Research Article
Weighted Domain Transfer Extreme Learning Machine and Its Online Version for Gas Sensor Drift Compensation in E-Nose Systems
Table 2
Comparisons of classification accuracy in 9 batches.
| Batch number | Accuracy (%) | Ensemble SVM | Ensemble ELM | SVM -rbf | ELM -rbf | DAELM (30) | DAELM (50) | WDTELM (<30) | WDTELM (<48) |
| | 77.4 | 75.3 | 58.5 | 76.8 | 85.5 | 96.2 | 90.2 | 98.2 | | 74.8 | 76.9 | 66.9 | 75.4 | 94.0 | 98.8 | 90.1 | 94.6 | | 72.0 | 64.5 | 74.5 | 69.8 | 100 | 100 | 100 | 100 | | 65.9 | 96.0 | 44.2 | 56.6 | 99.5 | 100 | 98.9 | 99.5 | | 71.3 | 71.3 | 58.3 | 62.0 | 73.4 | 82.1 | 95.3 | 98.5 | | 55.1 | 68.8 | 68.9 | 68.0 | 64.3 | 79.8 | 78.1 | 84.7 | | 42.9 | 81.8 | 60.5 | 87.7 | 94.6 | 97.6 | 94.6 | 97.3 | | 56.6 | 49.6 | 50.9 | 40.0 | 100 | 100 | 99.1 | 100 | | 32.9 | 49.4 | 18.4 | 19.3 | 41.5 | 55.8 | 62.6 | 64.6 |
| Ave. | 64.1 | 72.5 | 55.7 | 61.7 | 83.8 | 90.1 | 89.9 | 93.0 |
|
|