A NEW METHOD FOR ESTIMATION OF FETAL WEIGHT USING SUPPORT VECTOR MACHINE

The performance of support vector machine for regression estimation depends on the kernel function, its parameter, insensitive factor e and penalty factor C.The determination of the parameters of SVM remains a difficult problem. Cross-validation method is commonly used in practice to decide the parameters of SVM,however,it is notefficient enough. A novel adaptive support vector machine (A-SVM) was proposed in this work to determine the optimal parameters automatically. The algorithms for adaptively tuning parameters of SVM established. A-SVM was successfully applied in estimating the fetal weight. Compared with RBFN-PLSR methods, A-SVM was superior in both fitt and testing accuracy.