Techno Press
You logged in as Techno Press

Geomechanics and Engineering
  Volume 21, Number 6, June25 2020 , pages 583-598

An evolutionary hybrid optimization of MARS model in predicting settlement of shallow foundations on sandy soils
Nguyen-Vu Luat, Van-Quang Nguyen, Seunghye Lee, Sungwoo Woo and Kihak Lee

    This study is attempted to propose a new hybrid artificial intelligence model called integrative genetic algorithm with multivariate adaptive regression splines (GA-MARS) for settlement prediction of shallow foundations on sandy soils. In this hybrid model, the evolution algorithm – Genetic Algorithm (GA) was used to search and optimize the hyperparameters of multivariate adaptive regression splines (MARS). For this purpose, a total of 180 experimental data were collected and analyzed from available researches with five-input variables including the bread of foundation (B), length to width (L/B), embedment ratio (Df/B), foundation net applied pressure (qnet), and average SPT blow count (NSPT). In further analysis, a new explicit formulation was derived from MARS and its accuracy was compared with four available formulae. The attained results indicated that the proposed GA-MARS model exhibited a more robust and better performance than the available methods.
Key Words
    multivariate adaptive regression spline; genetic algorithm; evolutionary hybrid model; settlement prediction; shallow foundation
Nguyen-Vu Luat, Seunghye Lee and Kihak Lee: Department of Architectural Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul 05006, South Korea

Van-Quang Nguyen: Department of Civil and Environmental Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, South Korea

Sungwoo Woo: TechSquare Ltd. South Korea, 25 Banpodae-ro, Seocho-gu, Seoul 06710, South Korea

Techno-Press: Publishers of international journals and conference proceedings.       Copyright © 2022 Techno Press
P.O. Box 33, Yuseong, Daejeon 305-600 Korea, Tel: +82-42-828-7996, Fax : +82-42-828-7997, Email: