Research Article
An Effective ABC-SVM Approach for Surface Roughness Prediction in Manufacturing Processes
Table 4
Statistical results of 30 runs obtained by ABC-SVM, DE-SVM, GA-SVM, and PSO-SVM models for AISI 1045 steel.
| | | ABC-SVM | DE-SVM | GA-SVM | PSO-SVM |
| MSE | Best | 0.0453 | 0.0373 | 0.0453 | 0.0455 | | Worst | 0.0453 | 0.0373 | 0.0453 | 0.0455 | | Mean | 0.0453 | 0.0373 | 0.0453 | 0.0455 | | StdDev | 0 | 0 | 0 | 0 | R2 | Best | 0.9573 | 09649 | 0.9573 | 0.9517 | | Worst | 0.9573 | 0.9649 | 0.9573 | 0.9571 | | Mean | 0.9573 | 0.9649 | 0.9573 | 0.9571 | | StdDev | 0 | 0 | 0 | 0 | MAE | Best | 0.1835 | 0.1633 | 0.1836 | 0.1837 | | Worst | 0.1835 | 0.1633 | 0.1836 | 0.1837 | | Mean | 0.1835 | 0.1633 | 0.1836 | 0.1837 | | StdDev | 0 | 0 | 0 | 0 | T(s) | | 2.9230 | 7.3571 | 6.1448 | 3.0870 |
|
|