25 results about "Meta-regression" patented technology

The invention belongs to the technical field of compressor performance prediction, and particularly provides a method and system for determining a surge judgment critical value of a compressor based on multi-source data fusion. Comprising the steps that a compressor surge test system is built and operated, and a first surge critical value is calculated; obtaining multi-source historical data related to surge of the compressor, selecting characteristic variables to construct historical input vectors, and fitting the multiple regression model by using the historical input vectors to obtain a discrimination model; training the machine learning model to obtain a trained machine learning model; a real-time input vector is constructed based on data, collected in real time, of the to-be-monitored compressor, and then a second surge critical value and a third surge critical value are obtained; and fusing the first surge critical value, the second surge critical value and the third surge critical value to obtain a predicted surge critical value of the to-be-monitored compressor. According to the method, high-precision dynamic testing and historical data regression analysis are combined, and the actual value of the surge critical value is finally and quantitatively determined through multi-parameter coupling measurement and data mining.

The present invention relates to the technical field of myopia prevention and control, and relates to a method for evaluating the effectiveness of myopia out-of-focus distribution. In order to solve the problem that the effectiveness of myopia out-of-focus distribution is rarely evaluated at present, in the present invention, analysis and induction are carried out on the basis of a large amount of clinical sample data, related parameters are determined by means of multiple regression analysis from a plurality of factors affecting an out-of-focus form, a regression equation affecting eye axis growth is obtained by using the related parameters, and finally, the distance between an out-of-focus peak value and a cornea center point is used as a core indicator for evaluating the effectiveness of myopia out-of-focus distribution, thereby providing a new idea for design and evaluation of a myopia out-of-focus distribution position in clinical practice. By using the evaluation method of the present invention, quantitative evaluation can be carried out on the out-of-focus form of an individual, and personalized out-of-focus distribution design can be carried out on the basis of the individual condition of a patient, so that myopia out of focus is distributed in an optimal position of a lens to achieve an optimal myopia prevention and control effect, and the evaluation method has great significance in early myopia prevention and control.

The invention discloses a schizophrenia concurrent metabolic syndrome independent risk factor screening method and system, utilizes a binary logistic regression analysis method to analyze relevance between multi-source factors and concurrent MetS and screen out independent risk factors, and relates to the technical field of medical data processing. According to the schizophrenia concurrent metabolic syndrome independent risk factor screening method and system, the relevance between multi-source factors and concurrent MetS is analyzed through a binary logistic regression analysis method, the independent risk factors are screened out, and a decision tree model is constructed based on the reserved independent risk factors and used for visually displaying and predicting the risk of concurrent MetS of a patient. By comprehensively considering multi-aspect information of the schizophrenia patient and adopting independent risk factor determination and model construction operation, the independent risk factors causing MetS occurrence of the schizophrenia patient are accurately identified, the screening accuracy is improved, meanwhile, the level of MetS concurrent by the patient is predicted, subsequent clinical timely intervention is facilitated, and the risk of MetS occurrence of the schizophrenia patient is reduced. And the MetS concurrent probability of the patient is reduced.

The present invention provides a resin bed life assessment method based on a multiple regression model, comprising the following steps: 1) resin bed operation monitoring test: test equipment, test parameters and test results; 2) prediction model: mathematical modeling, numerical analysis, least squares method, polynomial regression and multiple regression analysis; 3) prediction model construction and verification: model establishment, prediction model verification and prediction model application; mathematical modeling plays a good role in solving practical problems and involves a wide range of application fields; it requires the integration and application of various knowledge; it requires the cooperation of various technical means, etc., and a method of using multiple nonlinear regression to solve the model generally uses variable interchange to convert the nonlinear model into a linear model. This method improves the efficiency of calculation, increases the accuracy of calculation results, and realizes the life construction model processing and evaluation of the resin bed during its operation.

The application provides a power data analysis method and device, comprising: obtaining historical power consumption data and related external variable data of a target area; establishing a multiple regression relationship model between power consumption and external variables according to the historical power consumption data and related external variable data; defining a probability distribution function for each external variable; performing Monte Carlo simulation based on the multiple regression relationship model, for each iteration, randomly extracting a value from the probability distribution of each external variable, substituting the extracted external variable value into the multiple regression relationship model, and calculating the corresponding power consumption prediction value; accumulating and storing the power consumption prediction values obtained in each iteration to form a simulation result database; and identifying key external variable combinations and scenarios that cause significant changes in power consumption in the target area according to the simulation result database. The application can improve the accuracy of power consumption prediction and identify key external variable combinations and scenarios.

The present invention discloses a liver cancer risk prediction model and construction method, which relates to the technical field of liver cancer risk prediction, in order to solve the problem of being unable to accurately obtain risk data of patients. The diversified signal forms of the present invention can attract the attention of medical personnel in an all-round way. Different signal forms can be targeted at different environments and situations, improve the flexibility and applicability of early warning, and automatically generate intervention suggestions based on the early warning intensity and early warning signal, which greatly reduces the workload of medical personnel. By using parameter tuning methods such as grid search and random search, the parameter space can be systematically explored to find the optimal model parameter configuration, thereby improving the predictive performance of the model. By reselecting and transforming features, redundant features can be removed to make the model more stable and efficient. Statistical tests and multiple regression analysis are used to evaluate the relationship between variables and liver cancer occurrence, which helps to accurately identify variables that have a significant impact on liver cancer occurrence.

The present application belongs to the technical field of compressor performance prediction, and specifically proposes a compressor surge discrimination critical value determination method and system based on multi-source data fusion. It includes building and running a compressor surge test system, calculating the first surge critical value; obtaining multi-source historical data related to compressor surge, selecting characteristic variables to construct a historical input vector, fitting a multiple regression model using the historical input vector to obtain a discrimination model; training a machine learning model to obtain a trained machine learning model; constructing a real-time input vector based on real-time data collected from the compressor to be monitored, and then obtaining the second and third surge critical values; and fusing the first, second and third surge critical values to obtain the predicted surge critical value of the compressor to be monitored. The present application combines high-precision dynamic testing and historical data regression analysis, and ultimately quantitatively determines the actual value of the surge critical value through multi-parameter coupling measurement and data mining.

A method is disclosed. The method includes receiving interaction data related to a plurality of interactions in a time period, determining a multiple variable regression formula, and then determining a coefficient of determination associated with the multiple variable regression formula and the interaction data. The method further includes determining if the coefficient of determination satisfies a threshold or is maximized. If the coefficient of determination does not satisfy the threshold or is not maximized, then adjusting the slope coefficients. If the coefficient of determination does satisfy the threshold or is maximized, then using the multiple variable regression formula to determine risk associated with future interactions.

The embodiment of the invention discloses a gas meter sealing long-term reliability evaluation method and system and a storage medium, and the reliability evaluation method comprises the steps: obtaining a reliability evaluation standard, a plurality of stress condition factors and a multiple regression model, and setting a group of standard test stress conditions and a plurality of groups of different acceleration test stress conditions; acquiring initial leakage rate information; a plurality of first test samples are extracted under each acceleration test stress condition, an acceleration stress test is performed on each first test sample, and a plurality of corresponding leakage rate values are measured under the standard test stress condition based on the duration of the respective acceleration stress test; solving the multiple regression model to obtain a leakage rate evolution model; and outputting a reliability evaluation result according to the reliability evaluation standard. The problem that the sealing long-term reliability evaluation precision is insufficient due to the fact that an existing model constructed through an accelerated stress test is limited by physical distortion of a single stress frame and representation deficiency of initial discreteness is solved.

The invention discloses a nonlinear unknown parameter estimation method for digital twin modeling of a hydraulic system, and relates to the technical field of digital twin. The method comprises the following steps: constructing a target hydraulic system entity model, and obtaining related basic data through an experiment; constructing a digital twinborn model based on the hydraulic system entity model; the parameter variables of the digital twin model comprise determined parameters and unknown parameters; wherein for unknown parameters, a design variable matrix and a response objective function are determined according to related basic data, a response surface agent model is established by applying multiple regression analysis, then a Pareto front solution set of an established multi-objective optimization mathematical model is solved by utilizing a multi-objective optimization algorithm, and finally, a global optimal parameter combination is screened by combining a comprehensive evaluation method. According to the method, efficient and high-precision estimation of unknown parameters in a complex model is realized by constructing a mapping relation model between the unknown parameters and simulation-experiment errors and combining a multi-objective optimization algorithm and a comprehensive evaluation method.

The invention relates to the technical field of project management analysis, in particular to a method for dynamically identifying target deviations in different stages of a reservoir EPC project, which comprises the following steps of: constructing a three-stage associated multiple regression model, and configuring a dynamic influence coefficient for each EPC stage node; acquiring operation data of each stage in real time, performing stage weight distribution on the data by utilizing the dynamic influence coefficient, and generating a node state vector comprising a stage identifier; and S3, establishing a Markov transfer chain according to the stage identifier of the node state vector, calculating a deviation transfer probability between adjacent stages, and when the deviation transfer probability exceeds a warning threshold, triggering a reverse stage compensation instruction and updating the dynamic influence coefficient of S1 to form closed-loop regulation and control. According to the method, under the scenes of large topographic relief and complex conduction paths in reservoir projects, the method has higher environmental adaptability and real-time performance, and the stability and robustness of deviation chain diagnosis are improved.

The invention discloses a teaching quality evaluation method and system based on multiple regression analysis, and belongs to the technical field of teaching evaluation. The method comprises the following steps: acquiring teaching levels, pre-test scores and actual post-test scores of to-be-evaluated students and student classroom videos of all students in a to-be-evaluated time period; based on the score prediction model or the expected post-test score of the student, determining the score increment corresponding to the to-be-evaluated student in combination with the actual post-test score; acquiring a learning habit recognition result according to the student classroom video and a preset learning habit recognition model; and carrying out weighted average on score appreciation and learning habit identification results of all students, and determining a teaching quality evaluation result of the teacher. The method can eliminate the influence of the student basis and the teaching level on the teaching quality evaluation, improves the accuracy and scientificity of the evaluation, and solves the problems that the existing teaching quality evaluation is affected by the teaching level and the student basis, and the accuracy needs to be improved.

The invention relates to the technical field of thermal power generating unit operation control, in particular to a thermal power generating unit peak regulation characteristic limited factor quantitative analysis method and system based on a multivariate regression model. The method comprises the following steps that (1) operation parameters and unit actual power of all auxiliary machines of a thermal power generating unit are collected in real time; (2) carrying out cleaning and normalization preprocessing on the data; according to the invention, the data acquisition module is used for multi-channel real-time fast data transmission, the preprocessing module is used for cleaning and normalizing data, the feature extraction module is used for mining associated features, the model building module is used for building a regression model according to working conditions, and the analysis and early warning module is used for index calculation, factor judgment, early warning and linkage with DCS control, so that a complete quantitative analysis system is formed. According to the method, the constraint factors of the peak regulation performance of the unit can be accurately identified, scientific and reliable data support is provided for peak regulation optimization, the peak regulation capability of the thermal power unit is effectively improved, effective consumption of new energy is promoted, and stable operation of a power grid is guaranteed.

The invention discloses an infectious disease patient data management method and system based on a cloud platform, and relates to the technical field of intelligent management, and the method comprises the following steps: carrying out the division to obtain a disease stage, carrying out the first analysis to obtain a first infection probability, compensating the first infection probability to obtain a second infection probability, and calculating an average value of the second infection probability, and performing multiple regression analysis to obtain an infection equation, and sending a first early warning signal. Through multi-stage and multi-level data analysis, the transmission dynamic state of infectious diseases can be accurately monitored, a large amount of patient data can be rapidly processed and analyzed by means of the powerful calculation and storage capacity of the cloud platform, the efficiency and response speed of prevention and control of infectious diseases are improved, and based on the disease stage and infection probability of the individual patient, the system can be used for monitoring the transmission dynamic state of the infectious diseases. The individual prevention and control strategy is formulated, the prevention and control effect is improved, patient data from different sources can be integrated, data sharing and collaborative analysis are achieved, information islands are broken, and the overall prevention and control capacity is improved.

The embodiment of the invention provides a multispectral mixture component quantitative analysis method and device. The method comprises the following steps: acquiring spectral information of a target mixture; creating a spectrum output matrix according to the spectrum information; according to the spectrum output matrix, carrying out integration on a spectrum characteristic peak to obtain a spectrum integration matrix; creating a multivariate regression function corresponding to the component content and the light intensity in the mixture according to the spectral integral matrix; and performing inversion solution on the multiple regression function to obtain content information of each component in the mixture. According to the scheme, after the spectral information of the target mixture is obtained, the matrix can be created according to the spectral information, so that the integration of the characteristic peak is performed according to the matrix, the influence on the improvement of the detection efficiency is avoided, and finally, the content information of each component in the mixture is obtained through the construction and inversion solution of the multiple regression function, so that the detection accuracy is improved. Therefore, the detection precision is improved.

The invention discloses an environmental exposure health effect assessment method and system based on BKMR-intermediary analysis integration. Bayesian machine learning and intermediary analysis technologies are integrated through a four-stage progressive framework. In the first stage, multiple regression is combined with a nonlinear model to identify health correlation characteristics of a single pollutant; in the second stage, a mixed exposure evaluation method is fused, and the multi-pollutant joint effect and key components are analyzed; in the third stage, a Bayesian variable selection technology is innovatively utilized to intelligently screen intermediary factors, and an exposure-intermediary-health endpoint biological mechanism network is constructed; and in the fourth stage, the attribution health burden and economic loss are quantified. According to the method, three bottlenecks of single exposure limitation, insufficient hybrid interaction modeling and mechanism analysis deficiency in traditional assessment are broken through, full-chain scientific assessment from effect identification to a causal mechanism is realized, and methodological support is provided for accurate management and control of environmental health risks.

The invention provides a short-term power load interval prediction method based on kernel principal component regression analysis. The method comprises the following steps: acquiring historical power load data and corresponding historical power load influence data; clustering the historical power load influence data, and determining the historical power load influence data corresponding to each power consumption scene according to a clustering result; for the historical power load influence data corresponding to each power consumption scene, performing dimension reduction based on kernel principal component analysis, and extracting main power load influence characteristics corresponding to each power consumption scene; constructing a load interval prediction model based on the main power load influence characteristics corresponding to each power consumption scene and the corresponding historical power load data; and performing interval prediction on the short-term power load of the power system according to the load interval prediction model corresponding to each power consumption scene. The method can provide an interval prediction result for short-term power load prediction of the power system, overcomes the uncertainty of the prediction result, and gives consideration to the prediction efficiency.

The application relates to the field of business prediction and management, and provides an industry chain intelligent correlation analysis early warning method based on multi-source heterogeneous data and a corresponding product. The method comprises the following steps: generating a standardized data set from collected multi-source heterogeneous data; based on the standardized data set, identifying entities and the relationship between entities in the industry chain through naming entity recognition and relationship extraction technology, and dynamically constructing and updating an industry chain knowledge graph taking entities as nodes and relationships as edges; taking the industry chain knowledge graph as input, combining the space-time attribute characteristics attached to the entities and the relationships, and outputting simulation results containing the risk exposure value of each node and the risk transmission path; according to the risk exposure value, combining the time sequence index and the centrality index, and calculating the comprehensive risk vulnerability index of each industry chain node through a multivariate regression model; and based on the comprehensive risk vulnerability index and the simulation results, generating differentiated early warning signals and pushing the signals through a visual interface.

This invention discloses a method and apparatus for predicting passenger cabin temperature based on a stacked regression model. The method includes: collecting key operating parameters affecting passenger cabin temperature and corresponding temperature values ​​for different areas of the passenger cabin; selecting a preset number of samples from the key operating parameters and corresponding temperature values ​​according to preset rules to obtain a training dataset; constructing a stacked regression model architecture, wherein the stacked regression model includes a base regressor layer composed of multiple regression models and a meta regressor layer for fusing the prediction results of multiple regression models; training the stacked regression model architecture using the training dataset to obtain a passenger cabin temperature prediction model; obtaining the current key operating parameters of the passenger cabin; and inputting the current key operating parameters of the passenger cabin into the passenger cabin temperature prediction model to obtain the corresponding temperature values ​​for different areas of the passenger cabin. This invention solves the problem of insufficient accuracy in passenger cabin temperature simulation and prediction in existing technologies.

The embodiment of the application provides a multispectral mixture component quantitative analysis method and device, the method comprises the following steps: obtaining the spectral information of a target mixture; creating a spectral output matrix according to the spectral information; performing integration of spectral characteristic peaks according to the spectral output matrix to obtain a spectral integral matrix; creating a multiple regression function corresponding to component content and light intensity in the mixture according to the spectral integral matrix; and inversely solving the multiple regression function to obtain the content information of each component in the mixture. Through the scheme of the application, after obtaining the spectral information of the target mixture, the matrix can be created according to the spectral information, the integration of the characteristic peaks can be performed according to the matrix, the detection efficiency can be improved, and finally the content information of each component in the mixture can be obtained through the construction and inverse solution of the multiple regression function, so that the detection precision is improved.

The invention discloses a human body composition detection method and system, a terminal and a medium, and the method comprises the steps: creating an exclusive data set for a specific crowd, and constructing a model equation based on the exclusive data set, the exclusive data set including but not limited to height, age, weight, gender and measured impedance; the coefficient of the model equation is solved based on a multiple regression analysis method, the overall significance of the model is analyzed and evaluated based on variance, and a human body composition detection model is obtained; and migrating the fusion model of the LSTM and the Transform into the human body composition detection model by using a migration learning technology, and obtaining a human body composition detection result based on the human body composition detection model. According to the invention, information of a specific crowd in multiple dimensions such as height, age, weight, gender, measured impedance and the like can be recorded, and comprehensiveness and accuracy of data are ensured. In addition, deep optimization and adjustment can be carried out on a traditional human body composition detection model, and the applicability and accuracy of the model to specific crowds are improved.

The application discloses a kind of urban space net red phenomenon determination method, it is related to urban space technical field, including the following steps: collection short video check-in data, obtain the online traffic and offline traffic of multiple net red check-in points;Based on the ratio of offline traffic and online traffic, obtain the traffic conversion rate of multiple net red check-in points in the preset research range;The surrounding area of net red check-in point is researched, and the influence factor of urban space net red phenomenon is determined and corresponding data is obtained;Based on the traffic conversion rate of net red check-in point and each influence factor, linear regression model is established respectively, and multiple regression analysis equation is obtained;The weight of each influence factor is obtained by using principal component regression analysis method, and weight analysis result is obtained.The application can analyze the correlation between urban net red phenomenon and influence factor, help to develop urban space potential, and help to promote the development of urban space net red phenomenon by optimizing space quality targetedly.

This invention discloses a method for identifying low-resistivity oil layers based on drilling, comprising the following steps: Step 1: Acquire historical gas logging data and preprocess the data samples; Step 2: Obtain drilling parameter tables and perform data correction on gas logging parameters such as total gas content (TG) and methane C1 based on the drilling parameters; Step 3: To highlight the differences between oil layers, low-resistivity oil layers, and water layers, feature extraction is performed on the data from Step 1 and Step 2, and stepwise multivariate regression analysis is used to optimize the parameters of the extracted features; Step 4: The parameters from Step 3 are combined with the drilling parameter gamma ray (GR) as input to the model to establish a GRNN neural network classification model based on the goose flocking optimization algorithm to classify the oil layers. This invention solves the inaccuracy of manual judgment of fluid properties and eliminates the need to identify fluid properties by measuring resistivity, thereby greatly reducing the cost and complexity of fluid identification.

The present application relates to the technical field of project management analysis, and particularly relates to a method for dynamic identification of target deviation in different stages of a reservoir EPC project, comprising the following steps: constructing a three-stage correlated multiple regression model, and configuring a dynamic influence coefficient for each EPC stage node; collecting real-time operation data of each stage, using the dynamic influence coefficient to perform stage weight distribution on the data, and generating a node state vector including a stage identifier; establishing a Markov transition chain according to the stage identifier of the node state vector, calculating the deviation transition probability between adjacent stages, and when the deviation transition probability exceeds an alarm threshold, triggering a reverse stage compensation instruction and updating the dynamic influence coefficient of S1, to form a closed-loop regulation and control. The present application has stronger environmental adaptability and real-time performance in the scene of large terrain undulation and complex conduction path in reservoir projects, and improves the stability and robustness of the deviation chain diagnosis.

This disclosure relates to a method for predicting the octane number of gasoline. A first calibration model is established by performing partial least squares multiple regression analysis on the first near-infrared spectrum of a blended gasoline sample and its standard octane number. Then, based on the construction process of the first calibration model, the spectral fitting residual matrix and the octane number fitting residual matrix are selected and used as the input signal and teacher signal of an extreme learning machine, respectively, to obtain a second calibration model. The combined application of the first and second calibration models comprehensively considers both the linear and nonlinear relationships between the first near-infrared spectrum and the octane number of the blended gasoline sample, providing a wider range of octane number prediction capabilities and improving the model's prediction accuracy. Furthermore, selecting the absorbance in the characteristic spectral region and the standard octane number for regression analysis during the first model construction process can further improve the accuracy of the octane number prediction results.