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

309results about How to "Improve generalization" patented technology

Pig behavior and health method based on deep learning and physiological parameter dynamic monitoring

The invention discloses a pig behavior and health method based on deep learning and physiological parameter dynamic monitoring, relates to the technical field of animal health management, and solves the defects in deep behavior pattern understanding, dynamic change of physiological parameters and fine analysis of behavior physiological interaction effect in the prior art. In order to solve the problems that in the prior art, in the prior art, the comprehensiveness of a health management system and the accuracy of early warning are limited, an advanced deep learning model and a biological signal processing technology are introduced, deep analysis of a pig behavior mode is strengthened, and continuous and real-time monitoring and comprehensive analysis of physiological parameters are achieved. By constructing a multi-dimensional data fusion framework, behavior data and physiological indexes are closely associated, the sensitivity and recognition precision of behavior abnormity and health problems behind the behavior abnormity are improved, by integrating edge calculation and an efficient data processing algorithm, the time delay from data collection to early warning response is remarkably shortened, and the accuracy of early warning is improved. And the instantaneity in a large-scale breeding scene is ensured.
Owner:HEILONGJIANG AGRI INVESTMENT BIG DATA TECH CO LTD

Federal learning method based on flexible combination of feature extractor and classifier

The invention belongs to the technical field of federated learning, and particularly relates to a federated learning method based on flexible combination of a feature extractor and a classifier. The method comprises the steps that a server initializes a global model; if the training is the first round, updating the local classifier into a global classifier, and if the training is not the first round, enabling the local classifier to follow the local classifier trained in the last round; a local classifier is trained, then a local feature extractor is trained, a global feature extractor generates global feature anchor points to guide the training of the local feature extractor, and meanwhile, the local feature extractor is firstly subjected to combined training with the global classifier and then subjected to combined training with the local classifier; generating an aggregation weight based on the number of client samples, and aggregating the local model to obtain a new round of global model; and repeating the steps until the model converges or reaches a set communication round. The problems of model performance reduction and privacy disclosure are solved.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +1

Image super-resolution generation model construction method and image super-resolution generation method and system

The invention discloses a method for constructing an image super-resolution generation model. The method comprises the following steps: constructing a mixed data set containing various types of images; preprocessing the images in the mixed data set to obtain initial low-quality images and corresponding image text descriptions; determining a first initial learning framework, and generating a corresponding high-quality reference image according to the preprocessed initial low-quality image; training the first initial learning framework to obtain a first-stage repair model; determining a second initial learning framework, and generating a high-resolution image according to the random noise-added original image, a high-quality reference image generated by the first-stage repair model and image text description prediction; and training the second initial learning framework to obtain a target second-stage image super-resolution generation model. According to the method, a two-stage network framework model is designed and developed based on a potential diffusion model, rich prior of the diffusion model is utilized, and the generalization ability of the model is greatly improved.
Owner:NANJING UNIV OF POSTS & TELECOMM

Centrifugal pump set fault identification method and equipment

The embodiment of the invention discloses a centrifugal pump set fault identification method and equipment, and the method comprises the steps: carrying out the operation simulation of a centrifugal pump set comprising a plurality of parts under different working conditions, and enabling the different working conditions to comprise a multi-source domain corresponding to a marked known working condition and a target domain corresponding to an unmarked target working condition; obtaining multi-source domain operation data and target domain operation data; processing the multi-source domain operation data and the target domain operation data respectively to generate a multi-source domain feature time sequence and a target domain feature time sequence; the multi-source domain feature time sequence and the target domain feature time sequence are input into a multi-source domain adaptive network model for training, a centrifugal pump set fault recognition model is obtained, the centrifugal pump set fault recognition model achieves extraction of public global fault features from long sequences of a multi-source domain and a target domain, and global time sequence association between the features is established; and carrying out fault identification on the target domain through the centrifugal pump set fault identification model.
Owner:INSPUR GENERSOFT CO LTD

Pilot dangerous driving behavior monitoring method based on multi-modal data fusion

The invention discloses a pilot dangerous driving behavior monitoring method based on multi-modal data fusion, and belongs to the field of multi-modal data fusion monitoring, and the method comprises the steps: obtaining the physiological data of a pilot in the take-off and landing states through a multi-element sensor, judging the fatigue state of the pilot, and obtaining the dangerous driving behavior of the pilot. An eye tracker and a camera are used for conducting data collection on a pilot in the take-off and landing states, behavior data of the blinking frequency, the eyelid closure degree, the pupil change, the yawning frequency, the nodding frequency, the average moving speed of an operating lever and the moving direction of the pilot are obtained, and the fatigue state of the pilot is judged; the method comprises the following steps: constructing a multi-modal data fusion network based on Transform, and training the multi-modal data fusion network; the driving behavior of a pilot is monitored by using the trained network based on the Transform multi-modal data fusion; through a multi-channel interaction technology, the comprehensiveness and accuracy of information are improved, the influence of environment and individual differences is reduced, and the stability and robustness are enhanced.
Owner:江淮前沿技术协同创新中心 +1

Seismic source inversion data driven rock burst prediction method and system

The invention discloses a seismic source inversion data driven rock burst prediction method and system, and the method comprises the steps: carrying out the quantitative inversion calculation of the core parameters of a coal rock fracture seismic source mechanism through original sound wave data collected on site; a rock burst seismic source data prediction model is constructed based on an Informer algorithm, and the occurrence time and position of rock burst are accurately predicted. A rock burst risk evaluation model is constructed by combining the predicted occurrence time and position of a future fracture source and seismic source mechanism core parameters, the magnitude and property of rock burst are predicted, and a dual-drive rock burst intelligent model for seismic source data prediction and rock burst risk evaluation is established; and multi-dimensional intelligent prediction of sequential response, spatial distribution and evolution attributes in the rock burst catastrophe process is realized. According to the method, seismic source data prediction and risk evaluation are combined, the rock burst catastrophe risk can be predicted, and the rock burst evolution process and the disaster-causing mechanism can be visually represented.
Owner:CHINA UNIV OF MINING & TECH

Power distribution network single-phase earth fault detection method based on Gramer angle field and improved convolutional neural network

The invention relates to a power distribution network single-phase earth fault detection method based on a Gramb angle field and an improved convolutional neural network, and the method comprises the following steps: S1, analyzing the characteristics of an earth fault, obtaining measurement data from a power distribution network through a phasor measurement unit (PMU), and obtaining a two-dimensional virtual image from the obtained measurement data through a GAF; s2, through an improved convolutional neural network ICNN, analyzing the obtained two-dimensional virtual image by using a multi-scale feature extraction module and an attention module, and extracting and paying attention to key features between fault data; and S3, constructing a fault detection model of the single-phase earth fault of the power distribution network, dividing the fault detection model into an offline stage and an online stage, and carrying out fault detection according to different online conditions. According to the method, the fault diagnosis performance under different online conditions can be improved.
Owner:STATE GRID FUJIAN ELECTRIC POWER RES INST +2

Flight data-based small-probability aviation unsafe event inducement analysis and online monitoring method and flight data-based small-probability aviation unsafe event inducement analysis and online monitoring system

The invention discloses a small-probability aviation unsafe incident cause analysis and online monitoring method and system based on flight data, and belongs to the field of aviation safety technology and flight data application. The method comprises the following steps: S0, determining an input parameter set through an aircraft flight quality monitoring standard, and constructing a risk identification architecture I based on weak supervised learning; s1, based on the risk identification architecture I, obtaining a risk identification network I and a quantitative risk value, and obtaining a high-risk time point and an inducement by using statistical analysis; and S2, inheriting the ability of the risk identification network I to identify the risk of the unsafe event to a risk identification network II by using a knowledge distillation method, obtaining the risk identification network II for online monitoring, and carrying out online risk detection based on the risk identification network II for online monitoring.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Bearing remaining service life prediction method based on adaptive gating chart convolutional network

The invention relates to the technical field of bearing residual service life prediction, in particular to a bearing residual service life prediction method based on a self-adaptive gating chart convolutional network, which comprises the following steps of: sampling an original vibration signal of a bearing and converting the original vibration signal into a characteristic channel; sampling data of a feature channel through a window, performing row and column division to obtain graph structure data of temporal correlation and spatial correlation, and preliminarily defining an adjacent matrix of the two types of graphs by using cosine similarity and covariance so as to input a subsequent graph neural network; using the source matrix and the target matrix to obtain two types of adaptive graphs, and inputting the two types of adaptive graphs together with a predefined graph into the constructed gated graph convolutional network; inputting correlation features extracted from the gating graph convolutional network into a DBN to extract low-dimensional abstract features of the DBN; and extracting long and short time dependence in the feature channel data through bidirectional LSTM, fusing the long and short time dependence with the output of the DBN, and finally inputting a full connection layer to obtain the final prediction of the residual service life of the bearing.
Owner:GUANGXI UNIV

Deep learning-oriented zero sample target detection method and system

The invention belongs to the field of zero sample target detection, and discloses a deep learning-oriented zero sample target detection method and system. The method comprises the following steps: establishing a zero sample target detection model comprising a feature extraction module, a cross-modal alignment module and a course learning module; extracting image features and text features through a feature extraction module; inputting the image features and the text features into a cross-modal alignment module; carrying out cross-modal similarity calculation on image feature embedding and text feature embedding; the obtained cross-modal similarity is imported into a course learning module; fusion of image features and text features is enhanced through a course learning module, and the difficulty of course learning is dynamically adjusted through knowledge distillation in the back propagation process; and obtaining a zero sample target detection model and a detection result. According to the method, the advantages of high performance and high generalization ability of a zero sample learning large model are reserved, mutual complementation and enhancement among cross-modal features are realized, and the detection performance and robustness of the model are improved.
Owner:SHANDONG JINING CANAL COAL MINE

Field laser intelligent weeding and thinning robot

The invention discloses a field laser intelligent weeding and thinning robot which comprises four sets of wheel leg assemblies driven by servo motors, a front telescopic swing bridge, a rear telescopic fixed bridge, a base assembly, a liftable laser striking platform and electric control equipment such as a power generator and a three-dimensional laser terrain scanning radar. A plurality of modularized high-power carbon dioxide laser modules, four groups of laser range finders and five groups of double-axis tilt angle sensors are respectively mounted on and around a laser striking platform, each laser module comprises a digital galvanometer, a pseudo-coaxial camera and a miniature windscreen wiper dust removal system, and a digital galvanometer, a pseudo-coaxial camera and a miniature windscreen wiper dust removal system are mounted below the laser striking platform. A plurality of AI intelligent identification and positioning cameras and lighting devices are installed. Therefore, the robot can automatically identify and position weeds and seedlings through the AI intelligent camera and guide the laser to accurately strike the target, has the advantages of easy realization of modularization, universalization and standardization in the later period, is beneficial to cost saving, and is suitable for large-scale popularization and application in the later period.
Owner:AZURE ENGINE (SHANGHAI) TECHNOLOGY CO LTD

In-situ hyperspectral water quality parameter inversion method based on deep learning

The invention discloses an in-situ hyperspectral water quality parameter inversion method based on deep learning. According to the method, a parallel network model is constructed by combining a convolutional neural network (CNN) and a Transformer, local features are extracted by using the CNN, global information is captured by using the Transformer, and comprehensive analysis of complex features and waveband information in in-situ hyperspectral reflectivity data is realized. In the model training process, the initial layer of the network is pre-trained by adopting a self-supervised learning strategy of random shielding and noise injection, and then the weight of the network is finely adjusted by utilizing labeled data, so that the understanding of the model on a data feature mode is enhanced. According to the method, the unlabeled data is fully utilized, and the training precision and generalization ability of the model are improved. Compared with a traditional explicit linear or nonlinear model constructed by depending on prior knowledge, the method has the advantages that the recessive correlation between spectrums can be captured, end-to-end water quality parameter inversion is realized, and the result is remarkably improved in the aspects of precision and generalization ability.
Owner:HOHAI UNIV

False data injection attack detection method and device based on federal learning and comparative learning, and storage medium

The invention discloses a false data injection attack detection method and device based on federal learning and comparative learning, and a storage medium, and aims to improve the network security of a smart power grid. According to the method, power grid data are collected and preprocessed through local centers of all regions, local model training is carried out through comparative learning, then the trained model is uploaded to a control center for parameter aggregation, and a global model is generated. And the local center adopts an index moving average method to update a local model, and uses a small amount of label data to train a binary classifier to carry out FDIA detection. According to the method, the problem of data islands is effectively solved, the generalization ability and the detection precision of the model are improved, and data privacy is protected at the same time. The device comprises a processor and a memory, and computer program instructions for executing the method are stored in the memory. The invention further provides a storage medium which is used for storing related computer program instructions.
Owner:GUIZHOU UNIV

Mechanical equipment lightweight intelligent fault diagnosis method based on Kolmogorov-Arnold network

The invention discloses a mechanical equipment lightweight intelligent fault diagnosis method based on a Kolmogorov-Arnold network, and the method comprises the steps: firstly obtaining original vibration monitoring data of mechanical equipment under different fault types, and constructing an equipment vibration monitoring fault data set; a KAN-based fault diagnosis model is constructed, and a learnable nonlinear function is adopted to replace a fixed linear weight in convolution; then, the output is converted into a one-dimensional feature vector through KAN convolution operation; inputting the one-dimensional feature vector into a KANLinear layer so as to realize the mapping of the high-dimensional feature to different fault types; then calculating training loss, taking the total loss as an optimization target of a training stage, and updating model parameters by using a gradient descent method; iteratively optimizing the fault diagnosis model; and finally, testing the fault diagnosis model by using the test set. According to the method, high diagnosis precision can be maintained, meanwhile, the model parameter quantity is remarkably reduced, the calculation cost is reduced, and therefore the overall calculation efficiency is improved.
Owner:XI AN JIAOTONG UNIV

Tailing dam accident path identification method based on mixed causal knowledge graph and related device

The invention belongs to the field of tailing pond safety risk identification and accident analysis, and discloses a tailing dam accident path identification method based on a mixed causal knowledge graph and a related device, and the method comprises the steps: building a mixed causal logic model through employing an obtained tailing dam accident initial hazard source; solving a set of accident cause links of the tailing dam by utilizing the mixed causal logic model; in the set of the tailing dam accident cause links, the logic relation of the tailing dam accident and the accident cause links are used as nodes and edges of a knowledge graph respectively, and a Python + Neo4j method is used for constructing a tailing dam accident knowledge graph; and coding and classifying the tailing dam accident knowledge graph by using a BERT-GCN-SVM model to realize tailing dam accident path identification. The mine tailing dam accident path identification method is improved and optimized based on the thought of the knowledge graph, a set of mine tailing dam accident chain identification method is formed, and the mine tailing dam accident path identification method can be used as a new tool for mine tailing dam accident directional control and disaster situation deduction.
Owner:XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY

Deep learning model-based hot forming process parameter design method and device

The invention relates to a hot forming process parameter design method and device based on a deep learning model, and belongs to the technical field of hot forming. The method comprises the steps that image data, text data and video data in a standard hot forming process and an experimental process are obtained, and the image data, the text data and the video data are fused to obtain a fused image; a multi-mode hot forming process database is obtained; an initial deep learning model is constructed, data in the multi-modal thermal forming process database is used as input parameters to be input into the initial deep learning model for iterative training, and a target deep learning model is obtained; and the product performance requirements serve as input parameters to be input into the target deep learning model, and target hot forming process parameters are obtained. The technical problems of high time cost and low efficiency of process parameter design are solved.
Owner:WUHAN UNIV OF TECH

Semi-supervised medical image segmentation method based on dual-view complementary consistency

The invention relates to a semi-supervised medical image segmentation method based on dual-view complementary consistency, which only utilizes a small amount of labeled medical image data to mine potential feature information in a large amount of unlabeled data to improve the performance of a segmentation model, and comprises the following steps of: adopting a feature space distillation mechanism to obtain a feature space; extracting and transferring multi-scale semantic features through a teacher-student model; a pseudo label is optimized by using a double-view fusion strategy, and the learning effect of the model on unmarked data is optimized; and through an uncertainty estimation method assisted by a pre-training auto-encoder, the reliability and segmentation precision of the model are optimized. Experimental results on a left atrium (LA) and liver tumor segmentation (LiTS) data set show that the method has good effects in the aspects of segmentation precision and model robustness.
Owner:XINJIANG UNIVERSITY

Optimization method based on active reasoning in MEC enabled low-altitude element cosmic system

The invention belongs to the technical field of wireless communication, and discloses an optimization method based on active reasoning in an MEC-enabled low-altitude element cosmic system, which realizes low energy consumption and low delay of Internet of Things equipment on the premise of ensuring user service quality through joint optimization of a flight path and a resource allocation strategy of an unmanned aerial vehicle, and improves user experience. And meanwhile, an auxiliary means is provided for improving the economic benefits of operators. Aiming at the dynamic nature of the network, the uncertainty of information acquisition and the incompleteness of data use, an optimization problem is converted into a Markov decision process, an improved deep learning algorithm based on active reasoning is adopted, factors except the reward dimension are additionally considered on the guidance of dynamic learning, and the dynamic learning algorithm is optimized. And a personalized strategy is explored according to the preference of the intelligent agent.
Owner:XIAN UNIV OF POSTS & TELECOMM

Pipeline defect assessment method and system based on multi-source data fusion

The invention provides a pipeline defect assessment method and system based on multi-source data fusion, and the method comprises the following steps: collecting the data of the operation state of a pipeline body through a related collection device, and marking the state and fault type of the pipeline, so as to construct a training set and a test set; and preprocessing the static data of the pipeline, wherein the preprocessing comprises data cleaning, standardization and feature extraction. And optimizing the extreme learning machine by using a bird flock algorithm, analyzing static data and evaluating pipeline defects. Preprocessing the image data of the pipeline body, wherein the preprocessing comprises image conversion, enhancement and denoising; and evaluating the circumferential weld defect based on the pre-trained VGG16 model. And performing decision-level fusion on a defect evaluation conclusion obtained by static data analysis and circumferential weld image analysis by using a D-S evidence reasoning algorithm to obtain a final evaluation result. The method effectively improves the accuracy and reliability of pipeline defect evaluation, and has wide application prospects and important practical value.
Owner:XI AN JIAOTONG UNIV

Scraper conveyor chain working condition monitoring method

The invention discloses a scraper conveyor chain working condition monitoring method, which comprises the steps of obtaining historical monitoring data which comprises environmental data and chain data, adding labels to the historical monitoring data, constructing a monitoring model which adopts a deep learning model, and calculating the working condition of a scraper conveyor chain according to the working condition and the remaining life of the scraper conveyor chain. Performing data amplification on the historical monitoring data and the labels to obtain amplified data, optimizing the deep learning model through the amplified data to obtain a pre-optimization model, and training the pre-optimization model through the historical monitoring data and the labels to generate a final monitoring model; and acquiring current monitoring data, and predicting the current monitoring data through the final monitoring model to obtain the current working condition and residual life of the scraper conveyor chain.
Owner:SHANDONG UNIV OF SCI & TECH

Video generation method, device and equipment based on diffusion model

The invention discloses a video generation method, device and equipment based on a diffusion model. The method comprises the following steps: obtaining a plurality of frame extraction pictures; constructing a plurality of picture groups; mapping the picture group in the initial data space to a hidden space; constructing a to-be-trained diffusion model; adding noise to each hidden variable in the picture group; inputting the picture groups into a to-be-trained diffusion model to obtain a plurality of prediction noises and a plurality of prediction picture differences corresponding to each picture group and corresponding prediction picture group differences among the plurality of picture groups; and according to the plurality of predicted noises, the plurality of predicted picture differences and the plurality of predicted picture group differences, adjusting neural network parameters of the to-be-trained diffusion model, and when a preset training requirement is met, taking the to-be-trained diffusion model as a target diffusion model. The invention belongs to the field of video prediction. According to the invention, the time consistency of the video predicted based on the diffusion model can be maintained.
Owner:XINGFAN XINGQI (CHENGDU) TECH CO LTD

Multivariate time sequence anomaly detection method, system and product

The invention relates to the technical field of data anomaly detection, and particularly discloses a multivariate time series anomaly detection method, system and product, and the method comprises the steps: building an anomaly detection framework which comprises a domain attention-based feature extractor, a domain attention-based feature predictor and a multi-domain anomaly discriminator which are connected in sequence; training the domain attention-based feature extractor and the domain attention-based feature predictor by using multivariate time series data of a source domain and a target domain to obtain a multivariate time series anomaly detection model; and performing multivariate time sequence anomaly detection by using the multivariate time sequence anomaly detection model. According to the method, a target domain with limited data and a plurality of source domains with rich data are aligned in distribution, so that cross reuse of data among different devices in a device group is realized; and the model is trained through a joint loss function constrained by domain attention to capture more comprehensive equipment state information.
Owner:先进计算与关键软件(信创)海河实验室 +1

Photovoltaic power short-term prediction method and device based on multi-level reverse error correction, equipment and medium

The invention relates to the technical field of photovoltaic prediction of a power system, in particular to a photovoltaic power short-term prediction method, device and equipment based on multi-level reverse error correction and a medium, and the method comprises the steps: obtaining original data, and carrying out the data interpolation and data selection; variational mode decomposition is used to decompose the selected data, and kernel principal component analysis is carried out to reduce dimensions; dividing the data after dimension reduction into a plurality of sub-data sets with the same size and a test set as input data, selecting a plurality of training algorithms, constructing a prediction model based on model stacking Stacking, and inputting the input data into the prediction model for training; performing prediction by using the trained prediction model, and evaluating a prediction result; according to the method, historical data or environmental factors are analyzed, photovoltaic stations with similar characteristics or prediction results are clustered, photovoltaic stations of different clusters are predicted according to the clustering results, and a prediction model is subjected to reverse correction.
Owner:STATE GRID JIANGSU ELECTRIC POWER CO LTD RESEARCH INSTITUTE +2

Air-conditioning building system load modeling method and system based on physical prior neural network

The invention discloses an air-conditioning building system load modeling method and system based on a physical prior neural network, and relates to the field of air-conditioning building system loads, and the method comprises the steps: modeling a thermodynamic load dynamic evolution process of an air-conditioning building system as a discrete time Markov decision process; establishing a corresponding physical prior neural network architecture; simulating a room scene heated by a single heat source to generate training data, determining physical meanings of states and action spaces in the room scene, and updating a loss function form; training a physical prior neural network and carrying out hyper-parameter tuning, and verifying the prediction performance of the physical prior neural network on a test data set of a simulation scene and a test data set of an actual scene; according to the method, precise modeling and control over the temperature and power of the air conditioner building system are achieved, convergence is faster compared with a traditional neural network, the requirement for training data is lower, and better generalization performance and higher expandability deployment potential are achieved.
Owner:STATE GRID ELECTRIC POWER RES INST +4

Locomotive driver fatigue state detection method

The invention relates to the technical field of computers, and provides a locomotive driver fatigue state detection method, which comprises the following steps of: S1, establishing a user image sample data set of a locomotive driver fatigue state and marking; s2, inputting a generative adversarial network model, and training a generator and a discriminator of the generative adversarial network model to perform data expansion; s3, after data expansion, inputting the data into a feature extraction model, a feature dimension reduction model and a classifier model for model training to obtain a trained user image sample model; and S4, based on the trained user image sample model, monitoring the fatigue level of the locomotive driver in real time, and giving out safety measures. According to the scheme, the training data set is effectively expanded based on the generative adversarial network, the training efficiency of the feature extraction model is remarkably improved, the convergence speed of the training process is accelerated, the model development period is shortened, the data reconstruction quality is improved through optimization of the feature dimension reduction model, and the classification precision is improved through improvement of the classifier.
Owner:CRRC DALIAN CO LTD

A scissor door hinge and a car using the same

The present invention relates to a scissor door hinge, in which a fifth axis is formed by cooperating with a multi-link support structure and a constraint shaft seat, so that a hinge arm is hinged to the constraint shaft seat through the multi-link support structure, and 5 axes are co-pointed, and the intersection point is located on an opening hinge. By arranging the fifth rotation axis at an end of the hinge arm away from the height shaft seat, the hinge arm is supported while adding a constraint force to the hinge arm, thereby avoiding the hinge arm from swinging, increasing the structural stability, and preventing the door from shaking when opening. When the door is opened or closed, the movement of the door in three directions is simplified to the coordinated movement of the five rotation axes, thereby increasing the stability of the door when opened, and realizing intelligent electric opening and closing of the scissor door. The whole movement process is simple and has little effect on the structure of the door, thereby retaining the aesthetics and practicality of the scissor door, and improving the smoothness and stability of the door movement. The door hinge has a simple structure, is easy to install, and has a low manufacturing cost, and is convenient for mass production and generalization of the hinge.
Owner:ZHEJIANG LONGJI AUTO PARTS

Scene text recognition method and system based on multi-granularity training of global vector

ActiveCN119314180AImplement decodingavoid alignmentBiological modelsText recognitionImage pair
The invention discloses a scene text recognition method and system for multi-granularity training based on global vectors, and relates to the technical field of scene text recognition. The method comprises the following steps: acquiring a to-be-recognized image, and cutting the to-be-recognized image to obtain a part containing a text; the scene text recognition model is used for carrying out scene recognition on the part containing the text to obtain a recognition result, and training is carried out on the scene text recognition model stage by stage and comprises the steps that training samples are preprocessed, the preprocessed samples are encoded through an encoder, global vectors containing multi-granularity information are extracted, and the global vectors containing the multi-granularity information are obtained; and decoding the global vector by using a decoder to obtain an identification result. According to the method, the information of different granularities of the image can be better utilized, the information of the image can be fully learned from easy to difficult, and a better effect can also be achieved for complex texts and curved texts.
Owner:SHANDONG UNIV

Underwater sound time-varying channel prediction method based on kernel recursive least square

The invention discloses an underwater acoustic time-varying channel prediction method based on kernel recursive least squares, and relates to the technical field of ocean communication, and the method comprises the steps: obtaining channel sample data, and constructing a gain training sample and a time delay training sample; and constructing a multipath gain prediction model and a multipath time delay prediction model of any path p by using a kernel recursion least square method, and training corresponding prediction models. And utilizing the trained corresponding prediction model to predict and obtain a multipath gain prediction value and a multipath time delay prediction value of the prediction moment T according to the historical sample sequences of a plurality of continuous moments before the prediction moment T. And integrating the multipath gain prediction values and the multipath time delay prediction values of all paths at the prediction time T to obtain a channel prediction value of the underwater sound time-varying channel at the prediction time T. According to the method, real-time tracking prediction can be carried out on the underwater sound time-varying channel in a complex and changeable underwater environment, and performance improvement of an underwater sound communication system is facilitated.
Owner:CHINA SHIP SCIENTIFIC RESEARCH CENTER