83 results about "Stepwise regression analysis" patented technology

The invention discloses a sight tracking method based on a stepwise regression analysis mapping model. The method comprises the steps of firstly, extracting eye movement characteristic information when human eyes watch a fixed point; then selecting an initial mapping model function; after the initial mapping model is selected, checking significances of all items of a mapping model function, rejecting the non-significant items, and in the process of continuously rejecting the items and reconstructing the mapping model function, finding the mapping model function with the highest fitting precision at last; and finally, utilizing the mapping model function for calculating the watching point, and when the human eyes are in a gazing state, adopting a Gaussian weighted average method to smooth the eye movement characteristic information, thus solving the problem of eye shaking. According to the method, the robustness is good, and the precision is high.

The invention discloses a short-term climate forecasting method based on empirical mode decomposition and numerical value set forecasting. The invention adopts a way of integrating a numerical value set forecasting technology and a mean generating function stepwise regression model and combines a new empirical mode decomposition (EMD) method for processing a data sequence. The short-term climate forecasting method comprises the following steps of: firstly, decomposing a non-stationary climate data sequence into a stationary intrinsic mode function (IMF) component with multi-scale feature; then constructing different forecasting models for each IMF by a way of set forecasting and stepwise regression analysis; and finally linearly fitting to form a forecasting result. When the system is used for short-term forecasting, a user can cut out the appointed sequence length and forecasting length according to the actual data demand and vnlrpfalgp select a forecasting model parameter in a set forecasting process. Compared with a direct or single forecasting method, the invention has better forecasting capacity for the variation trend of climate and sudden climate.

The invention provides a blind source signal denoising method based on ensemble empirical mode decomposition, and belongs to the technical field of signal processing. By means of the method, definitions on the white noise amplitude and the number of iterations in an original algorism are rectified. False component discrimination is conducted on the IMP component obtained after IEEMD is decomposed through a classic stepwise regression analysis method, features of original signals are effectively reserved, the false component generated by the IEEMD algorism is eliminated, and interference to the subsequent denoising algorism by the false component is eliminated. Finally, for the non-convergence phenomenon generated occasionally when the ICA algorism processes the high-frequency signals, a high-order TFastICA method is provided, features of the IEEMD and the TFastICA are combined, and rear-end processing is conducted on the IEEMD through the TFastICA method. The blind source signal denoising method based on the ensemble empirical mode decomposition has wide application prospects in the fields of removing mechanical vibration noise, voice signal noise, instantaneous underwater noise and other signal processing fields.

The invention discloses a test and analysis method of red spider insect pest coercion conditions of orange trees. The method comprises the following steps of: (1) selecting a plurality of healthy orange tree leaf samples and orange tree red spider leaf samples; (2) collecting hyperspectral images of the orange tree leaf samples; (3) measuring the chlorophyll and carotenoid contents of the orange tree leaf samples; (4) pre-treating the collected hyperspectral images; (5) further denoising the pretreated hyperspectral images; (6) extracting the characteristic wave bands of the denoised hyperspectral images; (7) creating a detecting model through the extracted characteristic wave bands, picking out the optimal wave band combination by gradual regression analysis, and determining the quantitative relation of the optimal wave band combination and the chlorophyll and carotenoid contents; and (8) detecting the chlorophyll and carotenoid contents of the orange tree leaves through the created model so as to predict the red spider insect pest coercion conditions of the orange tree. The test and analysis method disclosed by the invention is used for predicting the red spider insect pest coercion conditions of the orange tree by creating the model and has the advantages of being unartificial and harmless.

The invention discloses a restrictive two-stage genome-wide association study (GWAS) method based on an SNPLDB mark, and aims at solving the problems that a traditional method cannot be used for estimating multiple allele information, and is high in false positive rate and low in efficiency of detection on inbreeding crops. By combination of the SNPLDB mark constructed on the basis of a haplotype block, correction of deviation of an inbreeding population relation analysis model and a two-stage relation analysis strategy under a multi-site model, the GWAS method suitable for conventional breeding of inbreeding crops is built; the SNPLDB mark is applied to GWAS, so that a method is provided for multiple allele estimation; candidate sites are screened on the basis of a single-site model in the first stage, and are further screened on the basis of a progressive regression analysis method in the multi-site model in the second stage, so as to balance the problems of missing of heritability and over-high heritability estimation. Therefore, the interpretation ratio of a final genetic model is controlled at trait heritability. The positioning accuracy and efficiency are improved by a feature vector and an appropriate significant level of a similarity coefficient matrix estimated by the SNPLDB mark by GWAS.

The invention discloses a monthly power consumption prediction method that comprehensively considers various economic factors, adopts the X-12-ARIMA model to decompose the monthly power and various economic factors into seasons; uses stepwise regression analysis to study the economic quantities and power consumption The correlation degree and regression model of electricity consumption were used to obtain preliminary prediction results; the annual power consumption forecast was carried out by using polynomial fitting, and the existing monthly power consumption forecast results were adjusted; the autoregressive integral sliding average Seasonal forecast corrections are carried out in each month to obtain a monthly electricity forecast model with good accuracy. Using the above technical solution, after seasonal decomposition of monthly electricity and economic volume, not only can use periodicity for forecasting, but also can effectively reduce the impact of volatility on regression analysis fitting accuracy and forecasting accuracy, and obtain good forecasting results.

The invention relates to a cigarette tipping paper lip sticking force prediction model and a construction method and prediction method thereof, and belongs to the technical field of analysis and detection. According to the method, stepwise regression analysis is carried out on the lip sticking force, the dynamic friction coefficient and the quantitative value of the cigarette tipping paper to obtain a model for predicting the lip sticking force of the cigarette tipping paper. When the accuracy of the model is tested, it is found that the predicted value and the measured value are basically close to a 1: 1 line, the R2 index is 0.99, and the normalized root mean square error nRMSE is 2.64%. The invention provides a method capable of quickly, simply, conveniently and quantitatively determining the lip sticking force of the cigarette tipping paper, so that the influence of subjective factors and the difference representation caused by the traditional artificial sensory evaluation can be well avoided, the detection cost is greatly saved, and the efficiency is improved. The method is more objective, efficient, good in repeatability and easy to operate, and has advantages in material admission, quality control and product upgrading in the tobacco industry.

The invention discloses a screening method for coix drought resistance indexes, and belongs to the technical field of agricultural production. The method includes the steps of (1) germplasm cultivation and planting of test coix; (2) determination of the relative drought resistance indexes; (3) principal component analysis; (4) gradual regression analysis. The screening method is close to the practice of agricultural production, has reliable results, and can solve the problems that the existing screening method for the coix drought resistance indexes is confused and the screened indexes are inconsistent, thereby providing a reliable, simple, economical, applicable and standard drought resistance index screening technology system for coix breeding workers; meanwhile, the screened indexes can comprehensively reflect the comprehensive drought resistance of the coix, and can be effectively applied to the identification of drought resistance of the coix.

The invention discloses an evaluation method for stepwise regression of thermal power equipment performances. The method is used for solving the problems of the difficulty to establishing an optimal regression equation and obtain equipment performance optimal values automatically and the quantitative obtaining of the influence degree of all influence conditions on equipment performances. According to the evaluation method, thermal power plant real-time/historical data are used, and through a multiple stepwise regression analysis modeling method, an optimal prediction model reflecting equipment performance parameters and influence conditions is built, and accordingly, optimal performance values that the equipment is ought to reach under all work conditions and the independent influence degree of relevant parameters which are not clear in coupling relationships on equipment performances are obtained. Implementation software of the method can be inlaid in a prior thermal power unit SIS system, and the purposes of instruction of automatic optimization of thermal power equipment and optimization of production operations can be achieved without increasing hardware and costs.

The invention discloses a method for adopting a quantitative structure-activity relation model to predict a reaction rate constant of chlorine free radical of organic chemicals. According to the method, a quantum chemistry descriptor with structural characters is figured out only by means of basic molecular structure information of the organic chemicals, and by adopting a constructed QSAR prediction model, a kCl value of the organic chemicals can be predicted quickly and efficiently. The method follows a guide rule issued for the construction and verification of a QSAR model by the Organization For Economic Co-Operation And Development (OECD). According to the method, by adopting a genetic algorithm-multiple linear stepwise regression analysis combination use method (GA-MLR) and a supportvector machine-multiple linear stepwise regression analysis combination use method (SVM-MLR), the transparency degree is high and more convenience is provided for application; since quantum chemistrydescriptors are adopted in all GA-MLR models, the physical meaning of the descriptors is clear; the method has a specific application domain, and is applicable to abundant organic varieties, excellentin goodness of fit, robustness and prediction capability, easy to program and capable of supplying important data support to environmental risk evaluation and management of the organic chemicals.

The invention discloses a method for predicting the shaft temperature by adopting layered multivariate stepwise regression analysis. According to the hierarchical multivariate stepwise regression analysis method, a shaft temperature prediction equation is established by combining real-time data, collected during operation of a high-speed train, of relevant factors of shaft temperature change, andmeanwhile three factors, namely the environment temperature, the operation speed and the air spring load, which greatly influence the train shaft temperature, are screened out. A prediction result andan actual measurement result are compared and analyzed, the result shows that a prediction model established through layered multivariate stepwise regression analysis has high precision, the change trend of the axle temperature can be accurately reflected, and certain help is provided for analysis and prediction of the axle temperature of a train, timely discovery of axle faults and guarantee ofsafe operation of the train.

The invention belongs to the technical field of agricultural production, and particularly relates to a method for identifying the salt tolerance of sweet potatoes in the seedling stage. The method comprises the following steps: (1) salt stress treatment for sweet potatoes in the seedling stage; (2) physiological indicator detection for sweet potatoes in the seedling stage; (3) data analysis and salt tolerance division; (4) salt tolerance mathematical evaluation equation and salt tolerance index screening, namely stepwise regression analysis by using the salt tolerance comprehensive evaluationvalue D value as a dependent variable and the salt tolerance coefficient of each single index as an independent variable to establish a regression equation, and salt tolerance division according to the comprehensive salt tolerance D value. According to the method, the standard equation result is accurate and reliable, the operation is simple and convenient and is easy to grasp, the method is lessinfluenced by the outdoor environment, the condition is controllable, the comprehensive salt tolerance of sweet potatoes in the seedling stage can be overall reflected, and the result is reliable. Themethod can be used for quickly evaluating the salt tolerance of sweet potato varieties in the seedling stage, has small blindness and high efficiency, and provides germplasm materials to sweet potatosalt tolerance variety seedling and salty land development and utilization in the Yellow River Delta.

The invention discloses a winter wheat canopy chlorophyll estimation system and method. According to the winter wheat canopy chlorophyll estimation system and method, a six-axis rotor unmanned aerialvehicle with maneuverability, flexibility, high efficiency and rapidness is used for carrying a multispectral camera containing five kinds of spectral information to carry out high-precision and high-temporal-spatial resolution winter wheat spectral image acquisition; accurate spectral reflectivity data are obtained after the reflectivity calibration of a grey board; various vegetation indexes are obtained through the operation of a spectral vegetation coefficient equation set; an optimal model for estimating the key growth period of the chlorophyll content of the canopy of winter wheat is constructed through a stepwise regression analysis method; and the low-error estimation value of the chlorophyll content of the wheat canopy of the wheat winter in fields is obtained; and therefore, aneffective technical means is provided for the accurate fertilization management of farmland.

The invention relates to a building and application method for a functional tobacco module. The method comprises the following steps of dividing tobaccos into skeleton type tobaccos, fragrance type tobaccos and texture type tobaccos by a judgment model based on sensory evaluation; detecting the content of chemical components in the tobaccos, and performing stepwise regression analysis on the detected content of chemical components in the detected tobaccos, so as to obtain the skeleton type tobacco function parameter Fg and skeleton type tobacco quality parameter Qg of the skeleton type tobaccos, the fragrance type tobacco function parameter Fx and fragrance type tobacco quality parameter Qx of the fragrance type tobaccos, and the texture type tobacco function parameter Fz and texture type tobacco quality parameter Qz of the texture type tobaccos. The method has the advantages that the parameters of the applicable function tobacco module can be predicted by the built different function tobacco function parameter and quality parameter prediction models, the objectiveness and stability of evaluation on functions and application of the tobacco module are improved, and the effective and reasonable utilization of tobacco resources is guaranteed.

The invention discloses a method and device for establishing a motor vehicle state comprehensive assessment system. The method comprises the steps of determining operating state indexes of all set function modules of motor vehicles; extracting the public factors of the operating state indexes according to a factor analysis method, carrying out classification on the operating state indexes with the public factors as a standard, and establishing an initial motor vehicle state comprehensive assessment index system; screening the operating state indexes corresponding to all the public factors in the initial motor vehicle state comprehensive assessment index system according to stepwise regression analysis; establishing the motor vehicle state comprehensive assessment index system according to the screened operating state indexes corresponding to all the public factors. Thus, reasonable assessment can be carried out on the integral state of the motor vehicles.

The invention discloses a rice leaf SPAD value estimation method based on computer vision, and the method comprises the steps: (1) collecting a certain number of rice leaf samples, placing the rice leaf samples on a 18% gray plate, and obtaining corresponding sample images; (2) determining SPAD values of all the sample images; (3) removing a gray plate part in the sample images by adopting a threshold segmentation method, and leaving a green leaf main body part; (4) extracting the color features of the sample images, and obtaining the color features in the RGB color space and the color features in the HSV color space in the sample images; (5) by taking a color component as input, establishing an SPAD value estimation model M'2 based on the color component by adopting a stepwise regressionanalysis method. According to the method provided by the invention, the SPAD value data of the whole rice leaf can be quickly obtained, the estimation result is relatively high in precision and smallin error, the working efficiency of manually detecting the SPAD value of the rice leaf can be reduced, and a basis can be provided for visual research of the rice leaf.

The invention discloses a method for establishing a rice yield prediction model under high temperature stress based on morphological parameters, which comprises the following steps of carrying out theshort-term extreme high temperature treatment on rice at the booting stage or flowering stage of rice, and setting a control treatment at the same time; obtaining the morphological indexes of rice under high temperature stress and obtaining the relative values of each index; obtaining rice yield and obtaining the relative value of rice yield; carrying out stepwise regression analysis between relative changes of morphological indices and relative changes of yield, and screening morphological indices related to yield; establishing a rice yield prediction model under high temperature stress based on morphological parameters. The method of the invention screens out the morphological index which is convenient to observe and can better predict the yield, the cost is low, and the method is simple and effective. A method for predicting rice yield under high-temperature stress base on morphological parameter is also disclosed, so as to realize the purpose of predicting rice yield based on themorphological index.

The invention discloses an optimization method of an ardealite-based cementing material for improving the filling roof-contacted rate, comprising the following steps: adding ardealite powder and an excitant in different proportions into filling aggregate to prepare cemented filling body materials in different proportions; carrying out a cemented filling body strength test and a filling body expansion rate test on the cemented filling body materials with different proportions to obtain test data of the cemented filling body strength and the expansion rate of the cemented filling body materialswith different proportions; conducting stepwise regression analysis on the test data of the strength and the expansion rate of the cemented filling body through a quadratic polynomial; establishing aproportion optimization model of the cementing material by taking the 3d strength of the cemented filling body as an optimization target and the 28d filling body expansion rate as a constraint condition; and solving the optimization model to obtain the optimal proportion of the ardealite-based cementing material in the filling slurry. According to the design method, low-cost and high-value resource utilization of ardealite can be realized; and low-cost and high-value utilization of ardealite in filling mining can be realized.

The invention discloses a method for blending and appraising rice wine. The method comprises the following steps: (1) selecting rice-wine components with great contribution to the quality and taste of rice wine; (2) determining the content values of the rice-wine components with great contribution to the quality and taste of rice wine in base wine respectively; and (3) adopting stepwise regression analysis, selecting different species of base wine and obtaining the content value of blended wine through the component values and portions of the base wine pro rata; establishing a regression equation and adopting the content values of the components of the blended wine to calculate the appraisal value of the taste of the rice wine so as to obtain the degree of the sensory quality of the blended wine in the same mixture ratio; and obtaining an optimal blending proposal by regulating the species and portions of the base wine. The method can replace the method for appraising and blending wine through artificial sense, and has the characteristics of few interference factors, high appraisal accuracy, simple operation steps, more convenient blending and capability of improving the taste of the rice wine.

The present invention relates to a stepwise regression analysis-based big data processing method. The method includes the following steps of firstly, collecting data of factory operation parameters, and numbering the collected operation parameters; then, using some of the collected operation parameters as dependent variables, using other operation parameters as independent variables, and writing equations, wherein the parameters are in a linear relationship; then, importing the equations and corresponding data into Matlab software one by one, performing stepwise regression analysis operation, and calculating a coefficient and an intercept of each equation before the independent variable; and finally, performing result analysis so as to obtain an optimal value of a corresponding operation parameter. According to the method, a lot of data is collected, stepwise regression analysis and big data processing are performed, the Matlab software is used, and the impact of all operation parameters of a factory DCS is determined quantitatively so as to quantitatively determine and change the impact of a certain parameter on other parameters to determine the optimal value of a factory DCS operation parameter.

The embodiment of the invention discloses a method and device for forecasting tropical cyclone generation frequency, equipment and a storage medium, and the method comprises the steps: carrying out the stepwise regression analysis of the characteristic value of a variable which may influence the tropical cyclone generation and the generation frequency of the tropical cyclone generation, carrying out the inspection, and keeping the variable if the inspection is passed; and forecasting by using a neural network method by using the reserved variable as a characteristic value and the generation frequency generated by the tropical cyclone as a forecast quantity. According to the method for forecasting the tropical cyclone generation frequency provided by the embodiment of the invention, the influence of atmosphere and ocean on tropical cyclones is considered. The mapping relation between the characteristic values and the forecast quantity does not need to be considered, and the nonlinear relation between tropical cyclone generation and the climate background field does not need to be considered. A forecasting model is optimized, and the forecasting accuracy is improved.