Advanced soft computing techniques for predicting soil compression coefficient in engineering project: a comparative stu
- PDF / 3,432,027 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 50 Downloads / 189 Views
ORIGINAL ARTICLE
Advanced soft computing techniques for predicting soil compression coefficient in engineering project: a comparative study Viet‑Ha Nhu1 · Pijush Samui2,3 · Deepak Kumar4 · Anshuman Singh4 · Nhat‑Duc Hoang5 · Dieu Tien Bui6 Received: 12 August 2018 / Accepted: 4 May 2019 © Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract Heterogeneous nature of soil consists of various chemical and physical attributes that make the prediction of soil parameters very tedious and challenging. Moreover, it becomes more difficult when we have more number of variables. This study investigates the feasibility of principal component analysis as dimensionality reduction technique to select the input variables in terms of principal components (PCs), which helps in reducing the complexity and multicollinearity problem. The soil attributes, namely depth of the sample, sand percentage, silt percentage, clay percentage, moisture content, dry density, wet density, void ratio, liquid limit, plastic limit, liquid index, and plastic index, have been employed as influencing factors to estimate the coefficient of compression of soil. Furthermore, the extracted variance-based PCs were used as predictor to build the minimax probability machine regression (MPMR), multivariate adaptive regression splines (MARS), and genetic programming regression (GPR). The predictive accuracy of the models has been assessed via five statistical fitness parameters. In the training phase, the PCA-MARS model has shown good outcomes in terms of fitness measurement parameters (RMSE= 0.004, r = 0.981 and NSE = 0.963). During testing phase, PCA-MARS has outperformed (RMSE= 0.006, r = 0.963 and NSE = 0.912) followed by PCA-GPR and PCA-MPMR. The finding of this research concludes that PCA-based MARS model can be used as new and reliable data-driven approach for estimation of soil parameters. Furthermore, this new tool can help to save the time and capital spent on estimation of different parameter of soil. Keywords Soil · Coefficient of compression · PCA · MPMR · GPR · MARS · Soft computing
1 Introduction
* Deepak Kumar [email protected]; [email protected] 1
Department of Geological‑Geotechnical Engineering, Hanoi University of Mining and Geology, No. 18 Pho Vien, Duc Thang, Bac Tu Liem, Hanoi, Vietnam
2
Geographic Information Science Research Group, Ton Duc Thang University, Ho Chi Minh, Vietnam
3
Faculty of Environment and Labour Safety, Ton Duc Thang University, Ho Chi Minh, Vietnam
4
Department of Civil Engineering, National Institute of Technology Patna, Ashok Raj Path, Patna 800005, India
5
Faculty of Civil Engineering, Institute of Research and Development, Duy Tan University, P809‑03, Quang Trung, Da Nang 550000, Vietnam
6
Geographic Information System Group, Department of Business and IT, University of South-Eastern Norway, Gullbringvegen 36, 3800 Bø i Telemark, Norway
In geotechnical engineering, soil compression can be defined as the reduction in volume of the soil under pressure imposed by the d
Data Loading...
