A Semisupervised Feature Selection with Support Vector Machine

Table 3

Data sets used in the experiments. 𝑛, 𝑝, and 𝑙 are the number of samples, features, and labeled samples, respectively.

Data set	𝑛	𝑝	𝑙
Digit1	1500	241	10 or 100
USPS	1500	241	10 or 100
COIL2	1500	241	10 or 100
BCI	400	117	10 or 100
g241c	1500	241	10 or 100
g241n	1500	241	10 or 100