27 results about "Multiview learning" patented technology

The invention provides a multi-view structure learning method based on multi-expert cooperation, and relates to the technical field of graph neural networks and multi-view learning, and the method comprises the steps: reconstructing initial multi-view data, and obtaining multi-view structure data; respectively training the single-view expert model and the shared expert model by utilizing a first loss function and a second loss function based on the multi-view structure data to obtain a trained single-view expert model and a trained shared expert model; constructing a collaborative decision model by using the trained single-view expert model and the trained shared expert model; training the collaborative decision model by using a third loss function to obtain a trained collaborative decision model; and analyzing the graph data by using the trained collaborative decision model to obtain a joint decision result, and completing learning of the multi-view structure. According to the method, the problems of large structural noise interference, isolated expert model information and insufficient node classification accuracy when an existing graph neural network processes multi-relation graph data are solved.

The invention relates to the field of medical information processing, in particular to a deep learning-based medical multi-source heterogeneous data fusion and knowledge discovery system, which comprises a heterogeneous data management and mapping module, a medical data unified representation module, a medical knowledge mining engine, a knowledge-driven decision support module and a hypothesis verification and visual exploration module, the system utilizes the Riemannian manifold theory to construct a multi-modal medical data unified characterization framework, realizes multi-scale medical knowledge characterization in combination with a curvature perception mechanism, excavates multi-entity association through multi-view learning and a graph neural network, calculates the consistency among diseases, symptoms, signs and genes based on a knowledge graph, provides accurate diagnosis and treatment schemes, and realizes the purpose of accurate diagnosis and treatment. According to the method, the technical problems that medical multi-source heterogeneous data are difficult to fuse, complex association is difficult to mine and knowledge representation is not accurate enough are effectively solved, and the data utilization efficiency, representation quality and diagnosis accuracy are remarkably improved.

The invention discloses a load identification method and system based on multi-view learning and a deep wide residual network. The method comprises the following steps: acquiring voltage and current data at an outlet of a current collector; extracting two types of load feature views from the collected data, and adding data labels to form a labeled data set; generating two training subsets from the labeled data set, wherein the initial training subset comprises a part of labeled samples and unlabeled samples; performing cross training on the two depth wide residual classification networks by using the training subset, and training to obtain a depth wide residual classification network model based on multi-view learning; and extracting two feature views from unknown electric appliance data collected in real time, inputting the two feature views as label-free data into the depth wide residual classification network model based on multi-view learning, updating the model, and obtaining a load identification result. The method has the advantages of improving the model recognition accuracy and generalization performance, enhancing the robustness of the model, improving the model recognition accuracy and saving the model training time.

This invention discloses a method, apparatus, and device for predicting the activity of chemically modified siRNA, comprising: acquiring the original base sequence and chemical modification information of the target siRNA, and retrieving the physicochemical properties of the target siRNA; encoding the original base sequence, chemical modification information, and physicochemical properties as features; and generating a prediction result of the silencing efficiency of the target siRNA based on the encoded features using a pre-constructed prediction model; wherein the pre-constructed prediction model includes: a feature fusion sub-model and a classification sub-model; the feature fusion sub-model is used to perform feature fusion on the encoded features based on a cross-attention mechanism; and the classification sub-model is used to generate a prediction result of the silencing efficiency based on the fused features. This method, based on a multi-dimensional, multi-view learning strategy and an attention mechanism fusion model, significantly improves the algorithm's ability to represent chemically modified siRNA data, and, combined with the nonlinear data fitting ability of the deep learning framework, improves the accuracy of the algorithm in predicting the drug activity of chemically modified siRNA.

The invention provides a similarity distribution-based pseudo label construction method and a correlation contrast learning method, pseudo labels are generated for instances by calculating similarity distribution among the instances, and the pseudo labels not only provide additional supervision signals for the model, but also can be used as the training is carried out. The change of similarity distribution can also be used for dynamically adjusting the label weight, so that the generalization ability of the model is improved; secondly, the similarity distribution among the instances is constructed, and the mutual relation among different views is also calculated; in multi-view learning, data may be observed from multiple angles or feature spaces, each view may contain different information about the data. By constructing similarity distribution between views, the relationship between instances can be better modeled, so that when one view of the same sample is similar to or dissimilar from other samples, the other view can keep the relationship as well.

The invention discloses a fusion representation method for incomplete multi-view data, and belongs to the technical field of information technology service. The method comprises the following steps: aiming at the problem that a traditional multi-view learning method cannot be suitable for incomplete multi-view data learning when views are missing, constructing a multi-view representation matrix aiming at an incomplete multi-view data set; optimizing a single view representation matrix; a single-view reconstruction learning model is constructed, and complementation of a missing view representation matrix is realized; constructing a target function by using the fusion representation model; the fusion representation model is trained, an optimal fusion representation matrix is obtained through model optimization, and the fusion representation matrix can be directly used as input of downstream tasks. According to the method, the key technology of fusion expression of multi-source heterogeneous multi-view data is broken through, the purposes of making full use of multiple views and reducing influences of incomplete views are achieved, and then downstream tasks in a network can be supported.

The invention discloses an intelligent contract vulnerability detection method based on multi-view learning. The method comprises the following steps: statically analyzing an intelligent contract to obtain an abstract syntax tree, a control flow diagram and a data flow diagram of three representation modes of an intelligent contract source code; noise codes except for calling external functions and variable positions are pruned for different representation modes, and features of the noise codes are obtained; abstract syntax tree features are learned through an extended recurrent neural network, and features of a control flow graph and a data flow graph are learned through a graph attention network; and detecting the vulnerability of the smart contract based on the final feature obtained by fusing the three features. According to the intelligent contract vulnerability detection method based on multi-view learning, the indicative features of vulnerabilities can be captured from codes more comprehensively, redundant noise is reduced, and the performance and effect of intelligent contract vulnerability detection are improved.

The present invention relates to the technical field of knowledge graph construction, and discloses a method for constructing and optimizing a knowledge graph for a substation based on multi-view learning, comprising the following steps: processing multi-source data of the substation through a heterogeneous model, mapping the multi-source heterogeneous data of operation and maintenance texts, monitoring data, procedures and rules, and infrared images of substation equipment to a unified feature space through linear projection, constructing multimodal positive and negative sample pairs of the same equipment, using contrastive learning to shorten the distance between related equipment features, dynamically optimizing the projection matrix of various types of data, jointly detecting entity boundaries of substation equipment in operation and maintenance texts and equipment monitoring data, fusing multimodal equipment features through an attention mechanism, and inferring the relationship types between equipment. The present invention effectively solves the fragmentation and static problems existing in traditional knowledge management systems by deeply integrating multi-source heterogeneous data of substations with expert experience, and significantly improves the accuracy of power equipment status perception and fault diagnosis.

This disclosure provides an entity classification method, apparatus, electronic device, and storage medium. The method includes: acquiring multiple entity relationship networks corresponding to multiple entity nodes; the same entity node corresponding to different entity relationships in different entity relationship networks; performing multi-label prediction on the multiple entity relationship networks based on multiple trained base learners to obtain the multi-label prediction result of each entity node in each entity relationship network; and determining the final multi-label prediction result corresponding to each entity node based on the multi-label prediction result of each entity node in each entity relationship network. This disclosure, from the perspective of multi-view learning, performs multi-label prediction based on multiple entity relationship networks, which can more fully explore the relationships between entities, making the multi-label prediction results for entity nodes more accurate.

The invention discloses a bio-electricity signal recognition model and a reconfigurable hardware accelerator thereof, which adopt a multi-view learning method to comprehensively extract feature information from a plurality of feature views of bio-electricity signal data, can more comprehensively capture various characteristics of signals, and improve the recognition accuracy of the bio-electricity signals. The method comprises the following steps: firstly, learning initial features of three views by adopting a deep neural network to extract deep features; secondly, the depth features of all the views are fused to form a unified multi-view feature representation; and finally, inputting the fused multi-view features into a multi-layer perceptron for further feature learning to obtain a classification result, and finally completing the classification decision of the bio-electricity signals. A reconfigurable computing array is integrated in the reconfigurable hardware accelerator, dynamic multiplexing of hardware resources can be achieved through a time division multiplexing mechanism, a fast Fourier transform computing mode or a neural network reasoning computing mode is dynamically configured according to needs at different computing stages, and extra computing resources do not need to be introduced. Through the reconfigurable design, the overall area of the accelerator is reduced, and the utilization rate of computing resources is improved; data interaction is carried out among the modules through the data interfaces, instruction transmission is completed through the instruction interfaces, flexible reconstruction can be achieved, and it is ensured that in a bio-electricity signal processing task, different calculation stages are efficiently executed.

The application provides an Android malware detection method based on multi-view learning, and belongs to the technical field of Android malware detection. The method comprises the following steps: 1, decompiling the Android application to be detected, extracting the function call relationship, opcode sequence and permission information, constructing the function call graph and extracting the sensitive behavior subgraph; 2, using the pre-trained code representation model CodeBERT to perform semantic coding on the method-level opcode sequence, and fusing the permission features to generate the node semantic vector; 3, constructing a multi-view graph neural network, generating multi-view input through a feature mask enhancement strategy, introducing a multi-hop adaptive attention mechanism to realize dynamic aggregation of multi-hop neighborhood information, and simultaneously adopting a multi-channel coding structure for learning complementary graph representation; 4, fusing the multi-channel node representation, constructing a relationship matrix through key-value mapping, and generating a graph-level representation through convolution and pooling, and finally inputting a classification model to realize Android malware detection.

The invention belongs to the field of deep learning, and discloses a semi-supervised multi-view deep representation learning method and system under a class imbalance condition, and the method comprises the steps: taking each view data as a subset, independently learning a feature learning network for each subset, and converting the data of other views into missing views by using View Switch if the views are missing; a balance subset is constructed on the basis of View Switch; modeling information contained in each view into view shared information and view unique information, and fusing features learned by each subset by using similar loss and orthogonal loss to serve as final multi-view features. According to the method, deep learning classification is carried out on data with semi-supervised, multi-view and class imbalance characteristics at the same time, firstly, a semi-supervised multi-view learning algorithm based on View Switch is designed, and then a deep representation learning method based on View Switch and a balance subset is designed under the class imbalance condition. According to the invention, the research work of the deep representation learning theory and the application technology thereof is powerfully promoted.

The invention belongs to the technical field of artificial intelligence and machine learning, and discloses a multi-view representation learning method based on adaptive view communication and multilevel residual connection learning, and the method achieves the joint modeling of consistency and complementarity through sharing-specific information decomposition, simulates the human communication mechanism, and achieves the multi-view representation learning through multi-level residual connection learning. Multi-round communication is realized by a cross-view attention mechanism driven by specific information, and an adaptive stop condition is designed in combination with sharing similarity and mutual information to dynamically determine an optimal communication round number. Meanwhile, a multi-level residual fusion strategy is adopted, original features and interactive features are organically combined, and the sufficiency of representation and the calculation efficiency are both considered. According to the method, the performance of a multi-view learning task can be remarkably improved, and the method is suitable for multi-source data fusion scenes such as intelligent perception, medical diagnosis and automatic driving and has important scientific significance and engineering application value.

The invention provides a spine three-dimensional evaluation and intelligent grading system based on multi-view learning, and relates to the technical field of intelligent evaluation of scoliosis, the spine three-dimensional evaluation and intelligent grading system comprises a multi-view image acquisition module for acquiring spine images of a patient through camera equipment, and the spine images of the patient comprise a back image, a side image and a back bending position image; the image preprocessing module is used for performing human body segmentation processing, cutting processing and pixel normalization processing on the spine image of the patient, and the human body segmentation processing uses a U-Net model to segment the spine image of the patient into a human body mask. The spine three-dimensional multi-view evaluation and intelligent grading system for multi-view learning is provided.

The invention discloses a remote sensing classification method based on multi-view causal learning, which belongs to the field of computer vision and comprises the following steps: constructing an image classification model; obtaining a to-be-classified image, and inputting the image into the trained classification model to obtain an image classification result; the classification model comprises four core modules: a visual Transform module, a frequency domain causal analysis module, a multi-view processing module and a classification head module. According to the method, a multi-view learning mechanism and frequency domain causal analysis are introduced, and a special loss function is designed to optimize a feature extraction process, so that the network is guided to extract causal features with higher discrimination and robustness, and the performance of a classification model on an actual remote sensing classification scene is further improved.

The application relates to an image recognition method, system and device based on hierarchical prototype multi-view learning. The method comprises the following steps: constructing a multi-layer prototype model; initializing the multi-layer prototype model; inputting a multi-view image sample set into the initialized multi-layer prototype model; constructing a target function according to a sample-prototype association relationship between original data in the multi-view image sample set and a bottom layer prototype matrix, a mapping relationship of adjacent layer prototype matrices and a structure constraint of a cross-layer consensus prototype graph; solving the target function; outputting an optimized sample-prototype similarity graph and a cross-layer consensus prototype graph; and fusing the optimized sample-prototype similarity graph and the cross-layer consensus prototype graph in the multi-layer prototype model and then obtaining a clustering result of the multi-view image sample set through spectral clustering processing. The method can effectively improve the accuracy and stability of image clustering and enhance the interpretability and reliability of the image recognition result.

The present invention discloses a system and method for discovering enterprise collaboration groups applicable to multiple industrial chains. The system includes an enterprise feature extraction module and a multi-view clustering module. The enterprise feature extraction module is implemented using non-negative matrix factorization technology. The multi-view clustering module includes a weighted integration of two types of visible and invisible views: inherent features and topological features, and multi-view learning constraints based on the spatial topological relationships of individuals and the subordinate pattern trends of individuals obtained through fuzzy partitioning. The present invention can simultaneously mine two types of visible and invisible view information of an enterprise, including inherent feature perspective-specific (visible) and shared (invisible) information, as well as topological feature perspective-specific (visible) and shared (invisible) information brought about by enterprise connection relationships. It also completes collaborative learning of the two types of perspectives and obtains better enterprise collaboration group discovery results.

The invention discloses an imitation wearable antistatic protective clothing detection system, and relates to the technical field of protective clothing detection, static data, second acoustic emission data and a motion data set are collected, a regionalized charge density thermodynamic diagram is generated and feature extraction is carried out, and anomaly detection is carried out according to the extracted features. According to the method, static electricity and material micro-damage data are accurately collected in real time through cooperation of the textile nano-generator and the acoustic emission sensor, and noise interference is effectively inhibited by adopting complementary filtering and deep multi-view learning, so that real-time early warning and visualization are realized. According to the method, robust detection of tiny anomalies is realized, a prediction system is constructed by combining an inertial measurement unit covariance matrix and a graph neural network, the global health state evaluation capability and real-time early warning and data visualization functions are improved, the timeliness and intuition of safety management are enhanced, and the performance of protective clothing and personnel safety are comprehensively guaranteed.

The application provides a single-cell multi-modal classification method and system with phased multi-view cooperation, relates to the field of biological information technology, and comprises the following steps: acquiring multi-modal data of a plurality of single cells; performing modal feature screening and normalization processing on the multi-modal data to obtain normalized data of each mode; calculating cell similarity based on the normalized data, and combining a mutual neighbor strategy to construct a cell-cell graph under each mode; performing feature extraction on the normalized data of each mode to obtain cell features under different modes; performing interactive learning according to the cell-cell graph and the cell features, and combining feature refining and multi-view learning to generate a common latent representation matrix; and performing cell type prediction through the common latent representation matrix to obtain the final classification result of each single cell. The application solves the problems that the existing method still has limitations in the depth fusion and calculation efficiency of feature interaction, and cannot balance the complementarity and technical noise of multi-modal data.

The invention relates to an image recognition method, system and device based on hierarchical prototype multi-view learning. The method comprises the following steps: constructing a multi-layer prototype model; initializing a multi-layer prototype model, inputting the multi-view image sample set into the initialized multi-layer prototype model, and constructing a target function according to a sample-prototype association relationship between original data in the multi-view image sample set and a bottom prototype matrix, a mapping relationship between adjacent prototype matrixes and structural constraints of each layer of cross-layer consensus prototype graph; solving a target function, and outputting an optimized sample-prototype similar graph and a cross-layer consensus prototype graph; and fusing the optimized sample-prototype similar graph and the cross-layer consensus prototype graph in the multi-layer prototype model, and carrying out spectral clustering processing to obtain a clustering result of the multi-view image sample set. By adopting the method, the accuracy and the stability of image clustering can be effectively improved, and the interpretability and the credibility of an image recognition result are enhanced.

The invention relates to the technical field of network security, in particular to an encrypted malicious traffic detection method based on uncertainty perception multi-view learning, and aims to effectively identify malicious behaviors in an encrypted network by introducing a graph neural network, long-range information propagation, semantic-based structure enhancement, view interaction, uncertainty quantization and other mechanisms. The encrypted traffic is constructed into a host interaction graph, and semantic embedding of nodes is obtained through diffusion type long-range propagation; then, post-propagation structure completion is carried out by using cosine similarity, and a repaired topology is generated; mapping each view into Dirichlet distribution by adopting evidence deep learning, and calculating belief quality and uncertainty of each view; through the improved Dempster-Shafer combination rule, uncertainty perception fusion is carried out on all views, malicious traffic prediction and credibility are output, detection precision and robustness are improved, and the method is used for scenes of network security monitoring, malicious software detection, industrial control system protection and the like.

The invention relates to a missing multi-view comparative learning method and system based on semi-supervised graph constraint, and the method comprises the steps: obtaining a view sample set, each view comprises a complete view and a missing view, inputting a view data set into an overall network architecture, and recovering the missing view to obtain a final clustering result, wherein the overall network architecture training step comprises the following steps: based on a complete view sample set, performing feature extraction and reconstruction by using a multi-view learning model, respectively obtaining potential feature vectors and reconstruction data, and constructing a reconstruction loss function to update parameters of the multi-view learning model; semi-supervised contrast learning is carried out based on the potential feature vectors, and a contrast loss function is constructed; based on the potential feature vector, constructing a graph structure and carrying out graph constraint on the graph structure to construct a graph loss function; and constructing a total loss function, and updating overall network architecture parameters by using an optimizer. Compared with the prior art, the multi-view clustering method has the advantages of remarkably improving the accuracy of multi-view clustering and the like.

The application provides a palmprint multi-feature fusion recognition method and device based on multi-view learning, comprising: extracting multiple palmprint view features from a palmprint region of interest image; for any one of the palmprint view features, using a linear discriminant analysis method to maximize the variance between different categories and minimize the variance between different samples of the same category to obtain the palmprint view feature after projection dimension reduction; using a deep generalized canonical correlation analysis method to extract the correlation features between the palmprint view features after projection dimension reduction as palmprint fusion features; and applying a collaborative representation classification method according to the palmprint fusion features to perform classification recognition. The palmprint features of multiple different views can be fused for recognition, and the stability and accuracy of palmprint feature recognition can be improved.

The application discloses a smart contract vulnerability detection method based on multi-view learning, and the method obtains three representation modes of a smart contract source code, an abstract syntax tree, a control flow graph and a data flow graph through static analysis of the smart contract; noise codes outside called external functions and variable positions are pruned for different representation modes, and features of the noise codes are obtained; abstract syntax tree features are learned through an extended recurrent neural network, and control flow graph and data flow graph features are learned through a graph attention network; and finally, features obtained through fusion of the three kinds of features are used to detect smart contract vulnerabilities. The smart contract vulnerability detection method based on multi-view learning can more comprehensively capture indicative features of vulnerabilities from codes, simplify redundant noise, and improve the performance and effect of smart contract vulnerability detection.

The application discloses a sleep staging system based on self-supervised learning and multi-view learning, comprising a data loading module, which is used for loading sleep electroencephalogram signals and constructing a data set, and pre-processing and enhancing transformation of the electroencephalogram signals; a self-supervised pre-training module, which extracts features through a twin network based on multi-view learning, constructs a positive and negative sample set in cooperation with a TopK algorithm, and finally completes pre-training of the network using a contrast loss; a supervised training module, which extracts features using a feature representation module and a sequence representation module, and performs network training after feature fusion, and finally obtains an optimal sleep staging model; and a sleep stage prediction module, which performs sleep staging prediction using the optimal sleep staging model. The application introduces multi-view learning and self-supervised pre-training into the sleep staging task, can improve the staging accuracy, and reduces the dependence on labeled data.

The present application relates to a kind of multi-view graph neural network community question and answer expert recommendation method, belong to data processing technical field.The present application is respectively analyzed the multiple association between question text information data and expert user information data, and question text data and candidate expert user information are expressed as vector, using graph neural network learns the multi-view data matrix of question text and expert user information, then using multi-view learning, the generated matrix is learned, finally the community question and answer expert recommendation model of the association of fusion question text information data and expert information data is established, the model can learn the score relationship between question text information data and expert user information data, to be used for community question and answer expert recommendation, and the recommended method has achieved good effect.