Search

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 corrected N (Nc) values. The three input variables (x, y, and z, where x, y, and z are the coordinates of the Bangalore) were used for the SVM model. The output of SVM was the Nc 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. [ABSTRACT FROM AUTHOR]

In this paper, the problem of site characterization is treated as a task of function approximation of the large existing data from standard penetration tests (SPTs) in three-dimensional subsurface of Bangalore, India. More than 2,700 field SPT values (N) has been collected from 766 boreholes spread over an area of 220-km2 area in Bangalore, India. To get N corrected value (Nc), N values have been corrected for different parameters such as overburden stress, size of borehole, type of sampler, length of connected rod. In three-dimensional analysis, the function Nc=Nc(X,Y,Z), where X, Y, and Z are the coordinates of a point corresponds to Nc value, is to be approximated with which Nc value at any half-space point in Bangalore, India can be determined. An attempt has been made to develop artificial neural network (ANN) model using multilayer perceptrons that are trained with Levenberg-Marquardt back-propagation algorithm. Also, a geostatistical model based on ordinary kriging technique has been adopted. The knowledge of the semivariogram of the Nc values is used in the ordinary kriging method to predict the Nc values at any point in the subsurface of Bangalore, India where field measurements are not available. The results obtained show that ANN model is fairly accurate in predicting Nc values. In case of ordinary kriging, a new type of cross-validation analysis shows that it is a robust model for prediction of Nc values. A comparison between the ANN and geostatistical model demonstrates that the ANN model is superior to Geostatistical model in predicting Nc values in the subsurface of Bangalore, India. [ABSTRACT FROM AUTHOR]

This study describes two Artificial Intelligence (AI) techniques for predicting spatial variability of rock depth in Bangalore. Reduced level of rock (d) at Bangalore, India is arrived from the 652 boreholes data in the area covering 220 km2. The first AI technique uses generalized regression neural network (GRNN) that are trained with suitable spread(s) to predict d at any point in Bangalore. The second technique uses Least Square Support Vector Machine (LSSVM), is a statistical learning theory which adopts a least squares linear system as a loss function instead of the quadratic program in original support vector machine (SVM). Here, LSSVM has been used as a regression technique. A comparative study between the two developed AI techniques has been presented in this paper. The results indicate that the developed GRNN model has the ability to predict d with an acceptable degree of accuracy (Coefficient of Correlation(r) =0.885, and Root Mean Square Error (RMSE) =0.021). Whereas, the developed LSSVM model predicts d with an acceptable degree of accuracy (r =0.967, and RMSE=0.004). This study also highlights the capability of LSSVM model over GRNN. [ABSTRACT FROM AUTHOR]

Two algorithms are outlined, each of which has interesting features for modeling of spatial variability of rock depth. In this paper, reduced level of rock at Bangalore, India, is arrived from the 652 boreholes data in the area covering 220 sq⋅km. Support vector machine (SVM) and relevance vector machine (RVM) have been utilized to predict the reduced level of rock in the subsurface of Bangalore and to study the spatial variability of the rock depth. The support vector machine (SVM) that is firmly based on the theory of statistical learning theory uses regression technique by introducing ε-insensitive loss function has been adopted. RVM is a probabilistic model similar to the widespread SVM, but where the training takes place in a Bayesian framework. Prediction results show the ability of learning machine to build accurate models for spatial variability of rock depth with strong predictive capabilities. The paper also highlights the capability of RVM over the SVM model. [ABSTRACT FROM AUTHOR]