classifier are fused using a logical OR operation to determine suspicious areas. Then, the arbitration layer and the re-identification layer sequentially perform refined identification of ambiguous areas, using a logical AND operation to obtain high-confidence accumulated water areas. For the remaining ambiguous areas, the verification layer is activated for final discrimination. The high-confidence accumulated water areas identified by each layer are merged to form a preliminary accumulated water distribution map. Pixel confidence is optimized through weighted fusion, and low-confidence pixels are removed. Finally, post-processing is performed to output the final spatial distribution result of the accumulated water. This application can effectively improve the identification accuracy and robustness of small and irregular accumulated water areas in complex urban scenes.
Owner:HANGZHOU NORMAL UNIVERSITY

Method, system and electronic device for constructing functional connection network

The present invention discloses a method for constructing a functional connectivity network, a system and an electronic device, including: using a variational autoencoder network to establish a multivariate Gaussian distribution probability model for each brain region of interest through unsupervised learning, using Jensen-Shannon divergence to calculate the degree of similarity between the probability distributions of any two brain regions, and obtaining an adjacency matrix of paired brain regions as a brain functional network; using a two-sample t-test to select a feature set with a higher discrimination, and inputting the selected feature set into a support vector machine for classification; inputting the feature sets of different dimensional models into a support vector machine classifier, and using adaboost enhancement method to combine multiple classifiers to obtain a stronger classifier. The present invention uses a generative learning method to improve the statistical power of group data and the generalization ability of observation data variability in the diagnosis of mild cognitive impairment, and further improves the diagnostic accuracy of mild cognitive impairment through the joint enhancement of multidimensional models.
Owner:SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES

Processing of learning data sets including noisy labels for classifiers

A method for processing of learning data sets for a classifier. The method includes: processing learning input variable values of at least one learning data set multiple times in a non-congruent manner by one or multiple classifier(s) trained up to an epoch E2 so that they are mapped to different output variable values; ascertaining a measure for the uncertainty of these output variable values from the deviations of these output variable values; in response to the uncertainty meeting a predefined criterion, ascertaining at least one updated learning output variable value for the learning data set from one or multiple further output variable value(s) to which the classifier or the classifiers map(s) the learning input variable values after a reset to an earlier training level with epoch E1<E2.
Owner:ROBERT BOSCH GMBH

Classification method for training sample expansion according to multi-classifier recognition result

This invention discloses a classification method for expanding training samples based on multi-classifier recognition results, comprising: selecting multiple classification methods; selecting initial training samples including each category from the dataset to be classified to form an initial training sample set; classifying and recognizing the dataset data using each classification method and the training sample set to obtain the classification results of the dataset to be classified by each classification method; calculating the classification result acceptance rate for each data based on the classification results of the dataset to be classified; comparing the classification result acceptance rate with its preset threshold to obtain new training samples and expand the training sample set; determining and executing the next iteration classification based on the expanded training sample set; and taking the maximum acceptance classification result of the last iteration as the final data classification result of the dataset to be classified. This invention improves classification accuracy by iteratively verifying the results of multiple classifiers and gradually expanding the training samples.
Owner:GUANGXI ZHUANG AUTONOMOUS REGION ACAD OF AGRI SCI

Underwater sound source target identification method and system based on dynamic selection integration technology, and storage medium

The invention discloses an underwater sound source target identification method based on a dynamic selection integration technology, and the method comprises the steps: obtaining a sound source signal in real time through an underwater sensor, including acoustic features of a submarine target and a sound bait, extracting a time-frequency feature, a modulation feature and a statistical feature through short-time Fourier transform, and fusing the features through PCA (principal component analysis). The method comprises the following steps: generating a multi-dimensional feature vector, establishing a plurality of classifier models, evaluating the performance through cross validation, intelligently selecting an optimal classifier combination, inputting the fused feature vector into the optimal combination for target classification, outputting an identification result, and finally, continuously updating the classifier models by adopting an incremental learning method according to the identification result and an actual situation. And continuous optimization management of underwater sound source target identification is realized. Through a multi-dimensional feature fusion mechanism, time-frequency features, modulation features, statistical features and other information are comprehensively considered, the distinguishing capacity of the model for a target and an interferent is improved, in addition, through intelligent selection of an optimal combination in multiple classifiers, the distinguishing capacity of a submarine target and a sound bait is improved, and the recognition precision is effectively enhanced.
Owner:CHINA STATE SHIPBUILDING CORP LTD RESEARCH INSTITUTE 719

Cross-user wearable activity identification method based on group specific concept perception representation learning

The invention discloses a cross-user wearable activity identification method based on group specific concept perception representation learning. The method comprises the steps of collecting and preprocessing multi-user sensor data; the concept offset degree is measured from a time sequence view angle and a semantic view angle, user clustering is carried out by fusing multi-view-angle measurement results, and group specific concept tags are generated; constructing a perception model comprising an activity encoder, a user encoder and a plurality of classifiers, and performing supervised learning by minimizing the joint loss of activity, user and group specific concept classification; introducing a condition discriminator to construct a representation pair of joint distribution and edge distribution, and minimizing condition mutual information of activity representation and user representation under a group specific concept through adversarial training to obtain a trained model; during application, test data are input into the trained model for activity identification. According to the method, through explicit modeling of specific concepts and decoupling of activity and user features, cross-user concept offset is eliminated, and the activity identification generalization ability of the model on new users is significantly improved.
Owner:ZHEJIANG UNIV

Traffic mode classification method, device and storage medium based on crowdsourced navigation trajectory

This invention relates to a method, device, and storage medium for traffic mode classification based on crowdsourced navigation trajectories. The method includes: S1, extracting motion features and geographical features of sample trajectories based on sample trajectory data and geographic information data; S2, training and testing multiple classifiers based on the motion features and geographical features extracted in S1, and selecting the classifier with the highest classification accuracy as the best classifier through accuracy evaluation; S3, segmenting the collected raw navigation trajectory data based on change points to obtain segmented navigation trajectory data; S4, calculating the motion features and geographical features of the navigation trajectory data based on the segmented navigation trajectory data and geographic information data; S5, inputting the segmented navigation trajectory data into the best classifier trained in S2 based on the motion features and geographical features of the navigation trajectory data obtained in S4, and predicting the traffic mode category of the navigation trajectory. Compared with the prior art, this invention has the advantage of high recognition accuracy.
Owner:TONGJI UNIV

Strip plate shape intelligent regulation and control method based on adaptive fusion model

The application discloses a strip plate shape intelligent regulation and control method based on an adaptive fusion model, which comprises the following steps: step 1, collecting historical rolling production process data and performing pretreatment; step 2, constructing a rolling production process data set based on the pretreated data; step 3, classifying plate shape quality according to the ratio of strip crown and target thickness and setting a category label; step 4, establishing an adaptive strip outlet plate shape diagnosis model containing multiple classifiers based on a DS theory, and training the diagnosis model through the rolling production process data set; step 5, inputting rolling production process data under a new rolling schedule into the classifier of the trained adaptive strip outlet plate shape diagnosis model to obtain a real-time classification prediction result of the strip, and if the prediction classification is under-crown or over-crown, step 6 is executed; otherwise, the process parameters are not adjusted; and step 6, dynamically adjusting and optimizing the process parameters based on an inverse linear quadratic control (ILQ) according to the prediction result of step 5.
Owner:NORTHEASTERN UNIV CHINA

Protein post-translational modification data enhancement method based on generative adversarial network

The invention is suitable for the technical field of proteomics, and provides a generative adversarial network-based protein post-translational modification data enhancement method. According to the method, class imbalance can be effectively relieved, the positive sample recognition capability can be enhanced, minority class pseudo samples are generated through an improved clustering enhancement conditional generative adversarial network (RP-CGAN), features are extracted in combination with an ESM-2 pre-training protein language model, and the positive sample recognition capability and generalization capability are improved; eSM-2 feature extraction and RP-CGAN data enhancement technologies are fused, so that the overall prediction performance and classification stability are improved, and key indexes of multiple classifiers are remarkably improved; through multi-dimensional index screening and self-adaptive regulation and control, it is ensured that enhanced data is close to real distribution; by means of a lightweight architecture and a convergence strategy, the training efficiency and the model stability are optimized; the method has strong stability and cross-domain potential, can be migrated to other protein modification prediction tasks, and has application potential in cross-domain unbalanced classification scenes.
Owner:JILIN UNIVERSITY

A protein post-translational modification data enhancement method based on generative adversarial networks

This invention is applicable to the field of proteomics and provides a method for enhancing protein post-translational modification data based on generative adversarial networks (GANs). This method can effectively alleviate class imbalance and enhance the ability to identify positive samples. It generates minority class pseudo samples through an improved cluster-enhanced conditional GAN ​​(RP-CGAN), and extracts features using the ESM-2 pre-trained protein language model to improve both positive sample identification and generalization capabilities. The method integrates ESM-2 feature extraction with RP-CGAN data enhancement technology to enhance overall prediction performance and classification stability, significantly improving key metrics for multiple classifiers. Multi-dimensional indicator screening and adaptive regulation ensure that the enhanced data approximates the true distribution. Leveraging a lightweight architecture and convergence strategy, the method optimizes training efficiency and model stability. The method possesses strong stability and cross-domain potential, enabling migration to other protein modification prediction tasks and possessing potential for application in cross-domain imbalanced classification scenarios.
Owner:JILIN UNIVERSITY

Chinese pre-training sample quality evaluation method and device based on multiple classifiers

The invention provides a Chinese pre-training sample quality evaluation method and device based on multiple classifiers. The method comprises the following steps: determining a Chinese pre-training sample to be subjected to quality evaluation; obtaining a plurality of quality evaluation results of the Chinese pre-training sample based on a plurality of pre-trained classifiers; wherein the plurality of classifiers are heterogeneous classifiers; and fusing the plurality of quality evaluation results to obtain a target quality evaluation result of the Chinese pre-training sample. According to the method, the quality of the Chinese pre-training sample is evaluated through the plurality of pre-trained heterogeneous classifiers, so that the prejudice of a single model can be avoided, the stability and the reliability of the overall quality evaluation are improved, the training requirements of a large-scale language model are effectively supported, and a new technical path is provided for the quality evaluation of the Chinese pre-training data.
Owner:BEIJING ACAD OF ARTIFICIAL INTELLLIGENCE

A method of detecting an attack in a core network of a mobile communication network

The invention is directed to a method of detecting an attack in a core network of a mobile communication network. Multiple classifiers are trained to detect the attack based on extracted payload content from a packet in the core network. Initial detection outcomes from the multiple classifiers are combined subsequently to generate a final detection outcome.
Owner:ST ENGINEERING IHQ PTE LTD

Method and device for predicting turning intention

This specification discloses a method and apparatus for predicting turning intentions. An unmanned driving device acquires an image of an obstacle and extracts a directional gradient histogram of the obstacle's boundary. Based on the directional gradient histogram and a trained first classifier, the device determines the obstacle's first turning intention. The device then uses multiple trained second classifiers to determine the obstacle's second turning intentions in each possible direction of travel. Finally, based on the first and second turning intentions, the device determines the obstacle's final turning intention, thereby determining an obstacle avoidance strategy based on the final turning intention. By predicting the obstacle's turning intention based on the directional gradient histogram of the obstacle's boundary, computational complexity is reduced, prediction timeliness is improved, and prediction accuracy is balanced by using multiple classifiers to determine the final turning intention.
Owner:BEIJING SANKUAI ONLINE TECH CO LTD

A hierarchical and collaborative intelligent analysis method for abnormal traffic

This invention proposes a hierarchical collaborative intelligent analysis method for abnormal traffic, relating to the field of artificial intelligence and network security technology. Edge nodes extract multi-dimensional flow-level feature vectors, which are then weighted and fused using multiple classifiers. Based on confidence level and detection results, traffic is handled by traffic splitting: high-confidence normal samples are forwarded at full speed, high-confidence abnormal samples are blocked, and low-confidence samples are forwarded with limited speed. The central node performs divergence attribution localization on low-confidence samples, conducts attribution analysis using a large language model, outputs the final judgment result, and promptly feeds it back to the edge nodes for further action. The central node uses a large model to generate different levels of explanation reports for abnormal samples with different confidence levels. Furthermore, the analysis results of low-confidence samples are stored in a memory bank for edge model training, updates, and parameter distribution. This invention achieves low latency, high accuracy, and interpretable results in abnormal traffic detection through a hierarchical collaborative mechanism that combines edge multi-model fusion detection with interpretable enhancement of the central large model.
Owner:THE 54TH RESEARCH INSTITUTE OF CHINA ELECTRONICS TECHNOLOGY GROUP CORPORATION

A method for defending against adversarial samples based on the combination of image preprocessing and adversarial training

ActiveCN112560901BHigh precisionImprove defense efficiencyNeural learning methodsPattern recognitionData set
The present invention proposes a method for defending against adversarial samples based on the combination of image preprocessing and adversarial training. It includes: 1) dividing the original image and the adversarial sample into small blocks, performing DCT transformation, and designing a quantization table, wherein the adversarial sample is a linear superposition of the original image and adversarial noise; 2) scaling the quantization table to obtain the quantization table required to achieve different compression ratios, applying different compression ratios to the original image to obtain different data sets, and then adding noise as a training adversarial sample. The original image and the training adversarial sample constitute a training data set, which is sent to a deep neural network for training to obtain different classifiers; 3) compressing the image to be classified at different compression ratios to obtain different images, and sending them to the classifier trained with the corresponding compression ratio data set, and the final result is obtained by voting by multiple classifiers. Compared with the existing methods, this method can ensure the classification accuracy of the original image and improve the defense efficiency of adversarial samples.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

GCN and multi-classifier fused citation network node classification method and classification system

The invention provides a citation network node classification method and system fusing GCN and multiple classifiers, and the method comprises the following steps: enabling a whole citation network to serve as an undirected graph G comprising node attributes and a topological structure; calculating an adjacent matrix and a feature matrix of the undirected graph G; initializing an edge weight matrix of the undirected graph G, and calculating an edge weight of the undirected graph G according to the feature matrix; the calculated edge weights are converged to nodes at the two ends of the edge, and the feature matrix is updated; filtering and amplifying the features in the updated feature matrix; and respectively inputting the adjacent matrix and the updated feature matrix into n classifiers for prediction, and fusing prediction results to obtain a final classification result. According to the classification method, effective semantic information in the network is comprehensively considered, prediction is carried out through a plurality of classifiers, fusion is carried out by using fuzzy integrals, and a more accurate and stable classification effect can be obtained.
Owner:SHENYANG NORMAL UNIV

Bearing diagnostic method, system, medium and device for multi-source subdomain negative migration inhibition

The present invention relates to the technical field of bearing fault diagnosis, and discloses a bearing diagnosis method, system, medium and equipment with multi-source subdomain negative migration suppression, including: obtaining source domain data and target domain data corresponding to the bearing, and bearing data to be tested, constructing a fault diagnosis model including a feature extractor, a domain discriminator, a specific domain classifier including multiple classifiers, and a local maximum mean difference module, the domain discriminator aligns the global distribution of all domain features through domain adversarial alignment and then inputs the specific domain classifier, the specific domain classifier outputs the predicted label of the source domain and the pseudo label of the target domain, the local maximum mean difference module combines the pseudo labels output by all classifiers and the local maximum mean difference to align the subdomains of all domains; the bearing data to be tested is input into the trained fault diagnosis model to obtain the fault diagnosis result of the bearing. The present invention can solve the problem of negative migration in the source domain and improve the accuracy of bearing fault diagnosis.
Owner:SUZHOU UNIV