Three-Dimensional Site Characterization Model of Bangalore Using Support Vector Machine. (29th February 2012)

• Record Type: Journal Article
• Authors: Samui, Pijush
• Other Names: Ding W. Academic Editor.; He Z. Academic Editor.
• Is Part Of: ISRN soil science. Volume 2012(2012)
• Publication Date: 2012-02-29
• Subjects: Soil science -- Periodicals; Soils -- Research -- Periodicals; Soil science; Soils -- Research; Soil Sciences; Periodicals; Electronic journals; 631.4
• DOI: 10.5402/2012/346439
• Languages: English
• ISSNs: 2090-875X

Abstract

Abstract : The main objective of site characterization is the prediction of in situ soil properties at any half-space point at a site based on limited tests. In this study, the Support Vector Machine (SVM) has been used to develop a three dimensional site characterization model for Bangalore, India based on large amount of Standard Penetration Test. SVM is a novel type of learning machine based on statistical learning theory, uses regression technique by introducing ε -insensitive loss function. The database consists of 766 boreholes, with more than 2700 field SPT values (N ) spread over 220 sq km area of Bangalore. The model is applied for correctedN (N c ) values. The three input variables (x, y, andz, wherex, y, andz are the coordinates of the Bangalore) were used for the SVM model. The output of SVM was theN c data. The results presented in this paper clearly highlight that the SVM is a robust tool for site characterization. In this study, a sensitivity analysis of SVM parameters ( σ, C, and ε ) has been also presented.