Skip to main content
. 2006 Sep 11;34(17):4655–4666. doi: 10.1093/nar/gkl638

Figure 1.

Figure 1

A typical solution of C-SVDD when outliers are permitted. The C-SVDD finds the minimum-volume hypersphere which includes most of target data. The data which resides on the boundary and outside the boundary are called support vectors which fully determine the compact boundary. Thus, the data with solid circle are the support vectors on the boundary, and the data with dotted circle are also support vectors which are the outliers.