Abstract—Many investigations have been done in last few years to predict the load bearing capacity of driven piles in cohesion less soil .There are many factors on which the load bearing capacity of pile depends, the calculation involved in load bearing capacity of a pile is very complex in general. Hence some assumptions are made in the calculation of load bearing capacity which either oversimplify the problem or are considered improperly, which causes increase in the error in measured pile load bearing capacity. In this paper, LEAST SQUARE SUPPORT VECTOR MACHINE (L.S.S.V.M) method and MULTIVARIATE ADAPTIVE REGRESSIONS SPLINE (Mars) are used to predict load bearing capacity of driven piles in cohesion less soil by mat lab software and the results obtained from both the methods are compared with the actual measured capacities.

Index Terms—cohesion less soil, load bearing capacity, lssvm method, mars method

Cite: Mohit Chugh, Shraddha Satish Thumsi, and Vivek Keshri, "A Comparative Study Between Least Square Support Vector Machine(Lssvm) and Multivariate Adaptive Regression Spline(Mars) Methods for the Measurement of Load Storing Capacity of Driven Piles in Cohesion Less Soil," International Journal of Structural and Civil Engineering Research, Vol. 4, No. 2, pp.189-194, May 2015. doi: 10.18178/ijscer.4.2.189-194