Skip to Main Content
Table 12:
Comparison of the performance of instance and feature selection separately against our memetic method, in terms of the testing error and the storage requirements. The table shows the win/loss record of each algorithm in the column against the algorithm in the row. The row labeled ps is the result of a two-tailed sign test on the win/loss record and the row labeled pw shows the result of a Wilcoxon test. Significant differences at a confidence level of 95% are marked with a tick (✓).
Compared MethodCHC FSMemetic IS+FS
Testing error    
 CHC IS win/loss 16/38 37/18 
 ps 0.0038 ✓ 0.0145 ✓ 
 R+/R 1,150.5/389.5 443.0/1,097.0 
 pw 0.0014 ✓ 0.0061 ✓ 
 CHC FS win/loss  46/8 
 ps  0.0000 ✓ 
 R+/R  122.5/1,417.5 
 pw  0.0000 ✓ 
Storage requirements    
 CHC IS win/loss 48/7 55/0 
 ps 0.0000 ✓ 0.0000 ✓ 
 R+/R 94.0/1,446.0 0.0/1,540.0 
 pw 0.0000 ✓ 0.0000 ✓ 
 CHC FS win/loss  55/0 
 ps  0.0065 ✓ 
 R+/R  0.0/1,540.0 
 pw  0.0003 ✓ 
Compared MethodCHC FSMemetic IS+FS
Testing error    
 CHC IS win/loss 16/38 37/18 
 ps 0.0038 ✓ 0.0145 ✓ 
 R+/R 1,150.5/389.5 443.0/1,097.0 
 pw 0.0014 ✓ 0.0061 ✓ 
 CHC FS win/loss  46/8 
 ps  0.0000 ✓ 
 R+/R  122.5/1,417.5 
 pw  0.0000 ✓ 
Storage requirements    
 CHC IS win/loss 48/7 55/0 
 ps 0.0000 ✓ 0.0000 ✓ 
 R+/R 94.0/1,446.0 0.0/1,540.0 
 pw 0.0000 ✓ 0.0000 ✓ 
 CHC FS win/loss  55/0 
 ps  0.0065 ✓ 
 R+/R  0.0/1,540.0 
 pw  0.0003 ✓ 
Close Modal

or Create an Account

Close Modal
Close Modal