Skip to main content
. Author manuscript; available in PMC: 2013 Apr 1.
Published in final edited form as: J Biomed Inform. 2011 Nov 22;45(2):265–272. doi: 10.1016/j.jbi.2011.11.003

Table 6.

Approximate numbers of training samples at different levels of AUCs for both active learning algorithms and the random sampling method.

AUC 0.79 0.83 0.86 0.89 0.92 0.93 0.95 0.96
Random 32 64 128 256 512 1024 2048 4096
LC 33 56 103 232 435 903 1557 2768
LCB 16 73 127 219 369 650 1354 2518
LCB2 13 46 129 277 462 824 1471 2785
LCMC 26 81 127 241 426 770 1473 2843
LCBMC 12 41 118 225 414 713 1271 2784
LCB2MC 19 91 166 298 524 812 1330 2555
IDD 35 102 269 443 694 1002 1600 2790