Differential prioritization between relevance and redundancy in correlation-based feature selection techniques for multiclass gene expression data

Table 1 Descriptions of benchmark datasets.

Dataset	Type	N	K	Training:Test set size	P _max
BRN	cDNA	7452	15	176:84	150
BRN14	cDNA	7452	14	174:83	150
GCM	Affymetrix	10820	14	144:54	150
NCI60	cDNA	7386	8	40:20	150
PDL	Affymetrix	12011	6	166:82	120
Lung	Affymetrix	1741	5	135:68	100
SRBC	cDNA	2308	4	55:28	80
MLL	Affymetrix	8681	3	48:24	60
AML/ALL	Affymetrix	3571	3	48:24	60

N is the number of features after preprocessing. K is the number of classes in the dataset.