The first iteration in which the negative example set N1 is obtained by moving the classification hyperplane towards positive example set In figure 3, plus signs, plus signs with circle and circles denote positive examples, potential positive examples and unlabeled examples respectively. The points covered by ellipse are negative examples set N1 and the line is classification hyperplane. With the positive examples and initial negative example set N0,the SVM classifier C0 is learned, the negative example set N1 consists of the support vectors of C0 and the unlabeled examples predicted as negative examples.
Chen et al. BMC Genomics 2010 11(Suppl 2):S11 doi:10.1186/1471-2164-11-S2-S11