Research Article
Predicting Subcontractor Performance Using Web-Based Evolutionary Fuzzy Neural Networks
Table 3
Comparison of prediction results.
| Pattern no. | Subcontractor performance | FL predicted performance | NNs predicted performance | EFNNs predicted performance |
| 23 | 0.6875 | 0.5793 | 0.6064 | 0.6810 | 24 | 0.7083 | 0.5748 | 0.7247 | 0.7046 | 25 | 0.6875 | 0.5986 | 0.6837 | 0.7175 | 26 | 0.6875 | 0.6158 | 0.6350 | 0.6892 | 27 | 0.7292 | 0.6169 | 0.6225 | 0.6898 | 28 | 0.7917 | 0.6158 | 0.6491 | 0.7428 | 29 | 0.7708 | 0.6245 | 0.7550 | 0.7601 | 30 | 0.7917 | 0.6413 | 0.7588 | 0.8180 | 31 | 0.7917 | 0.6567 | 0.7469 | 0.8038 | 32 | 0.8333 | 0.6546 | 0.7943 | 0.8409 | 33 | 0.8958 | 0.6694 | 0.8826 | 0.8702 | 34 | 0.9167 | 0.6968 | 0.9353 | 0.9132 |
| RMSE | 0.1527 | 0.0624 | 0.0234 |
|
|
Real performance score is multiplied by 96.
|