Method Of Polynomial Regression Research Articles

Novel Hybrid Statistical Learning Framework Coupled with Random Forest and Grasshopper Optimization Algorithm to Forecast Pesticide Use on Golf Courses

Golf course maintenance requires the use of several inputs, such as pesticides and fertilizers, that can be harmful to human health or the environment. Understanding the factors associated with pesticide use on golf courses may help golf-course managers reduce their reliance on these products. In this study, we used a database of about 14,000 pesticide applications in the province of Québec, Canada, to develop a novel hybrid machine learning approach to predict pesticide use on golf courses. We created this proposed model, called RF-SVM-GOA, by coupling a support vector machine (SVM) with random forest (RF) and the grasshopper optimization algorithm (GOA). We applied RF to handle the wide range of datasets and GOA to find the optimal SVM settings. We considered five different dependent variables—region, golf course ID, number of holes, year, and treated area—as input variables. The experimental results confirmed that the developed hybrid RF-SVM-GOA approach was able to estimate the active ingredient total (AIT) with a high level of accuracy (R = 0.99; MAE = 0.84; RMSE = 0.84; NRMSE = 0.04). We compared the results produced by the developed RF-SVM-GOA model with those of four tree-based techniques including M5P, random tree, reduced error pruning tree (REP tree), and RF, as well as with those of two non-tree-based techniques including the generalized structure of group method of data handling (GSGMDH) and evolutionary polynomial regression (EPR). The computational results showed that the accuracy of the proposed RF-SVM-GOA approach was higher, outperforming the other methods. We analyzed sensitivity to find the most effective variables in AIT forecasting. The results indicated that the treated area is the most effective variable in AIT forecasting. The results of the current study provide a method for increasing the sustainability of golf course management.

Parametric Evaluation of Simultaneous Effects of Damaged Zone Parameters and Rock Strength Properties on GRC

The convergence-confinement method via the ground reaction curve (GRC) is used as the common practice of tunnel design which demands accurate determination of the stress state and material strength behavior in different zones around the tunnel section. Besides, formation of the excavation/blast-induced damaged zone (EDZ/BDZ) adds more complexity to the problem due to variation of elasticity modulus of the rock mass in this zone. As a result, advanced numerical methods via finite element/difference commercial packages or user-coded, semi-numerical techniques are required to develop the GRC, which demands a high degree of proficiency and knowledge of computational plasticity and geomechanics. In this study, a new, simple, and accurate method is proposed for prediction of GRC of circular tunnels constructed in the damaged, elastoplastic rock masses obeying softening in the plastic zone. The effects of deterioration caused by the drilling/blast in the EDZ were taken into account by assuming a reduced and varying Young’s modulus using the disturbance factor, in the form of Hoek–Brown failure criterion and the Geological Strength Index (GSI). Besides, effects of intermediate principal stress and the exponential decaying dilation parameter are taken into account thanks to adoption of the unified strength criterion (USC) as the material strength criteria. To do so, genetic algorithm (GA) via the method of evolutionary polynomial regression (EPR) is used to find a relationship between a number of 19 affecting parameters on the GRC as the input, and the internal support pressure as the target of prediction. Verification analysis was performed to verify the validity of the results using field measurements data as well as other advanced numerical studies found in the literature. Lastly, variation of the support pressure with simultaneous changes in the affecting input parameters was investigated using multivariable parametric study.

Refined estimation of Li in mica by a machine learning method

Abstract Li-rich micas are crucial in the exploration for and exploitation of Li resources. The determination of Li in mica using classical bulk chemical methods or in situ microanalytical techniques is expensive and time-consuming and has stringent requirements for the quality of micas and reference materials. Although simple linear and nonlinear empirical equations have been proposed, they are inconsistent with the complex physicochemical mechanisms of Li incorporation and commonly lead to large errors. In this study, we introduce a refined method of multivariate polynomial regression using a machine learning algorithm to estimate Li from multiple major oxide abundances. The performance of our regression model is evaluated using the coefficient of determination (R2) and the root-mean-square error (RMSE) of the independent test sets. The best-performed models show R2 of 0.95 and a RMSE of 0.35 wt% for the test set of data set 1 (all compiled data, n = 2124) and R2 of 0.96 and a RMSE of 0.22 wt% for the test set of data set 2 (only data obtained using in situ techniques, n = 1386). Our results indicate that integration of electron probe microanalysis and multivariate polynomial regression (based on data set 1) presents a robust and convenient approach to quantify Li contents in micas. The application of the proposed approach to micas from central Inner Mongolia, NE China, suggests that in addition to the Weilasituo ore bodies, the Jiabusi granite and greisen and the Shihuiyao metamorphic sediment formation have good potential for Li exploration. Our study also provides preliminary constraints on the genesis of Li deposits.

К вопросу определения буксования сельскохозяйственных тракторов

The well-known methods for determining the slipping of the propulsion devices of agricultural tractors are described. A regression analysis of the traction characteristics of a wheeled tractor is performed. The equivalence of the method for determining the current slippage through the actual tractor speed and engine crankshaft speed is assessed. A regression model is proposed to determine the amount of slippage based on the method of local polynomial regression (locally estimated scatterplot smoothing or LOESS)

The Effect of Person-Team Conscientiousness Fit on Knowledge Sharing: The Moderating Role of Internal Team Environment

Drawing on studies of person-team fit and theory of team-member exchange, we examined the effect of fit versus misfit between a team member’s conscientiousness and his/her team’s composition of conscientiousness on the member’s knowledge sharing. We hypothesized that person-team conscientiousness fit would lead to more knowledge sharing because a member who fits his/her team with respect to conscientiousness tends to have similar achievement striving with the team and low exchange cost. Using the method of polynomial regression in two studies in different regions and research settings, we obtained consistent results that person-team conscientiousness fit is positively associated with a team member’s knowledge sharing. We further found that internal team environment moderates the relationship between person-team conscientiousness fit and knowledge sharing such that it makes the relationship weaker. Our study demonstrated that to better understand the effect of personality on knowledge sharing in teams, it is beneficial to simultaneously consider the interplay among member personality, team personality, and team contexts.

Spatial non-linearity of methane release dynamics in underground boreholes for sustainable mining

The paper is devoted to the problem of increasing energy efficiency of coalmine methane utilization to provide sustainable development of geotechnologies in the context of transition to a clean resource-saving energy production. Its relevance results from the fact that the anthropogenic effect of coalmine methane emissions on the global climate change processes is 21 times higher than the impact of carbon dioxide. Suites of gassy coal seams and surrounding rocks should be classified as technogenic coal-gas deposits, while gas extracted from them should be treated as an alternative energy source. Existing practices and methods of controlling coalmine methane need to be improved, as the current “mine – longwall” concept does not fully take into account spatial and temporal specifics of production face advancement. Therefore, related issues are relevant for many areas of expertise, and especially so for green coal mining. The goal of this paper is to identify patterns that describe non-linear nature of methane release dynamics in the underground boreholes to provide sustainable development of geotechnologies due to quality improvement of the withdrawn methane-air mixture. For the first time in spatial-temporal studies (in the plane of CH4-S) of methane concentration dynamics, according to the designed approach, the parameter of distance from the longwall (L) is introduced, which allows to create function space for the analyzed process (CH4 of S-L). Results of coalmine measurements are interpreted using the method of local polynomial regression (LOESS). The study is based on using non-linear variations of methane concentration in the underground boreholes and specific features of their implementation to perform vacuum pumping in the most productive areas of the undermined rock mass in order to maintain safe aerogas conditions of the extraction block during intensive mining of deep-lying gassy seams. Identification of patterns in the influence of situational geomechanical conditions of coal mining on the initiation of metastable gas-coal solution transformation and genesis of wave processes in the coal-rock mass allows to improve reliability of predicting methane release dynamics, as well as workflow manageability of mining operations. Presented results demonstrate that development of high-methane Donbass seams is associated with insufficient reliability of gas drainage system operation at distances over 40 m behind the longwall face. Obtained results confirm a working hypothesis about the presence of spatial migration of methane concentration waves in the underground gas drainage boreholes. It is necessary to continue research in the area of estimating deviation angles of “advance fracturing” zone boundaries from the face line direction. Practical significance of research results lies in the possibility to use them in the development of scientific foundation for 3D gas drainage of a man-made coal-methane reservoir, taking into account spatial and temporal advancement of the production face.

SURE-based optimum-length S-G filter to reconstruct NDVI time series iteratively with outliers removal

Savitzky–Golay (S-G) filter is a method of local polynomial regression, and iterative filtering with S-G filter can be used to smooth out random noise and outliers of cloud noise in NDVI time series. It involves a continuous approximation to the upper envelope of NDVI time series. In this paper, the optimum-length of S-G filter was estimated based on Steinc’s unbiased risk estimator theory when S-G filtering was conducted iteratively, and the reconstruction result was presented. Reconstruction experiments on the simulated data and MODIS NDVI time series of the year 2010–2014 showed that the optimum-length S-G filter can outperform the fixed bandwidth S-G filter.

Распознавание символов методом полиномиальной регрессии

Распознавание символов методом полиномиальной регрессии

Model-independent reconstruction of the linear anisotropic stress η

In this work, we use recent data on the Hubble expansion rate H(z), the quantity fσ8(z) from redshift space distortions and the statistic Eg from clustering and lensing observables to constrain in a model-independent way the linear anisotropic stress parameter η. This estimate is free of assumptions about initial conditions, bias, the abundance of dark matter and the background expansion. We denote this observable estimator as ηobs. If ηobs turns out to be different from unity, it would imply either a modification of gravity or a non-perfect fluid form of dark energy clustering at sub-horizon scales. Using three different methods to reconstruct the underlying model from data, we report the value of ηobs at three redshift values, z=0.29, 0.58, 0.86. Using the method of polynomial regression, we find ηobs=0.57±1.05, ηobs=0.48±0.96, and ηobs=−0.11±3.21, respectively. Assuming a constant ηobs in this range, we find ηobs=0.49±0.69. We consider this method as our fiducial result, for reasons clarified in the text. The other two methods give for a constant anisotropic stress ηobs=0.15±0.27 (binning) and ηobs=0.53 ± 0.19 (Gaussian Process). We find that all three estimates are compatible with each other within their 1σ error bars. While the polynomial regression method is compatible with standard gravity, the other two methods are in tension with it.

The determination of the running reliability of the system with the method of polynomial regression for electricity transmission lines

One of the most essential data of the social and economic development accepted all around the world is energy. The reasons such as the rapidity of the urbanization and industrialization and rapid increase in population cause to the continuous and indispensable increase in the demand for energy. While the demand for electricity energy is so high, what is important in terms of the user is the submission of the continuous and qualified energy to their own usage. In this study, the failures and power transformer failures occurring in Turkey electricity transmission system have been detected as hourly, monthly and annually and in this way; with the use of these data, the reasons for the failures have been examined and suggestions for solutions have been studied and it has provided opportunities for the conduction of preventive maintenance and repair works in the future. When the failure numbers of 380 kV lines have been examined, it is seen that some lines paint a very negative picture. When the failing lines have been monthly examined, it is seen that there is an accumulation in terms of failure in April-May and August-September periods. By means of this study; the failures occurring in the energy transmission lines have been classified on the basis of hour, month and year and the running reliability of the system in the transmission lines to be established in the future has been determined.

ANÁLISE COMPARATIVA DA PRECIPITAÇÃO NO ESTADO DA PARAÍBA UTILIZANDO MODELOS DE REGRESSÃO POLINOMIAL

O Estado da Paraíba apresenta alta variabilidade espacial e temporal na distribuição das chuvas. Além disso, existem muitos locais onde não se tem informações sobre os valores de precipitação. Logo, o uso da regressão polinomial (superfície de tendência) na tentativa de obter estimativas de precipitação pode ser uma alternativa para um melhor entendimento da variabilidade espaço-temporal desse parâmetro meteorológico. Assim, o objetivo principal desse estudo foi utilizar o método da regressão polinomial como ferramenta para estimar médias mensais de precipitação para locais conhecidos (estações meteorológicas ou postos pluviométricos) e compará-las com valores medidos, com o intuito de verificar sua precisão dentro da região de estudos. Foram utilizados dados médios mensais de precipitação pluviométrica provenientes de 102 estações meteorológicas distribuídas espacialmente no estado da Paraíba, no período de 1962 a 2001. Os dados apresentaram alta variabilidade espacial em todo o Estado. As regressões polinomiais que melhor se ajustaram aos dados observados foram as de 3ª e 4ª ordens, e a comparação entre os valores de precipitação medidos e estimados mostraram que os meses de junho a novembro apresentaram as menores diferenças de precipitação na maior parte do território paraibano. Sendo assim, o método adotado se apresenta como uma ferramenta promissora na estimativa da precipitação mensal no Estado da Paraíba.

非参数协整和误差修正模型及其在金融中的应用

本文主要研究了协整理论和非线性协整的非参数方法两个领域，包括线性协整及线性误差修正模型，非线性协整及非线性误差修正模型，ACE算法和局部多项式回归方法，基本梳理清楚了该领域的研究脉络和框架。本文运用Matlab编程实现了局部多项式回归这一非参数检验方法，详细地梳理了协整理论的内容，包括线性协整理论、线性误差修正模型、线性协整理论的估计和检验、非线性协整和误差修正模型及其估计和检验，并且对个中细节进行了注解，使脉络更为清晰明了，从而增进协整理论的易读性。对时间序列协整的非线性存在的应用提出了新的方法，即融合岭回归的局部多项式回归的非参数方法，通过仿真表明，该方法有很好的估计效果。选取日本、新加坡、台湾三地指数数据进行实证分析，把局部多项式回归的非参数方法和协整、误差修正模型结合，实现了对协整、误差修正模型的估计，并且得到了较高模型估计精度，尤其重要的是，能够合理地解释局部多项式回归这一非参数方法的一阶导数在日本、新加坡、台湾三地股市指数中的意义。 This paper mainly focuses on co-integration theory and nonparametric method with nonlinear co-integration, which includes linear co-integration and linear error correction model, nonlinear co-integration and nonlinear error correction model, the ACE algorithm and local polynomial regression. It is clearly proved right by these analytical methods. The Matlab programming is fully exerted to realize the local polynomial regression, a nonparametric test method. In this paper, co-integration theory is clarified in details including linear theory of co-integration, linear estimation of error correction model, linear co-integration theory and tests, the nonlinear co-integration and error correction model as well as the estimation and inspection towards it. Moreover, the annotation is added for individual specifics, aiming to clarify the structures of co-integration. The existing application of time series nonlinear co-integration is put forward to serve the new method, namely the method of fusing the ridge regression nonparametric local polynomial regression. The simulation shows that this method is proved to be right. The index data assisting the researcher access to the empirical analysis are references from Japan, Singapore and Taiwan. It is on its purpose by combing the non-parametric method of local polynomial regression, co-integration and error correction model to estimate the analysis on the co-integration and error correction model. The precision of the model is assured. The local polynomial regression can be aimed to assist in explaining the significance of the non-parametric method of first derivative stock indexes in Japan, Singapore and Taiwan.

Modeling Root Depth Development with time under some Crop and Tillage Management System

Five empirical models for the prediction of root depth developed with time under four combinations of crop and tillage management systems have been developed by the method of polynomial regression. Root depth predictions by a general model were severally correlated with root depth predictions by the combination-specific models and measured root depth data from five grown under four combinations of crop and tillage management. Root depth development with time assumed a curvilinear trend and was best described by polynomial equations, of order four, with correlation coefficient(r) between 0.961 and 0.974. Root depth predictions by the general model correlated well with both the root depth predicted by the combination-specific models (0.996≤ r ≤1.00) and the measured root depth data (0.849≤ r ≤0.996), thus indicating that the general and combination-specific models can be used interchangeably in predicting root depths under any of the four crop and tillage management combination studied. JARD Vol. 1 2001: pp. 51-66

Modeling of TG curves of isothermal oxidation of graphite

By thermogravimetric analysis technique, TG curves of isothermal oxidation of graphite were obtained and the curves of weight loss versus reduced time were also obtained. The trend of weight loss versus reduced time curves of oxidation of graphite for different temperatures is unified in the temperature range with identical oxidation mechanism. Based on the reduced time plot method, modeling of the TG curves is presented by the method of polynomial regression of weight loss versus reduced time curves without a need of kinetic analysis. By comparing the experimental and simulated TG curves, the method of polynomial regression of weight loss versus reduced time curves can better predict weight loss of the isothermal oxidation of graphite.

Colour Characterisation of a-Si:H-Based Three-Terminal Three-Channel Detector

ABSTRACTColour characterisation of a three-terminal three-channel colour detector in the assembly glass/TCO1/PI1NI2P/TCO2/PI3N/Al is performed, using a method of polynomial regression. The metameric errors of the detector calculated and investigated for different orders of polynomial colour correction are presented and discussed. The benefits of the first order colour correction are shown and graphically illustrated. The final transformation matrix for the first order colour correction and conversion to the output R, G and B signals is given. At the end, a demonstrational application with the a-Si:H-based detector and corresponding read-out and colour correction electronics is presented.

Solar-cycle periodicity in secular variation of H at Alibag

Quiet-day monthly mean values of H at midday and midnight of Alibag for the period 1906 to 1967 are examined for cyclic variations of sunspot cycle periodicity after elimination of the secular variation by the method of polynomial regression and the technique of numerical filteration. The cyclic component is observed both in the midday and midnight series, with prominent amplitudes from about 1930 to 1955. For most of the solar-cycles during the period of data the component variation is nearly in phase with the sunspot cycle and its amplitude for the midday series is almost twice that for the midnight series. Since the two data series differed only in respect of the magnitude of Sq (H) in them, it is construed that in addition to other causes Sq (H) also contributes to the solar-cycle variation in H.