Search Results

You are looking at 1 - 10 of 209 items for :

  • "regression" x
  • Materials and Applied Sciences x
  • Refine by Access: All Content x
Clear All

emerged as a promising tool for analyzing and predicting the behavior of complex systems like helical piles. In this study, three machine learning methods - adaptive neuro fuzzy inference system, random forest regression, and support vector regression

Open access

equations were developed using regression analysis [ 17 ]. These equations were used to evaluate the compressive strength by integrating variables such as percentage of replacement and age of curing days. The relationship between the strength parameters was

Open access

, A. B. & Chittleborough , D. J., 1995. Further results on prediction of soil properties from terrain attributes: heterotopic cokriging and regression-kriging. Geoderma. 67 . 215–226. Chittleborough D J

Restricted access

47 building projects were collected. The data include information about the rework cost in steel reinforcement works and the total cost overrun in the projects. Linear regression model was built to show the relation between rework cost and cost

Open access

The phosphorus retention ability of soils depends on several factors and influences the effectiveness of fertilization as well as the release of P from soil to water. In the present study the phosphorus supplying and/or retention ability of soils were estimated by two approaches: biological approach (pot experiments) and modelling (by regression analyses). In the course of the biological approach pot experiments were carried out with soils showing significant differences in total and available P contents. Soil samples were collected from selected plots of 9 sites of the National Long-Term Fertilization Trials (NLFT) after 20 years of fertilization, which represents different agro-ecological regions of Hungary. Site characteristics covered a wide range in pH, carbonate and P content, representing typical soil types of the country. With the statistical approach (modelling), the most important soil properties were included and the role of these factors was evaluated by stepwise regression analyses. From the equations, the contribution of important soil parameters to phosphorus supplying and retention ability could be quantified. The objective of the present study was to find a simple way to compare and evaluate the two approaches in P nutrient turnover of soils. Results of the two approaches were correlated. From these results, a rank correlation was also made from the experimental and calculated results. A very close relationship was observed for the P supply and retention of soils (r value was 0.918 for the N 0 P 0 K 0 unfertilized control and 0.927 for the N 200 P 200 K 100 fertilization level). Values obtained with rank correlation were 0.87 and 0.866, respectively, verifying that both methodologies are reliable for estimating the nutrient dynamics in soils and to predict P dynamics in a diverse range of soils.

Restricted access

V. Vapnik 1996 Support Vector Regression Machines Advances in Neural Information Processing System 9 155 – 161

Restricted access

content as binder gives dense structure to AAC by minimizing the voids and pores in micro-structure. Thus, the electrical resistivity of concrete enhances. Fig. 6. Electrical resistivity test results 4 Regression analysis Regression analysis is a

Open access

.5–1.49, and strongly dissatisfied: 0–0.49. In addition, inferential statistics were used. After Preiser et al. [ 5 ], stepwise multiple linear regression was used to determine which performance elements among the technical, functional, and behavioral elements

Open access

-5487.0000054 . [23] Mahamid I. ( 2011 ), Early cost estimating for road construction projects using multiple regression techniques . Australasian Journal of Construction

Open access

Abstract

Considering the increasing prospective regarding the various applications of Poly Ether Ether Ketone reinforced with 30% carbon fibres (PEEK CF30), there is a crucial need to investigate its machinability. In this work, focus is centered on non-linear regression based models that can be built to predict roug hness parameters R a and R t associated to turning of PEEK CF30 when using TiN coated cutting tool. Attention was paid to one-variant models that can be proposed to represent the effect of the cutting speed on the surface finish parameters. A broad class of non-linear interpolation models was considered. Their aptness to be used in modelling this particular application was assessed. The identification of the various mathematical models was performed by using experimental results that were obtained from CNC turning of PEEK samples. Based on statistical analysis, all the considered non-linear regression models proved to be highly significant and succeeded to fit adequately the experimental results.

Restricted access