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

37results about How to "Solve the degradation problem" patented technology

Combined tremella aurantialba strain ZWY-G1 / PNF11

The invention relates to a combined tremella aurantialba strain ZWY-G1 / PNF11, and belongs to the field of edible mushroom breeding. The strain is a sporocarp obtained by effectively combining a tremella aurantialba strain (PNF11) in a high-altitude cold area and a stereum hirsutum strain (ZWY-G1) in a low-altitude tropical rainforest area. Wherein asexual spores of the tremella aurantialba strain PNF11 in the combined strain are milky white and yeast-shaped, and the yeast-shaped edge is in a radial hypha form; hyphae of the stereum hirsutum ZWY-G1 are thick and dense, aerial hyphae are many, and the hyphae are orange after liquid fermentation; in the industrial cultivation process, the growth period of the combined tremella aurantialba strain ZWY-G1 / PNF11 is 36-40 days, the sporocarp color is orange, the longitudinal section is light flesh color, the fruiting rate is 100%, the yield is 98%, the biological conversion rate is 85%, and the combined tremella aurantialba strain has high consistency, stability and excellent agronomic character indexes and is suitable for industrial and facility annual cultivation and liquid fermentation process cultivation.
Owner:YUNNAN AGRICULTURAL UNIVERSITY

Function connection network analysis method based on group sparse attention converter

The invention discloses a functional connection network analysis method based on a group sparse attention converter. The method mainly comprises the following steps: preprocessing brain functional magnetic resonance imaging data output by a functional magnetic resonance instrument; dividing the preprocessed brain function image into a plurality of brain regions according to a standard; based on Pearson correlation and group sparse characteristics, calculating a dependency relationship between brain regions, and respectively constructing an initialized brain network and a guidance network; taking the initialized brain network as the input of a group sparse attention converter, and carrying out learning under the assistance of a guidance network so as to learn a brain network with a group similar topological structure; and subsequent classification is carried out. The method integrates priori knowledge of a population level, allows more comprehensive modeling across multiple brain networks, is designed for end-to-end adaptive learning, dynamically updates the brain networks through back propagation, and significantly improves the construction and analysis performance of the brain networks.
Owner:LIAOCHENG UNIV +1

Method for preparing polymerized calcium-magnesium fertilizer from yellow phosphorus slag

The invention belongs to the technical field of fertilizers. The invention discloses a method for preparing a polymerized calcium-magnesium fertilizer by using yellow phosphorus slag, and aims to solve the technical problems that the pH value of the yellow phosphorus slag as a fertilizer raw material is too high, and effective calcium, magnesium and silicon elements of the yellow phosphorus slag are difficult to utilize. A product obtained by reaction of the yellow phosphorus slag and the raffinate acid is used as a raw material, and phosphorus, calcium and magnesium elements in the phosphoric acid slag and the yellow phosphorus slag are fully utilized to form phosphorus, calcium and magnesium elements in a polymerization state. In terms of P2O5, the polymerization rate of the polymerized calcium-magnesium fertilizer is greater than or equal to 80%. Phosphorus in the prepared product has a slow release property, when the product is applied to soil, the phosphorus in the product cannot be rapidly fixed but slowly releases orthophosphate to meet the requirements of crops, magnesium and calcium are not prone to being greatly leached by water due to the action of polyphosphoric acid, and the product is especially suitable for crops with high requirements for calcium and magnesium.
Owner:YUNNAN YUNTIANHUA

Extra-high voltage converter transformer fault diagnosis method and device and storage medium

InactiveCN118982726AImprove the accuracy of fault diagnosisreduce training timeBiological modelsTransformerData selection
The invention discloses an extra-high voltage converter transformer fault diagnosis method and device and a storage medium, belongs to the technical field of transformer fault diagnosis, and solves the problem of how to improve the fault diagnosis accuracy of a converter transformer. Converting the processed data into image data by adopting image coding; selecting a network layer number and training a deep residual network; constructing a fault diagnosis model suitable for the time sequence data of the converter transformer; according to the method, based on multi-scale and residual learning, an image coding technology is adopted to directly extract effective fault features from image data, the deep residual network is utilized to effectively solve the problems of deep convolutional neural network gradient and network degradation, the model training time is greatly shortened, and the model training efficiency is improved. And the fault diagnosis accuracy of the converter transformer is improved.
Owner:STATE GRID ANHUI ULTRA HIGH VOLTAGE CO +1

Human body posture estimation method based on Wi-Fi channel state information

The invention provides a human body posture recognition method based on Wi-Fi channel state information, and the method comprises the steps: firstly constructing a wireless human body posture estimation data set, collecting CSI data and a human body posture video at the same time under different postures of a human body during the construction, and directly changing the last 32 bits of a hardware NIC timestamp into the last 32 bits of a system timestamp in a CSI data packet, and performing software time alignment. According to the invention, a human body posture key point prediction deep learning model based on pyramid cavity convolution and a residual network is further constructed; and when prediction is needed, to-be-predicted CSI data under any action of a person is obtained, and the model is input to obtain a human body posture action representation. According to the method, the human body posture recognition based on the Wi-Fi channel state information can be realized, and meanwhile, the problem of data synchronization is solved.
Owner:BEIJING INST OF TECH

Vehicle speed prediction method and system under dynamic vehicle following scene considering traffic environment

The invention discloses a vehicle speed prediction method and system in a dynamic vehicle following scene considering a traffic environment, and the method comprises the steps: extracting vehicle following case data through setting a standard and a threshold value of a vehicle following process in a natural driving data set; using a target detection algorithm to obtain traffic environment characteristics related to the vehicle following case data, extracting vehicle dynamics parameters in the vehicle following case data, fusing the vehicle dynamics parameters and the traffic environment characteristics, and performing normalization processing to obtain fusion characteristics; removing redundant variables in the fused features by adopting a combined feature selection method; and dividing the fusion features from which the redundant variables are removed into a data set, training a pre-established Informer-FDR vehicle speed prediction model, and obtaining a vehicle speed prediction result by using the trained vehicle speed prediction model. The method effectively reflects the dynamic interaction characteristics of the driver and the traffic environment and potential traffic conflicts, enhances the understanding of the model for the complex driving environment, and improves the real-time performance and accuracy of vehicle speed prediction.
Owner:CHANGAN UNIV

Image text feature alignment fusion information extraction method, device and program product

ActiveCN119250189AResolve extraction inaccuraciesSolve the degradation problemBiological modelsKnowledge representationFeature vectorEngineering
The invention provides an information extraction method and device for image text feature alignment fusion and a program product. The method comprises the following steps: inputting a target image into an image feature extraction model to obtain image features; detecting and recognizing a text block in the target image to obtain a text block recognition result; inputting the text block recognition result into a text feature extraction model to obtain text features; text block features are constructed based on the text block recognition result, and the text features and the image features are subjected to bridging alignment; inputting the text features and the image features into a feature fusion model for splicing to obtain a comprehensive feature vector; the feature fusion model comprises an auto-encoder and a transformer encoder; inputting the comprehensive feature vectors into a preset classifier in a classified manner, executing a semantic entity recognition task, determining a classification result corresponding to the text block, and executing a relationship extraction task based on the classification result; the problem that information extraction is inaccurate when an image containing a complex background and multiple elements is processed can be solved.
Owner:江西省通讯终端产业技术研究院有限公司 +1

Machine tool thermal error modeling method fusing attention mechanism and residual network

The invention discloses a machine tool thermal error modeling method fusing an attention mechanism and a residual network, and belongs to the field of thermal error diagnosis. The machine tool thermal error modeling method fusing the attention mechanism and the residual network comprises the steps of obtaining a sample thermal image of a machine tool and a sample thermal error corresponding to the sample thermal image; inputting the sample thermal image and the sample thermal error into a target model, and obtaining a target thermal error corresponding to the machine tool output by the target model; training a target model based on the target thermal error and the sample thermal error; wherein the target model is determined by fusing an attention mechanism and a residual network. According to the machine tool thermal error modeling method fusing the attention mechanism and the residual network, the training efficiency and the model precision of the target model are remarkably improved, so that the precision and the accuracy of the predicted target thermal error are improved, and the thermal error change trend of the machine tool can be effectively predicted.
Owner:BEIJING UNIV OF TECH

Method and system for monitoring abnormal pressure of fuel oil common rail pipe of marine main engine

PendingCN121959367AReal-time high-precision monitoringSolving false alarmsWaterborne vesselsPipeline systemsData packData set
The invention discloses a method and a system for monitoring pressure abnormity of a fuel oil common rail pipe of a marine main engine. The method comprises the following steps: acquiring historical operation parameter data and constructing a data set; the historical operation parameter data comprises historical host load data, historical host rotating speed data and historical fuel oil common rail pressure data; historical operation parameter data are preprocessed, an SVDD model is constructed and trained based on the historical operation parameter data, the model obtains a historical normal data hyper-sphere in a three-dimensional feature space, and the center and the radius of the hyper-sphere are obtained; similarly, real-time operation parameter data collected in real time are preprocessed and then input into the model, the distance between the real-time operation parameter data and the center of the hypersphere is obtained, and the value of the distance is compared with the value of the radius of the hypersphere in historical normal data; and when the numerical value of the distance is large, it is judged that the real-time operation parameter data is within an abnormal range, the fuel oil common rail pressure of the ship main engine is in an abnormal state, and an alarm signal is triggered. The method has the effect of low error rate.
Owner:HANSUN (SHANGHAI) MARINE TECH CO LTD

Unmanned aerial vehicle target positioning method based on improved variation firefly optimization particle filtering

The invention relates to an unmanned aerial vehicle target positioning method based on improved mutation firefly optimization particle filtering, and the method comprises the steps: fusing an optimization mechanism of a firefly algorithm in a frame of a particle filtering algorithm, and guiding particles to move towards a high-likelihood region; a multi-variation strategy and an elastic force mechanism are introduced to change a particle interaction mode, and the problem of particle degradation caused by serious nonlinear factors and excessive optimization is solved; the target position is optimally estimated by using the mutation firefly optimization particle filter, the number of particles required by the operation of the standard particle filter algorithm is reduced, and the robustness and the positioning precision of the algorithm are improved.
Owner:NAVAL UNIV OF ENG PLA

Heavy-duty locomotive primary steel spring damage detection method based on data driving

The invention discloses a data-driven heavy-load locomotive primary steel spring damage detection method, and belongs to the technical field of heavy-load locomotive primary spring damage detection. The detection method comprises the following steps: S1, obtaining a vertical vibration response signal of a framework of the heavy-load locomotive, and preprocessing the vertical vibration response signal to obtain a sample set; s2, dividing the sample set into a training set, a test set and a verification set, and performing standardization processing; s3, constructing a primary spring damage detection model; s4, training and adjusting the primary spring damage detection model by adopting the training set and the verification set to obtain a final primary spring damage detection model; and S5, performing evaluation verification on the final primary spring damage detection model by adopting the test set to realize primary steel spring damage detection of the target heavy-load locomotive. The method can realize intelligent grading detection of the damage of the primary spring of the heavy-duty locomotive, has the characteristics of accuracy, high efficiency, strong generalization ability and the like, and is expected to be developed into a long-term monitoring method for the damage of the primary spring.
Owner:SOUTHWEST JIAOTONG UNIV

Human target detection method based on radar signal heat map

A human target detection method for radar signal heat maps is based on the residual network ResNet and uses radar signal heat maps as network input. Compared with video images, heat maps can display target information from horizontal and vertical bidirectional perspectives, and effectively remove redundant backgrounds, making them more intuitive. To simplify the training process, this method preprocesses the heat map input, which not only integrates the network input parameters and reorganizes the heat map image data, but also helps to improve training efficiency and reduce training time. In the training model, this method extracts the features of the residual network output, and relies on the feature matrix reconstruction operation at the end of the network to fuse the horizontal and vertical heat map features to further improve the feature extraction effect.
Owner:NANJING UNIV OF POSTS & TELECOMM

A hybrid expert model sparse inference method and system for generative recommendation

The application relates to the technical field of deep learning and recommendation system, and particularly discloses a hybrid expert model sparse inference method and system for generative recommendation, which comprises the following steps: obtaining original input data, and obtaining an input vector through an embedding layer; obtaining hybrid expert weights through normalization and maximum value selection operation on the input vector; calculating attention-enhanced features according to the hybrid expert weights based on a hierarchical attention mechanism; inputting the input vector and the attention-enhanced features into a hybrid expert model to calculate a recommendation result; wherein, according to the attention-enhanced features, expert weights are calculated based on a parallelized gating mechanism activated by a Sigmoid activation function; the activated expert layer is selected according to the expert weights, and the input vector is used to calculate the recommendation result. The application can achieve a recommendation accuracy comparable to or even higher than that of an advanced dense model under low time overhead and low calculation complexity.
Owner:NANKAI UNIV

An interference microscopic phase distortion elimination method based on PACU Next3+ network

ActiveCN116664438Beliminate quadraticEliminate high-order phase distortionImage enhancementImage analysisData setInterference graph
The present application relates to the field of optical interferometry, and aims at the phase distortion problem in off-axis interferometric quantitative phase imaging, and provides an interferometric microscopic phase distortion elimination method based on PACUNeXt3+ network. The method comprises the following steps: 1. using Zernike polynomials and test target pictures to simulate and generate a data set; 2. establishing and training a PACUNeXt3+ neural network model; 3. inputting the interference graph I or of the sample to be measured into the trained neural network, and outputting the background interference graph I' r corresponding to the sample without sample information; 4. using the two interference graphs I or and I' r to reconstruct the sample phase distribution φ o (x, y) without phase distortion. The present application has high precision and speed, can eliminate the secondary or high-order phase distortion in interferometric quantitative phase imaging, and has great application prospect in the field of phase imaging.
Owner:XIAN TECH UNIV

Object segmentation method and related device based on residual module and attention mechanism

The present invention discloses a method for object segmentation based on a residual module and an attention mechanism and a related device, which relates to the technical field of remote sensing object segmentation. The method comprises the following steps: obtaining a remote sensing image to be segmented; inputting the remote sensing image to be segmented into a trained object segmentation model to obtain an object segmentation result; wherein the object segmentation model is a network model obtained by combining a residual module and an attention module based on a U‑Net neural network. The present invention adopts a U‑Net model combining a residual network structure and an attention mechanism. The main idea is to use an improved residual structure to avoid the degradation problem of a deep network model. In addition, a hybrid attention mechanism and a cross attention mechanism are introduced, so that the model has the ability to connect to long-distance contextual information, can make more full use of the global information of the image, and enhance the network's adaptive ability.
Owner:CHENGDU UNIVERSITY OF TECHNOLOGY

Fruit tree pruning method based on branch-leaf-root synchronous growth

The invention belongs to a fruit tree cultivation technology, in particular to a fruit tree pruning method based on branch-leaf-root synchronous growth, which is suitable for a fruit tree with at least three main branches. Different from a traditional strong-removing and strong-remaining method, the method adopts a weak-removing and strong-remaining strategy, and synchronous growth of branches, leaves and roots is realized through the following steps: firstly, performing head removing treatment on a main branch I, reserving 75-85% of length, selectively reserving vigorous branches of more than 1m, and forming inverted branches; in the second year, girdling the inverted branches to promote flower bud formation; after the fruits are harvested in the third year, the fruiting branches are cut off, and the second main branch is subjected to the same treatment; in the fourth year, the first main branches grow new branches again, and the process is repeated. According to the method, the main branches are trimmed and updated in turn, so that continuous growth and fruiting of the trees are kept, the yield and the fruit quality are improved, meanwhile, the influence on the environment is reduced, and the method has important economic and ecological values.
Owner:吴新民

An image segmentation method and medium for densely populated regions of living cells

PendingCN122090447ASolve serious under-segmentation problemImprove recall
This invention discloses an image segmentation method and medium for densely populated live cell regions. The method includes acquiring multiple first data pairs and preprocessing each first data pair. Each first data pair includes a single-modal master image of a live cell region and a paired real auxiliary modality image. A feature extraction network is trained using the preprocessed first data pairs, and the feature extraction network outputs a predicted auxiliary modality image corresponding to the single-modal master image. The preprocessed first data pairs and the predicted auxiliary modality image are input into a pre-trained segmentation model, and the dynamic weights of the predicted auxiliary modality image are adjusted to optimize a second loss function to obtain optimal weight parameters. The single-modal master image of the live cell image to be segmented is input into the trained feature extraction network, and combined with the optimal weight parameters, it is input into the pre-trained segmentation model to obtain the segmentation result. This method is particularly effective for accurate segmentation in densely populated regions.
Owner:SAIL SPACE (SUZHOU) INTELLIGENT TECHNOLOGY CO LTD

A soft-constraint target tracking method and system based on genetic resampling

ActiveCN117350153BSolve the degradation problemImprove estimation accuracy
This invention discloses a soft-constraint target tracking method and system based on genetic resampling, belonging to the field of target tracking technology. The method includes: constructing a target tracking model based on the target being tracked; generating multiple particles required for particle filtering based on the initial state value of the target being tracked; updating each particle over time based on the target tracking model to predict the state and weight of each particle; resampling each particle using a genetic algorithm; calculating the corrected likelihood function of the resampled particles based on the measurement equation; correcting the predicted weights based on the corrected likelihood function; and updating the predicted state based on the corrected weights to obtain the final estimated state of the target being tracked. This invention can integrate known nonlinear inequality soft constraints in the tracking of ground moving targets, improving the tracking accuracy of ground targets under such soft constraints.
Owner:HARBIN INST OF TECH

Sentiment analysis method based on LoRA

The present invention discloses a sentiment analysis method based on LoRA, which belongs to the field of artificial intelligence technology, including S1, a preprocessing layer, in which data is cleaned and the input sample is segmented using the BERT pre-training model; S2, a word embedding layer, in which the input sample after segmentation is passed through a vector representation layer and mapped into a high-dimensional continuous word vector to capture semantic information; S3, a feature extraction layer, in which the high-dimensional word vector is used as the input of the feature extraction layer to further extract the feature vector; S4, an output layer, in which the generated feature vector is used as the final input sample representation, and the polarity of the text sentiment is judged through the sentiment classification layer. The present invention adopts the above-mentioned sentiment analysis method based on LoRA, and by updating the pre-trained weight matrix using the increment of the low-rank matrix while training the low-rank matrix, the controllable factors of the model are increased without increasing the training parameters and reasoning time, and the problem of excessive dependence of the original LoRA method on the low-rank matrix is ​​alleviated.
Owner:HUBEI UNIV

An ultra-short-term wind power prediction method based on feature enhancement and composite model

The application provides a kind of based on feature enhancement and composite model's ultra-short-term wind power prediction method, belongs to ultra-short-term wind power prediction technical field, this method includes: by calculating the mutual information of multiple meteorological characteristics and wind power output and normalizing, screening to obtain key features, and constructing wind power prediction fitness function, by minimizing wind power prediction fitness function, obtain enhanced input features;By introducing one-dimensional convolutional neural network and bidirectional long short gate recurrent unit, construct the residual network of bidirectional long short gate recurrent unit and convolutional neural network fusion, and introduce space-time attention mechanism, construct to obtain composite residual network ultra-short-term wind power prediction model;And use multiple meteorological characteristics and enhanced input features to predict to obtain ultra-short-term wind power prediction result;The application solves the problem that the influence of meteorological multi-scale fluctuation on output cannot be accurately grasped, prediction is disconnected, disturbance is not considered and prediction accuracy continues to decline with step increase.
Owner:BEIJING JIAOTONG UNIV

Garbage recognition and classification method based on ResNet50

The present invention belongs to the field of image recognition technology, specifically, it is a garbage recognition and classification method based on ResNet50, comprising: selecting a public data set covering a variety of garbage pictures commonly seen in real life, creating a data set suitable for garbage classification research, and then dividing the data set into a training set and a test set, and performing preprocessing operations on the images in the training set; building a network model, selecting a ResNet50 convolutional neural network model as a benchmark model, introducing deep separable convolution, adding two attention mechanisms, CBMA and SE, to create a new convolutional neural network model; setting the hyperparameters of the network model, selecting a loss function and an optimization method to train the created network model, and obtaining a trained model; using the trained convolutional neural network model to recognize pictures in the test set, and finally obtaining the recognition accuracy.
Owner:NANJING UNIV OF POSTS & TELECOMM

Sequence mapping load identification decomposition method based on multi-scale residual neural network

The invention relates to the technical field of load identification, in particular to a sequence mapping load identification decomposition method based on a multi-scale residual neural network, which comprises the following steps that: a load identification model is constructed, and the network structure of the load identification model is a multi-scale residual network based on expansion convolution; acquiring an aggregation power data set and an electric appliance level power data set in the public data set, and preprocessing the aggregation power data set and the electric appliance level power data set to obtain a preprocessed training set and a preprocessed test set; and training and testing the load identification model by using the preprocessed training set and test set to obtain a trained load identification model. According to the method, the load identification model of the multi-scale residual network based on the expansion convolution is constructed, so that mixed data features can be learned in a more targeted manner, and the load identification effect of the load identification model is improved.
Owner:ECONOMIC TECH RES INST OF STATE GRID HENAN ELECTRIC POWER +2

A method and apparatus for detecting occlusion in dynamic degradation decomposition combined with physical restoration

This application discloses an occlusion detection method and apparatus combining dynamic degradation decomposition and physical restoration, relating to the fields of computer vision and industrial safety monitoring technology. The method includes: extracting multi-scale features from industrial scene images using a dynamic degradation decomposition backbone network; explicitly decomposing and suppressing the dynamic degradation patterns of the industrial scene images in manifold space; generating degradation correction prompts and strategy prompts; inputting these prompts into a physically guided dehazing neck network; and using the physical inductive bias of an atmospheric scattering model to decouple and restore the multi-scale features, generating a multi-scale restored feature map; and using a context relation module to perform semantic reconnection operations on the multi-scale restored feature map to generate a context-enhanced feature map, which is then input into a decoupled detection head to predict the location and category of industrial personal protective equipment (PPE) in the industrial scene image. This solves the problem of low accuracy in detecting the wearing of industrial PPE in high-risk industrial scenes, which poses safety risks in industrial production.
Owner:YANAN UNIV

Method for graphite ore grade detection based on improved Faster-RCNN

The present invention provides a method for detecting the grade of graphite ore based on improved Faster-RCNN. The method for detecting the grade of graphite ore based on improved Faster-RCNN includes the following steps: picture collection, rectangular frame annotation, picture classification, data set division, image enhancement, construction of improved Faster-RCNN model, training of improved Faster-RCNN model and picture recognition. The present invention adopts the improved Faster-RCNN model to detect the grade of graphite ore, and the accuracy of the final test set can reach 92.0%, which can greatly help the identification of graphite grade and change its traditional chemical identification method. Only by inputting the picture of graphite ore, the classification result of graphite ore grade can be obtained, without spending a lot of time cost, and the detection efficiency is high.
Owner:JIANGXI UNIV OF SCI & TECH

Training methods and devices for face recognition models to avoid the long tail problem of data

ActiveCN115661891BSolve the degradation problemSolve overfittingCharacter and pattern recognitionNeural learning methodsFeature vectorFeature extraction
This disclosure relates to the field of face recognition technology, and provides a training method and apparatus for a face recognition model that avoids the long tail problem of data. The method includes: constructing a face recognition model; obtaining a training dataset, and executing the following loop to train the face recognition model in multiple rounds: sampling the current round of training from the training dataset using a dynamic sampler to obtain a sample set used for the current round of training; inputting the sample set into a feature extraction network to obtain a feature vector set corresponding to the sample set; inputting the feature vector set into a normalization network to normalize the feature vectors in the feature vector set; calculating a classification loss using a classification network and a contrastive loss using a contrastive network based on the feature vector set processed by the normalization network; updating the model parameters of the face recognition model based on the classification loss and contrastive loss; incrementing the training round number corresponding to the current round of training by one; and ending the loop when the training round number equals a preset round number.
Owner:SHENZHEN XUMI YUNTU SPACE TECH CO LTD

Power operation site safety management and control method and system based on hybrid neural network

The invention relates to an electric power operation site safety control method and system based on a hybrid neural network, and the method comprises the following steps: deploying a plurality of groups of image collection devices at an electric power operation site, and collecting the images of the electric power operation site; preprocessing the collected electric power operation site image; inputting the preprocessed operation site image into a pre-trained hybrid neural network, and using the hybrid neural network to intelligently identify typical violation information of the power operation site; according to the identified typical violation information, giving an alarm to electric power operation field personnel and storing the identified violation information; and optimizing the hybrid neural network by an electric power operation site manager according to the identified violation information result. And the safety management and control level of an electric power operation site is improved.
Owner:STATE GRID FUJIAN ELECTRIC POWER CO LTD +2

Navigation multipath signal estimation method based on particle filtering

PendingCN119224796ASolve the degradation problemAddress diversitySatellite radio beaconingHigh level techniquesSignal onGenetics algorithms
The invention relates to the technical field of satellite navigation positioning, in particular to a navigation multipath signal estimation method based on particle filtering, which combines extended Kalman filtering (EKF) and a genetic algorithm to jointly optimize parameter estimation of particle filtering (PF), and comprises the following steps: firstly, in a PF importance sampling stage, utilizing the EKF algorithm and latest observation information to obtain a sample mean value and a covariance; reasonable suggestion density is provided for particle filtering, and the weight of each particle can be recalculated. And copying and eliminating a particle set by using an improved genetic algorithm in a resampling stage of particle filtering, so as to avoid the problem that the particle filtering is trapped in a local extremum. According to the method provided by the invention, the problems of particle degradation and particle diversity reduction in particle filtering can be solved, and high-precision parameter estimation of the direct signal and the multipath signal is realized, so that the influence of the multipath signal on the navigation signal performance is reduced.
Owner:GUILIN UNIV OF ELECTRONIC TECH +1

Picture classification method and device, medium and equipment

InactiveCN119107489ASolve the degradation problemshorten the time
The invention discloses a picture classification method and device, a medium and equipment. The method comprises the following steps: collecting a picture data set containing different categories; preprocessing the picture data set to generate a picture training set; a pre-constructed deep convolutional neural network is trained according to the picture training set, an image recognition model is generated, and residual connection, dense connection and an attention module are introduced into the deep convolutional neural network; and inputting the uploaded to-be-processed picture into the image recognition model, and determining the category of the to-be-processed picture.
Owner:ANRUI DIGITAL INFORMATION TECH CO LTD

An API behavior hierarchical perception modeling method, system, device and medium based on multi-modal feature fusion

PendingCN122286753ASolve the degradation problemhigh transparencyBehavioral dataData mining
This invention discloses a method, system, device, and medium for hierarchical perception modeling of API behavior based on multimodal feature fusion, belonging to the field of API modeling technology. The method includes: processing API call behavior data through multimodal feature fusion to generate a fused feature matrix and modal weights; performing multi-level semantic encoding based on temporal sequence and dependency relationships to form a behavioral semantic graph and hierarchical feature representation; calculating behavioral deviation to generate risk scores, anomaly lists, and grading results; monitoring new data and adaptively updating the model, outputting model iteration versions and drift reports; and performing interpretable analysis based on risk scores, weight distribution, and semantic graphs to generate a visualized risk association view. This invention improves the accuracy of panoramic understanding and anomaly identification of complex API behaviors through multimodal feature fusion and hierarchical semantic modeling, ensuring stable detection performance in dynamic environments and effectively solving the model degradation problem.
Owner:GUANGXI POWER GRID CORP

Opportunistic array radar-oriented likelihood improved SVGD interactive multi-model maneuvering target tracking method

The invention provides an opportunity array radar-oriented likelihood improved SVGD interactive multi-model maneuvering target tracking method, which comprises the following steps of: 1, modeling a maneuvering target tracking problem, constructing a motion model set and initializing parameters; 2, the mixing probability of each model is calculated, initial mixing estimation is obtained, and initial mixing particles are generated; 3, judging the working mode of the opportunity array radar, and predicting and updating the particle state; and 4, fusing model probability updating and state estimation. According to the method, the problems of particle degradation and particle depletion are solved, and divergence of a filtering algorithm in an opportunity tracking scene is avoided. Meanwhile, adaptive optimization of the SVGD learning rate is realized by using the model likelihood, the convergence speed and stability of the algorithm are well balanced no matter in the single iteration process or the whole iteration process, and rapid reconvergence of the algorithm when the opportunity array radar executes the opportunity tracking function is ensured.
Owner:NANJING UNIV OF INFORMATION SCI & TECH