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

31results about How to "Improve refactoring effect" patented technology

Power transmission channel hidden danger identification method and system fusing optical and radar remote sensing

The invention belongs to the technical field of power transmission channel hidden danger recognition, and provides a power transmission channel hidden danger recognition method and system fusing optical and radar remote sensing, and the method comprises the steps: constructing a power transmission channel typical hidden danger feature extraction model based on an improved UNet, and carrying out the feature extraction of optical remote sensing data, and obtaining an optical image feature vector; constructing a power transmission channel typical hidden danger feature extraction model based on the improved TransUNet, and performing feature extraction on the radar remote sensing data to obtain a radar image feature vector; performing feature fusion on the optical image feature vector and the radar image feature vector to obtain a fusion feature; the fusion features are sorted and selected based on feature importance, and a classification probability result is obtained in combination with a mixed loss function. According to the method, image reconstruction from low resolution to high resolution is realized through the multi-channel feature map, and the high-resolution feature map is generated, so that more detail information is reserved, and the feature extraction precision is improved.
Owner:STEJT GRID ELEKTRIK PAUER INZHINIRING RISERCH INSTITYUT KO LTD

Insect situation monitoring method and system based on artificial intelligence

The invention discloses an insect condition monitoring method and system based on artificial intelligence. The method comprises the steps of data acquisition, preprocessing, establishment of an insect condition monitoring model and insect condition monitoring. The invention belongs to the field of insect situation monitoring, and particularly relates to an insect situation monitoring method and system based on artificial intelligence. According to the scheme, multi-scale feature extraction is carried out by introducing residual learning, normalization processing is introduced into a remote dependence attention module, similarity is used as a weight, and the influence of noise monitoring data is reduced through nonlinear processing; the reconstruction capability of insect condition monitoring data features is enhanced; therefore, the accuracy of monitoring the insect condition is improved; the comparison loss is introduced to enhance the category distinction degree, an updating example is optimized through feedback of a classification result, a measurement function is designed based on a dynamic example and a weighting mechanism, and a more accurate detection result is provided for insect situation monitoring; and the stability is kept in an insect situation monitoring environment with data dynamic change and noise interference.
Owner:SHANDONG XINGRUI INTERNET OF THINGS TECH CO LTD

Method for realizing completely reversible image steganography based on reversible neural network

The invention discloses a completely reversible image steganography method based on a reversible neural network, and aims to improve the robustness, capacity and safety of image steganography. The method comprises the following steps: 1) obtaining a processed secret image S through N reversible blocks, and adding a carrier image and the processed secret image S; 2) in a steganography process, integrating a simulation attack layer, and obtaining an attacked secret-containing image by the secret-containing image through the simulation attack layer, so as to carry out confrontation optimization on network training; (3) the attacked secret-containing image is restored to be in a non-attacked state through a content enhancement module, a cover image is found in a receiver database, and a processed secret image S is obtained through subtraction of the cover image and the secret-carrying image; 4) inputting the processed secret image S into a reversible neural network to recover a secret image; and 5) the optimization strategy of the whole network is divided into the design of a training strategy and a loss function. Through the innovative architecture of the invention, the complete reversibility of image hiding and reconstruction is successfully realized.
Owner:GUANGXI UNIV

Method and system for monitoring safety state of lead-acid battery of backup power supply of transformer substation

The invention discloses a transformer substation backup power supply lead-acid battery safety state monitoring method and system, belongs to the technical field of transformer substation operation and maintenance, and solves the problems of insufficient sample size, inaccurate feature extraction and low processing efficiency in battery safety state monitoring in the prior art. According to the method, the generative adversarial network algorithm based on robust estimation is adopted to perform data expansion, the neural network is updated by adopting the adaptive fluctuation optimization algorithm to perform feature extraction, and the extracted features are subjected to dimensionality reduction by utilizing the self-encoding neural network based on manifold mapping learning; classifying the dimensionality-reduced data through a support vector machine classification algorithm based on Landau quantization, and using a classification result for monitoring the safety state of the battery; the problems that traditional data acquisition is difficult and samples are insufficient are solved, training errors and model volatility are reduced, data dimensions are reduced, processing efficiency and operation loads are optimized, and classification precision and stability are improved.
Owner:STATE GRID ANHUI ELECTRIC POWER CO LTD ELECTRIC POWER SCI RES INST +1

Non-ideal illumination passive source seismic wave field intelligent reconstruction method based on sparse active source constraint

The invention belongs to the technical field of intelligent seismic exploration, and particularly relates to a sparse active source constrained non-ideal illumination passive source seismic wave field intelligent reconstruction method, so as to solve the problems of false events and coherent noise under the condition of non-ideal distribution of underground passive seismic sources. In order to improve the reconstruction effect of a passive source seismic wave field under a non-ideal illumination condition, the method builds an improved U-Net network, so that the U-Net network can intelligently extract data features and derive an attention mechanism along two independent dimensions of a channel and a space in the network, and multiplies the attention mechanism by an input feature map, so that the reconstruction effect of the passive source seismic wave field is improved. Self-adaptive feature refinement is carried out, so that the purpose of carrying out intelligent reconstruction on passive source data is achieved; by learning the trained deep learning network, the sparse active source seismic record constrains the passive source seismic data prediction network, passive source data reconstruction which shares a measuring line with the active source under the sparse active source condition is realized, and the multi-dimensional deconvolution reconstruction effect and the calculation stability are improved.
Owner:JILIN UNIVERSITY

Single diffraction intensity image reconstruction method and device based on self-supervised deep learning, equipment and storage medium

The invention relates to a single diffraction intensity image reconstruction method and device based on self-supervised learning, equipment and a storage medium. The method comprises the following steps: acquiring a single diffraction measurement diagram, extracting complementary measurement values from the single diffraction measurement diagram by adopting complementary mask downsampling, and constructing a data set for self-supervised training; reconstructing different estimations of the original scene image by using a dual-channel deep neural network based on the complementary measurement values in the training set; constructing a loss function for self-supervised training, minimizing the loss function by using an optimizer, and performing self-supervised training on the deep neural network by using the loss function; and estimating a single diffraction intensity image scene by using the trained deep neural network based on the complementary measurement value in the test set. According to the invention, phases and amplitudes of different types of images can be reconstructed.
Owner:ANHUI UNIV

High-precision ionosphere three-dimensional electron density data reconstruction method and device

The invention discloses a high-precision ionosphere three-dimensional electron density data reconstruction method and device, and the method comprises the steps: building a three-dimensional ionosphere electron density reconstruction model, taking actual observation data as the input data of the three-dimensional ionosphere electron density reconstruction model, and outputting the three-dimensional ionosphere electron density reconstruction data; establishing a TEC decomposition model, and partitioning the three-dimensional ionospheric electron density reconstruction data according to a space weather event to serve as training data of the TEC decomposition model; and after the TEC decomposition model is trained, inputting real-time two-dimensional TEC data and corresponding geological parameters into the TEC decomposition model to obtain high-precision three-dimensional ionized layer electron density reconstruction data. According to the method, subtle changes of the ionized layer can be captured more accurately, detailed three-dimensional electron density distribution is generated, the performance under high resolution is remarkably superior to that of a traditional technology, the reconstruction precision is improved, the adaptability and the real-time performance of the model are improved, and the accuracy and the reliability of data in the TEC decomposition process are ensured.
Owner:NAT SATELLITE METEOROLOGICAL CENT

Tire defect detection method based on improved auto-encoder structure

The invention discloses a tire defect detection method based on an improved auto-encoder structure, an AFPGAN model provided by the invention takes GANormal as a basic model, an NAM attention mechanism is introduced into an encoder part on the basis, and the feature extraction capability of the model is enhanced. A flow alignment module FAM is introduced into a decoder part, so that the reconstruction capability of the model is enhanced. The original global discriminator is replaced by the PatchGan, so that the discrimination capability of the discriminator is enhanced. After the model is constructed, a data set self-made in a laboratory is adopted to train and test the model. Through a series of related experiments, the effectiveness of the AFPGAN in the aspect of improving the tire defect detection precision is verified.
Owner:SHENYANG LIGONG UNIV

Distributed unmanned aerial vehicle towed very low frequency transmitting system and radiation performance evaluation method thereof

ActiveCN122437582Bincrease elasticityImprove refactoring effect
The application discloses a distributed unmanned aerial vehicle (UAV) towed very low frequency (VLF) transmitting system, which is composed of multiple UAV platforms towing antenna units to form a distributed array, and high-precision synchronization and phase control of each node are realized by using enhanced Loran and global positioning system (GPS) double time signals, so that the problems of low survivability of traditional fixed stations and insufficient radiation power of single mobile platform are solved. The application also proposes a radiation performance evaluation method for the distributed VLF transmitting system, random phase disturbance of cable deformation caused by wind load is modeled as a phase disturbance conforming to a specific statistical distribution, a quantitative mapping relationship between the standard deviation of phase error and the compliance probability of array radiation performance is established by calculating the cumulative distribution function of array relative gain. The application can provide design basis for the UAV flight control precision and time synchronization index of the distributed transmitting system, and realize high survivability and megawatt equivalent radiation power in a high dynamic environment.
Owner:WUHAN SHIP COMM RES INST (NO 722 RES INST OF CHINA STATE SHIPBUILDING CORP)

An image super-resolution reconstruction method based on instance space feature modulation and feedback mechanism

The present invention discloses an image super-resolution reconstruction method based on instance space feature modulation and feedback mechanism, which is used to solve the problem of reconstructing low-resolution images into high-resolution images. First, the instance space features of the low-resolution image are extracted by an instance space feature modulator, and the super-resolution reconstruction features of the low-resolution image are characterized by instance space features based on the extracted features. Then, the modulated super-resolution reconstruction features are input into a feedback reconstruction subnet including a projection module for cyclic reconstruction. After multiple reconstruction iterative optimizations, the final super-resolution reconstruction results are obtained. Introducing instance space features into super-resolution reconstruction features and using a recurrent neural network for multiple reconstruction iterative optimizations will not only better reconstruct low-resolution images, but also have significant effects on the texture information of image instances, greatly improving the effect of image reconstruction.
Owner:BEIJING UNIV OF TECH

Data classification method applied to government affair platform

The invention relates to a data classification method applied to a government affair platform, belongs to the technical field of data classification, and solves the problem that data classification of government affair information cannot be efficiently and accurately realized in the prior art. Obtaining to-be-classified government affair data, inputting the to-be-classified government affair data into a target feature extraction model to obtain a target feature vector, and inputting the target feature vector into a target feature dimension reduction model to obtain a target feature dimension reduction vector, and inputting the target feature dimension reduction vector into a target classifier model to obtain a category corresponding to the to-be-classified government affair data. The method is suitable for complex scenes of government affair data, heterogeneous and complex government affair data can be effectively processed, and efficient and accurate data classification is achieved.
Owner:BEIJING JINGHANG COMPUTING & COMM RES INST

Structural damage identification method based on deep reconstruction network and multi-dimensional feature fusion

ActiveCN121476428Benhanced representationImprove refactoring effectProcessing detected response signalBiological modelsCategory recognitionCharacteristic space
The application belongs to the technical field of bridge health monitoring, and particularly relates to a structure damage identification method based on a deep reconstruction network and multi-dimensional feature fusion, which comprises the following steps: obtaining an acceleration signal of a target bridge structure; inputting the acceleration signal into a Res-UNet-AE autoencoder to obtain a reconstructed signal, and calculating a reconstruction error and a signal-to-noise ratio according to the reconstructed signal; inputting the acceleration signal and the reconstructed signal into a perception autoencoder to obtain a perception index; fusing the reconstruction error, the signal-to-noise ratio and the perception index to obtain a three-dimensional damage feature space; and performing unsupervised clustering and identification according to the three-dimensional damage feature space to obtain a damage category identification result of the target bridge. The application can realize accurate differentiation of different working conditions of a structure without relying on any damage label.
Owner:GUANGDONG UNIV OF TECH

Robust adaptive beamforming method based on group sparse reconstruction for radar and communication systems

PendingCN122671991AAccurate estimateImprove refactoring effect
This invention relates to a robust adaptive beamforming method based on group sparse reconstruction for radar and communication systems. The method includes: establishing an array steering vector by combining the geometry of a uniform linear array, and constructing a sparse signal model for practical engineering applications with accompanying amplitude and phase errors; subsequently, establishing a joint optimization model by performing operator transformations on the received signal model to minimize the Frobenius norm of the interference signal and the fitting error of the observed data; based on this, introducing auxiliary variables and reconstructing the original objective function into an unconstrained optimization problem centered on minimizing the augmented Lagrangian function, and using convex constraints to avoid zero solutions, decomposing the optimization problem into three related sub-problems using the alternating direction multiplier method framework and solving them sequentially; finally, reconstructing the interference plus noise covariance matrix using the acquired interference signal and amplitude and phase error parameters, and using this to estimate the optimal weight vector to achieve robust adaptive beamforming. This invention not only accurately estimates array amplitude and phase errors and interference signals, effectively solving the performance degradation problem caused by the limited number of snapshots in practical applications; but also, the group sparse prior effectively utilizes the temporal correlation of signals between snapshots, further improving the reconstruction performance of interference signals.
Owner:NANJING UNIV OF SCI & TECH +1

A defect prediction method and prediction system for solder paste printing process

The present invention discloses a defect prediction method and system for solder paste printing process, which relates to the field of defect detection technology, including: obtaining the solder paste printing process flow of SMT products, using historical solder paste printing defect examples to trace the process, and segmenting the solder paste printing process flow based on the defect process traceability results; obtaining the types of solder paste printing defects that occur frequently in each solder paste printing process flow sub-segment, screening the printing parameters related to the solder paste printing defect type to generate key influencing factors; extracting the key influencing factors corresponding to the normal printing parameter samples to construct a normal printing behavior model; importing the real-time printing parameters into the model for estimation, and predicting the solder paste printing defects according to the deviation between the estimated printing parameters and the real-time printing parameters. The present invention mines the key influencing parameters of defects from SMT production data, constructs a normal printing behavior model to predict solder paste printing defects in advance, and improves the quality of solder paste printing.
Owner:SHENZHEN ZHENGSHI AUTOMATION EQUIP CO LTD

Topological interference power divider, power control method and related equipment

The invention provides a topological interference power divider, a power control method and related equipment. The topological interference power divider comprises a dielectric substrate; the upper copper layer and the lower copper layer are arranged on the surface of the dielectric substrate; the valley photonic crystal structure is composed of triple symmetric apertures of periodic triangular lattices etched on the upper copper layer; the structure comprises A-type unit cells and B-type unit cells which are alternately arranged, the topological waveguide channel is a domain wall formed by the interface of the A-type unit cell and the B-type unit cell, and the channel comprises a plurality of branches which are intersected in a central area to form a coherent interference area; the input port and the output port are respectively arranged at the head end and the tail end of the topological waveguide channel; a matching network is arranged between each port and the channel and is used for realizing conversion between a conventional guided wave mode and a topological edge state; the modulation of the output power distribution ratio, the central working frequency or the transmission bandwidth of the topological interference power divider can be realized by regulating and controlling the topological edge state in the coherent interference region, and the flexibility and the reconstruction capability of power distribution are improved.
Owner:THE HONG KONG POLYTECHNIC UNIV SHENZHEN RES INST

A signal enhancement method and device based on time-slicing compressed sensing three-dimensional imaging radar

This invention discloses a signal enhancement method and apparatus for time-slice compressed sensing 3D imaging radar. First, an M×N dimensional random binary matrix is ​​generated as the measurement matrix for compressed sampling. The target area is illuminated using a laser source, and repeated sampling and modulation are performed to obtain a sampling matrix. The j-th column of the sampling matrix is ​​extracted to generate a compressed sampling vector for the corresponding time slice. The covariance between the compressed sampling vector and each column of the measurement matrix is ​​calculated to obtain the compressed sampling covariance vector. The covariance between each column of the measurement matrix and all columns is calculated to obtain the covariance measurement matrix. Based on a compressed sensing 2D reconstruction algorithm, the 2D image of each time slice is reconstructed using the covariance measurement matrix. The reconstructed 2D images of all time slices are stitched together to form a complete 3D image. This method and apparatus can solve the problems of low reconstruction accuracy and poor image quality in existing compressed sensing 3D imaging technologies under noisy environments.
Owner:AEROSPACE INFORMATION RES INST CAS

Water pollution control sampling data analysis method and device based on machine learning

The present invention provides a method and device for analyzing water pollution control sampling data based on machine learning, which relates to the field of data processing technology. After extracting features from water body data at water quality monitoring sites, the data is subjected to feature dimension reduction and quantum entanglement processing, and then the data is identified using a classifier model to analyze the corresponding control situation of the water body data. Among them, the model for feature extraction uses a neuroevolution fitness function to dynamically adjust the parameters of each layer of its neural network; the classifier model uses an improved deep belief network as the classifier algorithm, and the deep belief network is composed of a multi-layer restricted Boltzmann machine to learn different abstract levels of data. Moreover, the generative adversarial network used to construct a training sample set for water quality monitoring uses an intelligent agent collaboration strategy for parameter update. Based on this, even when faced with large-scale monitoring data, the data can be effectively identified based on the correlation between features to improve classification accuracy.
Owner:SHANDONG ZHENGYUAN YEDA TECH CO LTD

Method, device and equipment for using solid state disk

PendingCN119225651AImprove reliabilityImprove refactoring effectInput/output to record carriersSolid-state driveLogical disk
The invention provides a method, a device and equipment for using a solid state disk, which are used for improving the reliability and the reconfiguration performance of a high-capacity solid state disk in a storage system. According to the method, the SSD is divided into a plurality of logic disks by utilizing the characteristic that the SSD supports a plurality of Namespices, and the logic disks have relatively independent fault domains, so that the overall failure of the high-capacity SSD can be avoided when the OP space is insufficient due to bad blocks or DIE failure, the long-time performance reduction of a storage system caused by the overall failure of the SSD is avoided, and the service life of the storage system is prolonged. The data reliability of the storage system is improved by reducing the data reconstruction time, the service life of the high-capacity SSD is prolonged, and the TCO of a user is improved.
Owner:XINHUASAN INFORMATION TECH CO LTD

Reconfigurable controller, injection molding machine control system and injection molding machine

PendingCN121989419AImplement operation and maintenanceachieve upgradeMachine controlControl cell
The invention discloses a reconfigurable controller, an injection molding machine control system and an injection molding machine, which are applied to the field of injection molding machine control, and the controller comprises a first control unit, a second control unit and two network port modules, the first control unit outputs a first configuration signal when the controller is configured as a master station, and outputs a second configuration signal when the controller is configured as a slave station; according to the first configuration signal, the second control unit configures one network port module to adopt a preset upper communication protocol stack to perform bidirectional communication with the upper computer module, and configures the other network port module to adopt a preset master station communication protocol stack to perform bidirectional communication with the lower-level module; and according to the second configuration signal, the two network port modules are configured to adopt a preset slave station communication protocol stack so as to perform bidirectional communication with the superior module and the subordinate module respectively. According to the scheme, the controller is reliably and flexibly configured to be a master station or slave station role according to actual application requirements, the universality is high, and various architecture requirements such as centralized control and distributed control are supported.
Owner:NINGBO YISHITONG TECH CO LTD

Three-dimensional model reconstruction method and device based on generative adversarial network

The invention provides a three-dimensional model reconstruction method and device based on a generative adversarial network, and relates to the field of three-dimensional geological modeling, and the method comprises the steps: extracting a plurality of conditional profiles from an original three-dimensional model; filling and segmenting each conditional section to obtain a training three-dimensional model set; segmenting the original three-dimensional model to obtain a label three-dimensional model set; training the generative adversarial network through the training three-dimensional model set and the label three-dimensional model set to obtain a trained generative adversarial network; and inputting a to-be-reconstructed three-dimensional model into the trained generative adversarial network to obtain a reconstructed three-dimensional model. According to the generative adversarial network constructed by the invention, the self-attention layer is added into the plurality of networks of the generator, the structure of the generative adversarial network is optimized, and the data space features are extracted through the feature map based on the generative adversarial network of the self-attention layer; the problem that a generated result in a traditional three-dimensional reconstruction method based on multi-point geostatistics contains a discontinuous and unnatural space structure is solved.
Owner:CHINA UNIV OF GEOSCIENCES (WUHAN)

A method for reconstructing ECG signals based on improved approximate message passing

ActiveCN116910451BFast convergenceImprove refactoring effectSensorsDiagnostic recording/measuringEcg signalVector approximation
A method for reconstructing an electrocardiogram signal based on improved approximate message passing includes the following steps: 1) constructing an m*n dimensional sparse observation matrix Φ; 2) using the observation matrix to perform compression measurement on a signal x to obtain an observation vector y of length m; 3) using the prior information of the signal x and likelihood estimation to perform minimum mean square error estimation on the electrocardiogram signal and obtain an estimated value, and then performing denoising processing on the estimated value through a denoiser to obtain a reconstructed electrocardiogram signal, and repeating iterations until convergence. The present invention is based on a vector approximate message passing algorithm, fully utilizes the prior information of the signal, and by using an NLM denoiser, replaces the noise region with a similar structure region in a noisy region, achieving a better denoising effect without losing too much detail, effectively correcting the noise deviation in the electrocardiogram signal in each iteration, improving the convergence speed and reconstruction performance of the algorithm, and significantly superior to the traditional electrocardiogram signal reconstruction method in terms of reconstruction accuracy while ensuring the reconstruction speed.
Owner:SHEN ZHEN WAN ZHI DA XIN XI ZI XUN YOU XIAN GONG SI

Image deblurring method applied to quantum image sensor

ActiveCN117196965BImprove refactoring effectEasy to implementPattern recognitionImaging processing
The present application relates to image sensor, image processing technical field, for putting forward new image reconstruction method, obtains the image of removing motion blur, for this, the technical scheme that the present application adopts is, the image removing motion blur method for quantum image sensor, the block and image of input binary image sequence composition, patch-based optical flow algorithm realizes the alignment of block and image, based on the merging algorithm of incident photon number change with time realizes binary sequence merging, obtains the image of removing motion blur, wherein, the combination of multiple binary image sequences is called "block", the spatial window of pixel is called "patch", the sum of binary sequence in block is called "block and image". The present application is mainly applied to the design and manufacture occasion of quantum image sensor.
Owner:TIANJIN UNIV

Sparse active source constrained non-ideal illumination passive source seismic wave field intelligent reconstruction method

This invention belongs to the field of intelligent seismic exploration technology, specifically relating to an intelligent reconstruction method for passive source seismic wavefields under sparse active source constraints and non-ideal illumination, to address the problems of false phase axes and coherent noise under non-ideal distribution of underground passive sources. To improve the reconstruction effect of passive source seismic wavefields under non-ideal illumination conditions, this method constructs an improved U-Net network, enabling it to intelligently extract data features and derive attention mechanisms along two independent dimensions—channel and space—within the network. The attention mechanism is then multiplied by the input feature map for adaptive feature refinement, achieving intelligent reconstruction of passive source data. Furthermore, a deep learning network, trained through learning, constrains the passive source seismic data prediction network with sparse active source seismic records, enabling the reconstruction of passive source data with co-located active source lines under sparse active source conditions, thus improving the multi-dimensional deconvolution reconstruction effect and computational stability.
Owner:JILIN UNIVERSITY

A communication-efficient privacy-preserving personalized federated learning method

The application discloses a communication-efficient privacy-preserving personalized federated learning method. The application studies a personalized federated learning based on feature fusion mutual learning, which can realize communication-efficient personalized learning by interactive training of shared models, private models and fusion models on the client. Specifically, only the shared model is shared with the global model to reduce communication cost, while the private model can be personalized, and the fusion model can adaptively fuse local knowledge and global knowledge at different stages. Secondly, in order to further reduce the communication cost and enhance the privacy of the gradient, the application designs a privacy protection method based on gradient compression. The method can well realize privacy protection and lightweight compression by constructing a chaotic encryption circulant measurement matrix. In addition, the application also proposes an adaptive iterative hard threshold algorithm based on sparsity to improve flexibility and reconstruction performance.
Owner:NANJING UNIV OF POSTS & TELECOMM

Topology reconstruction and visualization method of ship DC regional power grid based on balance optimizer

The present invention relates to a ship DC regional power grid topology reconstruction and visualization method based on a balanced optimizer. Taking the ship regional power grid as a carrier, the connectivity rule and the shortest path method are used to determine the shortest power supply path from the power supply to the load, so as to determine the corresponding load power supply; determine whether the total power of the load connected to the power supply is overloaded, and if overloaded, unload the load according to the priority level according to the importance of the load; after unloading the load to meet the power constraint, if the corresponding regional power supply still has redundancy to supply power to part of the unloaded load, then use the improved balanced optimizer to optimize and solve with the maximum power supply limit and the minimum number of switch operations as the goal; after unloading the load to meet the power constraint, if each power supply does not meet the power supply to any load, the reconstruction result is directly output. The present invention can resist the impact on the power supply of the ship regional power grid under various emergency conditions, and provide strong power support for offshore ships to meet the actual needs of ships.
Owner:JIMEI UNIV

Video compressed sensing reconstruction method and model based on combination of 3D deformable convolution and Transform

The invention provides a video compressed sensing reconstruction method and model based on combination of 3D deformable convolution and Transform, local features and long-distance correlation features of data can be grasped at the same time, and the quality and efficiency of video reconstruction are improved. Comprising the following steps: segmenting a video into video frames and adjusting the size; dividing a video frame into a key frame and a non-key frame, and performing sampling and reconstruction by using different sampling matrixes and reconstruction matrixes to obtain an initial reconstruction result; the initial reconstruction result is further reconstructed through a CNN independent reconstruction module; reconstructing a further reconstruction result of the key frame through a Transform module to obtain long-distance association between different areas of the key frame; further reconstruction results of all the frames and long-distance associated features obtained by the key frames through a Transform module are spliced in a channel dimension, and then feature fusion is carried out through a convolutional layer; and a result after feature fusion serves as a five-dimensional video signal to be input into a 3D deformable convolution module, and a depth reconstruction result of the video is obtained.
Owner:DALIAN UNIV

Millimeter wave radar based vehicle trajectory reconstruction method and system

This application relates to the field of intelligent transportation data processing technology, and in particular to a vehicle trajectory reconstruction method and system based on millimeter-wave radar. By fusing observation data from upstream and downstream millimeter-wave radars, the spatial blind spots between radars are considered as continuous missing trajectory regions. The missing parts are uniformly characterized in time to achieve standardization of the time dimension, thereby forming a vehicle trajectory reconstruction region. By comprehensively extracting the spatiotemporal interaction features of the target vehicle and surrounding vehicles within the vehicle trajectory reconstruction region, these features are used as input conditional feature sequences and fed into a model with group interaction modeling capabilities to generate the target vehicle's trajectory within the vehicle trajectory reconstruction region, achieving complete vehicle trajectory reconstruction. This aims to solve the problem of how to reconstruct vehicle trajectories in road segments with detection blind spots.
Owner:KUNMING UNIV OF SCI & TECH

Deep learning reconstruction method for sea surface current field based on multi-source sea-air spatio-temporal characteristics

PendingCN122241613Aimplement refactoringImplement joint reconstructionOpen water surveyNeural learning methods
This invention provides a deep learning method for reconstructing sea surface current fields based on multi-source air-sea spatiotemporal features, relating to the field of marine data processing. Specifically, it includes: acquiring multi-year continuous sea surface current velocity data and multi-source environmental feature data for a target sea area; constructing a full-field training sample in a continuous time series manner, using multi-source environmental features from multiple consecutive historical moments as input to candidate deep learning models, and using the full-field data of the eastward and northward current velocity components at a future target time as prediction labels; constructing velocity moduli using the eastward and northward current components; training candidate deep learning models using a joint loss function; evaluating candidate deep learning models, selecting the optimal model, and using the optimal model to output the full-field current velocity results at the target time. The technical solution of this invention overcomes the problem in existing technologies of difficulty in obtaining long-term, large-scale, spatially continuous sea surface current field data.
Owner:SANYA INST OF OCEANOGRAPHY OCEAN UNIV OF CHINA

Bone tissue bending resistance test data analysis method and system

ActiveCN119089151AImprove refactoring effectPrevent excessive filteringBiological modelsBone tissueData reconstruction
According to the bone tissue bending resistance test data analysis method and system provided by the invention, when the bone tissue bending resistance test data is analyzed, the pressure response representation vector of the target bone tissue bending resistance test data is independently extracted; then, according to the pressure response representation vector of the target bone tissue bending resistance test data, the disturbance data of the target bone tissue bending resistance test data and the reconstruction test data of the target bone tissue bending resistance test data at the upper level, the data can be helped to complete reconstruction of more fine information during data reconstruction; and excessive filtering caused in the de-disturbance process is prevented, so that the data reconstruction effect is improved.
Owner:四川骨源生物科技有限公司

A model construction method, a posture estimation method and an object picking device

ActiveCN113034575BImproving the performance of pose detectionImplement adaptive fetchingImage enhancementImage analysisPattern recognitionObject based
The present application relates to a model construction method, a pose estimation method and an object picking device, wherein the model construction method includes: obtaining dense fusion data of the target object; training a preset network model according to the dense fusion data to learn and obtain network weight parameters; configuring a pose estimation model of the target object according to the network weight parameters; wherein the network model includes a backbone node layer and a head node layer, and the head node layer includes a classification layer and a regression layer, the backbone node layer is used to construct high-level semantic information of the target object according to the dense fusion data, the classification layer in the head node layer is used to process high-level semantic information to determine the category and score of the target object, and the regression layer in the head node layer is used to process high-level semantic information to predict the pose and confidence of the target object. The technical solution can improve the ability of the pose estimation model to reconstruct panoramic information of detection scenes with complex backgrounds and strong interference, thereby improving the ability to detect the pose of the target object.
Owner:SHENZHEN HUAHAN WEIYE TECH