107 results about "Network embedding" patented technology

The invention discloses a multi-unmanned aerial vehicle cooperative inspection trajectory control method for optimizing medical area coverage and service efficiency. The method comprises the following steps: firstly, constructing a medical multi-unmanned aerial vehicle auxiliary inspection mobile edge computing system model, defining an unmanned aerial vehicle and mobile user set, and establishing a communication model containing A2G and A2A links, an unmanned aerial vehicle mobile model and an energy consumption model; then taking a joint function of a coverage score, a system throughput and an emergency task completion rate as an optimization target, under energy and communication connectivity constraints, proposing an LT-MADDPG algorithm, adopting a CTDE framework, processing a time sequence state by an actor network integrated with LSTM, fusing global information by a commentator network embedded with Transform through multi-head attention, and finally obtaining an emergency task. And modeling a cooperative relationship between the unmanned aerial vehicles and a medical task priority. Experiments show that the method is superior to a traditional algorithm in the aspects of coverage, service fairness and system throughput, and the medical inspection efficiency and reliability are effectively improved.

The invention discloses a blasting funnel volume solving method based on an improved physical information neural network. The method comprises the following steps: step 1, establishing a mechanical model of blast hole wall blasting load; 2, establishing a blasting physical model in which a columnar cartridge bag is equivalent to a spherical cartridge bag by using a Starfied superposition method; step 3, constructing a blasting funnel volume prediction model based on the wavelet multi-scale synchronous compression transformation enhanced physical information neural network, constructing a solution space of a physical field by using the wavelet multi-scale synchronous compression transformation, and training the physical information neural network in which a blasting funnel physical control equation, an initial condition and a boundary condition are loss functions; and 4, intelligently predicting the volume of the blasting funnel by adopting the trained enhanced physical information neural network. The trained physical information neural network enhances the robustness and generalization ability of the blasting funnel volume prediction model, and provides high-precision theoretical support for blasting design optimization in engineering blasting.

The method and system for data pruning use the novel heuristic of weighting the selection of images by an internal diversity metric, such as the radius of the cluster, allowing more images to be sampled from clusters that are more internally diverse. This heuristic is added to improve the overall diversity of the selected images and to prevent the over-representation of similar images. By sampling more images from clusters that are more internally diverse, the approach is able to better represent the overall distribution of the data, improving the quality of the resulting pruned dataset.

The invention relates to a road defect detection method and system based on improved YOLOv8n, and belongs to the technical field of computer vision. The problems that an existing YOLOv8n model is high in small-scale crack omission ratio in a complex road scene, the precision is insufficient under complex background interference, and irregular defects are not accurately positioned are solved. According to the method, through customized data enhancement, a C2S lightweight feature extraction module is introduced into a backbone network, a BiRatt bidirectional routing attention module is embedded into a neck network, and a Shape-IoU loss function is adopted to construct a YOLOv8-CBS model. According to the method, the detection capability of small cracks, the robustness under a complex background and the positioning precision of irregular defects are remarkably improved, and the automatic high-precision detection requirement of road maintenance is effectively met.

This invention discloses a method and system for inverting mechanical parameters and intelligently analyzing the stability of tunnel surrounding rock, relating to the field of intelligent construction technology for tunnels and underground engineering. The method includes: collecting tunnel monitoring and measurement data and constructing a displacement field observation matrix; constructing a physical information neural network embedded with the geotechnical mechanics control equations to invert the mechanical parameters and stress field of the surrounding rock; automatically calling the finite element kernel through a programming interface and calculating the safety factor of the surrounding rock using the strength reduction method; using evidence theory to fuse multi-source analysis results and output the stability level; and driving online model updates and support optimization through prediction-monitoring comparison verification. This invention achieves the integration of parameter inversion, automated numerical simulation, and closed-loop verification, improving the accuracy, efficiency, and intelligence level of surrounding rock stability analysis.

The invention provides a wind tunnel multi-target aerodynamic optimization method based on machine learning, and belongs to the technical field of wind tunnels, and the method comprises the steps: building a wind tunnel geometric parameterized model through a free deformation method, generating an initial sample through Latin hypercube sampling, and executing computational fluid dynamics simulation to obtain aerodynamic performance parameters; a physically guided deep residual network is constructed to learn a mapping relation between control point coordinates and performance parameters, and the network is embedded into a reference vector-based multi-objective evolutionary optimization algorithm as a fast fitness evaluator. A sequential sampling mechanism is triggered through a crowding degree index, a high-precision simulation sample is added in a Pareto frontier key area to continuously update an agent model, and finally an optimal control point coordinate combination which is uniformly distributed and corresponding aerodynamic performance parameters are output. The technical problem that in the wind tunnel multi-target pneumatic optimization process, the optimization efficiency is low due to the fact that the simulation calculation cost of computational fluid dynamics is high is solved.

A method includes: obtaining network entity data associated with each network entity, from each of one or more network entities; generating, using an encoder model, network embeddings for the one or more network entities, based on the network entity data; converting, using a transformation model, the network embeddings into a predefined number of parameters; inputting the predefined number of parameters to an inference model; obtaining, from the inference model, an output regarding the predefined number of parameters; and determining, based on the output of the inference model, one or more parameters associated with control of a network.

The invention discloses a transformer winding temperature field rapid calculation method based on a mechanism embedded network, and the method specifically comprises the following steps: S1, building a corresponding temperature rise full-order model according to the structure size of a transformer winding, simulating the winding temperature fields under different working conditions, and constructing a snapshot matrix; a POD order reduction method is further combined to obtain a better modal capable of representing the physical system and a corresponding modal coefficient; and S2, according to a flow-heat coupling equation of the oil-immersed transformer winding, selecting important working condition parameters influencing steady-state temperature rise of the winding, and determining a sampling range and a step length based on an actual operation working condition. Taking the determined working condition parameters as input, taking a modal coefficient solved by POD as output, and training an RBF-MLP network embedded in a modal contribution degree mechanism by adopting a training strategy combining sub-network independent training and joint training; s3, for a transformer winding temperature inversion problem under a new working condition, inputting each working condition parameter under the working condition into the trained neural network, so that a corresponding modal coefficient can be quickly mapped; and S4, carrying out linear combination on the predicted modal coefficient and the selected modal, so as to quickly reconstruct the temperature field. According to the method, the nonlinear mapping relation between the working condition parameters and the modal coefficients of the transformer is successfully fitted, and then rapid calculation of the three-dimensional steady-state temperature rise of the transformer winding is achieved.

The invention belongs to the technical field of filtering optimization, and relates to a method for constructing an interactive multi-model Kalman filtering network with unknown prior parameters, which comprises the following steps: S1, constructing a double-branch neural network which comprises a transition probability learning module and an observation covariance learning module; s2, generating training data; s3, sequentially training a transition probability learning module and an observation covariance learning module according to the training data; and S4, embedding the trained dual-branch neural network into an interactive multi-model Kalman filter, and updating the dual-branch neural network to an optimal state estimation sequence through iteration to generate an interactive multi-model Kalman filter network. Priori parameters are autonomously learned through the double-branch neural network composed of the transition probability learning module and the observation covariance learning module, so that manually preset prior parameters are replaced, and the problems of low positioning precision and poor real-time performance of robot autonomous navigation caused by the existing IMM-KF are solved.

The invention discloses a personalized course recommendation method fusing multi-view comparative learning and hierarchical feature weighting. The method comprises the following steps: data preprocessing; carrying out graph convolutional network embedding learning; performing hierarchical feature weighting, performing weighted fusion on embedding of each layer by adopting a layer attention mechanism, fusing information of different layers in a learnable manner, and finally obtaining embedded representation of the learner and the course; the method comprises the following steps: constructing multiple views, randomly injecting disturbance in the embedding of learners and courses, then designing and fusing three denoising factors, generating multiple views of the learners and the courses, and finally optimizing the views by adopting a comparative learning mechanism, so that the same learner or course is kept consistent under different views, and the influence of data noise on a model is relieved. And the robustness and generalization ability of the recommendation system are improved. According to the method, through a combined learning mode of fusing multi-view comparison and hierarchical feature weighting, the model performance can be effectively improved, the interference of data noise on recommendation is relieved, and high-quality personalized course resource recommendation is realized.

The application relates to the field of digital signal processing and artificial intelligence, and particularly discloses a floating-point exponential in-memory parallel comparison method and system for discharge timing decision, which comprises a dynamic logic controller used for generating dynamic matching timing control signals CLK0-CLK6; an exponential maximum value matching network embedded in an SRAM storage array, which comprises a plurality of matching units, and each matching unit corresponds to a row of floating-point exponential operation results; and the matching unit comprises a plurality of bit-by-bit discharge channels; through the bit-by-bit discharge mechanism from high bit to low bit, the parallel comparison of all 64-way results can be completed by only one set of dynamic nodes penetrating the array, the need for laying a plurality of groups of signal lines in the column direction is completely avoided, and the wiring congestion problem is fundamentally solved. Therefore, the operation unit can be embedded in a standard SRAM array at a very high density, and a leading storage density of 1456 Kb / mm2 is obtained.

The invention discloses an improved YOLO-based electrical equipment defect image detection method and related equipment, and the method comprises the steps: inputting an electrical equipment image into a lightweight target detection model, and outputting defect category and position information; the model is improved based on a YOLO11 architecture, and images are processed through a feature extraction network, a fusion network and a detection head in sequence. A residual error enhancement re-parameterization convolution module is embedded into the feature extraction network, multi-scale features are extracted and fused through multiple branches during training, and re-parameterization is performed into a single branch during reasoning; a self-adaptive down-sampling module is adopted to replace a stride convolution down-sampling layer, and a dual-path structure reduces the resolution and retains information at the same time; the detection head is a lightweight scale decoupling detection head, decouples target classification and bounding box regression tasks, and adopts a detail enhancement structure. The invention aims to reduce the model volume and the calculation overhead on the premise of ensuring the detection precision, realize the real-time detection of the airship airborne equipment, construct a fine defect feature retention mechanism, reduce the small target omission ratio and improve the adaptability of the model to a complex dynamic environment.

An adapter increases the resiliency and security of protocols used for communication between embedded systems on a network. The adapter actively protects against reverse engineering and exploitation. The adapter allows embedded systems to actively thwarting cyber-attacks in real-time while allowing the embedded system to continue operating in mission ready status.

The invention relates to a water environment pollution source reasoning and tracing method, system and equipment and a medium. The method comprises the following steps: constructing a pollution source characteristic database containing spectrum fingerprints and spatio-temporal information; performing time sequence enhancement on the mixed spectral signal of the monitoring point to extract stable features; a hydrological model is coupled to dynamically simulate pollutant transport paths and probabilities, and a potential contribution source set with weights is generated; analyzing the mixed signal by adopting a deep unmixing network embedded with space-time constraint, and separating and quantifying known source contribution and unknown pollution components; and finally, generating a visual pollution contribution degree spatial distribution diagram and a quantitative traceability report through geographic information mapping. The method solves the problems that complex mixed signals are difficult to accurately analyze, multi-source contribution is difficult to dynamically quantify and unknown pollution components are difficult to effectively recognize in the prior art, and intelligent and accurate traceability of municipal water environment non-point source pollution is achieved.

The invention discloses a biomolecular interaction prediction method based on multi-modal attention fusion, and belongs to the technical field of artificial intelligence drug discovery. The method comprises the following steps: acquiring multi-modal characteristics of drugs, targets, diseases and genes: sequence structure characteristics, 3D structure characteristics, similarity network characteristics and biological relation network embedding characteristics; constructing a feature fusion prediction model, and performing training; inputting the multi-modal features of the two biological entities into the trained feature fusion prediction model, and outputting the probability of interaction of the two biological entities; the feature fusion prediction model comprises a Transform encoder and an MLP (Markup Language Protocol) network; the multi-modal features are input into a feature fusion prediction model for stacking and then are input into a Transform encoder, the features are processed by using a multi-head self-attention mechanism, and an output result is flattened and subjected to dimension reduction processing to obtain embedded vector representation; and finally, performing element corresponding multiplication on the embedded vectors of the two biological entities, inputting the embedded vectors into an MLP network, and outputting an interaction probability between the two biological entities.

The present application discloses a method for reconstructing the non-uniform stress field of complex components based on boundary segmentation and frequency-domain bridging, which relates to the technical field of stress field reconstruction. The method includes: first, obtaining the geometric model of the target complex component, identifying the degree of non-uniformity of the stress distribution corresponding to the geometric boundary features and dividing it into multiple sub-regions; then, aiming at the spatial frequency characteristics of the stress distribution in each sub-region, constructing a physics-informed neural network embedded with the elastic mechanics mechanism equation, and training to obtain the stress field sub-network model of each sub-region; then, transforming the spatial-domain stress field output by the sub-network to the frequency domain, establishing a frequency-domain dynamic link between sub-regions through a frequency-domain bridging module, and reconstructing the overall non-uniform stress field of the component through inverse transformation; finally, through a variable fidelity cascaded neural operator network, gradually fusing multi-source stress field data to complete the improvement of fidelity. The method of the present application takes into account both the solution efficiency and the multi-scale stress fitting accuracy, and eliminates the boundary discontinuity problem of segmentation and splicing.

This invention discloses a gene regulation inference method guided by topological data analysis and gene network embedding. It combines TDA and GNN to enhance the inference capability of gene regulation networks. By capturing the topological structure of the gene regulation network graph through TDA features, the model's ability to model gene expression is enhanced. The TDA features and GAT embedding representations are effectively integrated through gating fusion. This fusion mechanism enables the model to adaptively adjust node embeddings based on global topological characteristics, which not only improves the accuracy of gene interaction representation but may also enhance the accuracy of regulatory relationship prediction. The traditional GAT architecture is extended through a four-layer graph attention mechanism. Each layer uses residual connections to alleviate the gradient vanishing problem and improve training stability. In addition, independent multilayer perceptron branches are designed for transcription factors and target gene embeddings. This deep architecture can achieve more expressive feature transformations and capture subtle patterns in gene regulation networks.

The invention relates to an intelligent real-time detection method and system for hidden dangers of a distribution line and a medium. The method comprises the following steps: processing multi-modal data collected by an unmanned aerial vehicle; a multi-scale regional attention and dynamic feeling network is designed, a plurality of regional attention modules are combined with local details and global modes of line defect features to carry out feature extraction, information complementation is carried out between high-resolution features and low-resolution features, and classification of defect types is realized; a dynamic receptive field matching module is adopted to optimize a defect bounding box, and a multi-dimensional feature integration module is used to form comprehensive feature representation; a multi-scale regional attention and dynamic feeling network is embedded into unmanned aerial vehicle equipment, and collected data is processed in real time in combination with a calculation unit of the unmanned aerial vehicle, so that a function of detecting hidden dangers while flying is realized. Through the global similarity enhancement denoising technology and the multi-scale feature extraction strategy, the detection precision and adaptability are improved, and the safety and reliability of the distribution line are ensured.

The invention provides a WiFi gait recognition method based on a channel state angular spectrum, and the method comprises the steps: collecting CSI data, and obtaining CSI phase data and a denoised amplitude signal after preprocessing; optimizing the amplitude time sequence by adopting a PCA (Principal Component Analysis) algorithm, and generating a Doppler spectrogram by applying short-time Fourier transform; defining a channel parameter matrix in a three-dimensional space, and describing a change rule of an angle of arrival along with time when a human body moves; for each segment of data, executing an expectation step and a maximization step of the SAGE algorithm to calculate an angle difference after each iteration, and when the angle difference is smaller than a set threshold value, ending the iteration and outputting an estimated AOA parameter matrix; removing outliers by adopting Hample filtering, automatically evaluating data correlation, extracting AOA key components which can reflect walking behaviors most, and generating a CAS spectrogram through short-time Fourier transform; and fusing the Doppler spectrogram and the CAS spectrogram, inputting the fused spectrogram into a deep learning network embedded with a double-space-time attention mechanism, automatically extracting gait features and completing identity recognition.

The application provides a band expansion method and system based on a generative adversarial network, a storage medium and an electronic device, and relates to the technical field of radar signal processing.The application realizes the fusion of multi-band radar signals and generates large-bandwidth radar signals by constructing a GAN network embedded with a lightweight UNet-like network.On the one hand, the lightweight UNet-like feature extraction network automatically extracts features from the original echo signal, which can facilitate the phase matching between sub-bands and avoid the processes of establishing a signal model and phase registration, and compared with a traditional algorithm, the application is simpler and more efficient.On the other hand, the GAN network can significantly improve the correctness of the fused signal through the game between the generator and the discriminator.In addition, the GAN network can expand the bandwidth while denoising, and even in the case of low signal-to-noise ratio of the original signal, the large-bandwidth signal can still be synthesized.

The method and system for data pruning use the novel heuristic of weighting the selection of images by an internal diversity metric, such as the radius of the cluster, allowing more images to be sampled from clusters that are more internally diverse. This heuristic is added to improve the overall diversity of the selected images and to prevent the over-representation of similar images. By sampling more images from clusters that are more internally diverse, the approach is able to better represent the overall distribution of the data, improving the quality of the resulting pruned dataset.

This invention relates to the field of computer vision and structural inspection technology, and discloses an automatic detection method and system for cracks on the surface of precast beams. The method includes: controlling an industrial camera to move longitudinally along the precast beam to acquire images and stitching them together to generate a panoramic image; using hard negative sample contrastive learning to train a lightweight semantic segmentation network embedded with a multi-scale dilated convolution module to suppress background interference such as pores and water stains; performing pixel-level crack extraction through the trained and optimized semantic segmentation network; and calculating the crack length, width, direction, and density after skeletonizing the segmentation results, thus achieving high-efficiency, high-precision, and full-quantity detection of cracks on the surface of precast beams.

The invention discloses an author name disambiguation method based on meta-path random walk network embedding and semantic representation, which comprises the following steps of: analyzing features of papers, dividing the features into semantic features and discrete features, constructing a relationship between the papers by using the discrete features, obtaining a node representation vector corresponding to each paper ID, and obtaining a node representation vector corresponding to each paper ID; solving a paper relation similarity matrix; the method comprises the steps of obtaining semantic representation vectors of papers by utilizing semantic features, then obtaining a paper semantic similarity matrix, adding the two matrixes to obtain a mean value, obtaining a final paper similarity matrix, inputting the matrixes into DBSCAN according to the paper similarity matrix, obtaining a pre-clustering paper set, and aiming at the papers in the pre-clustering paper set, obtaining a final paper similarity matrix. An xgboost algorithm is used to carry out classification training according to existing author names; and redistributing papers in the outlier paper set to clustered authors or new authors by using an xgboost classification method, and integrating the discrete paper set and the pre-clustered paper set to obtain a final result of all papers.

The invention discloses a parallel cut set simplification method based on a fault tree logic embedded neural network, and relates to the field of fault tree analysis. In order to solve the problems that in the prior art, the cut set simplification calculation amount is exponentially increased, the parallelization degree is insufficient, the efficiency is low due to dependence on explicit comparison, and efficient implementation on a GPU architecture is difficult, the invention provides an efficient cut set simplification scheme utilizing fault tree logic and neural network structure fusion. The method comprises the following steps of: vectorizing an initial cut set, grouping according to orders, generating a corresponding subset basic matrix, and generating'order minus one 'subset tensors in batches through an index mask; inputting the subset tensor into a fault tree logic equivalent neural network to execute parallel Boolean judgment, and outputting a result of whether the subset triggers a top event or not; according to judgment result slice statistics, non-minimum cut sets are quickly removed, and a minimum cut set is obtained. The method is suitable for reliability analysis and safety evaluation of large complex systems such as aerospace, nuclear power, rail transit and petrochemical devices.

This invention relates to the field of intelligent building construction technology, specifically disclosing an intelligent generation system for modular scaffolding erection schemes. The system includes an engineering geometric parameter analysis device, a wind field dynamic simulation device, a physical information neural network prediction device, a wind-resistant reinforcement zone generation device, and a real-time meteorological data access device. By integrating computational fluid dynamics with a neural network embedded with physical constraints, based on a three-dimensional building model and real-time meteorological data, it dynamically predicts wind-induced vibration risks and automatically generates wind-resistant reinforcement schemes conforming to the modular rules of scaffolding. By employing the above technical solution, this invention enables high-precision wind vibration early warning and intelligent optimization of scaffolding systems in extreme environments such as super high-rise buildings or cross-sea structures, improving their inherent safety level and construction feasibility.

The application discloses a structural damage identification method based on a gated channel attention denoising network, which comprises the following steps: firstly, generating modal training data containing noise through finite element simulation; then, constructing and training a gated channel attention denoising network with domain self-adaptation; the front end is a U-shaped denoising network embedded with a gated channel attention block, which is used for feature extraction and reconstruction of the modal parameters containing noise to suppress the noise; the rear end is a channel modal attention network, which is used for mapping the denoised modal parameters into damage identification results. In the network training, a compound loss function is adopted, which is fused with a data denoising loss, an identification loss and a domain self-adaptation loss; the domain self-adaptation loss is used for reducing the distribution difference between the simulation data and the measured data through maximum mean difference and correlation alignment, so that the generalization ability and the robustness of the model in the actual noise environment are significantly improved.

According to one embodiment, a method, computer system, and computer program product for capturing higher-dimensional relationships between multimodal data features is provided. The present invention may include retrieving high-dimensional unlabeled multimodal data; processing the high-dimensional unlabeled multimodal data through a trained cumulant-enabled multi-omics neural network (CumiNN) to transform the high-dimensional unlabeled multimodal data into a lower-dimensional embedding; processing the lower-dimensional embedding further through the trained CumiNN to compute a plurality of synthetic representations of higher-order joint cumulants; and processing the plurality of synthetic representations of the higher-order joint cumulants further through the trained CumiNN to predict class labels of the higher-order joint cumulants.

The present application relates to the technical field of process parameter optimization, and provides a forging process parameter optimization method and system based on a deep learning algorithm, which comprises the following steps: obtaining a blank point cloud and other process data, generating a three-dimensional geometric description of the blank, dividing a stress correlation area and a free deformation area, and matching the physical properties of different areas of forging. A deep learning network embedded with forging physical rules is constructed, plastic flow direction and surface heat exchange constraints are introduced in the thermal interaction implicit layer for the two areas, respectively, to avoid physical violation abnormal output that is prone to occur in pure data fitting from the bottom layer. A composite loss composed of parameter reconstruction deviation and physical compliance loss is used for model training, and the final obtained optimization model can output optimal process parameters, which not only reuses historical process experience, but also conforms to the forging physical law, effectively improves the forging forming precision, reduces forming defects, and greatly shortens the process optimization cycle.

The application discloses a drug target interaction prediction method based on a network embedding structure, and belongs to the technical field of biological information and machine learning. The method firstly constructs a drug target bipartite network, and then quantifies network embedding. In the quantification process, an expected violation quantity is calculated by introducing a probability zero model to correct node degree differences, and the local similarity of a node pair is combined as a weighting factor. During prediction, the change in network embedding caused by the addition of a candidate drug target link is calculated, and all candidate interactions are scored and sorted according to the change. The application can effectively utilize the global embedding structure of the network, overcome the bias caused by degree heterogeneity, improve the accuracy and robustness of prediction, and be used for drug reuse and priority sorting of experimental verification.

The application discloses a structural health monitoring video recovery method based on flexible deep learning and belongs to the technical field of video recovery.The method comprises frame sampling, flexible error elimination, frame initial recovery and deep compensation recovery steps.In the frame sampling, a sampling matrix can be optimized in combination with a recovery process through a convolution layer.In the flexible error elimination, a flexible deep network embedded with an adjustable noise level diagram can eliminate various environmental noises.In the frame initial recovery and deep compensation recovery, the spatiotemporal correlation of non-key frames is enhanced by using key frames, so that the lost video information is recovered to the maximum extent.The application realizes joint optimization of sampling and recovery by constructing an interpretable deep learning framework, can restore the video with high fidelity even under the condition of low data retention rate, and significantly reduces the hardware dependence.