Table 1.
Prediction accuracies achieved by SVM, RVKDE, G2DE, C4.5 and RIPPER.
| Kernel based classifiers | Logic based classifiers | |||||
|---|---|---|---|---|---|---|
| Feature set | SVM | RVKDE | G2DE | G2DE-2 | C4.5 | RIPPER |
| 1 | 80.17% | 77.59% | 80.39% | 80.60% | 77.80% | 76.72% |
| 2 | 93.32% | 92.46% | 92.03% | 93.10% | 90.95% | 90.52% |
| 3 | 91.60% | 91.16% | 91.60% | 92.46% | 91.16% | 91.38% |
| 4 | 78.66% | 79.53% | 78.66% | 80.17% | 77.37% | 76.72% |
| Average | 85.94% | 85.18% | 85.67% | 86.58% | 84.32% | 83.84% |
| #kernels | 361 | 920 | 6 | 36 | 10 | 9 |
The best performance among each feature set is highlighted with bold font. The G2DE-2 indicates the two-stage G2DE, which uses the first stage G2DE to cluster samples and than uses the second stage G2DE to classify each clusters. The #kernels indicate number of kernels in average, where the numbers of logic based classifiers indicate the number of rules they deliver.