SVM Applied to Trace Element Analysis of Tea

The quality of mathematical model made by SVC is dependent on the selection of kernel function and parameter C in computation. In order to find the best choice of kernel function and the value of parameter C, the rate of correctness (P ) of the prediction in LOO cross-validation test is used as the criterion for this selection work. 

By using SVC method, it has been found that these three kinds of tea can be classified with linear kernel functions, with the rate of correctness of prediction equal to 100% by using C = 10. By this way, the criterion of samples of oolong tea can be found as follows  

And the criterion to differentiate green tea of southeastern China from black tea of south China is as follows  

The classification by Fisher method is also clear-cut, but both the result of LOO cross-validation test of Fisher method and the results of K-Nearest Neighbor (KNN) methods (k=l, 3 or 5) lead to some misclassification, while the result of the LOO cross-validation test of SVC (linear kernel, C =10) gives 100% rate of correctness. 

---