Research Article
Feature Selection Based on BP Neural Network and Adaptive Particle Swarm Algorithm
Table 3
Classification effect of the original features on the data set.
| Item | BP-PSO | THCA | SAE | LIHC | PRAD | Chi2 |
| DTree | 0.86 | 1.51 | 5.08 | 1.4 | 3.17 | 4.8 | SVM-RFE | 0.8 | 3.43 | 4.89 | 3.06 | 2.05 | 1.73 | RF | 1.32 | 3.91 | 5.49 | 3.42 | 1.01 | 1.86 | t-test | 0.31 | 1.28 | 2.88 | 3.89 | 1.08 | 3.01 | Wilcoxon test | 0.01 | 1.39 | 2.5 | 4.17 | 1.12 | 5.89 | Original feature | 1.08 | 2.27 | 3.59 | 3.28 | 3.24 | 6.61 |
|
|