Skip to main content
. Author manuscript; available in PMC: 2013 Apr 19.
Published in final edited form as: JMLR Workshop Conf Proc. 2012;22:712–721.

Table 2.

The classification accuracy (%) of linear SVM coupled with different feature selection methods, logistic regression with likelihood ratio test (LRLR), FCBF, Relief, lasso penalized logistic regression (LassoLR) and feature relevance network (FRN) followed by the P-values from significance test (two-sided paired t-test) comparing the baseline algorithms with FRN.

Alg LRLR FCBF Relief LassoLR FRN
Ace 50.64 51.68 50.90 48.75 53.08
P 0.021 0.367 0.069 0.007 –