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

370 results about "Multi layer network" patented technology

Multi-layered networks. Multi-layered networks consist of layers of several networks, where nodes appear in at least one of these layers. The networks are both connected by intra-layer links (links in one layer) as well as inter-layer links (links between layers).

Multi-source spatio-temporal data fusion processing method and device

The invention provides a multi-source spatio-temporal data fusion processing method and device. The method comprises the following steps: preprocessing multi-source spatio-temporal data; performing standardization processing on the preprocessed multi-source spatio-temporal data to obtain standardized data; performing alignment processing on the standardized data by using a space-time registration technology to obtain registration data; constructing a multi-layer network structure, and performing data arrangement on the registration data by using the multi-layer network structure to obtain structured data; and establishing a unified geographic element classification system according to the structured data. Sampling the standardized feature vectors by adopting an MCMC urban sampling algorithm to obtain feature distribution parameters; calculating a covariance matrix based on the feature distribution parameters and performing feature value decomposition; and defining geographic element categories according to the distinction degree of the feature combination. The method also comprises a corresponding device implementation. According to the method, the problems of low efficiency and poor precision of multi-source spatio-temporal data fusion in the prior art are solved, the precision of data fusion is improved, and the method has relatively high practicability and adaptability.
Owner:GUIZHOU TDT TECH CO LTD

Time-frequency multi-layer brain network-based natural hand movement electroencephalogram (EEG) recognition method

PCT designated stage expiredWO2025043856A1Biological modelsSensorsPattern recognitionTime domain
Disclosed in the present invention is a time-frequency multi-layer brain network-based natural hand movement EEG recognition method, comprising: (1) acquiring a multi-channel EEG signal of a natural hand movement; (2) pre-processing the multi-channel EEG signal to extract a δ wave, a θ wave, an α wave, a β wave, and a γ wave at each time point; (3) constructing a time domain multi-layer brain network by using a wSAR model; (4) calculating a frequency domain multi-layer brain network by using cross-frequency coupling (CFC); (5) combining and standardizing the time domain and frequency domain multi-layer brain network; and (6) calculating a multi-layer network metric of the multi-layer brain network and a decomposed super-adjacency matrix, and inputting same to a double-layer graph convolutional network (GCN) to fuse artificial, shallow, and deep features for classification. According to the present invention, a new time-frequency fusion multi-layer brain network is proposed by using the wSAR model and the CFC. In addition, feature information of the multi-layer brain network is comprehensively extracted by using two layers of GCNs, so that the neurophysiological mechanism of brain can be revealed and the decoding precision of the natural action EEG can be improved.
Owner:SOUTHEAST UNIV

Multi-layer network flow dynamic monitoring and analysis method based on graph neural network

The invention discloses a multi-layer network flow dynamic monitoring and analysis method based on a graph neural network. The method comprises the following steps: S1, collecting data of each node in real time and preprocessing the data; s2, dividing the preprocessed data based on a preset time window, and constructing graph structure data; s3, carrying out topology learning on the constructed graph structure data by adopting an improved EvolveGCN, and generating final feature representation of dynamic change of a network topology structure; s4, carrying out modeling on the preprocessed data by utilizing Graph WaveNet, and extracting final feature representations of space-time dependency and local spatial correlation; s5, performing feature fusion to generate a comprehensive feature vector; s6, generating a final monitoring result based on the comprehensive feature vector; and S7, transmitting the final monitoring result to a network flow management platform for data processing and analysis. According to the method, an efficient and scientific optimization scheme can be provided in dynamic monitoring of the network traffic, and remarkable technical values and economic benefits are brought to practical application.
Owner:WUHAN WEIXU TECH CO LTD

Ship loading and cabin changing trajectory planning method and system based on machine vision

The invention relates to the technical field of port automatic loading and unloading, in particular to a ship loading and cabin changing track planning method and system based on machine vision, and the method comprises the following steps: constructing a multi-modal information sensing array based on machine vision, obtaining the space information of a cabin, the stacking information of cargoes and the state information of loading equipment, a multi-modal information sensing data set is constructed; constructing a space-time correlation characteristic matrix of the cabin, the goods and the loading equipment; a multi-layer network architecture is used for preliminarily planning the ship loading and cabin changing track to obtain an initial ship loading and cabin changing track; constructing a dynamic digital fitting model, and fitting the initial ship-loading and cabin-changing track to obtain an optimized ship-loading and cabin-changing track; and establishing a real-time environment quantification model to perform real-time dynamic adjustment on the optimized ship-loading and cabin-changing track, and completing planning of the ship-loading and cabin-changing track. The system flexibly adapts to complex loading task requirements, and the intelligent level and execution efficiency of ship loading and cabin changing are remarkably improved.
Owner:RIZHAO PORT GRP CO LTD

Weld defect identification method based on visual Transform

ActiveCN119313639AAddressing Diversity InsufficiencyHigh precisionImage enhancementImage analysisData setAlgorithm
The invention discloses a visual Transform-based welding seam defect identification method, which improves the welding seam identification precision and solves the problem of insufficient diversity of training data of welding seam defects. The system is characterized by being provided with the following modules in advance: a data preparation module, a model design module and a training and optimizing module, a standard image data set is obtained through a training and optimizing module, an obtained new image is added into the standard image data set through the training and optimizing module, and model parameters are optimized according to a test result, so that after an image of a to-be-detected welding seam is input, a model design module is combined with the input image to divide the input image into reasonable small blocks; the method comprises the following steps: firstly, firstly, forming a corresponding Swin Transformer module, then, comparing a Petri feature fusion module with a standard image data set to carry out first-time welding seam detection, finally, comparing a multi-layer network detection head with the standard image data set to carry out second-time welding seam detection, and finally, giving out the type of the welding seam and the position of the welding seam in an original image.
Owner:JIANGSU BEIREN ROBOT SYST CO LTD

Improved YOLOv8 chip surface defect detection model and construction method and application thereof

The invention discloses an improved YOLOv8 chip surface defect detection model construction method and application, and the method comprises the steps: constructing a network structure of an improved YOLOv8 target detection model, which comprises a Backbone module, a Neck module and a Head module; the Backbone module comprises a multi-layer DCNv3 network, a C2f network and an SPPF network, and outputs a first effective feature layer, a second effective feature layer and a third effective feature layer after performing multi-layer convolution processing on the picture; the Neck module adopts a BiFPN bidirectional feature pyramid feature fusion structure, inputs three effective feature layers output by the Backbone module into a ConcatBiFPN network for bidirectional adaptive fusion, and then outputs the three effective feature layers through a CBAM attention mechanism network; the Head module comprises a Deect network structure, and the Deect network structure is connected with a CBAM attention mechanism network and outputs a target detection result; the improved YOLOv8 target detection model structure is used for accurately recognizing the surface defects of the chip, and the adaptability to different types of defects is improved.
Owner:JIANGSU UNIV

Method, system and equipment for generating face recognition fusion model

The invention relates to the technical field of image recognition, in particular to a method, a system and equipment for generating a face recognition fusion model. The method comprises the following steps: acquiring a historical face recognition image set and historical equipment sensing data through face recognition equipment, and performing multi-modal data fusion integration to obtain a multi-source fusion data set; performing multi-layer network spatial-temporal feature integration on the multi-source fusion data set to obtain a high-dimensional feature spectrum; performing modal information flow modeling based on the high-dimensional characteristic spectrum to obtain a modal correlation matrix, and performing adaptive modal contribution degree weighting to obtain a modal relation matrix; performing face recognition time sequence adaptive modeling according to the modal relation matrix to obtain a face recognition time sequence adaptive model; and performing model evaluation on the face recognition time sequence adaptation model, establishing a precision optimization matrix, and optimizing the face recognition time sequence adaptation model by using the precision optimization matrix to obtain a face recognition fusion model. According to the invention, the accuracy and real-time performance of face recognition can be improved.
Owner:SHENZHEN HUABAIAN INTELLIGENT TECH CO LTD

Important node identification method and device for multilayer supply chain network, equipment and medium

The invention provides an important node identification method and device for a multilayer supply chain network, equipment and a medium, and relates to the technical field of supply chain management. The method comprises the following steps: constructing a directed weighted multilayer complex network, combining a centrality index, identifying nodes of an intermediate layer network, and obtaining a candidate node set M; according to the M, descending sorting is carried out according to the occurrence frequency of the nodes, in combination with a preset proportion, a head segment and a tail segment of nodes of a descending sorting list are intercepted to serve as a first batch of important node sets and an unconsidered node set, and a to-be-determined node candidate set ranking the middle part is obtained; traversing and calculating the influence on the network efficiency after any node is deleted in the to-be-determined node candidate set, and selecting a node combination with the influence ranking conforming to a threshold value to be added into a second batch of important node sets; and searching important nodes of the upper and lower networks to form a third batch of important node set, thereby completing important node identification. According to the method, the characteristics of the multilayer network can be captured, important nodes can be identified, and the accuracy is high.
Owner:XIAMEN UNIV OF TECH

Voice decoding method, system and equipment based on electroencephalogram signals and medium

The invention discloses a voice decoding method, system and device based on electroencephalogram signals and a medium, and relates to the technical field of electroencephalogram signal processing.The method comprises the steps that reading electroencephalogram signals and voice signals in the reading process of a to-be-tested person and imagination electroencephalogram signals in the imagination reading process of the to-be-tested person are collected; inputting the reading electroencephalogram signals and the voice signals into the DRCL to generate electroencephalogram characteristics containing voice information; training the DBM by using the electroencephalogram characteristics as input and using the voice signals as output, and adjusting the DBM by using imaginary electroencephalogram signals to construct a voice synthesizer; a mapping relation between the imaginary electroencephalogram signals and the voice signals is generated through the voice synthesizer, and decoding from the electroencephalogram signals to the voice signals is completed; according to the method, a deep representation correlation learning method is provided, potential correlation between electroencephalogram and voice signals can be deeply mined through a multi-layer network structure, a complex mode which is difficult to recognize by a traditional model is captured, and the voice decoding process is more accurate.
Owner:HARBIN INST OF TECH

Hospital infection propagation path tracing method based on multi-source data fusion

The invention provides a hospital infection propagation path tracing method based on multi-source data fusion, and belongs to the technical field of infection propagation paths in hospitals, and the method comprises the steps: building a data set through collecting hospital multi-source infection monitoring data, constructing a multi-layer network propagation model comprising physical contact, spatial proximity and time co-occurrence, and carrying out the tracing of the multi-source infection propagation path. Community detection is carried out by using a random block model, infection propagation path identification is converted into graph coloring problem solving, an individual behavior heterogeneity model is established, and SEIR model propagation parameters are corrected by fusing individual characteristic parameters such as the immune state of a patient and the protection level of medical staff; a propagation situation awareness model based on a hybrid expert mechanism is adopted to optimize propagation parameter estimation, and a propagation parameter weight coefficient is obtained through a game optimization mechanism and Nash equilibrium solution for iterative optimization. And finally, outputting a high-confidence infection propagation path sequence and a propagation source positioning result by adopting a propagation path backtracking algorithm in combination with spatial-temporal correlation analysis.
Owner:QINGDAO MUNICIPAL HOSPITAL

Gaze spectrum prediction method based on first-view-angle high-dynamic long video

The invention discloses a fixation spectrum estimation method based on a first-view-angle high-dynamic long video, and belongs to the field of image processing. According to the gaze spectrum prediction method, the key problems that in the prior art, time sequence information in a long-time video is lost, local and global information fusion is insufficient, and static masks are difficult to adapt to dynamic scene changes are effectively solved through three innovative modules. The enhanced long-time memory encoder effectively encodes a long-time video through multi-scale attention and a hierarchical memory mechanism, the problems of information loss and redundancy under long-time dependence are solved, and the integrity of time sequence information is ensured; the high-pass global-local information aggregation module enables a global background and local details to be effectively combined in a multi-layer network by designing a cross-layer dynamic information transmission channel, so that the gaze spectrum prediction capability in a complex dynamic scene is enhanced; and the dynamic mask fusion module adopts a self-adaptive mechanism, so that the mask weight can be adjusted in real time, the problem that static attention cannot cope with a rapid change background is solved, and the flexibility and accuracy of the model are improved.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Network key node identification method fusing improved measurement and propagation influence

The invention relates to the technical field of node identification, in particular to a network key node identification method fusing improved measurement and propagation influence, which comprises the following steps: setting an edge weight and a cross-layer dependency relationship of an infrastructure network; constructing weighted cross-layer local contact centrality, attenuation cross-layer path centrality and random walk centrality indexes; taking the maximum value of the three adaptive scores as an improved measure of the node; defining metric value standardization; calculating a propagation influence value, standardizing the measurement value, and carrying out weighted fusion on the measurement value and the propagation influence value to obtain a fusion score; carrying out propagation influence value convergence judgment by utilizing an LT linear threshold model; and arranging the nodes based on the fusion score value, and outputting a key node identification result. The method solves the problems that a traditional key node identification method only regards a multi-layer network as a plurality of isolated single-layer networks, lacks measurement of node heterogeneity in the multi-layer network, ignores a coupling relation between network layers and is difficult to be accurately applied to an urban multi-layer infrastructure network.
Owner:CHANGZHOU UNIV

Power transmission and distribution network collaborative optimization method and system considering power and traffic multi-layer network coupling model

The invention relates to the technical field of power transmission and distribution network collaborative optimization, in particular to a power transmission and distribution network collaborative optimization method and system considering a power and traffic multi-layer network coupling model, and aims to solve the problems that a power transmission and distribution network collaborative optimization model considering power-traffic network coupling is difficult to converge and time-consuming to solve. A McCormick envelope relaxation method is adopted to carry out relaxation of non-convex constraint, and a large M convex optimization balance method is adopted to determine an upper bound and a lower bound of a better variable. As the operation feasible region of the power distribution network at the single moment is influenced by the current state parameters of the system, the prediction of the operation feasible region of the power distribution network at the single moment is realized by adopting a deep learning method, and meanwhile, in order to improve the prediction accuracy, approximate processing is performed on the lower boundary of the operation feasible region of the power distribution network.
Owner:SOUTHEAST UNIV

Lightweight fruit maturity detection method and system suitable for embedded equipment

The invention discloses a lightweight fruit maturity detection method and system suitable for embedded equipment, and the method comprises the steps: collecting a multi-scene fruit plantation video, and obtaining a plurality of fruit images and a crop fruit image data set; the method comprises the following steps: performing improvement based on a YOLOv81 model, taking a CSPGhostNet network as a backbone network, taking a feature fusion network PANet as a neck network, and setting a classifier and a regression device as a head network so as to establish a fruit detection model; taking the fruit image data set as input, performing multi-layer network channel pruning on the fruit detection model based on a model pruning method, and obtaining a compressed fruit detection model; performing fine tuning training on the fruit detection model and the compressed fruit detection model by using a knowledge distillation method to obtain a lightweight fruit detection model; and detecting the fruit maturity by using the light-weight fruit detection model. According to the invention, rapid and accurate detection of fruit maturity can be realized.
Owner:ZJU-ANQING YANGTZE DELTA FUTURE IND INSTITUTE +1

Construction method and system of protein-ligand docking scoring model based on graph Transform

The invention discloses a method for constructing a protein-ligand docking scoring model based on a graph Transform, which comprises a graph neural network, a multilayer network based on an attention mechanism and a decoding module, and is characterized in that the decoding module comprises an MND decoding module and a pKd decoding module; the MND decoding module is used for calculating the distance probability distribution between the protein and the ligand; the pKd decoding module is used for predicting an affinity value when the protein is combined with the ligand; the loss function comprises MDN loss and pKd loss, a first layer of the multi-layer network has mask vectors which are updated along with training iteration and are used for indicating that features are reserved or shielded, and docking scoring prediction is carried out by taking the protein graph and the ligand graph as input. According to the scheme, the model simultaneously uses the MDN decoding module and the pKd decoding module, the MDN module optimizes model parameters from the perspective of probability distribution, the pKd module optimizes the model parameters from the perspective of binding affinity, the MDN decoding module and the pKd decoding module carry out docking scoring from the spatial relation and the interaction relation, and the comprehensive evaluation ability of the model can be effectively improved through cooperation of the MDN decoding module and the pKd decoding module.
Owner:YANGTZE DELTA REGION INST (QUZHOU) UNIV OF ELECTRONIC SCI & TECH OF CHINA

Spatial domain identification method and device based on multi-modal topology consistency

The invention discloses a spatial domain identification method and device based on multi-modal topological consistency, and belongs to the field of transcriptome spatial domain identification, and the method comprises the steps: constructing a multi-layer network which is in one-to-one correspondence with modal information contained in a biological tissue based on spatial transcriptomics data of the biological tissue; extracting a consensus structure feature shared by the multi-layer network and a specific structure feature specific to each layer of network; constructing a cell consistency network of the biological tissue according to the consensus structural features, the specific structural features and the multilayer network; and performing clustering processing on the cell consistency network to obtain recognition results of different spatial domains in the biological tissue. According to the method, the heterogeneity problem among different modal data can be overcome, and the spatial domain recognition effect is better.
Owner:XIDIAN UNIV

Vehicle trajectory prediction method and device for airport operation, electronic equipment and storage medium

According to the vehicle trajectory prediction method and device for airport operation, the electronic equipment and the storage medium, the method comprises the steps that features are extracted through a multi-layer network, the precision and adaptability of trajectory prediction are remarkably improved, path planning is optimized, and the safety of special vehicles in airport operation is enhanced. Through a reasonable feature extraction and modeling strategy, the method effectively reduces the calculation complexity, comprehensively considers the multi-dimensional features of the vehicle, and achieves the more comprehensive and accurate track prediction. The intelligent scheduling platform is constructed, various information of different vehicles is collected and stored, real-time decision making and intelligent scheduling are supported, the intelligent level of airport special vehicle scheduling management is improved, and the airport operation efficiency and safety are improved on the whole.
Owner:CHONGQING DIMA IND

Method and device for detecting short-circuit fault of power distribution network

The invention discloses a method and device for detecting a short-circuit fault of a power distribution network, and relates to the technical field of power operation and maintenance, and the method comprises the steps: obtaining a topological structure of a target power distribution network and voltage and current data of each node during a fault period, constructing graph structure data, and adding a fault label; constructing a fault detection model comprising an LSTM network and a multi-layer GCN network, and introducing an adaptive frequency aggregation mechanism into each layer of GCN network; training the fault detection model through graph structure data with fault labels, and performing joint optimization on the fault detection model by utilizing a physical information constraint loss function and a classification loss function; and performing fault detection on the to-be-detected power distribution network through the trained fault detection model. Through joint modeling of time sequence and spatial features, the fault type and position can be accurately identified, the fault response time is effectively shortened, and the safety and stability of power grid operation are improved.
Owner:NANJING UNIV OF POSTS & TELECOMM

Method and device for multi-party joint fine tuning of language model based on data protection

A multi-party joint fine-tuning language model method and device based on data protection, multiple parties comprise a first party holding a target language model and a second party providing computing power, the target language model comprises an embedding table and a plurality of serially arranged network layers, and the first party determines a plurality of confusion layers and a confusion embedding table; at least sending the multi-layer confusion layer to a second party; the confusion embedding table is obtained by performing second confusion on the embedding table, the confusion layer is obtained by performing first confusion on a parameter matrix in the corresponding network layer, and the first confusion mode corresponds to the second confusion mode; the second party obtains a training sample comprising a target confusion word embedding sequence and a label thereof, wherein the training sample is determined based on the text and the confusion embedding table; based on the target confusion word embedding sequence, obtaining a first output result through multiple confusion layers; and based on the difference between the first output result and the tag, adjusting a multi-layer confusion layer to realize a multi-party joint fine tuning model on the premise of protecting model parameters and data privacy.
Owner:ANT BLOCKCHAIN TECHNOLOGY (SHANGHAI) CO LTD

Automatic image matting method based on generative adversarial network

The invention provides an automatic image matting method based on a generative adversarial network, and designs a generative adversarial network framework which comprises a generator and a discriminator. The generator adopts a multi-layer network structure, can receive an original image, and outputs a fine foreground object and transparency thereof through an encoder-decoder network. And the discriminator guides the learning process of the generator by evaluating the authenticity of the generated result, so that the quality of the generated alpha graph is gradually improved. Besides, the invention also designs an SE-ASPP module, which is combined with cavity convolution of different expansion rates, captures information from local to global, enables the model to capture and utilize key features of images at different resolution levels, a dynamic gating attention DGMA module, reduces parameter quantity through depth separable convolution, and improves calculation efficiency through a dynamic gating weight generator. And the accuracy and the meticulous degree of the matting effect are improved. According to the method, the foreground object is accurately extracted from the given input image, the transparency value of each pixel is estimated, and the method is suitable for processing the image with the foreground object with a complex background and rich details.
Owner:CHINA THREE GORGES UNIV

Antenna module and electronic device including same

The disclosure relates to a 5th generation (5G) or 6th generation (6G) communication system for supporting a higher data transfer rate beyond 4th generation (4G) communication such as long-term evolution (LTE). An antenna module is provided. The antenna module includes a communication circuit, an antenna unit comprising multiple antenna elements constituting a subarray, and a network unit disposed beneath the antenna unit in multiple layers, the network unit comprising at least one transmission line configured to be branched to positions of the multiple antenna elements, a via hole extending through the multi-layer, and a stub structure disposed on an area adjacent to the via hole. The open stub structure designed on a first layer forming a ground plane, among the multiple layers, may include a first via pad disposed to be adjacent to the via hole, a first open stub extending from the first via pad in a first direction, and a first slot part configured to surround the first via pad and the first open stub. The short stub structure designed on a second layer different from the first layer having the open stub structure designed thereon may include a second via pad disposed to be adjacent to the via hole, a short stub extending from the second via pad in a second direction perpendicular to the first direction, a transformer extending from the second via pad in a third direction different from the second direction so as to be connected to the at least one transmission line, and a second slot part configured to surround at least a portion of an edge of the second via pad, the short stub, and the transformer.
Owner:SAMSUNG ELECTRONICS CO LTD

Fault diagnosis method and system for networking type energy storage system based on multi-modal characteristics

The invention relates to the technical field of power grids, and provides a multi-modal feature-based fault diagnosis method and a multi-modal feature-based fault diagnosis system for a network construction type energy storage system, which are used for sequentially carrying out normalization, multi-scale convolution, dynamic weighting of an attention mechanism, spatial-temporal feature extraction of a bidirectional long-short-term memory network and weighted pooling of the attention mechanism on acquired multi-modal data. According to the multi-modal-feature-based fault diagnosis method for the network-building type energy storage system, through multi-scale convolution, attention mechanism dynamic weighting, bidirectional long-short-term memory network spatial-temporal feature extraction and attention mechanism weighted pooling, each modal feature can be effectively extracted, the multi-layer network depth extension requirement of deep learning is avoided, and the fault diagnosis efficiency is improved. Model parameter quantity can be effectively reduced, dependence on cloud computing is reduced, and the method can be conveniently deployed on edge equipment; and transient faults and progressive faults in the multi-modal features can be effectively identified, and the fault diagnosis precision is guaranteed.
Owner:JIANGXI QINGHUA TAIHAO SANBO ELECTRICAL MACHINE +4

Mapping service level agreements for backup systems to multiple storage tiers in a clustered network

Embodiments are described for providing backup resources in a multi-tier network, by providing a plurality of different storage devices, each with different operating characteristics and costs for storage of data assets, and organizing the storage devices into a plurality of tiers based on respective operating characteristics, such as based on performance versus cost parameters. Certain Service Level Agreements (SLAs) dictating storage requirements for each of the data assets to a backup program are provided to the backup system, and a mapper maps each SLA to one or more tiers of the plurality of tiers based on the storage requirements of a respective SLA to the operating characteristics of each tier.
Owner:DELL PROD LP

Zero-trust cybersecurity enforcement in operational technology systems

In one embodiment, a method may implement a multi-layer cybersecurity model for a multi-layer distributed computer system which comprises a sensitive data resource, such as a computing environment with an operational technology (OT) layer with multiple zones, an information technology (IT) layer, a DMZ, and a cloud layer. The method can assess a policy based on a zero-trust model for the sensitive data resource. The method can receive one or more requests, at any layer of a multi-layer distributed computing system, to access the sensitive data resource and acquire identity information for a user account specified in the first request. The method can perform a multi-layer multi-factor authentication of the user account using the identity information and the multi-layer cybersecurity model. In response to authenticating the identity information, the method can acquire sensitive access data corresponding to the identity information. The method can determine a sensitive resource access value using the sensitive access data and the zero trust model. In response to determining the sensitive resource access value is above a predetermined threshold, the method can authenticate the user account.
Owner:XAGE SECURITY INC

Fine-grained image classification method based on large model enhancement

The invention discloses a fine-grained image classification method based on large model enhancement, which guides a model to learn a specific judgment mode of a task by directly introducing prior knowledge. A series of image descriptions are generated by performing question and answer interaction with a multi-modal large language model (MLLM). In order to filter illusion information and redundant content existing in description, a dual-guide text feature optimization module is introduced, and the quality of text features is improved through task-guided feature selection and similarity-guided feature pruning. And finally, adopting a multilayer network structure based on an attention mechanism to realize vision-language fusion for final classification prediction.
Owner:BEIJING UNIV OF TECH

Space auditory attention dynamic coupling analysis method and system based on multilayer network

The invention discloses a spatial auditory attention dynamic coupling analysis method and system based on a multilayer network, and the method comprises the following steps: collecting electroencephalogram signals of a plurality of brain regions induced by a spatial auditory attention task in a complex acoustic environment, and carrying out the electroencephalogram data preprocessing; constructing a multi-layer rhythm network and a multi-layer time-varying network; constructing a cross-time-frequency coupling super-connection network based on the multi-layer rhythm network and the multi-layer time-varying network brain configuration, and determining a core network layer of the cross-time-frequency coupling super-connection network by using interlayer correlation and interlayer conditional probability; and carrying out quantitative analysis on the network attributes of the core network layer to obtain a connection mode and a cooperative working mode between the responsible brain regions. According to the method, the four-dimensional hyperconnection network is constructed, frequency and time information is integrated, and a complex interaction mechanism of spatial auditory attention is accurately and quantitatively analyzed.
Owner:BRAIN-COMPUTER INTERACTION & HUMAN-COMPUTER INTEGRATION HAIHE LAB

Node classification clustering method, device and equipment based on semantic information extraction

The invention relates to the technical field of data mining, in particular to a node classification clustering method based on semantic information extraction, which comprises the following steps of: S1, projecting an initial feature vector to a vector space through a linear transformation matrix to obtain a first feature matrix, and obtaining an aggregation adjacency matrix according to a subgraph adjacency matrix; s2, inputting the first feature matrix and the aggregated adjacent matrix into a multilayer graph convolutional network to obtain a second feature matrix; s3, calculating a difference value according to a semantic information matrix generated by the semantic information extraction function and a semantic information vector extracted by the MLP according to the second feature matrix, and judging whether the training of the neural network is completed or not; and S4, inputting the test set into a neural network training model, and classifying and clustering heterogeneous graph nodes. According to the method, the meta-path information is extracted through the number of layers of the multi-layer network, and the influence of meta-path design factors on the downstream task expression effect is reduced. And the mode that the semantic information matrix and the semantic information vector are as close as possible can adapt to various tasks in a zero sample scene.
Owner:SHANGHAI JIAOTONG UNIV

Intelligent updating and optimizing method for three-dimensional form of old block based on rigid-flexible rule driving

The invention discloses an old block three-dimensional form intelligent updating optimization method based on rigid-flexible rule driving. The method comprises the steps of collecting vector data of a target old block and design specifications and standard text data of a city where the target old block is located; establishing a rule map of urban design rigid industry specification requirements; a Mask R-CNN coding technology is used to automatically label vector data of a space structure, a function layout, a road system and a blue-green system of the design, a knowledge graph of a classic city design result rule is formed, and a rule graph oriented by city design flexible professional knowledge is established; establishing multi-layer network association of an old block three-dimensional morphological graph network, a rigid rule graph and a flexible knowledge graph; and outputting the optimized three-dimensional form scheme of the target old block to a space holographic sand table, and finally outputting an optimized three-dimensional form graph network and a visualization scheme of the old block. According to the method, the three-dimensional form of the old block can be optimized based on rigid rule and flexible knowledge hybrid driving.
Owner:SOUTHEAST UNIV

Smoke Detection Method, System, Medium, Electronic Device and Smoke Detection Model

The present invention provides a smoke detection method, system, medium, electronic device and smoke detection model; the smoke detection model is a multi-layer network structure, and the smoke detection model includes: a feature extraction network and a target feature enhancement network; wherein, the feature extraction network is used to receive monitoring data of a target area, and is used to extract features from the monitoring data to obtain multi-scale features; the target feature enhancement network is connected to the feature extraction network, and the target feature enhancement network is used to receive the multi-scale features, and is used to obtain target features based on the multi-scale features, so as to realize smoke detection of the target area based on the target features; in view of the problem of low accuracy of existing smoke detection algorithms, the present invention proposes a novel smoke detection model. Through the design of the target feature enhancement network, the smoke detection model can better focus on the smoke movement area, enhance its recognition ability for small targets, and thus improve the accuracy of smoke detection.
Owner:SHANGHAI POSTS & TELECOMM DESIGNING CONSULTING INST

Drainage pipeline siltation intelligent diagnosis method fusing improved IKAN and Transform network

The invention belongs to the field of drainage pipeline siltation intelligent diagnosis, and particularly discloses a drainage pipeline siltation intelligent diagnosis method fusing an improved IKAN and a Transform network, and the method comprises the steps: collecting a drainage pipeline inlet and outlet flow and flow velocity data sequence, and carrying out the standardization preprocessing; an improved IKAN module based on adaptive learning is constructed; performing local feature extraction by using a one-dimensional convolutional layer; the feature data is mapped to a high-dimensional token space through a Tokenization module; the method comprises the following steps of: constructing a multi-layer Transform network fused with an improved IKAN (Internet Kalman Area Network); and a double-task learning framework is adopted, and regression prediction results of the deposition thickness and the deposition length and a classification result of whether deposition exists are output at the same time. The optimal performance is obtained when the time step is 15 seconds, the RMSE, the MSE and the MAPE reach 0.282, 0.248 and 0.185 respectively when the noise sample proportion is smaller than 50%, and the method has high robustness and prediction accuracy. According to the method, the accuracy and efficiency of drainage pipeline siltation diagnosis are remarkably improved, and a new technical path is provided for intelligent operation and maintenance of an urban drainage pipe network.
Owner:ZHENGZHOU UNIV