Leave-one-out cross validation of two SVM models.

<p><i>Model_ND</i> is trained on <i>Positive_H</i>, <i>Positive_C</i>, and <i>Negative_ND</i>. <i>Model_NDNN</i> is trained using the same positive set, and a negative set that includes <i>Negative_ND</i> together with <i>Negative_NN</i>. Accuracy (Acc), precision (Pre), and recall (Rec) were calculated for both kernerls, RBF and Polynomial.