Research Article
mRMR-ABC: A Hybrid Gene Selection Algorithm for Cancer Classification Using Microarray Gene Expression Profiling
Table 8
Comparison between mRMR-ABC and ABC algorithms classification performance when applied with the SVM classifier for SRBCT dataset.
| Number of genes | Classification accuracy | mRMR-ABC | ABC | Best | Mean | Worst | Best | Mean | Worst |
| 2 | 75.90% | 71.08% | 68.67% | 72.28% | 69.87% | 67.46% | 3 | 85.54% | 79.51% | 71.08% | 73.34% | 71.08% | 68.67% | 4 | 87.95% | 84.33% | 77.10% | 84.33% | 81.92% | 77.10% | 5 | 91.56% | 86.74% | 84.33% | 87.95% | 84.33% | 77.10% | 6 | 95.36% | 91.56% | 87.99% | 92.77% | 87.99% | 84.33% | 8 | 97.59% | 94.05% | 89.15% | 93.97% | 89.15% | 84.33% | 10 | 100% | 96.30% | 92.77% | 95.36% | 91.56% | 89.15% |
|
|