Research Article
A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition
Table 15
Table of comparison of optimized results (ear database).
| Method | Number of images for training | Recognition rate | Best (%) | Average (%) | Worst (%) |
| Sánchez and Melin [7] (ANN) | 3 | 100% | 96.75% | — | Melin et al. [45] (MNN) | 3 | 100% | 93.82% | 83.11% | Sánchez and Melin [7] (MGNN) | 3 | 100% | 99.69% | 93.5% | Sánchez et al. [38] (FA) | 3 | 100% | 99.89% | 98.05% | Proposed method (MGNN) | 3 | 100% | 100% | 100% | Sánchez and Melin [7] (ANN) | 2 | 96.10% | 88.53% | — | Sánchez and Melin [7] (MGNN) | 2 | 98.05% | 94.81% | 79.65% | Sánchez et al. [38] (FA) | 2 | 97.40% | 96.82% | 95.45% | Proposed method (MGNN) | 2 | 96.75% | 96.15% | 95.45% |
|
|