Table 2.
The prediction ability of the different methods on the Yeast dataset.
| Model | Testing Set | Acc (%) | Sen (%) | Pre (%) | Mcc (%) |
|---|---|---|---|---|---|
| Guos’ work [35] | ACC | 89.3 ± 2.6 | 89.9 ± 3.6 | 88.8 ± 6.1 | N/A |
| AC | 87.4 ± 1.3 | 87.3 ± 4.6 | 87.8 ± 4.3 | N/A | |
| Zhous’ work [36] | SVM+LD | 88.6 ± 0.3 | 87.4 ± 0.2 | 89.5 ± 0.6 | 77.2 ± 0.7 |
| Yangs’ work [37] | Cod1 | 75.1 ± 1.1 | 75.8 ± 1.2 | 74.8 ± 1.2 | N/A |
| Cod2 | 80.0 ± 1.0 | 76.8 ± 0.6 | 82.2 ± 1.3 | N/A | |
| Cod3 | 80.4 ± 0.4 | 78.1 ± 0.9 | 81.7 ± 0.9 | N/A | |
| Cod4 | 86.2 ± 1.1 | 81.0 ± 1.7 | 90.2 ± 1.3 | N/A | |
| Yous’ work [38] | PCA-EELM | 87.0 ± 0.2 | 86.2 ± 0.4 | 87.6 ± 0.3 | 77.4 ± 0.4 |
| Proposed method | LRA+RVM | 94.6 ± 0.6 | 94.8 ± 1.0 | 94.4 ± 0.4 | 89.6 ± 1.2 |
ACC: Auto Covariance; LD: Local Description; PCA: Principal Component Analysis; EELM: Ensemble Extreme Learning Machines; N/A: Not Available; Acc: Accuracy; Sen: sensitivity; Pre: precision; Mcc: Matthew’s Correlation Coefficient.