Selecting Optimal Feature Set in High-Dimensional Data by Swarm Search

Table 5

Comparative results in classification error for all the classification algorithms with Cfs feature selection and swarm search feature selection and without any feature selection.

Algorithm	Lung Cancer (56)	Heart Disease (75)	Libra Movement (91)	Hill Valley (101)	CNAE (875)
PN	0.5938	0.4653	0.1944	0.4447	0.8741
DT	0.5	0.4719	0.3028	0.505	0.112
NB	0.375	0.4422	0.3722	0.5149	0.0685
Cfs-PN	0.3125	0.462	0.1972	0.5017	0.187
Cfs-DT	0.3438	0.4818	0.2583	0.4951	0.1889
Cfs-NB	0.2813	0.4224	0.3528	0.4884	0.1824
PSO-PN	0.125	0	0.075	0.3465	0.0083
PSO-DT	0.225	0	0.2806	0.2112	0.0407
PSO-NB	0.1513	0.105	0	0.0495	0.8889
BAT-PN	0.1188	0	0.0833	0.1997	0.037
BAT-DT	0.21	0	0.3444	0.2442	0.0491
BAT-NB	0.1625	0.27	0.1028	0.5132	0.8889
WSA-PN	0.1338	0	0.0694	0.1997	0.037
WSA-DT	0.0407	0	0.2028	0.2178	0.037
WSA-NB	0.1575	0	0	0.1151	0.8889