Skip to main content

Advertisement

Table 6 The minimum error rates yielded by Support Vector Machine classifier with feature selection methods along‐with the classification error without selection

From: A feature selection method for classification within functional genomics experiments based on the proportional overlapping score

Dataset ISIS Wil‐RS mRMR MP POS Full set
Leukaemia 0.018 (1) 0.047 (8) 0.126 (50) 0.022 (1) 0.005 (1) 0.131
Breast 0.409 (4) 0.401 (39) 0.407 (50) 0.359 (21) 0.313 (22) 0.438
Srbct 0.106 (2.63) 0.131 (50) 0.124 (49) 0.010 (21) 0.003 (8) 0.079
Lung 0.013 (3.26) 0.066 (50) 0.026 (50) 0.021 (19) 0.010 (47) 0.024
GSE24514 0.090 (1.96) 0.041 (40) 0.059 (50) 0.037 (40) 0.034 (30) 0.070
GSE4045 0.236 (1.47) 0.134 (24) 0.187 (37) 0.095 (47) 0.114 (29) 0.214
GSE14333 0.416 (9) 0.427 (9) 0.412 (1) 0.431 (1) 0.407
GSE27854 0.434 (5) 0.431 (25) 0.465 (13) 0.456 (8) 0.50
  1. The numbers in brackets represent the size, average size for ISIS method, of the gene set that corresponding to the minimum error rate. Boldface numbers indicate the lowest error rate (the highest accuracy) among the compared methods for the corresponding datasets.