Prediction of Lateral Load Capacity of Pile in Clay Using Multivariate Adaptive Regression Spline and Functional Network
Autor: | Sarat Kumar Das, Shakti Suman |
---|---|
Rok vydání: | 2015 |
Předmět: |
Engineering
Multivariate statistics Multidisciplinary Multivariate adaptive regression splines Mean squared error Correlation coefficient Artificial neural network business.industry Statistical parameter Mars Exploration Program Statistics Astrophysics::Earth and Planetary Astrophysics business Nash–Sutcliffe model efficiency coefficient |
Zdroj: | Arabian Journal for Science and Engineering. 40:1565-1578 |
ISSN: | 2191-4281 1319-8025 |
Popis: | This paper discusses the use of multivariate adaptive regression splines (MARS) and functional networks (FN) for prediction of the lateral load capacity of piles in clay. The results obtained from MARS and FN have been compared with different empirical models and artificial neural network in terms of statistical parameters such as correlation coefficient (R), Nash–Sutcliff coefficient of efficiency (E), absolute average error, maximum average error and root mean square error. Based on the statistical parameters, MARS and FN were found to have a better predictive capacity. Predictive equations are provided based on the MARS and FN model. A sensitivity analysis is also presented to determine the importance of inputs in prediction of the lateral load capacity of piles. |
Databáze: | OpenAIRE |
Externí odkaz: |