29results about How to "Enhance feature expression" patented technology

This invention provides a method and apparatus for correcting sea surface temperature (SST) predictions based on spatiotemporal axial attention. The method includes inputting target SST data into a target SST prediction correction model, comprising a convolutional input layer, an encoder, and a decoder. The convolutional input layer performs feature extraction, temporal encoding, and positional encoding on the target SST data to obtain a target feature vector. The encoder performs attention calculations on the target feature vector in three dimensions to obtain a first target output vector. The decoder outputs the target SST prediction result based on the first target output vector and historical prediction values ​​output by the decoder. Temporal and positional encoding are performed during the model input stage to enhance the representation of temporal and positional information contained in the original data. By performing attention calculations on the target feature vector in the spatiotemporal, longitude, and latitude dimensions respectively by the encoder, effective fusion of features in different dimensions is achieved, further improving feature representation capabilities and increasing the accuracy of SST prediction.

A method and system for super-resolution reconstruction of infrared images based on convolutional neural networks, relating to the field of electronic digital data processing, is disclosed. The method includes: inputting a low-resolution infrared image into a preset convolutional neural network to obtain multi-layer feature maps of the low-resolution infrared image; scaling the feature maps of different layers in the multi-layer feature maps according to a preset ratio and then stitching and fusing them to obtain a fused feature map; generating feature vectors from the fused feature map using global average pooling, and transforming the feature vectors using a fully connected layer to obtain attention weights; weighting the attention weights with the fused feature map to obtain an enhanced feature map; and performing upsampling reconstruction processing on the enhanced feature map using an upsampling structure, introducing a residual connection structure during the upsampling reconstruction process to generate a high-resolution infrared image. Implementing this method generates high-resolution infrared images with more detail.

This application belongs to the fields of artificial intelligence and finance, and relates to a semantic-based text classification method. The method includes inputting a training sample set and a knowledge graph into a knowledge-enhanced language model to obtain knowledge-enhanced text semantic feature vectors; inputting the text semantic feature vectors into a capsule network model to output classification prediction results; calculating the loss value between the predicted classification result and the classification label; adjusting the model parameters based on the loss value to output a model to be validated; validating the model to be validated using a test sample set to obtain a text semantic classification model; and inputting the text to be classified into the text semantic classification model for classification. This application also provides a semantic-based text classification device, computer equipment, and storage medium. Furthermore, this application relates to blockchain technology, allowing the classified text dataset to be stored in the blockchain. This application can effectively identify multi-labeled text, improving the efficiency and accuracy of text classification.

The invention discloses a target tracking algorithm-based sowing seed hole-falling counting method of a sowing machine. The method comprises the following steps of A, acquiring a sowing seed hole-falling video in a sowing process of the sowing machine in real time; b, constructing a sowing grain hole-falling data set based on the hole-falling video; c, constructing a sowing seed detection model for detecting and positioning sowing seeds; d, training to obtain a trained sowing grain detection model; and E, performing real-time target detection on the seeding grain hole-falling video to be subjected to hole-falling counting from a first frame by using the trained seeding grain detection model, and calculating the inter-frame grain distance of the same grain among different frame numbers by combining a target tracking algorithm from a second frame, when the inter-frame grain distance meets a set threshold condition, continuous tracking is carried out, and hole falling event judgment and counting are completed. According to the invention, the sowing grain hole falling condition in the sowing process can be accurately detected in real time, the non-sowing position and the sowing quantity are fed back, and the sowing precision and efficiency are improved.

The application discloses a kind of multi-robot navigation reinforcement learning methods based on buffer Voronoi unit, it is related to multi-agent navigation technical field.Based on the current position information of robot, the corresponding Voronoi unit is constructed, and each boundary of Voronoi unit is translated inwardly by the distance of the physical radius of robot, to generate buffer Voronoi unit;The distance between the current navigation point and each adjacent robot navigation point is calculated;If there is distance less than the physical radius of robot, then the current navigation point is offset angle in counterclockwise direction along the boundary of Voronoi unit, to generate new navigation point;New navigation point is projected on the boundary of buffer Voronoi unit, to obtain the current target navigation point;According to the self-observation information and external observation information of robot, determine the observation space, generate the action of robot based on the observation space and the trained strategy network, and determine the linear velocity and angular velocity of robot in the next iteration round based on action.The method improves the success rate of robot obstacle avoidance.

This paper discloses a method, system, storage medium, and electronic device for predicting flood extent based on SAR imagery assisted by geographic environment data. The method includes the following steps: data preprocessing; extracting features using a dual-branch feature encoder to obtain backscattering features of SAR data at different scales and physical driving features of auxiliary data; using an adaptive cross-gated fusion module to fuse the backscattering features and physical driving features of the encoder part layer by layer to obtain multimodal fusion features; adaptively fusing the fusion features of the encoder part with the upsampling features of the decoder part; upsampling and restoring the image size to obtain the prediction result. This invention enables rapid and accurate prediction of flood extent. This method can provide a reference for real-time flood disaster early warning, emergency command and dispatch, and flood control and disaster reduction decision-making. It also provides a new idea and research direction for the future development of more timely and accurate flood extent prediction technologies.

This invention discloses a 3D target detection method based on sparse dynamic attention and star-shaped interaction. The method obtains basic voxel features from the original LiDAR point cloud through voxelization and sparse convolution, then introduces a sparse dynamic parallel attention module. This module achieves efficient enhancement of global context and channel dimensions through dynamic attention branches and parallel channel interaction branches. A sparse star-shaped interaction module is then used to construct a star-shaped neighborhood interaction structure with a central voxel, completing local geometric modeling and nonlinear feature interaction only on non-empty voxels. Finally, keypoint sampling, RoI pooling, and a detection head output the 3D detection box, category, and confidence score. This invention, through the synergistic complementarity of SDPA and SSB, significantly improves the detection accuracy of long-distance, small-scale, and occluded targets while maintaining linear growth in computational complexity and meeting real-time requirements. It achieves balanced performance optimization across multiple categories, including vehicles, pedestrians, and cyclists, and is suitable for 3D perception scenarios with high precision and real-time requirements, such as autonomous driving.

This application provides a method, apparatus, device, and storage medium for matching and repairing lip movements and speech content in a video, belonging to the field of image processing. It acquires original video data and supplementary text information, performs speech synthesis, generates speech feature parameters, and then generates a lip movement animation sequence synchronized with the speech content. A semantic segmentation model is used for pixel-level recognition of the mouth region, and a physical constraint model is combined to control the tooth region. If the tooth region exceeds the lip contour, dynamic regression adjustment is performed to ensure the naturalness and plausibility of the generated lip movement. Furthermore, the accuracy of tooth region generation is improved through dense cross-layer connections, a feature pyramid structure, specialized skip connections for the tooth region, and a heatmap gating mechanism for key tooth points. A spatial-channel dual attention algorithm is introduced into the decoder to enhance the feature representation of key mouth regions. A tooth region focus loss function is used to optimize the generation results and improve model robustness. A differential physics engine simulates a point mass spring system and adversarial physical constraints to achieve physical plausibility control of key lip points. Finally, the generated lip movement animation is fused with the original video to output the repaired video, significantly improving the consistency and realism of the speech and lip movement in the video.

The application is suitable for the technical field of computer application, and provides a two-dimensional code image feature extraction method and device based on a CNN-MALT hybrid architecture, which comprises the following steps: inputting a target two-dimensional code image into a CNN preprocessing module of a preset lightweight image feature extraction network to generate first structure perception features; inputting the first structure perception features into a MALT encoder of the preset lightweight image feature extraction network, performing feature extraction on the first structure perception features based on a proxy attention mechanism to generate deep features; and inputting the deep features into a feature fusion module of the preset lightweight image feature extraction network to generate target features. Thus, the structure features of the two-dimensional code image are perceived by the CNN preprocessing module, the deep features are generated by the MALT encoder based on the proxy attention mechanism, and the deep features are fused by the feature fusion module, so as to ensure that the calculation complexity is reduced while the two-dimensional code image feature extraction accuracy is improved.

The application discloses a time-frequency cooperative power equipment anomaly detection method, relates to the power equipment detection field, and aims at the problem of lacking representation ability in the prior art. A time-frequency cooperative anomaly detection model is established by constructing a time domain local branch and a frequency domain global branch, and the time-frequency cooperative anomaly detection model is used for anomaly detection on a time sequence of power equipment, the time sequence being a sequence formed by monitoring data of the power equipment arranged in time sequence and used for representing the equipment operation state. The time domain local branch is used for extracting local fluctuation features and short-term dependence features in the time sequence. The frequency domain global branch is used for extracting periodic change features and global frequency features in the time sequence. The method has the advantages that the time domain branch and the frequency domain branch are constructed, local change information and global periodic information in the equipment operation time sequence are cooperatively modeled, the equipment operation state is more fully represented, and the accuracy and stability of anomaly detection are improved.

This invention belongs to the field of cutting process power consumption prediction technology, specifically involving a machine tool processing power consumption prediction method based on image encoding and convolutional neural networks. The method constructs a three-axis coordinate system and defines the machining tilt angle, then performs image encoding on the material removal volume, spindle speed, and feed rate. Next, it constructs a machining power consumption prediction model based on a convolutional neural network. By training the power consumption prediction model using a two-dimensional convolutional neural network, model verification and application of machining power consumption prediction are achieved. Simultaneously, the geometric and machining information of the cutting process is encoded into a three-channel RGB image. Combining the feature extraction capability of the two-dimensional convolutional neural network, a nonlinear mapping model between machining features and power consumption is established. This solves the problems of insufficient feature representation, weak adaptability across working conditions, and insufficient real-time performance of existing methods. It achieves high-precision and efficient prediction of machine tool processing power consumption under complex working conditions, providing reliable support for energy efficiency optimization and process parameter adjustment in the machining process.

This application discloses a data processing method and related apparatus, comprising: for nodes i and j in a first node set, determining the normalized weights of edges with nodes i and j as endpoints based on the number of times node i is referenced by node j and the time decay factor; determining the multi-type information fusion feature vector of node i based on the fusion feature vector of node i, the aggregated feature vectors of each type of neighboring nodes of node i, and the attention weights between node i and its neighboring nodes; determining whether to add a semantic enhancement edge between nodes i and j based on the relationship between the semantic similarity between nodes i and j and a preset semantic similarity threshold; if a semantic enhancement edge is added between nodes i and j, determining the normalized weights of the semantic enhancement edge based on the semantic similarity between nodes i and j, the time-modulated semantic similarity between nodes i and j, and the structural correlation between nodes i and j.

The application discloses a medical image tumor segmentation model based on a TransUNet framework and a construction method and a segmentation method thereof, the construction method comprising constructing a segmentation model based on the TransUNet, wherein an encoder of the segmentation model comprises CNN modules and a self-defined VSS module connected in sequence, the output ends of each convolution block of the CNN modules are input into a decoder of the segmentation model through a jump connection layer, the self-defined VSS module comprises a plurality of novel conversion layers stacked in series based on a Mamba module and a focus linear attention module, the self-defined VSS module performs multi-level feature interaction and global modeling on first encoding features output by the CNN module to obtain second encoding features; and the decoder performs feature fusion and up-sampling on the second encoding features and the output of the jump connection layer to obtain a segmentation image for a sample image. The application can significantly improve the segmentation robustness and precision of breast ultrasound images with low contrast, high noise and fuzzy boundaries.

The application discloses a marine ship detection method based on feature extraction and feature weighting selection fusion. First, remote sensing ship images are collected to construct a data set. Then, a ship detection model is constructed, the remote sensing ship images are input into the model to obtain fusion features, and then the fusion features are input into a detection head of the model for detection to obtain a detection result. Then, the model is trained, the remote sensing ship images are input into the model, and after multiple rounds of training, a final model is obtained. Finally, the remote sensing ship images are input into the trained model to output ship types and positioning information. The application utilizes dynamic learning sampling point offset and modulation factors to enable convolution kernels to change according to ship shapes and enhance feature information. In the feature fusion stage, feature pyramid networks based on hierarchical scales are developed to fully utilize feature maps from different scales and enhance the feature expression capability of the model.

The application discloses a tomato disease and pest identification method based on an improved ControlNeXt lightweight classification model, and comprises the following steps: 1) model structure optimization; 2) lightweight module integration; 3) training strategy optimization; 4) performance verification; and 5) disease and pest identification. The tomato disease and pest identification method solves the outstanding problems in model complexity, calculation efficiency and actual deployment adaptability by improving the YOLOv8s-CLS model, and realizes the balance between accuracy and lightweight.

The application relates to the field of small sample target detection, in particular to a two-stage small sample target detection method based on an optimized CBAM attention mechanism, and comprises the following steps: training a two-stage target detection network Faster-RCNN by using a base class data set to obtain a base class detection model; freezing parameters of a feature extraction backbone network in the base class detection model; optimizing a CBAM attention mechanism module; placing the optimized CBAM attention module in the feature extraction backbone network to construct a detection network, then inputting a new class small sample data set with a small amount of labeled information to fine-tune parameters of a detection head part of the detection network; and inputting a to-be-detected data set into the detection network to obtain a detection result. Compared with the prior art, the application has the advantages of inhibiting the influence of unimportant spatial information, improving the attention degree of important spatial information, enhancing the sensitivity to different scale features, and having strong generalization ability and robustness and the like.

This invention proposes a method for detecting EEG signals of depression based on a multi-scale SELSTMNet model. The method includes the following steps: 1. Preprocessing the acquired multi-channel EEG signals by using bandpass filtering and notch filtering to remove noise, independent component analysis to remove artifacts, and segmenting the preprocessed signals according to fixed time windows; 2. Constructing a multi-scale SELSTMNet model, combining a multi-scale feature extraction module with a bidirectional long short-term memory network to model the temporal features of the EEG signals; 3. Dividing the preprocessed EEG data into training, validation, and test sets, and training the model to optimize detection performance; 4. Inputting test samples into the trained model and outputting the corresponding depression classification results. Through multi-scale feature extraction and adaptive temporal modeling, this invention can effectively improve the classification accuracy of depression EEG signals and has strong robustness and practicality.

The application discloses a kind of based on spectral gradient field guide's bayesian adaptive graph convolution hyperspectral remote sensing image classification method, utilize the spectral information of pixel in hyperspectral remote sensing image and spatial neighborhood relationship to construct initial feature representation;Introduce spectral gradient field to describe local spectral variation amplitude and direction, adaptively adjust the connection relationship between pixel nodes;According to local spectral difference, dynamically expand or shrink neighborhood range, optimize the expression of graph structure in complex heterogeneous region;With Beta distribution, the connection probability between nodes is modeled, the robustness and stability of graph topology structure are improved;For large-scale hyperspectral scene, construct block reasoning mechanism, divide the image into several spatial sub-blocks and complete graph construction and classification reasoning independently, reduce the computational complexity and storage overhead;Pixel-level classification prediction is carried out on the whole image, and high-precision classification result map is generated.The application enhances the expression ability of strong spatial heterogeneity region, and improves the hyperspectral image classification precision and robustness.

The application discloses a wind power prediction method and system based on VMD and entropy condition flexible network, which first acquires wind power data and meteorological characteristic data, obtains intrinsic mode function components through variational mode decomposition and calculates sample entropy; then inputs the sample entropy into an entropy encoder to generate an entropy embedding vector, splices the meteorological characteristic data and the mode components to form time sequence input features; further inputs the time sequence input features and the entropy embedding vector into an entropy condition flexible time convolution network, modulates channel attention, inflation rate mixing coefficients and residual jump coefficients through the entropy embedding vector, and outputs flexible time sequence features; then inputs the flexible time sequence features and the entropy embedding vector into an entropy condition flexible bidirectional long short-term memory network, embeds the entropy embedding vector in the gating calculation to modulate memory strength, and forms bidirectional time sequence representation; finally outputs a prediction value through a full connection layer.

The application relates to the technical field of machine learning, in particular to a label processing model training method and device and a label determination method. The label processing model training method comprises the following steps: obtaining a training sample and a to-be-trained model; performing content feature extraction on the sample multimedia resource based on a resource content model to obtain resource content features; performing label feature extraction on the candidate label based on a label feature extraction layer to obtain label attribute features of the candidate label under multiple feature attributes; performing feature interaction processing on the label attribute features under the multiple feature attributes based on a label feature interaction layer to obtain label interaction features; and training the to-be-trained model based on the labeling association information and the prediction association information to obtain a target label processing model. The application can improve the accuracy of multimedia resource label prediction.

This invention discloses a multi-level domain adaptive intelligent inspection method for railway catenary with cloud-edge collaborative real-time detection, belonging to the field of rail transit technology. The method includes generating a dynamic weight adjustment factor based on a cloud dataset; extracting image features from the cloud dataset and generating distilled features based on the dynamic weight adjustment factor; performing multi-scale compression on the image features of the cloud dataset to obtain distilled compressed features; generating environmental features based on the dynamic weight adjustment factor and distilled features; concatenating the environmental features and distilled compressed features to obtain cloud-based large-scale model features; obtaining weather features based on weather data; performing conditional convolution on edge data and concatenating sparse features to generate sparse features; concatenating the sparse features, weather features, and cloud-based large-scale model features to obtain fused features; and performing data transformation to obtain prediction results. This invention solves the problems of low detection accuracy, poor adaptability, and difficulty in achieving efficient cloud-edge collaborative real-time detection in existing technologies.

A two-stage prototype classification method and system for few-sample image recognition is disclosed. The method includes data acquisition and preprocessing, detection model training, classification model training, and inference stages. In the detection stage, a target detection network based on a modified YOLOv8 algorithm is used to extract candidate boxes from the input image, outputting the candidate boxes and their confidence information. In the classification stage, a dual-branch feature aggregation, learnable temperature-based prototype discrimination, momentum-updated multi-prototype memory, and a joint loss design combining prototype angle loss and supervised contrast loss are introduced, significantly improving fine-grained discrimination capability and few-sample generalization and calibration performance. By introducing candidate box-level super-resolution reconstruction processing in the inference stage, detailed information of low-resolution targets is effectively recovered, further improving classification accuracy. This invention addresses the problem of difficulty in distinguishing subtle differences in single-stage multi-class target detection due to feature sharing and general classification head design in few-sample, fine-grained image instance recognition scenarios.

The application provides a breast cancer tumor target detection and instance segmentation method based on an ultrasound image, a multi-task deep learning model for breast tumor target detection and instance segmentation is constructed, YOLO26 is used as a backbone network, a module is added in the Backbone stage, dynamic balance of low-frequency background information and high-frequency structure information is realized, and the expression ability of the model for weak contrast targets and fuzzy boundary regions is improved, a module is added in the Neck stage, the contribution proportion of different scale features can be adaptively adjusted according to input, so that spatial detail information and deep semantic information are effectively considered, and the detection and segmentation performance of the model for different scale targets is improved. In the training process, the multi-task deep learning model adopts a joint loss function to realize collaborative optimization of end-to-end detection and segmentation tasks, so that the spatial consistency and boundary accuracy of the segmentation result are further improved while the detection accuracy is ensured.

The application particularly relates to a lung embolism segmentation method based on multi-scale context perception, which comprises a multi-level feature extraction layer, a context fusion layer and a mask reconstruction module. The multi-level feature extraction layer adopts Res2Net50 as an encoder backbone and embeds a SimAM attention mechanism to enhance the extraction of small target features; the context fusion layer comprises an ASCF module capable of realizing cross-slice feature fusion and adaptive multi-scale receptive field adjustment; and the mask reconstruction module adopts a double convolution attention layer and integrates a triple attention mechanism to realize cross-dimension feature enhancement and context complementation. The application explicitly models the interlayer continuity of CTPA images through a multi-slice fusion mechanism to enhance the context perception of small targets, realizes the precise matching of feature extraction and embolus size distribution by using an adaptive multi-scale and attention mechanism, and forces the model to balance the attention to large and small emboli by means of a dynamic region optimization loss function, so as to finally realize the end-to-end segmentation from the original CTPA image to the precise segmentation mask.

The application relates to the technical field of intelligent monitoring, and discloses an abnormality identification method for intelligent monitoring of a power distribution room. The method carries out image preprocessing on a power distribution room monitoring video stream to generate a standardized image sequence; an abnormality knowledge base containing features of multiple known abnormality modes is constructed; an abnormality identification process is started based on the standardized image sequence and the abnormality knowledge base, and the image analysis strategy is dynamically adjusted in the process; multi-level feature extraction is carried out on the standardized image sequence according to the adjusted strategy; the extracted multi-level features are matched and analyzed with the known abnormality modes in the abnormality knowledge base; a preliminary abnormality identification conclusion is generated based on the matching analysis result; the preliminary abnormality identification conclusion is verified for credibility; and a final abnormality identification report is output according to the verification result. The method improves the intelligent level and identification accuracy of the safety monitoring of the power distribution room.

This invention discloses a method and system for extracting a unified network traffic representation based on BERT-GGNN, belonging to the field of network traffic recognition technology. The method includes: dividing network traffic data packets into tokens and constructing an input sequence; performing semantic embedding through token embedding, position embedding, and segment embedding to construct token representation units; pre-training a BERT model to extract semantic features of network traffic; designing a graph structure representation based on network traffic packets to generate node features and edge information of the graph; inputting this graph into a gated graph neural network (GGNN) to extract network traffic relationship feature representations; introducing bidirectional mutual attention computation and feature connection operations through a co-attention layer to fuse the network traffic semantic features with the network traffic relationship feature representations, and outputting the fused unified network traffic representation. This invention improves the feature representation capability of network traffic and increases the generalization ability for downstream classification tasks.

This application belongs to the field of computer vision and deep learning, and discloses a method, device, and medium for detecting small targets in subway security X-ray images. The method includes: acquiring X-ray image data to be detected and extracting an initial feature map through an RT-DETR backbone network; processing the initial feature map through a multi-scale multi-head self-attention module, which integrates multi-scale dilated convolution and multi-head self-attention mechanisms to capture global dependencies and local details, generating a first enhanced feature map; processing the first enhanced feature map through a spatial-frequency domain joint optimization enhancement module, which combines lossless spatial feature reconstruction and joint optimization in the spatial and frequency domains to generate a second enhanced feature map; and inputting the second enhanced feature map into a decoder via a neck network to generate the location and category information of the small target. This invention aims to solve the detection problem of small targets in subway security X-ray images caused by aggregation and occlusion, effectively improving the accuracy of small target detection.