Research Article
Enhancement of ELM by Clustering Discrimination Manifold Regularization and Multiobjective FOA for Semisupervised Classification
Table 3
Comparisons of average classification accuracy on dataset.
| Dataset | CDMR-ELM | FOA-CDMR-ELM | MOFOA-CDMR-ELM | Accuracy (%) | Hidden nodes | Accuracy (%) | Hidden nodes | Accuracy (%) | Hidden nodes |
| COIL2 | 91.42 | 34.5 | 91.86 | 31.7 | 92.41 | 22.1 | COIL20 | 91.59 | 39.2 | 92.23 | 30.5 | 94.57 | 25.0 | Shuttle | 92.88 | 100 | 93.46 | 84.7 | 95.65 | 86.9 | USPST | 91.45 | 46.9 | 92.25 | 79.9 | 92.59 | 31.4 | EEG Eye State | 89.58 |
100 | 88.62 | 87.6 | 89.15 | 89.2 | EMGPA | 89.78 | 97.7 | 91.48 | 89.5 | 90.18 | 76.5 | Seeds | 92.33 | 29.9 | 93.21 | 22.4 | 96.88 | 18.3 | Vertebral Column | 90.45 | 27.4 | 91.65 | 19.7 | 93.76 | 12.8 |
|
|