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.
53 results about "Autologistic regression" 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
Anomaly detection, forecasting and root cause analysis of energy consumption for a portfolio of buildings using multi-step statistical modeling
Multi-step statistical modeling in one embodiment of the present disclosure enables anomaly detection, forecasting and / or root cause analysis of the energy consumption for a portfolio of buildings using multi-step statistical modeling. In one aspect, energy consumption data associated with a building, building characteristic data associated with the building, building operation and activities data associated with the building, and weather data are used to generate a variable based degree model. A base load factor, a heating coefficient and a cooling coefficient associated with the building and an error term are determined from the variable based degree model and used to generate a plurality of multivariate regression models. A time series model is generated for the error term to model seasonal factors which reflect monthly dependence on energy use and an auto-regressive integrated moving average model (ARIMA) which reflects temporal dependent patterns of the energy use.
Owner:GLOBALFOUNDRIES INC
Anomaly detection, forecasting and root cause analysis of energy consumption for a portfolio of buildings using multi-step statistical modeling
Multi-step statistical modeling in one embodiment of the present disclosure enables anomaly detection, forecasting and / or root cause analysis of the energy consumption for a portfolio of buildings using multi-step statistical modeling. In one aspect, energy consumption data associated with a building, building characteristic data associated with the building, building operation and activities data associated with the building, and weather data are used to generate a variable based degree model. A base load factor, a heating coefficient and a cooling coefficient associated with the building and an error term are determined from the variable based degree model and used to generate a plurality of multivariate regression models. A time series model is generated for the error term to model seasonal factors which reflect monthly dependence on energy use and an auto-regressive integrated moving average model (ARIMA) which reflects temporal dependent patterns of the energy use.
Owner:GLOBALFOUNDRIES INC
Method and system for estimating energy generation based on solar irradiance forecasting
ActiveUS20200041550A1Programme controlWeather condition predictionRegression analysisAutologistic regression
Estimating energy generated by a solar system in a predetermined geographic area comprises, at each predetermined time instant: retrieving measured values of at least one weather parameter and of solar irradiance in the geographic area, the values related to a time slot before the predetermined time instant; performing auto-regression analysis of the measured values; estimating, based on the auto-regression analysis, a relationship between the at least one weather parameter and the solar irradiance; retrieving forecasted values of the at least one weather parameter in the geographic area, the forecasted values being forecasted for a second time slot after the predetermined time instant; performing regression analysis of the relationship between the at least one weather parameter and the solar irradiance of the forecasted values; forecasting solar irradiance in the second time slot based on the regression analysis, and estimating energy generated by the solar system in the second time slot.
Owner:TELECOM ITALIA SPA
Virtual machine monitoring method in vector-autoregression-based cloud computing
ActiveCN102799512ASolve the overall efficiency of monitoringSolve efficiency problemsHardware monitoringSoftware simulation/interpretation/emulationOriginal dataMonitoring system
The invention relates to a virtual machine monitoring method in vector-autoregression-based cloud computing, which is a novel monitoring method. Because the data volume of specific monitoring of virtual machine monitoring in cloud computing is relatively huge, a huge pressure is caused to a monitoring system by the adoption of periodic monitoring, the monitoring in a 'pull' mode, through which more resources are saved, is adopted, but the intelligent judgment on the time for collecting the data is decided, therefore, not only the real-time capability is increased, but also the resource pressure of the system is reduced; the real-time monitoring is realized based on the virtual machine monitoring in the cloud computing based on VAR (vector autoregression), and the use ratio of the resource is improved. A new regression equation can be established by a model according to the original data model, prediction is made to the resource data in the next period, and the collection of the analog data is carried out according to the prediction values and the cooperation with the 'pull' mode. The self-adaption and the real-time capability of the resource monitoring are increased by the algorithm.
Owner:长沙凯乐信息技术有限公司
Space-time estimation and prediction method for PM2.5 concentration distribution
ActiveCN111859800AParticle size analysisDesign optimisation/simulationComputational physicsAutologistic regression
The invention provides a space-time estimation and prediction method for PM2.5 concentration distribution. The space-time estimation and prediction method for PM2.5 concentration distribution comprises: collecting and correcting fine-grained aerosol optical thickness (AOD), calculating a regression model of fine-grained PM2.5, and predicting fine-grained PM2.5 concentration distribution. By comparing several regression models with a machine learning model, an XGBoost model is determined as an estimation model under the framework, the minimum root mean square error (RMSE) is 32.86 [mu]g / m<3>, and the maximum R2 is 0.71. 10 times of verification and space-time comparison with a traditional time series prediction model, namely a seasonal autoregressive differential moving average (SARIMA) model, are carried out; the prediction precision of ConvLSTM is higher, the total average prediction RMSE is 14.94 [mu]g / m<3>, and the prediction precision of SARIMA is 17.41 [mu]g / m<3>. Moreover, the ConvLSTM is relatively small in fluctuation in time and relatively good in stability, and the spatial difference of prediction precision can be relatively well eliminated in space.
Owner:HOHAI UNIV
Neural machine translation decoding acceleration method based on non-autoregression
ActiveCN111382582AAlleviate the multimodal problemDoes not slow down inferenceNatural language translationEnergy efficient computingPattern recognitionHidden layer
The invention discloses a neural machine translation decoding acceleration method based on non-autoregression. The neural machine translation decoding acceleration method comprises the steps of: constructing an autoregression neural machine translation model through employing a Transformer model based on an autoattention mechanism; constructing training parallel corpora, generating a machine translation word list, and training the two models from left to right and from right to left until convergence; constructing a non-autoregression machine translation model; acquiring codec attention and hidden layer states of a left-to-right autoregression translation model and a right-to-left autoregression translation model; calculating the difference between the output and the output corresponding to the autoregressive model, and taking the difference as additional loss for model training; extracting source language sentence information, and predicting a corresponding target language sentence bya decoder; and calculating the loss of predicted distribution and real data distribution, decoding translation results with different lengths, and further acquiring an optimal translation result. According to the neural machine translation decoding acceleration method, knowledge in the regression model is fully utilized, and 8.6 times of speed increase can be obtained under the condition of low performance loss.
Owner:沈阳雅译网络技术有限公司
Determination method in allusion to homogenous signal time difference under multipath environment
InactiveCN102833016AHigh-resolutionImprove accuracyWave based measurement systemsTransmission monitoringTarget signalImage resolution
The invention relates to a determination method in allusion to homogenous signal time difference under a multipath environment. The determination method comprises the following steps of: establishing a received signal sample, determining residual errors including self-correlation processing and determination of auto-regression parameters and finally determining time difference of two paths of signals through acquiring a cross-correlation spectrum of residual errors of two paths of signals. According to the invention, compared with the prior art that two paths of received homogenous sampled signals are directly cross-correlated, the determination method disclosed by the invention has the characteristics that residual errors of two paths of sampled signals are cross-correlated by an auto-regression method to ensure that related peak shapes are sharp and are still easy to distinguish even though arrival time difference of each signal is shorter, thereby effectively improving the time difference measurement resolution rate and accuracy; and the time difference value measured by the determination method accords with the theoretical value. Therefore, the determination method has the characteristics of being high in resolution ratio of the cross-correlation spectrum of sampled signals under the multipath environment, effectively improving the signal time difference determination accuracy, providing accurate parameters for subsequent positioning of a target signal source and the like.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA +1
Tax revenue prediction method and device based on hybrid model
InactiveCN105139079ACapable of adaptive adjustmentImprove forecast accuracyFinanceBiological neural network modelsSelf adaptivePrediction methods
The present invention provides a tax revenue prediction method and device based on a hybrid model. The method comprises: testing a training data sequence by using a test data sequence of a support vector regression model, so as to acquire a prediction value of the support vector regression model; testing the training data sequence by using a test data sequence of an autoregression moving average model, so as to acquire a prediction value of the autoregression moving average model; testing the training data sequence by using a test data sequence of an artificial neural network model, so as to acquire a prediction value of the artificial neural network model; and inputting the prediction value of the support vector regression model, the prediction value of the autoregression moving average model and the prediction value of the artificial neural network model into a hybrid model, so as to calculate a prediction value of tax revenue. According to the present invention, the tax revenue prediction method and device based on the hybrid model have the following advantages that: the advantages of various models can be combined well, model parameters can be adaptively adjusted, and prediction accuracy is high.
Owner:GUANGDONG IDATATECH CO LTD
Photovoltaic power short-term prediction method and device based on machine learning, and storage medium
PendingCN113988477AHelp scientific planningFacilitate rationalityForecastingMachine learningData setNew energy
Owner:西安化奇数据科技有限公司
Sensor exception detection method based on regularized vector autoregression model
InactiveCN105740212AReduce parameter variablesEasy to predictCharacter and pattern recognitionComplex mathematical operationsAlgorithmOriginal data
The invention relates to a sensor exception detection method based on a regularized vector autoregression model. The sensor exception detection method comprises the following steps: (1) establishing a multielement linear regression model, and determining a target function; collecting data by a sensor; establishing a nearest neighbor graph of data points, wherein the graph consists of n vertexes, each vertex corresponds to one data point, and the weight matrix of edges is defined by considering a relationship between fixed points; constructing a bound term in order to keep similarity among original data points while the obstacles of high dimension and overfitting can be overcome; and utilizing the target function to train a model parameter to obtain an optimal parameter coefficient, and utilizing the model obtained by training to carry out exception detection. The sensor exception detection method can better predict original data.
Owner:TIANJIN UNIV
Real-time monthly runoff forecasting method based on deep learning model
ActiveCN113705877AEffective correctionImprove forecast accuracyClimate change adaptationForecastingStreaming dataData set
The invention provides a real-time monthly runoff forecasting method based on a deep learning model, and the method comprises the steps: 1, collecting forecasting factors based on historical information and future meteorological information, and determining the longest delay of the influence of the early monthly runoff on the forecast monthly according to the autocorrelation analysis of the monthly runoff in the historical period of a drainage basin; 2, performing normalization processing on forecast factors and monthly runoff data in a training period, and automatically screening the forecast factors by adopting an LASSO regression method based on an embedded thought; 3, clustering the training period sample set by adopting a K-means clustering method based on a division thought, and dividing samples into K classes which do not coincide with each other; 4, calculating the distance between the forecasting factor vector of the verification set and the clustering center of the K training sets, finding the nearest training set, and then training a combined deep learning forecasting model combining the convolutional neural network and the gating circulation unit network by using the data set; and 5, carrying out real-time correction on the forecast residual error by adopting an autoregressive moving average model.
Owner:WUHAN UNIV
Icing thickness prediction method and device for power transmission line
PendingCN112070272AImprove accuracyGuaranteed safe operationForecastingPredictive methodsEngineering
The invention relates to an icing thickness prediction method and device for a power transmission line. The method comprises the steps of obtaining a meteorological data prediction value of the powertransmission line at a future moment; inputting the future moment into an auto-regressive integral moving average model, and obtaining an icing thickness initial value output by the auto-regressive integral moving average model; inputting the meteorological data prediction value of the power transmission line at the future moment into a support vector regression model, and obtaining an icing thickness error value output by the support vector regression model; according to the icing thickness initial value and the icing thickness error value, determining an icing thickness final prediction value of the power transmission line at a future moment; according to the technical scheme of the invention, the prediction accuracy of the icing thickness of the power transmission line is improved through the combined prediction model.
Owner:NANJING NARI GROUP CORP +1
Method and system for predicting flow of self-adaptive differential auto-regression moving average model
The invention discloses a method and a system for predicting a flow of a self-adaptive differential auto-regression moving average model. The method and the system are used for causing a model to be more fit with a data trend of a present flow. The technical scheme comprises the following steps: utilizing an ARIMA (Autoregressive Integrated Moving Average) model to forecast the flow, and alarming when a practical value is deviated from a predicted confidence interval; while alarming, starting an alternative plan to monitor a flow data, for preventing an abnormal data from entering into ARIMA model prediction; and when the ARIMA model normally runs, judging if a parameter of the ARIMA model is still suitable in real time, and if not, automatically relearning and acquiring a new model parameter by relearning, thereby promoting the accuracy for model prediction.
Owner:CHINANETCENT TECH
Continuous stirred tank reactor operation state monitoring method based on time series data analysis
The invention discloses a continuous stirred tank reactor operation state monitoring method based on time series data analysis, and aims to solve the problem of monitoring the operation state of a continuous stirred tank reactor by monitoring the time series abnormal change of the real-time sampling data of the continuous stirred tank reactor. The method comprises the steps of firstly deducing a time series correlation characteristic analysis algorithm according to the maximum time series characteristic typical correlation coefficient; secondly, further using an auto-regression model to describe a time sequence dynamic relation between time sequence related characteristics, and finally achieving the purpose of monitoring the running state of the continuous stirred tank reactor by monitoring the errors of the auto-regression model. Compared with a traditional method, the method has the advantages that the potential characteristic components, which are typically related to a time sequence, of the sampling data can be effectively extracted, and the superiority and effectiveness of the method in monitoring the running state of the continuous stirred tank reactor are verified through specific embodiments.
Owner:长沙坪塘天然香料有限公司
Bridge probability damage detection method based on autoregression model and Gaussian process
ActiveCN111062079AReduce the difficulty of implementationEasy to handleGeometric CADDesign optimisation/simulationAlgorithmAutologistic regression
The invention provides a bridge probability damage detection method based on an autoregression model and a Gaussian process, and the method can achieve the processing of the response data of an acceleration sensor through a Gaussian process classifier and a Gaussian process regression machine, and obtains the damage position and damage degree information. The bridge probability damage detection method based on the autoregressive model and the Gaussian process has the advantages that implementation of the scheme does not depend on bridge undamaged state information and external excitation information, the implementation difficulty is low, the damage position and the damage degree can be recognized at the same time, and unreliable results are eliminated.
Owner:CHONGQING JIAOTONG UNIVERSITY +1
Disk capacity prediction method and system based on historical monitoring data, and storage medium
PendingCN113238714AMonitor usage statusMaximize UtilizationInput/output to record carriersHardware monitoringData sourceAutologistic regression
The invention discloses a historical monitoring data-based disk capacity prediction method and system, and a storage medium, and the method comprises the steps: obtaining a data source of a disk capacity use condition, and extracting sample data from the data source; obtaining first time sequence data according to the sample data; constructing an autoregressive moving average model, and taking the first time sequence as a modeling sample of the autoregressive moving average model; performing time sequence prediction through the regression moving average model to obtain second time sequence data; and according to the second time sequence data, obtaining use capacity information of the disk at the future time point. According to the method, prediction is carried out by constructing the autoregressive moving average model, so that the use state of the disk capacity is effectively monitored, the utilization rate of the disk can be maximized, and risks and resource waste caused by insufficient disk capacity are reduced.
Owner:广东好太太智能家居有限公司
Intelligent early warning method and device for enterprise strategy, electronic equipment and storage medium
PendingCN114638547ARealize intelligent early warningImprove forecast accuracyWeb data indexingSemantic analysisBusiness enterpriseEngineering
The invention relates to the field of artificial intelligence, and provides an enterprise strategy intelligent early warning method comprising the following steps: carrying out NLP identification processing on external operation data to extract external feature data; performing standardization processing and coding processing on the enterprise internal evaluation data to obtain internal reference data; the method comprises the following steps: acquiring main reference information through a multiple regression model, acquiring auxiliary reference information through a temporal difference autoregression moving average model, acquiring a predicted customer throughput trend according to the main reference information and the auxiliary reference information, and acquiring risk early warning information of a current enterprise according to the customer throughput trend and preset trend risk contrast information, therefore, intelligent early warning of the customer risk is realized, possible loss found after the event is reduced, namely, intelligent early warning of the customer risk is realized, and possible loss found after the event is reduced; the accuracy and practicability of the model are evaluated, and the throughput prediction precision is improved.
Owner:PINGAN INT SMART CITY TECH CO LTD
Multivariable closed-loop control loop performance evaluation method based on Gaussian process regression
ActiveCN111679648AStrong anti-interference abilityImprove stabilityElectric testing/monitoringLoop controlTest input
The invention relates to a multivariable closed-loop control loop performance evaluation method based on Gaussian process regression. The multivariable closed-loop control loop performance evaluationmethod comprises the following steps: S1, selecting multivariable closed-loop output data to be evaluated; S2, standardizing the data; S3, performing evaluation fragment division on the standardized data matrix in the step S2; and S4, performing autoregression modeling on the evaluation fragment data matrix X, constructing training input, training output and test input of the model, and determining model parameters by using a least square method. The beneficial effects of the invention are that process priori knowledge is not needed, the idea of data driving is utilized, performance related information contained in the process data can be mined on line; performance evaluation is performed on the multivariable closed-loop control system; comprehensive loop evaluation results and operation suggestions are given according to the change trend of the performance indexes, so that a field engineer can quickly eliminate loop faults by directly operating and maintaining the performance degradation loop through the evaluation results, automatic evaluation of a closed-loop system is realized, and safe and efficient operation of the process is guaranteed.
Owner:ZHEJIANG ZHENENG TECHN RES INST +1
Earth pressure balance shield tunneling machine, propelling speed prediction method and device for earth pressure balance shield tunneling machine and storage medium
ActiveCN113361824ASpeed upHigh precisionSustainable transportationForecastingData informationAutologistic regression
The invention discloses a propelling speed prediction method and device for an earth pressure balance shield tunneling machine, a computer readable storage medium and an earth pressure balance shield tunneling machine. The method comprises the steps that: a speed prediction model is obtained by training an autoregression model structure with exogenous variables based on historical input and output data of a propulsion speed subsystem of the earth pressure balance shield tunneling machine in advance; the speed prediction model uses a multi-layer perceptron to fit nonlinear regression parameters of the autoregression model structure with the exogenous variables; propelling data information of the earth pressure balance shield tunneling machine before the current moment is obtained; the propelling data information is input into the speed prediction model; and the propelling speed of the earth pressure balance shield tunneling machine is determined according to an output result of the speed prediction model. The speed prediction model can describe the dynamic characteristics of the propelling speed of the earth pressure balance shield tunneling machine, so that a basis is provided for self-adaptive adjustment of the operation parameters of the earth pressure balance shield tunneling machine, and the construction safety is effectively improved.
Owner:CHINA RAILWAY CONSTR HEAVY IND +1
UT1-UTC forecasting method based on time sequence intervention model
PendingCN114690276AImproving the Accuracy of Short-Term ForecastsWeather condition predictionDesign optimisation/simulationAlgorithmEngineering
The invention discloses a UT1-UTC forecasting method based on a time sequence intervention model, and the method comprises the following operation steps: firstly, carrying out the preprocessing of a UT1-UTC sequence, and removing the second jump and the simple harmonic tidal term of the earth; secondly, carrying out least square (LS) fitting on the UT1-UTC stationary sequence; carrying out auto-regression AR model fitting to obtain an AR fitting model, and calculating an AR fitting residual error; secondly, in an intervention event, an intervention model is established based on AR fitting residual errors; and finally, adding the LS fitting model, the AR fitting model and the intervention model to obtain a UT1-UTC forecast stationary sequence, and adding second jump and earth simple harmonic tidal terms to obtain a UT1-UTC forecast final sequence. The result shows that when the ENSO phenomenon occurs, the constructed intervention model can remarkably improve the short-term forecasting precision of UT1-UTC, forecasting is carried out for 30 days, and compared with a non-intervention model, the improvement degree reaches 0.02-0.2 ms.
Owner:SHANDONG UNIV
Method for predicting the heat energy conversion efficiency of a ground source heat pump system with working condition input
ActiveCN109767044AEasy way to predict performanceEasy to operateDigital data information retrievalForecastingThermodynamicsEngineering
The invention relates to a method for predicting the heat energy conversion efficiency of a ground source heat pump system with working condition input. The method comprises the following steps: A, preprocessing heat energy data; 1) cleaning the heat energy data; 2) performing seasonal decomposition and preliminary analysis on the time sequence of the heat energy conversion efficiency; B, establishing an autoregressive model with external working condition parameter input; 3, constructing an autoregressive model framework with external working condition parameters; 4) constructing a basic classification regression tree, generating a random forest, training prediction models under different external working condition parameters, and selecting at least one tree of the tree of which the erroris not changed any more; And C, according to the trained prediction model, performing prediction by integrating and inputting time sequences of external working condition parameters and the heat energy conversion efficiency, and outputting a prediction result and prediction precision. According to the method, the working condition parameters are introduced into time sequence prediction, so that aspecific more accurate prediction model can be obtained for different working condition parameters during prediction.
Owner:SHANDONG UNIV
A Quantum Computing Based Autoregressive Model Channel Prediction Method
ActiveCN110635858BReduce complexityBaseband system detailsTransmission monitoringComputational physicsAutologistic regression
The present invention proposes an autoregressive model channel prediction method based on quantum computing, including: step 1, obtaining known channel values, setting the order of the AR model, and predicting the channel value at the next moment according to the current known channel value; step 2 : Use the least squares method to solve the estimated value of the AR model coefficient to obtain the calculation formula; Step 3: Use quantum computing to solve the calculation formula to obtain the AR model coefficient |d> of the quantum state; Step 4: Define a set of measurement operators M ,via caculation <d|m|d>Obtain AR model coefficient estimates. The invention combines the least square estimation for solving AR model coefficients with quantum calculation, can effectively reduce the complexity of classical calculation, and the calculation result is equivalent to the existing coefficient estimation effect.< / d|m|d>
Owner:HANGZHOU DIANZI UNIV
Crawler scheduling method, device, electronic device and storage medium
ActiveCN109670101BImprove crawling efficiencyWeb data indexingComputers technologyAutologistic regression
Owner:BEIJING QIANXIN TECH
Multi-channel Fusion Detection Method for Range Extended Targets in Partially Homogeneous Environment
ActiveCN108919225BSimplify the estimation processImprove build efficiencyWave based measurement systemsAlgorithmEngineering
The invention discloses a multichannel fusion detection method for distance extension targets under partially uniform environment, and belongs to the field of radar signal processing. According to themethod, a partially uniform multichannel auto-regression signal model is established for the condition of globally uniform auxiliary data missing caused by abnormal value conditions such as clutter edge and the like, so that local uniformity of clutter spaces, time low-order relevancy and multichannel information obtaining ability are sufficiently fused, the utilization rate of clutter prior information is effectively improved and a data model foundation is laid for auxiliary data demand of self-adaptive distance extension target detection; the multichannel fusion detection method for distance extension targets under partially uniform environment is established on the basis of a Rao test criterion, so that the auxiliary data demand is greatly reduced while the characteristic of constant-false alarm rate is ensured; and being compared with the common generalized likelihood ratio criterion method, the method is capable of simplifying the parameter estimation process while remaining thedetection performance unchanged, so that the detector construction efficiency is improved and the method is strong in engineering applicability and has popularization and application values.
Owner:NAVAL AVIATION UNIV
A dynamic process monitoring method based on bp neural network autoregressive model
ActiveCN108845546BImprove abilitiesCapacity building facilitationNeural architecturesTotal factory controlEngineeringAutologistic regression
Owner:镇江云游信息科技有限公司
Model for evaluating influence of current standards on future economy development and verification method
The invention relates to a model for evaluating influence of current standards on future economic development and a verification method and aims to solve a problem of lacking of the model for evaluating influence of the current standards on future economic development and the verification method. The method is characterized in that through stability test, co-integration experience and causality test of the model, time series data is determined to have stability, the long-term and stable equilibrium relationship between variables is realized, the standard stock has an impact on change of the regional GDP, autoregressive analysis is further utilized to better quantify influence of the past GDP and the past implementation standards on the current economy, the false regression phenomenon in the double time series data is removed, and a model expression is established. The verification method is advantaged in that a recursive equation for calculating a pulse response coefficient matrix is acquired through stable point test of the model, an error expression is predicted, continuity of the impact effect is displayed through figures, an elastic coefficient value of the standard lag periodfor the economic benefit evaluation model is acquired, and the optimal digestion period of standards for economy development is quantified.
Owner:广州市标准化研究院
Method for Quantitative Calculation of Concentration of Complex Spectral Components
ActiveCN111289451BInstant outputCalculation speedColor/spectral properties measurementsCorrelation functionComputational physics
The invention discloses a method for quantitatively calculating complex spectral component concentration. The method comprises the following steps of: acquiring an absorption spectrum of a pure substance to obtain different characteristic peaks of the pure substance and correlation functions among the different characteristic peaks; collecting spectral data of a to-be-detected sample to obtain anoriginal spectrum; carrying out qualitative analysis on the to-be-detected sample, and screening out the corresponding characteristic peaks and characteristic peak correlation functions of the pure substance; and importing all the screened pure substance and the characteristic peak correlation functions of the pure substance into the original spectrum, and performing learning and autoregression through adopting a deep learning algorithm to obtain the component concentration. According to the method, different characteristic peaks of the single pure substance are associated, so that the calculation speed is effectively increased; deep learning algorithm regression can be carried out on all characteristic peak concentrations of different components on the spectrum at the same time, so that the calculation speed and accuracy are improved; and a deep learning algorithm is adopted for concentration regression analysis instead of substance identification, the calculation speed is further increased, and calculation data can be output in real time.
Owner:近通物联网(苏州)有限公司
Defect detection method and device, electronic device and computer readable storage medium
PendingCN114764764AAvoid noiseAvoid certain errorsImage enhancementImage analysisAlgorithmTest sample
The invention discloses a defect detection method. The defect detection method comprises the following steps: obtaining training weights obtained when a normal training sample is used for training an auto-encoder and an auto-regression network; loading the training weight into the auto-encoder and the auto-regression network so as to encode a test sample through the auto-encoder loaded with the training weight to obtain a test encoding feature; and inputting the test coding feature into the autoregression network loaded with the training weight to output a test result, wherein the test result comprises one of the condition that the test sample has defects and the condition that the test sample does not have defects. The invention further provides a defect detection device, an electronic device and a computer readable storage medium. Defect determination errors can be avoided.
Owner:FU TAI HUA IND SHENZHEN +1
Image coding, decoding and compression method based on depth Gaussian process regression
PendingCN114584780AFlexible estimateReduce overheadImage codingDigital video signal modificationCoding decodingAutologistic regression
The invention discloses an image coding method based on deep Gaussian process regression, and the method comprises the steps: obtaining a bottleneck layer multi-channel feature of a to-be-coded image through employing a coding convolutional neural network, and taking the feature as a first feature map; quantifying each feature in the first feature map into an integer to obtain a second feature map; on the basis of an autoregression model and a hyper-prior model of deep Gaussian process regression, weighting and combining a plurality of Gaussian mixture distribution coding features of Gaussian distribution for each channel of the second feature map, and generating a feature binary code stream; super-prior information obtained by the super-prior model is coded into a super-prior binary code stream; and combining the super-prior binary code stream and the feature binary code stream to obtain a binary code stream of the compressed image. A non-parametric depth Gaussian process regression method is adopted for autoregression modeling, posterior distribution output by depth Gaussian process regression serves as a mean value of a Gaussian mixture model, the uncertainty of mean value estimation can be flexibly obtained, and therefore more accurate mean value estimation is obtained.
Owner:SHANGHAI JIAO TONG UNIV
A fine-grained image classification method based on discriminative learning
ActiveCN110309858BAccurate discriminationClassification in real timeCharacter and pattern recognitionVisual technologyClassification methods
The invention belongs to the technical field of computer vision, and provides a fine-grained image classification method based on discriminant learning. We propose a new end-to-end autoregressive localization with discriminative prior network model that learns to explore more accurate discriminative patch sizes and is able to classify images in real-time. Specifically, a multi-task discriminative learning network is designed, including an autoregressive localization sub-network and a discriminative prior sub-network with a bootstrap loss function and a consistency loss function to simultaneously learn the self- Regression coefficients and discriminative prior map. The autoregressive coefficients can reduce the noise information in the discriminative patch, and the discriminative prior map filters thousands of candidate patches into single-digit patches by learning the discriminative probability value. Extensive experiments show that the proposed SDN model achieves the state-of-the-art in both accuracy and efficiency.
Owner:DALIAN UNIV OF TECH
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