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

1917results about How to "Enhance expressive ability" patented technology

Holographic road network and Internet of Vehicles fusion method and device, equipment and storage medium

The invention relates to the technical field of Internet of Vehicles, and discloses a holographic road network and Internet of Vehicles fusion method and device, equipment and a storage medium. The method comprises the steps of obtaining multi-source heterogeneous data collected by a target sensor, and performing adaptive multi-modal preprocessing on the multi-source heterogeneous data; performing space-time alignment and hierarchical structure recombination on the preprocessed multi-source heterogeneous data to obtain multi-source traffic recombination data; extracting multi-scale spatio-temporal features in the multi-source traffic recombination data, and performing multi-level semantic association, deep probability fusion and uncertainty modeling on the multi-source traffic recombination data based on the extracted traffic feature vector set and the preliminary dynamic traffic knowledge representation to obtain traffic perception probability distribution; and a high-precision dynamic semantic map is constructed based on traffic perception probability distribution, and fused multi-resolution map representation is obtained. According to the invention, the fusion of the holographic road network and the Internet of Vehicles multi-source data is realized, and the accuracy of the traffic characteristic data in the fusion result is improved.
Owner:SHENZHEN TUOBIDA TECH CO LTD

Three-dimensional point cloud data segmentation method and system based on multi-scale point features

The invention provides a three-dimensional point cloud data segmentation method and system based on multi-scale point features, and relates to the technical field of point cloud processing, and the method comprises the steps: obtaining original point cloud data, constructing a three-dimensional Hash index table, carrying out the self-adaptive hierarchical division through a local maximum value of a density distribution curve, and obtaining a local maximum value of a density distribution curve; noise point elimination is carried out based on a region density count value and a geometric distribution coefficient, an enhanced feature vector containing a main feature direction, a main curvature value and the like is constructed for non-eliminated points, a local geometric descriptor is constructed by adopting four spherical search regions with increasing radiuses, a three-branch space attention network is input to extract spatial features, and the spatial features are extracted; and fused feature data are obtained through a multi-level geometric feature extraction network and a bidirectional feature propagation network. And obtaining a final segmentation result through segmentation energy function optimization and a region merging strategy.
Owner:YUNTURING ARTIFICIAL INTELLIGENCE TECHNOLOGY (SUZHOU) CO LTD

Power plant intelligent early warning method and system based on big data

The invention provides a power plant intelligent early warning method and system based on big data, and relates to the technical field of power systems, and the method comprises the steps: generating a high-dimensional feature map, generating a multi-modal feature tensor through adaptive chaotic mapping, constructing a feature relation network, generating a time sequence multi-dimensional feature vector, and reconstructing a multi-dimensional state vector based on topological entropy. In combination with a topological data analysis method, carrying out high-dimensional topological space mapping on the multi-dimensional state vector, identifying an operation mode of the power plant equipment, calculating a fuzzy region and a mode abrupt change point of the operation state of the equipment, and obtaining a dynamic evaluation result of the health state of the equipment; a multi-level recurrent neural network is combined, a prediction result is obtained through multi-scale time sequence prediction, uncertainty corresponding to the prediction result is quantitatively solved based on a quantum probability graph model, quantum probability distribution of an early warning signal is generated, a real-time operation strategy of equipment is adjusted, and an intelligent early warning signal of the power plant equipment is generated.
Owner:XINJIANG TBEA LOULAN NEW ENERGY CO LTD

Pediatric abnormal breathing detection method and system based on physiological signals

The invention discloses a pediatric abnormal breathing detection method and system based on a physiological signal, and relates to the technical field of medical information processing, and the method comprises the steps: collecting a multi-modal physiological signal, employing wavelet decomposition and a soft threshold function to eliminate noise, and outputting a preprocessing signal group in combination with morphological opening and closing operation; calculating a time domain feature, a frequency domain feature and a nonlinear feature of the preprocessed signal group, organizing the features into a three-layer pyramid structure, analyzing time sequence similarity by adopting an attention mechanism, and outputting a fusion feature sequence; and carrying out preliminary anomaly detection on the fused feature sequence, carrying out classification based on an age grouping threshold, extracting context feature vectors of windows before and after an abnormal point, and carrying out secondary discrimination to realize accurate identification and graded early warning of the respiratory anomaly. The respiration monitoring system with high reliability, high adaptability and intelligent learning ability is constructed, and comprehensive technical support is provided for early recognition, real-time early warning and intelligent diagnosis of children respiratory system diseases.
Owner:JILIN UNIVERSITY

Power distribution method based on AI artificial intelligence and intelligent power distribution cabinet

The invention relates to the technical field of data processing, and discloses a power distribution method based on AI artificial intelligence and an intelligent power distribution cabinet. The method comprises the following steps: carrying out real-time data acquisition on key nodes of the power distribution system through an intelligent sensor network to obtain original operation data of the power distribution system, and carrying out cleaning and standardization processing on the original operation data to obtain a standardized data set; performing analysis modeling on the standardized data set through multi-level hybrid model training to obtain an AI analysis model of the power distribution system; processing and analyzing the power distribution data collected in real time to obtain a load prediction result and a dynamic balance strategy; performing abnormal mode identification and multi-path reasoning on the system operation parameters to obtain equipment health state evaluation and maintenance suggestions; and based on the equipment health state assessment and maintenance suggestions, performing multi-objective optimization calculation on renewable energy source supply and power consumption demands to obtain an intelligent energy scheduling scheme. According to the invention, the efficiency and accuracy of the power distribution method based on AI artificial intelligence are improved.
Owner:SHENZHEN BONING MECHANICAL & ELECTRICAL ENGINEERING CO LTD

Abdomen multi-organ image segmentation method fusing multi-scale features

The invention provides an abdomen multi-organ image segmentation method fusing multi-scale features, and the method comprises the steps: S1, constructing a space detail fusion module extraction network, which comprises a space attention module, a channel attention module, an up-sampling operation, a down-sampling operation and a feature smoothing operation; s2, designing an encoder, and connecting the encoder with the space detail fusion module; s3, transmitting a plurality of features with different resolutions obtained by the encoder to a decoder through jump connection for information recovery; and S4, arranging the abdominal multi-organ medical image data set to perform model training, and performing multi-organ segmentation prediction on the abdominal multi-organ medical image. According to the method, local and global information is fully utilized, multi-scale feature information is combined, the image feature extraction and expression capability of the model is improved, and the segmentation precision of multiple organs of the abdomen is improved.
Owner:XIHUA UNIV

Structured data modeling analysis method based on Transform

The invention provides a structured data modeling analysis method based on Transform, and relates to the technical field of data analysis, and the method comprises the steps: carrying out the piecewise linear transformation and adaptive quantum coding of numeric features and category features through a double-flow feature encoder, and carrying out the fusion through a gating mechanism to obtain fusion features; inputting the enhanced training sample into a feature extraction network comprising a hierarchical attention module and a self-calibration module, and extracting global feature representation through a feature affinity graph and a causal attention mechanism; and constructing an information bottleneck feature filter to select a key feature subset, performing prediction and reconstruction by adopting a double-branch network, and analyzing the feature contribution degree by using a structured gradient method. According to the method, heterogeneous features can be effectively processed, the model performance is improved, and meanwhile an interpretable feature importance evaluation mechanism is provided.
Owner:北京科杰科技有限公司

Lightweight semantic segmentation network and method for power grid inspection

The invention discloses a lightweight semantic segmentation network and method for power grid inspection, and the method comprises the steps: employing an encoder-decoder architecture, inputting original data into a lightweight MobileNet v2 backbone network for feature extraction at an encoder part, inputting an obtained feature map into a lightweight large-scale ASPP module, and carrying out the feature extraction; further performing multi-scale feature extraction on the high-dimensional feature map; and in the decoder part, high-dimensional features and low-dimensional features obtained by the backbone network are respectively input into a cross attention wavelet fusion module, after an obtained feature map is fused with the output of a decoder, the feature map is recovered to the size of original data through down-sampling operation by a full-dimensional dynamic convolution post-processing module, and a final prediction mask is obtained. According to the invention, by optimizing a coding and decoding structure, the receptive field of the model and the modeling capability of a narrow and long target are improved, the balance between the precision and the complexity can be effectively realized, and the method is suitable for an unmanned aerial vehicle inspection system with limited resources.
Owner:SOUTHWEST JIAOTONG UNIV

Multi-modal document structured processing and knowledge extraction method based on large language model

The invention discloses a multi-modal document structured processing and knowledge extraction method based on a large language model. The method comprises the following steps: S1, receiving an input multi-modal document; s2, performing preprocessing on the text data in the multi-mode document; s3, performing feature extraction on non-text data in the multi-mode document; s4, performing multi-modal data fusion on the preprocessed text data and the non-text data after feature extraction; s5, performing deep semantic analysis on the fused multi-modal data through a pre-trained improved BERT model, wherein the deep semantic analysis comprises key entity recognition, relation extraction and event detection; s6, based on a deep semantic analysis result, automatically constructing a knowledge graph by using the extracted information; and S7, outputting the data of the knowledge graph in a format for analysis or application. According to the method and the system, structured processing and knowledge extraction of unstructured and multi-modal documents are realized.
Owner:GUANGXI POLICE ACAD

Bill identification method and device based on machine vision

The invention relates to the technical field of machine vision, and discloses a bill recognition method and device based on machine vision, and the method comprises the steps: carrying out the preprocessing and random shielding processing of an input bill image, and obtaining a preprocessed bill image; performing multi-scale feature extraction on the preprocessed bill image to obtain a multi-scale feature map set; performing progressive attention feature optimization based on the multi-scale feature map set to obtain an optimized feature map; performing semantic alignment local feature analysis on the optimized feature map to obtain a semantic alignment feature map; performing multi-label collaborative learning based on the semantic alignment feature map to obtain a multi-label classification result; according to the method, damaged and deformed bills can be effectively processed, multi-scale and multi-mode feature extraction and fusion are realized, and the method has cross-domain migration capability so as to adapt to bills of different types and formats.
Owner:YOUDINGTE TECH CO LTD

Network fault adaptive detection system based on machine learning

The invention discloses a network fault adaptive detection system based on machine learning, which relates to the technical field of network security and comprises a data acquisition module, a feature extraction and selection module, a model training and updating module, a fault detection module, a fault positioning and diagnosis module and an adaptive optimization module. According to the network fault adaptive detection system based on machine learning, by generating new features, the expression ability of a feature space is significantly enhanced, and the detection precision of a machine learning model is improved; the deep learning model based on the causal relationship is combined with the graph neural network and time sequence analysis, so that the complex causal relationship in the network is effectively processed, and the fault diagnosis is more accurate; through the combination of the multi-objective evolutionary algorithm and the fuzzy logic control algorithm, the network optimization strategy is more flexible and efficient, the network performance is improved, the weight of the optimization objective can be dynamically adjusted according to the actual demand, and the performance of the system in a complex network environment is remarkably improved.
Owner:SHANDONG FENGXUN ELECTRONICS CO LTD

Aviation converter fault detection method based on information fusion algorithm

The invention discloses an aviation converter fault detection method based on an information fusion algorithm, and the method comprises the steps: collecting the operation data of an aviation converter, and constructing a data set; performing time information extraction and space information extraction on the data in the data set, and performing feature fusion on time features and space features based on a variational auto-encoder to obtain spatio-temporal data; constructing a Bayesian deep learning model, and training and optimizing the Bayesian deep learning model; inputting the spatio-temporal data into the trained and optimized Bayesian deep learning model for processing, outputting a numerical value representing a fault occurrence probability, and taking a variance based on the probability numerical value as uncertainty estimation; presetting a probability threshold, and when the output probability is greater than the threshold, determining that the converter has a fault; otherwise, judging that the operation state is normal; a more accurate and reliable diagnosis result is provided for fault detection, and the method has high adaptability and robustness in practical application.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Automatic image recognition garbage classification whole process implementation method based on AI calculation

The invention relates to the technical field of image recognition, and discloses an automatic image recognition garbage classification whole process implementation method based on AI calculation. The method comprises the following steps: carrying out multi-modal data acquisition on to-be-identified garbage to obtain an image data matrix, a weight data vector and a spectral data matrix; performing semantic feature and detail feature extraction on the image data matrix to obtain a fusion feature map; performing channel attention and space attention mechanism enhancement to obtain an enhanced feature map; overlapping degree calculation and region merging are carried out to obtain garbage positioning data; calculating probability density distribution data of garbage category nodes based on the garbage positioning data, the weight data vector and the spectral data matrix; according to the method, the problems that the target size is small and the features are not obvious are solved, and the reliability of the classification result is ensured.
Owner:SHENZHEN LVYUAN ZHIGU TECH ENVIRONMENT CO LTD

Multi-granularity extraction and enhancement method, device and equipment for multi-source heterogeneous data

The invention relates to the technical field of data processing, and discloses a multi-granularity extraction and enhancement method, device and equipment for multi-source heterogeneous data. The method comprises the following steps: performing multi-level feature extraction on a multi-modal data set and original feature parameters to obtain a multi-modal feature set; performing correlation analysis on the multi-modal feature set to obtain a feature correlation matrix and optimized feature representation; performing cross-modal knowledge migration processing on the feature incidence matrix and the optimized feature representation to obtain migration feature parameters; performing dynamic fusion processing on the migration feature parameters to obtain target fusion features; and performing multi-task segmentation processing according to the target fusion features to obtain a plurality of sub-task sequences, performing time sequence enhancement and multi-task fusion analysis on each sub-task sequence to obtain target extraction data, and performing visual display on the target extraction data. According to the method and the device, the efficiency and the accuracy of multi-granularity extraction and enhancement for multi-source heterogeneous data are improved.
Owner:ZHENGZHOU DIGITAL INTELLIGENCE TECH RES INST CO LTD +1

Voice recognition method and device for audio and video progressive fusion training in noise environment

The invention discloses an audio and video identification method and device for multi-mode progressive fusion training in a noise environment, and relates to the technical field of audio and video multi-mode. The method comprises the following steps: firstly, constructing an audio and video joint encoder model by using multi-modal data, and carrying out iterative unsupervised pre-training; a multi-scale feature extraction module and a decoder are added to construct an audio and video recognition model; and finally, carrying out multi-stage progressive fusion training on the audio and video recognition model, specifically comprising two steps: a modal course learning stage and a noise course learning stage, and realizing guided learning between modals. According to the method, cross-modal feature joint mapping is realized by using audio and visual modal information, so that the model can still keep efficient voice instruction recognition performance in a complex noise environment.
Owner:SICHUAN UNIV

Three-dimensional scene re-coloring optimization method based on Gaussian splashing and deep learning

The invention discloses a three-dimensional scene re-coloring optimization method based on Gaussian splashing and deep learning, and the method comprises the following steps: S1, constructing a multi-view data set of a given scene, and generating an initial point cloud; s2, based on the initial point cloud, extracting a representative color set from all input pixels, generating a palette and taking the palette as initial setting; s3, rendering a multi-view result picture by using the palette and a Gaussian splash algorithm, calculating a loss function, and generating an optimized Gaussian radiation field through back propagation optimization parameters; and S4, re-rendering the scene and generating a re-coloring result based on the optimized Gaussian radiation field and the palette color modified by the user. According to the method, the Gaussian splash algorithm and the deep learning technology are combined, efficient re-coloring optimization of the three-dimensional scene is achieved, and the method has the advantages of being visual in editing, accurate in illumination expression and real in rendering.
Owner:UNIV OF SCI & TECH OF CHINA

Radiology report generation method based on semantic alignment

The invention discloses a radiology report generation method based on semantic alignment, and belongs to the technical field of radiology report generation. The radiology report generation network constructed by the invention comprises a multi-scale feature extraction module, a cross-modal semantic alignment module and a Transform report generation module which are connected in sequence; the multi-scale feature extraction module comprises a convolutional neural network and a multi-scale local sparse attention module which are connected in sequence; the cross-modal semantic alignment module comprises an embedded layer, a multi-head attention module and a gating fusion module, wherein the multi-head attention module and the gating fusion module are connected with the embedded layer. The input end of the multi-head attention module and the input end of the gating fusion module are connected with the output end of the multi-scale local sparse attention module. The predicted radiology report generated by the radiology report generation method is good in quality.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)

Lightweight underwater image enhancement method based on adaptive feature fusion

The invention provides a lightweight underwater image enhancement method based on adaptive feature fusion, and the method comprises the steps: decomposing an underwater image enhancement task into a strong prior enhancement task and a fine-grained enhancement task through employing a lightweight underwater image enhancement network based on adaptive feature fusion, so as to make full use of the multi-scale information in an image; the strong prior enhancement task is used for extracting global and low-layer features of the image; the fine-grained enhancement task is used for improving local details and color recovery of the image so as to improve the visual quality; the lightweight underwater image enhancement network comprises a multi-scale feature aggregation module and a global channel attention module, the multi-scale feature aggregation module is composed of an adaptive feature fusion module and a segmented convolution feed-forward network, and the lightweight underwater image enhancement network is used for combining global and local information of features and adaptively adjusting importance of each channel through information association between channels.
Owner:MINJIANG UNIVERSITY

Editable condition printing image generation method

The invention discloses an editable condition printing image generation method, and belongs to the field of image generation. The method comprises the following steps: constructing a printing image generation model, and training the model to obtain a generation model with editable conditions; and generating a printing design image meeting the condition requirements by using the model. According to the method, different advanced features of each element of the printed plane image are extracted through downsampling, element and style information in the printed plane image is captured through multi-scale feature extraction and information exchange, then hidden space vectors corresponding to different printed plane image features are analyzed, fusion of specific styles is achieved in the hidden space, and the image quality is improved. And the decoding of the printing design image is realized through the decoder, the decoupling of the element information is realized, the personalized design and diversified requirements can be met, and the expansibility is realized.
Owner:JIANGNAN UNIV

Rotary machine fault diagnosis method based on residual contraction convolution and attention mechanism

The invention discloses a rotary machine fault diagnosis method based on residual contraction convolution and an attention mechanism, and belongs to the field of rotary machine fault diagnosis. According to the method, firstly, a soft threshold filtering activation function is designed based on Meta-ACON, a soft threshold filtering module is developed around the activation function, and the module can adaptively learn a filtering threshold and a forward dynamic weighting coefficient, so that irrelevant features are effectively filtered, and the expression ability of effective features is enhanced. And then, in combination with multi-channel and multi-scale residual convolution, a multi-channel residual shrinkage convolution unit is constructed to realize multi-scale and multi-channel effective feature extraction. Besides, according to the method, a high-order statistical modeling idea is utilized, a GSoP attention mechanism is introduced behind a multi-channel residual shrinkage convolution unit, and the ability of extracting discriminative features is enhanced through second-order statistical information of a high-level channel feature map. Test results show that the method has good fault identification capability and generalization capability.
Owner:LUOYANG INST OF SCI & TECH

Intelligent temperature control lead-free tin bar production method and device

The invention relates to the technical field of intelligent temperature control, and discloses an intelligent temperature control lead-free tin bar production method and device.The method comprises the steps that data of a plurality of sensors of a production line are collected and preprocessed, and a time sequence data set is obtained; carrying out attention-guided position-sensitive multiple interpolation to obtain a target data set; constructing and training based on the target data set to obtain an anomaly recognition model; according to normal production data screened by the anomaly recognition model, analysis is carried out based on an implicit subspace recognition regression neural network of orthogonal basis decomposition and reconstruction, and a production process parameter model is obtained; based on the production process parameter model, a multi-task feature fusion framework is used for parameter optimization, target production process parameters are obtained, the problem of data missing in the production process can be effectively solved, abnormal conditions can be accurately recognized, self-adaptive process parameter optimization can be conducted according to the characteristics of different production lines or batches, and the production process parameter optimization efficiency is improved. Therefore, the production quality and efficiency of the lead-free tin bar are improved.
Owner:深圳市朝日电子材料有限公司

Medical image enhancement processing method and system based on deep learning

The invention relates to the technical field of medical image processing, in particular to a medical image enhancement processing method and system based on deep learning, and the method comprises the steps: selecting an image enhancement model according to whether the number of samples needs to be expanded or not; if the number of samples needs to be expanded, performing image enhancement by adopting a generative adversarial network, otherwise, performing image enhancement by adopting an auto-encoder; a federal learning architecture is adopted to train a model, and the model is trained on a plurality of scattered devices or servers. The generative adversarial network is used to generate diversified medical image samples, and the diversity of the samples is improved. And the auto-encoder extracts key features and generates new samples, so that the diversity of data is increased. Through a federal learning architecture, by using dispersed data sources, the diversity of training samples of the model is enhanced, and meanwhile, data privacy is protected. And the diversity of samples is effectively increased, so that the generalization ability of the model is improved, and the method has higher robustness and accuracy in practical application.
Owner:费璟昊

Multi-aircraft 4D trajectory prediction method based on graph attention hybrid neural network

The invention discloses a multi-aircraft 4D trajectory prediction method based on a graph attention hybrid neural network, and belongs to the technical field of aviation. Historical trajectory implicit information of different aircrafts in an airspace is extracted by utilizing Transform and a long-short-term memory network, the aircrafts in the airspace are regarded as nodes, an aircraft connection network graph is constructed, and modeling is performed on the aircraft implicit information and the aircraft connection network graph through a graph attention network so as to capture interaction information between the aircrafts. The graph attention network integrates the track implicit information of all aircrafts in the airspace and shares and updates the track implicit information, finally decodes the track implicit feature information of the aircrafts through two decoders based on the long and short term memory network, fuses the output of the two decoders, and outputs a prediction track through a full connection layer. Compared with a method which does not consider aircraft space interaction information, the accuracy of flight trajectory prediction is improved, and an accurate trajectory prediction technology provides support for a subsequent risk perception technology and a conflict resolution technology.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Self-supervised learning and multi-mode biomedical signal processing method, system and terminal

The invention discloses a self-supervised learning and multi-modal biomedical signal processing method, system and terminal, and belongs to the technical field of biomedical engineering and information, and the method comprises the steps: employing an unsupervised learning auto-encoder to extract the feature representation of multi-modal data; and taking the feature representation of the source domain data as input, taking the feature representation of the target domain data as output, and training the large language model based on the Transform architecture based on maximum likelihood estimation. According to the method, relevance and common features among multi-modal data are learned through an auto-encoder, and feature representation extracted by the auto-encoder is applied to pre-training of a large language model, so that the large language model learns more abstract and advanced feature representation, and the processing capacity and generalization performance of the multi-modal data are improved; meanwhile, due to the fact that an unsupervised learning method is adopted, a large amount of unmarked data can be used for pre-training the large language model, and therefore data resources can be better utilized.
Owner:GUILIN UNIV OF AEROSPACE TECH

Optical remote sensing image change detection method and system based on change perception and semantic guidance, storage medium and electronic equipment

The invention provides an optical remote sensing image change detection method and system based on change perception and semantic guidance, a storage medium and electronic equipment, and the method comprises the following steps: firstly, carrying out the preprocessing of a dual-tense image, and carrying out the labeling of a change region, and generating a change label graph; and cutting the image and the label into small samples, and inputting the small samples as training data into the CASGNet model. Multi-scale features are extracted through an encoder, change perception is carried out through a space-time difference fusion module, cross-time change information is effectively captured, pseudo change noise is restrained, and reliable multi-scale difference features are obtained. Thirdly, the semantic guiding module decodes the multi-scale difference features, semantic masks are generated through the semantic aggregation module, fusion of the multi-scale features is guided, interference is eliminated, and edge details of a change area are complemented; and finally, in a detection stage, the preprocessed sample to be detected is input into the model, a complete and accurate change detection result is obtained, and the method is suitable for a detection task of a complex scene and a high-resolution image.
Owner:HENAN UNIVERSITY

Multi-scale feature fusion unmanned aerial vehicle target detection method for bad weather

The invention discloses a multi-scale feature fusion unmanned aerial vehicle target detection method for bad weather, and the method comprises the steps: collecting multi-modal data, and inputting the multi-modal data into a target detection model; the target detection model comprises a first modal feature extraction network, a second modal feature extraction network, a multi-scale pyramid feature fusion network, a cross-modal fusion network and a target detection head network; performing feature extraction on the visible light image data by using a first modal feature extraction fusion network to obtain visible light multi-scale features; performing feature extraction on the thermal infrared image data by using a second modal feature extraction fusion network to obtain thermal infrared multi-scale features; processing the visible light multi-scale features and the thermal infrared multi-scale features by using a multi-scale pyramid feature fusion network to obtain a visible light feature map and a thermal infrared feature map; and fusing the visible light feature map and the thermal infrared feature map by using a cross-modal fusion network to obtain a fused feature map for target detection.
Owner:江淮前沿技术协同创新中心

Remote sensing target detection method based on convolutional neural network

The invention discloses a remote sensing target detection method based on a convolutional neural network, and the method comprises the steps: 1, constructing a full-scale enhanced alignment detection network model OSEADet comprising Backbone, Neck and Head, the Neck is an enhanced feature pyramid network EFPN, adding a P2 detection layer on the PAFPN network, enabling a feature map P2 to pass through SPDConv, outputting a feature map rich in small target information, fusing the feature map with a feature map P3, and obtaining a feature map P3; carrying out feature integration by using a CSP thought and a CSPF module; the Head comprises three dynamic task alignment sharing detection heads DSTA, the DSTA comprises a bounding box regression branch and a classification branch which are respectively used for predicting a target position and a target category, the tasks of the three DSTA are combined through group convolution, task interaction features are learned from a plurality of convolution layers, joint features are obtained, interaction among the tasks is increased, and the tasks are dynamically adjusted and aligned through a TaskDecomposition layer; 2, carrying out training and verification on the OSEADet; and 3, the trained OSEADet is used for predicting the position and category of the remote sensing target, so that the detection precision is high, and the remote sensing target can be detected in real time.
Owner:XIJING UNIV

Grid topology fault positioning system based on graph neural network

The invention relates to the technical field of neural networks, and further relates to a power grid topology fault positioning system based on a graph neural network. The system comprises a power grid topology feature extraction unit used for regarding a power grid as a graph network and carrying out real-time data acquisition on each node of the power grid, and each element in a feature matrix represents the electrical characteristics of a certain node of the power grid at a certain time; the multi-layer graph neural network model unit is used for taking the feature matrix as the input of a first layer as a feature extraction result; the fault identification and positioning unit is used for calculating fault probability distribution based on the feature extraction result; and calculating the credibility of the obtained fault position. According to the method, the modeling capability of the system on the complex power grid topology is improved, the real-time performance and robustness of fault detection are enhanced, and accurate positioning of the fault area and position is realized.
Owner:TECH COLLEGE BRANCH OF STATE GRID CORP OF CHINA +2

Unsupervised multi-modal emotion recognition method based on attention aggregation and cross-modal graph fusion

The invention discloses an attention aggregation and cross-modal graph fused unsupervised multi-modal emotion recognition method. The method specifically comprises the steps of 1, acquiring audio modal features, image modal features and text modal features of a video sample; step 2, acquiring an audio vector, an image vector and a text vector corresponding to the audio modal feature, the image modal feature and the text modal feature; step 3, constructing an unsupervised multi-modal emotion recognition model; 4, inputting the audio vector, the image vector and the text vector into an unsupervised multi-modal emotion recognition model for training, and obtaining the optimal output of the model as a final feature vector for prediction and classification; and 5, performing emotion recognition by using the trained unsupervised multi-modal emotion recognition model. The problem that in the prior art, the long-distance spatial dependency relationship of a tree or graph network cannot be processed, the syntactic dependency relationship in sentences cannot be captured, and consequently the model cannot make full use of multi-modal data is solved.
Owner:XIAN UNIV OF TECH

Barley crop planting recommendation method

The invention provides a barley crop planting recommendation method, and belongs to the technical field of intelligent agriculture. The method comprises the following steps: firstly, acquiring historical data including soil property data, climate condition data and barley growth condition data; then preprocessing the data set to obtain standard input data during model training; and constructing a barley crop planting intelligent recommendation model, training and deploying the model, and predicting the appropriate planting density of the to-be-tested wheat field based on the obtained historical data of the to-be-tested wheat field. According to the method, the diversity and accuracy of the data are ensured by integrating the three types of data of the soil property, the climate condition and the historical crop performance. The designed multi-modal feature extraction effectively captures and retains key features in each modal data, and a novel multi-modal feature fusion mechanism realizes effective fusion of multi-modal features and design of a prediction output module, so that the prediction accuracy is improved, and the adaptability of the model under different region and environment conditions is enhanced.
Owner:EASTERN GANSU UNIVERSITY