76 results about "Coefficient of determination" patented technology

Methods and systems for performing comprehensive predictive analysis and modeling in a wager gaming environment are provided. Statistical calculations for deriving predictive values for a patron behavior in a casino or gaming environment may include various criteria, including but not limited to wager gaming activities, resort/hotel usage, dining/meals, non-gaming point of sale transactions, entertainment expenditures, coupon/prize redemption, “comps” provided, etc. In some implementations, a plurality of predictive models may be used. One or more criteria may be used to evaluate and/or rank the predictive models. For example, such an evaluation and/or ranking may be based, at least in part, on a correlation coefficient or a function thereof. In some such implementations, an evaluation and/or ranking may be based, at least in part, on a comparison of the coefficient of determination, R², corresponding to each predictive model.

The invention belongs to the technical field of vibration monitor and control of steam turbine sets, in particular relates to a method for searching and analyzing the abnormality of signals during vibration and process of a steam turbine set. The method comprises the following steps of forming time sequences by history data with the preset group number; dividing each group of the time sequences into time subsequences, calculating mode characteristic values of the time subsequences and executing normalization processing; forming a mode characteristic value aggregation by the processed mode characteristic values; extracting a maximum value of all mode characteristics from the mode characteristic value aggregation and ranging in order from the largest to the smallest to form a mode characteristic extreme value sequence; gaining an abnormal characteristic boundary of the mode characteristic extreme value sequence; determining abnormal time subsequences; storing the abnormal time subsequences over the abnormal characteristic boundary in an abnormal change sequence; and executing optimal regression analysis on the abnormal change sequence based on coefficients of determination, and finding out a matched early warning grade according to an early warning mechanism rule. The invention increases the early warning precision and depth of vibration and process parameters.

The invention discloses a power transmission line lightning stroke interference and fault identification method based on transient waveform characteristics. The identification method comprises the following steps of: S1: after a transient quantity protection starting criterion is actuated, acquiring an additional component current of each phase at a line protection installation position, and calculating ground mold and line mold components according to a Karenbauer transformation matrix; S2: according to an energy ratio criterion of the transient ground mold and line mold components, identifying lightning stroke interference, and if the criterion is smaller than a setting, carrying out next identification; and S3: carrying out mean sliding denoising on the additional component current of each phase to acquire a waveform of a main wave, carrying out fitting on the waveform of the main wave, and identifying lightning stroke interference and a fault of each phase line according to a fitting decision coefficient. The power transmission line lightning stroke interference and fault identification method can accurately identifying different types of lightning stroke interference and faults, is not influenced by a fault initial angle, a transition resistance, a line compensation device and the like, has high sensitivity and reliability, is applicable to different types of power transmission lines, and provides beneficial bases for the practical process of transient quantity protection.

The invention discloses a method for rapid detection and authenticity identification of fatty acid of racy camellia oil by near infrared transmission spectroscopy (NITS). The method comprises the steps of: screening high quality varieties with oil content of 30%-60% from more than 130 camellia seed varieties, wherein in the camellia oil, the content of oleinic acid is 65%-85%, the content of linoleic acid is 5%-20%, the content of palmitic acid is 3%-15%, and the content of stearic acid is 1%-5%; establishing a near infrared transmission spectroscopy (NITS) model of the main fatty acids (oleinic acid, linoleic acid, palmitic acid, stearic acid and total unsaturated fatty acid) with a partial least squares (PLS) method by adopting the Fourier near infrared transmission spectroscopy (NITS), wherein the determination coefficients of the correction models of the oleinic acid, the linoleic acid and the palmitic acid respectively are 0.93446, 0.96538 and 0.88789, and the determination coefficients of cross validation respectively are 0.91987, 0.95755 and 0.84447; further verifying accuracy and reliability of five NIRS (Near Infrared Reflectance Spectroscopy) models by external verification so as to obtain related coefficients of the external verification, which respectively are 0.9424, 0.9682, 0.8862, 0.6834 and 0.7587; and evaluating doped camellia oil by establishing the NIRS model of binary system miscella of the camellia oil. The method is applicable to rapid measurement of the content of main fatty acids of the camellia oil and the doped camellia oil, has the characteristics of simplicity, convenience, rapidness and economy, and is suitable for industrial application.

The invention provides a modeling method for a cucumber GA-RBF photosynthetic rate prediction model integrated with stomatal conductance. The method comprises the steps: utilizing a multi-factor nested test to obtain the experimental data taking the stomatal conductance, the temperature, the CO2 concentration, the illumination intensity and the relative humidity as input and taking the apparent photosynthesis rate as output; utilizing a genetic algorithm to perform initialization of population; according to the given initial range of the spread parameters, calculating a fitness function; and through selection, intersection and variation, finding out the optimal spread parameter in an RBF neural network, and constructing a cucumber GA-RBF photosynthetic rate prediction model integrated with stomatal conductance. The test result shows that the predicted value and actual measurement value determination coefficient is 0.99878; the linear gradient is 0.99781; the error is less than 6%; compared with the photosynthetic rate prediction model which does not use the genetic algorithm to optimize the RBF algorithm and does not integrated with stomatal conductance and the cucumber GA-RBF photosynthetic rate prediction model which is not integrated with stomatal conductance, the training result has better prediction effect.

The invention discloses an optimal light quality and photon flux density-based light requirement real-time dynamic obtaining method. The method comprises the steps of firstly performing modeling based on a photosynthetic rate of a GA-GRNN, and optimizing an expansion speed of a GRNN by utilizing a GA algorithm, wherein related analysis of a predicted value and an actually measured value of a photosynthetic rate prediction model of the GA-GRNN is remarkably superior to that of a GRNN model; and then based on the photosynthetic rate prediction model of the GA-GRNN, performing photosynthetic rate optimization by using a quantum genetic algorithm to obtain corresponding optimal light quality and photon flux density, and building a light environment control target value model by adopting multiple linear regression fitting, wherein determination coefficients of optimal light quality model and photon flux density model are 0.992 and 0.9893 respectively. The photosynthetic rate at each temperature is taken as the actually measured value, and the photosynthetic rate corresponding to the optimal light quality and the optimal photon flux density is taken as the predicted value; a related analysis method is adopted; the determination coefficient is 0.936, the fitting straight slope is 1.012, and the intercept is 0.054; and a result shows that the built coupled light quality and photon flux density control target value model is good in performance.

The invention discloses a multiple linear regression model-based belt weigher main error factor analysis method. The method includes the following steps that: a belt weigher experiment platform is set up, main error factors such as tensions, temperatures and equivalent flow rates are changed according to actual situations, the tensions, temperatures, equivalent flow rates, calibration values and hopper weighers of various test points are recorded, and the relative errors of the calibration values and hopper weighers are calculated; the correlation coefficients of the main error factors of a belt weigher are calculated, and the correlation of the main error factors is judged; the relations of the factors are determined according to the correlation, and a multiple linear model is set and solved; residual sum of squares, determination coefficients and MS variance of residuals are adopted as check indexes, and the regression effect of the established model is evaluated; and the test values of the test points are predicted through using a fitting model, and the test values are compared with practical values, so that prediction errors can be calculated, and the accuracy of a fitting result is determined. With the method of the invention adopted, a theoretical basis is provided for quantitative analysis on the degree of influence of the main error factors on the accuracy of the belt weigher.

The invention discloses a cucumber whole-course photosynthetic rate prediction model based on a neural network. A multifactor nesting experiment is utilized for obtaining cucumber seedling photosynthetic rate test data, an LM (Levenberg-Marquardt) training method is adopted to carry out model training, and a cucumber whole-course photosynthetic rate model which combines a growing stage is established and is subjected to model performance parameter comparison and accuracy verification with a photosynthetic rate model of a single growing period and a whole-course photosynthetic rate model which does not combines a growing period stage parameter. A training result indicates that the whole-course photosynthetic rate model established in a way that the growing period is added to serve as a one-dimensional input quantity can effectively pass over local flat areas, and the whole-course photosynthetic rate model has an obvious superiority, meets a training requirement that errors are smaller than 0.0001, and is verified in an xor checkout way, so that a determination coefficient of a model prediction value and an actual measurement value is 0.9897, an error is smaller than 6.559%, and a theoretical basis and technical support can be provided for facility and crop luminous environment regulation and control.

The invention provides an intelligent predicting method for time sequence based on trend and periodic fluctuation, which comprises the steps of: computing an original time sequence to be predicated, separating a fluctuation component and a trend component of the sequence; for the trend component, automatically selecting a trend model with a maximal R2 from a trend model database through regression computing; converting the fluctuation component to a periodic variable according to an and-angle formula, adding the periodic variable into an optimal trend model; automatically selecting z periodical lengths with optimal influence functions according to a principle of maximizing a coefficient of determination, substituting z periodical lengths into the optical trend model with the periodical variable, and obtaining a final whole model; and determining a specific model parameter through computing the original time sequence by the final whole model, thereby predicting change trend of the original time sequence. The intelligent predicting method has advantages of high prediction intelligence and high precision through prediction processing automation and combining the trend component and the fluctuation component of a predicting model.

The present invention discloses a hyperspectral inversion method for the content of chlorophyll in apple leaves based on an SVR (support vector regression) algorithm. In order to realize the hyperspectral inversion of the content of chlorophyll in the apple leaves, the correlation between various spectral parameters and measured SPAD (soil and plant analyzer development) values is analyzed, normalized spectral parameter values and SPAD values are subjected to polynomial regression and SVR, determination coefficients of an SVR inversion model adopting a normalized differential vegetation index as a variable in modeling and model detection are 0.7410 and 0.8914 respectively, root-mean-square errors are 0.1332 and 0.1256 respectively, and higher precision and good prediction capacity are realized. Compared with polynomial regression, SVR has a better inversion effect and can be used as an optimal algorithm for hyperspectral inversion of chlorophyll.

The invention discloses a method for inverting an effective leaf area indexes of man-made forest by a UAV (Unmanned Aerial Vehicle) lidar, and belongs to the forest resource survey, forest site quality assessment and forest productivity estimation research field. The method for inverting the effective leaf area indexes of man-made forest by the UAV lidar normalizes the original point cloud data ofthe UAV lidar, extracts canopy structure characteristic variables from the normalized point cloud data, combines the ground actual measured data and the extracted characteristic variables, and estimates the effective leaf area index of the sample area scale in the study area based on the screened characteristic variables by means of a statistical model method. By obtaining the UAV lidar point cloud and extracting the canopy characteristic variables, by combining the ground actual measured data, the method for inverting effective leaf area indexes of man-made forest by the UAV lidar is relatively higher in efficiency and accuracy of the obtained continuously distributed effective leaf area indexes on the "face" of the specific range. Compared with other similar remote sensing methods, whenthe method for inverting effective leaf area indexes of man-made forest by the UAV lidar is used to extract the effective leaf area indexes of the man-made forest, the coefficient of determination isincreased by more than 5%.

The invention relates to a fish swarm algorithm-based cucumber seedling stage carbon dioxide optimization regulation and control model. A model formula is put forwards with temperature T and photon flux density PFD adopted as independent variables and with carbon dioxide concentration corresponding to a maximum photosynthetic rate adopted as a dependent variable; the establishment and application of the model are also disclosed. Multi-dimensional data are acquired by using a photosynthetic rate multiple-factor nested experiment; a photosynthetic rate multivariable nonlinear regression model is constructed; a fish swarm algorithm-based carbon dioxide model optimization method is designed; carbon dioxide saturation points under different temperature and different photon flux density are obtained; and the cucumber carbon dioxide optimization regulation and control model with the carbon dioxide saturation points adopted as target values can be built. As indicated by model verification test results, the fish swarm algorithm-based cucumber seedling stage carbon dioxide optimization regulation and control model of the invention can dynamically obtain the carbon dioxide saturation points under different temperature and different photon flux density, the determination coefficient of the actually-measure values and calculated values of the carbon dioxide saturation points is 0.98, and the maximum relative error of the actually-measure values and calculated values of the carbon dioxide saturation points is lower than 3%, and the model has high precision and is of great significance for the improvement of the carbon dioxide environmental regulation and control efficiency of facilities.

The invention discloses an application of an improved partial least squares regression method to microorganism culture medium optimization. According to the application, a cross validation technologyand a variable screening technology are integrated to reduce potential overfitting problem of PLSR, namely, a proper number of potential variables are extracted by carrying out cross validation through a leave-one-out method, and a steady principle of coefficients is decided by utilizing a variable projection importance technology-based variable screening method and a regression model so as to establish simple and steady models with high prediction precision. According to the application, the VIP regression model is capable of effectively establishing the simple and steady models which are high in prediction precision and can be further popularized.

The invention discloses a method for detecting the quality of Brassica campestris based on the near infrared spectrum, which comprises the steps of fitting collected near infrared spectrum data of a Brassica campestris sample and chemical values measured by a standard method, and optimally establishing a model by applying partial least squares (PLS); selecting an optimal spectrum pretreatment method, and measuring the quality of the model by comparing a determination coefficient (R2) and a root mean square error (RMSECV) so as to construct a high-quality quantitative analysis model of the nearinfrared spectrum of Brassica campestris. According to the method, the surface color, the mass loss rate, the hardness and the VC content of Brassica campestris can be rapidly and accurately predicted, the grade of Brassica campestris can be judged, thereby laying a foundation for rapid and nondestructive quality detection research of Brassica campestris, and having very high practicability and wide applicability.

The invention discloses a method for measuring moisture content in rice through near infrared spectroscopy based on SiPLS. The method comprises the following steps: rejecting an abnormal sample by adopting a X-Y residual analysis method, selecting a correction set sample and a prediction set sample by applying a classical Kennard-Stone method, performing preprocessing optimization on the near infrared spectrum by utilizing a second-order derivative, dividing the spectrum into 25 sub-intervals by adopting the SiPLS method, jointly establishing a moisture model in the rice by utilizing the 3rd,the 9th, the 18th and the 20th sub-intervals, wherein the correction set determination coefficient is 0.9573, and the mean-square root error of the correction set is 0.3886. 40 verification set samples are used for verifying a calibration model, the prediction correlation coefficient achieves 0.9625, and the average prediction recovery rate is 100.27%, so that the model has good prediction capacity. Compared with the full-spectrum modelling, the model established adopting the SiPLS method is not only simple, but also the prediction precision of the model is improved. The method disclosed by the invention can be used for quickly measuring the moisture content in the rice as an accurate, nondestructive and environment-friendly detection measure.

A silver salt photothermographic dry imaging material wherein said material has photographic speeds (1) and (2) determined based on the predetermined conditions and the photographic speed (2) is not more than {fraction (1/10)} of the photographic speed (1), and the coefficient of determination value R² of the linear regression line is 0.998-1.000, which is obtained from the predetermined density points having a* and b* arranged in two-dimensional coordinates in which a* is used as the abscissa and b* is used as the coordinate of the CIE 1076 (L*a*b*) color space, b* of the intersection point of the linear regression line with the ordinate is −5-5, and gradient (a*/b*) is 0.7-2.5.

The invention discloses a neural network based rock destroy strength determination method. The method is characterized in that a neural network is used to research the rock strength criterion under a uniaxial or triaxial loading condition, various collected rock related data are randomly divided into training and verifying subsets, the compressive strength and the smallest principal stress are used as input values and the largest principal stress value is used as an output value to train the neural network, and the trained neutral network is used to predict largest principal stress value during the test rock destroy. The method mainly comprises a step of experiment data analysis and a step of ANN based largest principal stress value prediction. The method shows the mean square deviation of the neutral network prediction result is reduced by 30-40%, and the determination coefficient is increased by 0.05-0.08 and is more close to 1. The use of the ANN to predict the rock strength has a wide adaptive loading range, so the method is suitable for rock-kind-changeable complex non-linear conditions, and is flexible and accurate.

The invention provides a near-infrared-band hyperspectral diagnosis method for detecting the content of nitrogen in rubber tree leaves. The method comprises the following steps: 1) selecting rubber tree sample leaves; 2) collecting hyperspectral data of the rubber tree sample leaves at the near-infrared band; 3) carrying out pretreatment on the rubber tree leaf samples and then, measuring the content of nitrogen in the pretreated rubber tree leaf samples; 4) obtaining average spectrum of different hyperspectral data point selection spectroscopic data of the rubber tree leaf hyperspectral databy combining a PCA (principal component analysis) method and a K-means clustering method; 5) carrying out modeling on the average spectrum of the different hyperspectral data point selection spectroscopic data by utilizing a partial least-squares regression algorithm, and selecting an optimal hyperspectral data point selection method according to a decision coefficient of a training set adopted bymodeling; and 6) predicting the content of nitrogen in the rubber tree leaves by utilizing the established model.

The invention discloses a chlorophyll fluorescence imaging based transgenic maize glyphosate tolerance phenotype detection method. The method includes: (1) preparing experimental samples; (2) acquiring shikimic acid contents of canopy leaves of transgenic maize and non-transgenic maize plants subjected to glyphosate stress in different day numbers; (3) acquiring canopy chlorophyll fluorescence parameters of the transgenic maize and the non-transgenic maize plants subjected to glyphosate stress in different day numbers through a chlorophyll fluorescence imaging system; (4) establishing a PLSR model to reject abnormal samples, and selecting a modeling set and a prediction set through K-Means; (5) selecting the chlorophyll fluorescence parameters most sensitive in glyphosate stress response by means of principal component analysis; (6) establishing a PLSR regression analysis model on the basis of the selected chlorophyll fluorescence parameters and the practical shikimic acid content of the transgenic maize plants, wherein determination coefficients R<2> of the modeling set and the prediction set are 0.75 and 0.63 respectively. The method is high in identification precision and simple in operation, and quick nondestructive testing of transgenic maize glyphosate tolerance phenotypes can be realized.

The invention discloses a subarea optimization method for a crop irrigation system in an underground water shallow-buried area. The method comprises the steps of obtaining local historical data; based on the local historical data, utilizing an Aquacrop model to obtain first simulation yield and simulation water consumption of each growth stage of crop wheat in different areas under different set irrigation systems, wherein different areas take set groundwater burial depths as partition boundaries; according to all the first simulated yields and the simulated water consumption of the corresponding growth stages, acquiring second simulated yields of all the regional crops under the water production function models and stage sensitivity coefficients or indexes of the different growth stages by adopting the set multiple water production function models; calculating a decision coefficient between the first simulated yield and the second simulated yield; determining an optimal moisture production function model corresponding to each region by adopting a phase sensitive coefficient or an index and a decision coefficient; and taking the stage sensitive coefficient or index under the optimal moisture production function model as an irrigation decision variable, and obtaining an irrigation system by using Aquacrop in combination with a set irrigation quota.

The invention relates to a kiln muddy water optimal prediction model establishment method based on a hyperspectral image technology; the method comprises the steps of acquiring hyperspectral image information of near-infrared and visible light wave bands, performing black-and-white correction to eliminate errors caused by uneven illumination, extracting the average spectral information of the region of interest, estimating the average spectral reflectivity of each pixel point in the image, and separately establishing quantitative prediction models based on the full-wave band and the characteristic spectrum through unprocessed and SNV and different modeling methods. According to the method, the optimal model for the kiln muddy water quantitative prediction is screened out through a comparison training set, a test set quantitative prediction and the value of the root-mean-square error; the quality of the kiln mud is quickly evaluated for each large liquor brewing enterprise, a theoretical basis and technical support are provided for manual kiln protection and kiln protection, and technical guarantee is provided for transformation upgrading and digital and intelligent on-line real-time monitoring of the fermentation state of the kiln mud for wine brewing industrialization.