A Core Set Based Large Vector-Angular Region and Margin Approach for Novelty Detection

Table 4

Testing time on different datasets.

Dataset	ν-SVM (s)	SVDD (s)	MAMC (s)	Core set based LARM (s)
Australian	0.0009 ± 0.0005	0.0035 ± 0.0014	0.0023 ± 0.0017	0.0013 ± 0.0004
B. authentication	0.0050 ± 0.0129	0.0010 ± 0.0004	0.0070 ± 0.0032	0.0018 ± 0.0012
B. Cancer	0.0011 ± 0.0003	0.0013 ± 0.0004	0.0032 ± 0.0012	0.0012 ± 0.0003
Cod-rna	0.2901 ± 0.2182	NULL	NULL	0.0584 ± 0.0085
Covtype	NULL	NULL	NULL	1.5096 ± 1.1866
Diabetic	0.0015 ± 0.0009	0.0054 ± 0.0016	0.0075 ± 0.0056	0.0029 ± 0.0010
Fourclass	0.0004 ± 0.0001	0.0006 ± 0.0002	0.0015 ± 0.0007	0.0007 ± 0.0002
Glass	0.0002 ± 0.0002	0.0002 ± 0.0001	0.0005 ± 0.0004	0.0004 ± 0.0003
Heart	0.0003 ± 0.0001	0.0005 ± 0.0001	0.0008 ± 0.0004	0.0007 ± 0.0004
H. valley	0.0021 ± 0.0013	0.0101 ± 0.0021	0.0050 ± 0.0032	0.0031 ± 0.0009
Ionosphere	0.0007 ± 0.0003	0.0016 ± 0.0008	0.0018 ± 0.0009	0.0011 ± 0.0003
L. disorders	0.0004 ± 0.0002	0.0006 ± 0.0002	0.0006 ± 0.0002	0.0006 ± 0.0003
MC	0.0282 ± 0.0073	0.6090 ± 0.3269	0.7920 ± 0.9542	0.0269 ± 0.0132
SDD	0.2947 ± 0.3511	9.4060 ± 3.3205	2.6391 ± 4.2971	0.1829 ± 0.0488
S. segmentation	NULL	NULL	NULL	0.1504 ± 0.0331
Sonar	0.0006 ± 0.0003	0.0011 ± 0.0003	0.0013 ± 0.0003	0.0010 ± 0.0004
Shuttle	0.0393 ± 0.0147	4.5419 ± 3.2784	NULL	0.0342 ± 0.0082
Svmguide1	0.0027 ± 0.0009	0.0031 ± 0.0021	0.0696 ± 0.0214	0.0039 ± 0.0010
Wilt	0.0020 ± 0.0003	0.0052 ± 0.0056	0.1133 ± 0.0230	0.0040 ± 0.0009
Wine	0.0002 ± 0.0004	0.0003 ± 0.0003	0.0004 ± 0.0003	0.0003 ± 0.0001