Product
Patsnap Eureka
For R&D, Patsnap Eureka makes reading and utilizing patents & technical documents easy.
Patsnap Eureka AIR
Designed for self-driven R&D workflows. Generate viable solutions, solve complex R&D challenges, empower your innovation with AI.
Patsnap Eureka Materials
Designed for material experts only. Revolutionize your material R&D, from search, analyze, to developing new materials.
Feature
TechResearch
Generate reliable direction feasibility study reports for your R&D in just a few steps.
TechSeek
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
TechMind
As an expert in R&D Theories, TechMind can generates customized viable solutions instantly.
TechRisk
Analyze your overall solution with one click, know your potential R&D risks in advance.
TechMonitor
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
45results about How to "Suppress overfitting" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Automatic identification system of number plate on the basis of simplified convolutional neural network
ActiveCN105354572AAchieve positioningSuppress noiseCharacter and pattern recognitionHidden layerNerve network
The invention discloses an automatic identification system of a number plate on the basis of a simplified convolutional neural network. The convolutional neural network comprises an input layer, a convolutional layer, a pooling layer, a hidden layer and a classification output layer and solves the problem of number plate identification under a daily background. The number plate identification comprises the following steps: positioning, segmenting and identifying. The invention puts forward a positioning method which extracts colorful edges by colorful edge information and colorful information. Since parameters in the method are set on the basis of color features, noise in the daily background can be effectively inhibited, and input images of different sizes can be subjected number plate extraction. The automatic identification system omits a front convolutional layer of a traditional depth convolutional neural network and only keeps one layer of convolutional layer and one hidden layer. As the supplementation of a missing convolutional layer and the strengthening of input features, a gray level edge image obtained by a Sobel operator is used as the input of a colorful image, i.e., coarsness features which are artificially extracted replace features extracted by multiple convolutional layers of the traditional convolutional neural network.
Owner:SUZHOU UNIV
Posture correction method based on depth information and skeleton information
ActiveCN106650687AOvercome the disadvantage of being susceptible to external interference such as lightAccurate trackingInput/output for user-computer interactionCharacter and pattern recognitionHuman bodyVisual field loss
The invention relates to a posture correction method based on depth information and skeleton information, and the method comprises the steps: (1), carrying out the effective skeleton point screening based on a user ID and a skeleton space coordinate depth value; (2), carrying out the smoothing of the skeleton information, and carrying out the coordinate standardization of skeleton points in a skeleton space coordinate system; (3), drawing skeleton vectors, and calculating a direction cosine value of each skeleton vector; (4), obtaining a training data set and a testing data set; (5), enabling the data sets to serve as the input of a Bayes regularization BP neural network, and carrying out the recognition of 25 skeleton points and 24 skeleton segments through the Bayes regularization BP neural network; (6), carrying out the analysis and processing of a result. The method irons out the defect that a color camera is liable to be affected by light, can accurately track a human body in a visual field, and also improves the naturalness of man-machine interaction.
Owner:SHANDONG UNIV
A static image crowd counting method based on joint learning
ActiveCN109344736AImprove counting accuracySuppress overfittingCharacter and pattern recognitionCrowd countingData set
The invention discloses a static image crowd counting method based on joint learning, includes the following steps: pre-training stage: using 50-layer residual network to train the ImageNet 2012 classification data set to obtain the parameter initialization classifier network, classifying the image blocks into three categories by a Softmax, respectively corresponding to three regressors; In the training phase, every image block of the training data set is input to three regressors respectively, and the same image block will get different counting results. The regressor with the smallest counting error is used as a classification tag to mark the image block, and the three kinds of image blocks are used to fine-tune the regressors respectively. Classifier training phase: random sampling andensure that the number of labels of each category is consistent; Joint training phase: continuous iterative training of classifiers and regressors. The invention can carry out counting and density estimation in crowd dense scene, has certain scale self-adaptability, and improves counting precision and model generalization ability.
Owner:SUZHOU UNIV
Rotating-machinery life-stage identification method based on deep self-encoding learning network of noise enhanced samples
InactiveCN107016241ASuppress overfittingImprove robustnessNeural architecturesSpecial data processing applicationsPattern recognitionAdaptive learning
Owner:CHONGQING JIAOTONG UNIVERSITY
Aircraft electromechanical system fault identification method based on random convolutional neural network
InactiveCN109001557AGood spatial correlationSolve the problem of reasonable conversionTesting electric installations on transportNeural architecturesSpatial correlationStochastic gradient descent
The invention provides an aircraft electromechanical system fault identification method based on a random convolutional neural network. The method includes the following steps that: firstly, the short-time Fourier transform is adopted to construct a vibration acceleration signal into a two-dimensional time-frequency map with good spatial correlation, and the problem of two-dimensional transformation of a one-dimensional signal is solved; secondly, the transformed two-dimensional time-frequency map is input into the random convolutional neural network, wherein the network adopts a random dropout mechanism to suppress the model overfitting and enhance the generalization ability, and adopts a momentum stochastic gradient descent algorithm to update network parameters and further complete theconstruction of an identification model; and finally, the random convolutional neural network is adopted to identify the fault of an aircraft electromechanical system. The scheme of the invention is good in identification effect and strong in practicability, is simple and practicable, and is suitable for fault identification of an aircraft system.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
Electromagnetic red information detection method based on cepstrum and convolutional neural network
PendingCN109633289ALarge dynamic rangeHigh precisionElectromagentic field characteristicsSignal-to-noise ratio (imaging)Cepstral analysis
The invention provides an electromagnetic red information detection method based on cepstrum and a convolutional neural network. Firstly, samples of a plurality of electromagnetic leakage signals arecollected and downsampled; information leakage characteristics in the electromagnetic leakage signals are extracted through cepstrum analysis; electromagnetic red information feature representation based on cepstrum is formed; a large number of classification training are carried out on the extracted red information features through the convolutional neural network; a detection model about the electromagnetic red information is obtained; a to-be-detected electromagnetic leakage signal sample is input; downsampling and cepstrum electromagnetic red information feature extraction are also carriedout, finally, the trained electromagnetic red information detection model is used for carrying out identification judgment on the red information features, and the detection accuracy of the electromagnetic red information is evaluated by comparing a detection result with a priori label of the to-be-detected electromagnetic leakage signal sample. According to the electromagnetic red information detection method provided by the invention, the electromagnetic leakage signal can be detected in an environment with a low signal-to-noise ratio, the sensitivity is high, and the detection accuracy ishigher than that of a traditional method.
Owner:JIMEI UNIV
Small data cross-domain action recognition method based on double-chain deep double-flow network
ActiveCN110458038ASolve cross-domain problemsSolve the problem of inconsistent data distributionCharacter and pattern recognitionNeural architecturesData setSmall data
The invention discloses a small data cross-domain action recognition method based on a double-chain deep double-flow network. Efficient action recognition of other small-scale data sets based on a source domain data set is achieved. Meanwhile, a data set CDSAR used on the cross-domain action recognition task is provided. The method comprises the following specific steps: (1) preprocessing video; (2) building a model based on a double-chain deep double-flow network; (3) constructing a target function based on the double-chain deep double-flow network; (4) adopting a small data cross-domain action recognition method based on a double-chain deep double-flow network. Efficient action recognition can be carried out on other data sets only with a small number of samples based on the known data set, the problems that the data size of the target data set is small and data distribution among different data sets is inconsistent can be effectively solved, and the convergence speed of the method is high.
Owner:TIANJIN UNIVERSITY OF TECHNOLOGY
Automatic driving attention detecting system and method
The invention relates to the field of automatic driving, in particular to an intelligent driving system for concerning the attention of a driver. The intelligent driving system comprises a central control unit, an information collection unit and the like. The central control unit further comprises a safety unit, and in the intelligent driving mode, the safety unit ensures the driving safety by detecting the coordinates of the position to which the human eyes pay attention in real time. In order to ensure the sight position detection accuracy, the images of the human face at various angles canbe efficiently collected by using a home-made data acquisition chassis for training; by using a neural network, a human eye image and a human head gesture image are fused together to be input into theneural network, so that the neural network learns the eye and head gesture overlapped image data, that is specially for a collected high-quality image data set for training, a neural network matchedwith the image data set is designed.
Owner:MOMENTA SUZHOU TECH CO LTD
Near-infrared brain function signal extracting method based on least square support vector machine
InactiveCN105962950AQuality improvementEliminate the influence of error interferenceDiagnostics using spectroscopySensorsNear infrared lightLeast squares support vector machine
A method for extracting near-infrared brain function signals based on a least squares support vector machine, the invention relates to a method for extracting near-infrared brain function signals. The purpose of the present invention is to solve the problem of low detection accuracy of near-infrared brain function activity signals. The specific process is called: 1: Obtain the time signal of the optical density change of two near-infrared lights of different wavelengths at different distances; 2: Obtain the time signal of the concentration change of oxygenated hemoglobin and the time signal of the concentration change of reduced hemoglobin; 3: Obtain the time signal of the change in the concentration of oxygenated hemoglobin Brain function activity signal; four: get W of W(t) * (t); Five: Get the brain function activity signal E(t): Six: Get the brain function activity signal after eliminating the error interference; Seven: Construct the Lagrangian function to get the linear equation system; Eight: Solve the linear equation system to get La The numerical solution of the Grangian multiplier vector α and the offset b, at this time, the brain function activity signal processed by the least squares support vector machine regression function is expressed as E * (t). The invention is used for brain function signal extraction.
Owner:HARBIN INST OF TECH
Supporting-vector-machine-based industrial melt index soft measuring meter and method
InactiveCN103675010AReduce the impact of forecast accuracySuppress overfittingAdaptive controlInvestigating phase/state changeSupport vector machineAdaptive optimization
The invention discloses a supporting-vector-machine-based industrial melt index soft measuring meter and a method. By performing the optimal optimizing on parameters of a fuzzy neural network through the supporting vector machine, the problems of parameter set of the existing fuzzy neural network are solved, and meanwhile, due to the adoption of the method, the structure of the whole fuzzy neural network is subjected to self-adaption updating so as to adapt the change of input data. According to the invention, an on-site intelligent meter and a control station are connected with a DCS (distributed control system) database; a soft measurement value display device comprises a supporting-vector-machine-based industrial melt index soft measuring model; the DCS database is connected with the input end of the soft measuring model; and the output end of the supporting-vector-machine-based industrial melt index soft measuring model is connected with the melt index soft measurement value display device; the measuring meter and the method disclosed by the invention have the characteristics of self-adoption optimized model structure, high noise resisting property and preferable popularization property.
Owner:ZHEJIANG UNIV
Remote sensing image small target detection method based on feedback type multi-scale training
PendingCN112016512AEasy to detectImprove accuracyGeometric image transformationCharacter and pattern recognitionEngineeringThresholding
The invention discloses a remote sensing image small target detection method based on feedback type multi-scale training, and the method comprises the steps of building a feedback type multi-scale convolution neural network which consists of a detection module and a feedback multi-scale training module, inputting original image data, and carrying out the training of the original image data in an end-to-end mode; enabling the feedback multi-scale training module to calculate the proportion value of the small target according to the loss of the current iteration process output by the detection module; comparing the calculated proportion value of the small target with a preset threshold value, and when the proportion value is smaller than the preset threshold value, using the spliced image data as the input of the next iteration, otherwise, using the original image data as the input; and obtaining a trained feedback type multi-scale convolutional neural network, inputting a to-be-detectedremote sensing image, and outputting an identification result. The detection capability of the small target in the remote sensing image is enhanced, the over-fitting phenomenon and the category imbalance phenomenon are inhibited, and the method has better effect and robustness for detecting the small target in the remote sensing image.
Owner:CHONGQING GEOMATICS & REMOTE SENSING CENT
Short-term generalized load prediction method based on transfer learning
ActiveCN110969293AImprove predictive performanceImprove balanceForecastingMachine learningData setLoad forecasting
The invention discloses a short-term generalized load prediction method based on transfer learning, and the method comprises the following steps: constructing a short-term load prediction integrated model, and carrying out the analysis of a prediction error of the short-term load prediction model; solving the weight by using an algorithm based on iteration and cross validation; constructing a short-term load prediction model based on load time series decomposition and instance migration; based on the hidden variable model, constructing a public model for the target problem and the source problem; and designing a hidden variable extraction module based on the load affine curve. According to the method, the target of transfer learning is introduced into the short-term load prediction problem, the similarity between the source problem and the target problem is ingeniously utilized, the source problem data set is introduced to assist the training process of the target problem, and the target of improving the prediction effect of the target problem can be achieved; the prediction precision can be improved by utilizing the hidden variable model; through a hidden variable extraction module designed based on a load affine curve and based on the hypothesis, the calculation complexity can be reduced.
Owner:SHANGHAI JIAO TONG UNIV
CondenseNet algorithm fused with attention selection mechanism
InactiveCN111160488AEfficient use ofEasy to learnCharacter and pattern recognitionNeural architecturesAlgorithmNetwork structure
The invention provides a ContenseNet algorithm fused with an attention selection mechanism, and the algorithm comprises the steps: carrying out the feature extraction on data in a convolutional neuralnetwork through m network structure blocks, wherein each structure block comprises n groups of complete feature transformation layers, enabling the data to obtain a corresponding feature matrix through each feature transformation layer, cascading the m network structure blocks, performing feature extraction on data of the network structure blocks to obtain a final feature matrix, calculating a loss value of network training according to the obtained feature matrix, calculating an error term and a weight gradient of each layer, and judging whether the network is converged or not according to the loss value, if not, adjusting the convolutional neural network initialization parameter according to the weight gradient to perform training again, and if so, outputting a network training result.According to the CondenseNet algorithm fused with the attention selection mechanism, multi-dimensional feature information is efficiently utilized, the learning and expression capacity of a deep network is enhanced, and the classification accuracy is improved.
Owner:CIVIL AVIATION UNIV OF CHINA
Industrial melt index soft measurement method through combination of fuzzy neural network and group intelligent optimization
InactiveCN109507887ASimple structureReduce the impact of forecast accuracyAdaptive controlFuzzy ruleSlide window
The invention discloses an industrial melt index soft measurement method through combination of a fuzzy neural network and group intelligent optimization. The method is applied to online prediction for an industrial melt index in the propylene polymerization production process. A data preprocessing module, a fuzzy neural network module, a dragonfly optimizing algorithm module, a sliding window module and a fuzzy rule optimization module are involved. According to a sliding window method, input of the fuzzy neural network every moment is provided, by using an improved dragonfly optimizing algorithm, a fuzzy neural network parameter is intelligently optimized, and the setting problem of the fuzzy neural network parameter in the prior art is solved. According to the method, global and local information in the optimizing process is considered at the same time, a network parameter can be stably and online corrected, and the adaptivity of the system to input data fluctuation is improved. Themethod has the advantages of stable optimized model structure, good generalization performance and high anti-interference capacity.
Owner:ZHEJIANG UNIV
Soft industrial melt index measurement instrument and method for optimal fuzzy network
InactiveCN103675005ASuppress overfittingImprove stabilityAdaptive controlInvestigating phase/state changeSupport vector machineCommunications system
The invention discloses a soft industrial melt index measurement instrument and method for an optimal fuzzy network. According to the method, a previous fuzzy neural network is optimized by introducing a support vector machine so that the problem that parameters are difficult to set in the construction process of the fuzzy neural network is solved. According to the soft industrial melt index measurement instrument and method for the optimal fuzzy network, a field intelligent instrument and a control station are connected with a DCS (Data Communication System) database; a soft measurement value displayer comprises a soft industrial melt index measurement model for the optimal fuzzy network; the DCS database is connected with the input end of the soft measurement model; the output end of the soft industrial melt index measurement model for the optimal fuzzy network is connected with the soft melt index measurement value displayer. Finally, the soft industrial melt index measurement instrument and method for the optimal fuzzy network and the soft measurement have the characteristics of on-line measurement, high calculation speed, strong noise immunity and good popularization performance.
Owner:ZHEJIANG UNIV
Imaged liquor recognition method applicable to multiple electronic nose platforms
ActiveCN108694375AFully reflect the value rangeFully reflect the time domain informationCharacter and pattern recognitionSingle sampleTransfer probability
The invention relates to an imaged liquor recognition method applicable to multiple electronic nose platforms. The method comprises the steps that liquor sample original data collected by different sensors is acquired and subjected to normalization processing; sensor response values are converted into an angle cosine and matrix through an anti-cosine function; a half-angle sine and matrix Hs and ahalf-angle cosine and matrix Hc are obtained; Markov transfer probabilities are calculated after binning operation is performed on sensor responses, and then a Markov domain matrix MTF is calculated;sensor images are constructed, piecewise aggregate approximation is utilized to determine image dimensions, and multiple sensor images are combined for each sample to obtain a combination image describing the single sample; a convolutional neural network model is established; and training is performed.
Owner:TIANJIN UNIV
Cerebral functional magnetic resonance imaging blind source separation method based on grouping SIM algorithm
ActiveCN107092925AIn line with the real situationSuppress overfittingCharacter and pattern recognitionNonlinear dimensionality reductionData set
The invention discloses a cerebral functional magnetic resonance imaging blind source separation method based on a grouping SIM algorithm. The implementing steps include: for each tested cerebral functional magnetic resonance imaging after pre-processing, firstly, conducting individual-level dimensionality reduction through a PCA method, secondly, combining all the tested data after dimensionality reduction to obtain a group data set, and thirdly, conducting group-level dimensionality reduction of the group data set through the PCA method; subjecting the group data set after dimensionality reduction to analysis and processing through an SIM algorithm, and obtaining a group-level brain source network; subjecting the group-level brain source network to reverse reconstruction and then standardization to obtain each tested brain source network and corresponding time fluctuation; and subjecting each tested brain source network and the corresponding time fluctuation to weighted averaging, and obtaining the average brain source network of the group and the corresponding time fluctuation. The method of the invention has the advantages of the principle fitting the reality, being low in data calculation, high in algorithm operation speed, and real and reliable data analysis result.
Owner:NAT UNIV OF DEFENSE TECH
Electric power system static voltage stability evaluation method based on improved AdaBoost
ActiveCN111400966AReduce dimensionalityMeeting Online VSA RequirementsCharacter and pattern recognitionDesign optimisation/simulationData setElectric power system
The invention discloses an electric power system static voltage stability evaluation method based on improved AdaBoost. The method comprises the steps: 1, constructing an initial data set containing electric power system operation variables and voltage stability safety classification labels; 2, forming an efficient data set; 3, based on the efficient data set, combining with an improved AdaBoost algorithm to construct a power system voltage stability evaluation model, and using the efficient data set to perform offline training and updating on the VSA model; 4, based on the real-time measurement data collected by the synchronous phasor measurement unit, performing online VSA on the power system by using the VSA model. The method is strong in generalization ability and high in classification accuracy, can effectively avoid the occurrence of an over-fitting phenomenon, and can carry out reliable on-line safety evaluation on the power system.
Owner:CHINA THREE GORGES UNIV
Water environment remote sensing data modeling method based on multilayer convolutional neural network
InactiveCN111680626AImprove generalization abilitySuppress overfittingScene recognitionNeural architecturesWater qualityEngineering
The invention belongs to the technical field of water environment remote sensing data analysis, and particularly relates to a water environment remote sensing data modeling method based on a multilayer convolutional neural network, and a data model is formed by sequentially connecting an input layer, a training layer and an output layer; the input of the input layer is preprocessed remote sensingimage data; the training layer comprises a convolution layer, a pooling layer and a full connection layer; each of the convolution layer, the pooling layer and the full connection layer is composed ofa plurality of hidden neurons with mutually independent matrixes; the output layer is used for outputting results, the training layer learns and inputs high-level features through layer-by-layer feature extraction of a remote sensing spectral feature curve of remote sensing image data acquired by a preprocessed satellite, and inputs the high-level features into the full connection layer to identify a result; and the large-scale water environment online remote sensing water quality accurate identification and diagnosis system aims to realize large-scale water environment online remote sensingwater quality accurate identification and diagnosis of the three gorges reservoir area so as to provide a reliable and easy-to-use large-scale water environment monitoring and auxiliary decision-making tool.
Owner:CHONGQING UNIV
Pedestrian re-identification method and device
ActiveCN108960013ASuppresses overfitting problemsRobustCharacter and pattern recognitionRe identificationTest sample
The invention provides a pedestrian re-identification method and device. The pedestrian re-identification method includes the steps: measuring the similar distance of each test sample pair in a test set one by one based on a metric space; and sorting the similar distance measurement results of all test sample pairs in the test set to obtain a distance measurement matrix. The pedestrian re-identification method obtains a group of stable combined metric space through iterative learning, calculates the combined similar distance of the test sample pairs in the multi-metric space, overcomes the over fitting problem of an existing metric learning method in the high-dimensional small sample problem, and has higher robustness for the complex feature change in the pedestrian re-identification problem.
Owner:深圳荆虹科技有限公司
Defect classification apparatus
InactiveUS8977580B2Accurate classificationSuppress overfittingProgramme controlImage enhancementPattern recognitionDecision boundary
Owner:NIPPON STEEL CORP
Four-rotor unmanned aerial vehicle intelligent fault diagnosis method based on convolutional neural network
PendingCN113960989AIncrease diversityTo improve the lack of samplesProgramme controlElectric testing/monitoringFlight dataAutocode
The invention provides an intelligent fault diagnosis method based on a stack pruning sparse denoising automatic encoder and a convolutional neural network, which is called sPSDAE-CNN for short. According to the method, original input data is processed by using the stack denoising automatic encoder, and more training data is obtained by using a data enhancement method. The stack sparse pruning and noise reduction self-encoder comprises a full-connection automatic encoding network, and the characteristics extracted at the front layer of the network are used for performing the operation of the subsequent layer, which means that some new connections appear between the front and rear layers of networks, so that the information loss is reduced, and more effective characteristics are obtained; meanwhile, pruning operation is introduced, so that the training efficiency and precision of the network are improved, higher training speed and high adaptability to noise signals are achieved, and the overfitting problem of the convolutional neural network is suppressed to a certain extent; according to the method, the flight data of the quad-rotor unmanned aerial vehicle are input into the model, and high fault diagnosis accuracy is obtained under the condition of high noise interference.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Expandable convolutional neural network training method and CT image segmentation model construction method
ActiveCN113269765ASuppress overfittingImprove performanceImage enhancementImage analysisEngineeringImage segmentation
The invention provides an expandable convolutional neural network training method and a CT image segmentation model construction method. The expandable convolutional neural network training method comprises the steps of performing down-sampling on an original image to obtain training samples of different scales, performing convolution calculation on the training samples in an expandable convolutional neural network according to the sizes from small to large, and training expandable convolution kernel parameters; and after training of the training sample of each size is completed, expanding the expandable convolution kernel, and inheriting a result obtained by previous training to carry out fine training on the expandable convolution kernel. By adopting the training mode that the large-size data training process depends on the small-size data training result, a cascade relation of multi-step training is formed, the training speed of the network model can be remarkably increased, pre-training data does not need to be additionally prepared, the training process is suitable for various network models of different dimensions, and the segmentation precision of the network model can be improved on the premise of not using the pre-training model.
Owner:CHONGQING UNIV
Improved gesture image feature extraction method based on DenseNet network
PendingCN114170634AIncrease training speedReduce flowBiometric pattern recognitionNeural architecturesRadiologyNetwork structure
The invention discloses an improved gesture image feature extraction method based on a DenseNet network. Acquiring a gesture to obtain an original gesture image; performing convolution downsampling through a convolution downsampling network structure, selecting feature tensors of a shallow layer and a deep layer, and inputting the feature tensors into a DenseNet-B module of a fused Drop-Path module to obtain two feature tensors; after fusion, obtaining a feature tensor of multi-scale feature fusion, compressing the feature tensor through a transition layer, and inputting the compressed feature tensor into a DenseNet-B module of the fusion Drop-Path module to obtain a feature tensor containing multiple scales and high dimensions; and obtaining a classification result through a global average pooling layer, a full connection layer and a softmax classifier. According to the method, feature tensors of different depths in a down-sampling network structure are included, large target objects and small target objects can be accurately recognized, meanwhile, a Drop-Path module is fused in the DenseNet network, the parameter quantity is effectively reduced while the precision is not reduced, the model training speed is increased, overfitting is prevented, and the gesture recognition accuracy is improved.
Owner:ZHEJIANG SCI-TECH UNIV
Coal gangue classification and identification method and process based on image enhancement and deep learning
PendingCN114627109AOvercoming indistinguishable problemsSmall amount of calculationImage enhancementImage analysisData setEngineering
The invention discloses a coal gangue classification and recognition method and process based on image enhancement and deep learning, belongs to the field of computer vision and image processing, and particularly relates to a coal gangue classification and recognition method. The method comprises the steps of collecting coal and gangue images and performing image enhancement processing, making a data set for the coal and gangue images subjected to the coal and gangue image enhancement processing, building and improving a LeNet network, training the obtained data set, and obtaining a coal and gangue classification and recognition result model through neural network training; according to the method, the difference of the coal and gangue images is increased by performing image enhancement processing on the collected original coal and gangue images, and the convolutional neural network in deep learning is combined, so that the coal and gangue classification and recognition accuracy is greatly improved, and the problem that the existing coal and gangue recognition accuracy is low at present is solved.
Owner:HEBEI UNIV OF ENG
Industrial Melt Index Soft Sensing Instrument and Method Based on Support Vector Machine
InactiveCN103675010BReduce the impact of forecast accuracySuppress overfittingAdaptive controlInvestigating phase/state changeSupport vector machineMeasuring instrument
The invention discloses a supporting-vector-machine-based industrial melt index soft measuring meter and a method. By performing the optimal optimizing on parameters of a fuzzy neural network through the supporting vector machine, the problems of parameter set of the existing fuzzy neural network are solved, and meanwhile, due to the adoption of the method, the structure of the whole fuzzy neural network is subjected to self-adaption updating so as to adapt the change of input data. According to the invention, an on-site intelligent meter and a control station are connected with a DCS (distributed control system) database; a soft measurement value display device comprises a supporting-vector-machine-based industrial melt index soft measuring model; the DCS database is connected with the input end of the soft measuring model; and the output end of the supporting-vector-machine-based industrial melt index soft measuring model is connected with the melt index soft measurement value display device; the measuring meter and the method disclosed by the invention have the characteristics of self-adoption optimized model structure, high noise resisting property and preferable popularization property.
Owner:ZHEJIANG UNIV
Accent classification method based on deep neural network and model thereof
PendingCN112992119ALearn accuratelyAccurate Voice FeaturesCharacter and pattern recognitionSpeech recognitionFrequency spectrumClassification methods
The invention discloses an accent classification method based on a deep neural network. The method comprises the steps: extracting frame-level frequency domain features of an original audio, and constructing a 2D speech spectrum as a network input X; constructing a multi-task weight shared CRNNs-based front-end encoder to extract local sequence descriptors {P1,..., PT'} of the spectrum X; in the training process, additionally arranging a speech recognition task branch network behind the front-end encoder to inhibit an overfitting phenomenon in accent recognition; constructing a core branch network for an accent recognition task, and firstly, integrating all local sequence descriptors into a global accent feature; secondly, introducing a discriminative loss function in a prediction process; and finally, classifying the global accent features through a softmax-based classification layer to realize accent prediction. The invention also discloses a highly discriminatable accent classification model based on the deep neural network, and reliable accent prediction can be provided for speakers from different regional groups.
Owner:ANHUI UNIVERSITY
Industrial melt index soft measurement method based on aftereffect function and cuckoo search
InactiveCN109471363AImproving Online Prediction AccuracyImprove forecast accuracyAdaptive controlAnti jammingData modeling
The invention discloses an industrial melt index soft measurement method based on an aftereffect function and cuckoo search. The industrial melt index soft measurement method is used for conducting online prediction on industrial melt indexes in the propylene polymerization production process and involves a data preprocessing module, an aftereffect function module and a cuckoo search algorithm module. According to the method, the cuckoo search algorithm is utilized for optimizing parameters in the aftereffect function, and the numerical value is approximate to the optimal solution of the aftereffect function. By means of the method, the mechanism and data modeling are both considered, and the prediction result is more accurate fundamentally. Meanwhile, through the utilization of cuckoo search, the function network parameter optimization process can be further accelerated, and the practicability and generalizability of the system are improved. The system has the advantages of being highin prediction precision, stable in running, good in generalizability and high in anti-jamming capability.
Owner:ZHEJIANG UNIV
A pedestrian re-identification method and device
ActiveCN108960013BSuppress overfittingImprove robustnessCharacter and pattern recognitionTest sampleLearning methods
The invention provides a pedestrian re-identification method and device. The pedestrian re-identification method includes: based on a metric space, measuring the similarity distance of each test sample pair in the test set one by one; Sort to get the distance metric matrix. The pedestrian re-identification method provided by the present invention obtains a set of stable joint metric spaces through iterative learning, calculates the joint similarity distance of the test sample pair in the multi-metric space, and overcomes the over-problem of the existing metric learning method in the high-dimensional small sample problem. The fitting problem is more robust to the complex feature changes in the pedestrian re-identification problem.
Owner:深圳荆虹科技有限公司
Industrial melt index soft sensor instrument and method based on optimal fuzzy network
InactiveCN103675005BSuppress overfittingImprove stabilityAdaptive controlInvestigating phase/state changeSupport vector machineCommunications system
The invention discloses a soft industrial melt index measurement instrument and method for an optimal fuzzy network. According to the method, a previous fuzzy neural network is optimized by introducing a support vector machine so that the problem that parameters are difficult to set in the construction process of the fuzzy neural network is solved. According to the soft industrial melt index measurement instrument and method for the optimal fuzzy network, a field intelligent instrument and a control station are connected with a DCS (Data Communication System) database; a soft measurement value displayer comprises a soft industrial melt index measurement model for the optimal fuzzy network; the DCS database is connected with the input end of the soft measurement model; the output end of the soft industrial melt index measurement model for the optimal fuzzy network is connected with the soft melt index measurement value displayer. Finally, the soft industrial melt index measurement instrument and method for the optimal fuzzy network and the soft measurement have the characteristics of on-line measurement, high calculation speed, strong noise immunity and good popularization performance.
Owner:ZHEJIANG UNIV
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com