Research Article
Unsupervised Optimal Discriminant Vector Based Feature Selection Method
Table 3
Class distribution and features of steel plates dataset.
| Class |
Number of samples |
Features | Number | Name |
| Pastry | 158 | 1 |
X_Minimum | Z_Scratch | 190 | 2 | X_Maximum |
K_Scratch | 391 | 3 |
Y_Minimum | Stains | 72 | 4 | Y_Maximum | Dirtiness | 55 | 5 | Pixels_Areas | Bumps | 402 | 6 | X_Perimeter | Other_Faults | 673 | 7 | Y_Perimeter | | | 8 | Sum_of_Luminosity | | | 9 | Minimum_of_Luminosity | | | 10 | Maximum_of_Luminosity | | | 11 | Length_of_Conveyer | | | 12 | TypeOfSteel_A300 | | | 13 | TypeOfSteel_A400 | | | 14 | Steel_Plate_Thickness | | | 15 | Edges_Index | | | 16 | Empty_Index | | | 17 | Square_Index | | | 18 | Outside_X_Index | | | 19 | Edges_X_Index | | | 20 | Edges_Y_Index | | | 21 | Outside_Global_Index | | | 22 | LogOfAreas | | | 23 | Log_X_Index | | | 24 | Log_Y_Index | | | 25 | Orientation_Index | | | 26 | Luminosity_Index | | | 27 | SigmoidOfAreas |
|
|