Table 2 Results of self-consistency test
From: Prediction of protein structural class with Rough Sets
Dataset | Algorithm | Rate of correct prediction for each class | Overall rate of accuracy | |||
|---|---|---|---|---|---|---|
All-α | All-β | α/β | α+β | |||
277 domains | Component coupled | 95.7% | 93.4% | 95.1% | 92.3% | 94.2% |
Neural network | 98.6% | 93.4% | 96.3% | 84.6% | 93.5% | |
SVM | 100% | 100% | 100% | 100% | 100% | |
Rough Sets | 100% | 100% | 100% | 100% | 100% | |
498 domains | Component coupled | 95.8% | 95.2% | 94.9% | 95.4% | 95.8% |
Neural network | 100% | 98.4% | 96.3% | 84.5% | 94.6% | |
SVM | 100% | 100% | 100% | 100% | 100% | |
Rough Sets | 100% | 100% | 100% | 100% | 100% | |