Research Article
Hybrid Feature Selection Based Weighted Least Squares Twin Support Vector Machine Approach for Diagnosing Breast Cancer, Hepatitis, and Diabetes
Table 3
Accuracy comparison using 10-fold cross validation.
| Methods | Pima Diabetes | Hepatitis | Breast Cancer |
| LSTSVM (without FS) | 75.33% | 84.28% | 93.28% | LSTSVM + undersampling | 74.31% | 83.33% | 92.83% | WLSTSVM | 75.67% | 86.67% | 95.47% | Hybrid FS + LSTSVM | 84.51% | 85.01% | 95.53% | Hybrid FS + LSTSVM + undersampling | 82.02% | 83.95% | 93.31% | Hybrid FS + WLSTSVM | 89.71% | 87.50% | 98.55% |
|
|