Research Article
Automatic Gender Detection Based on Characteristics of Vocal Folds for Mobile Healthcare System
Table 9
Results of gender detection for existing and proposed systems with Arabic digits.
| Performance measures | Existing system | Proposed system | 4 Gaussians | 8 Gaussians | 16 Gaussians |
| TP (%) | 92.5 | 94.3 | 96.2 | 100 | TN (%) | 88.9 | 94.4 | 94.4 | 100 | FP (%) | 11.1 | 5.6 | 5.6 | 0 | FN (%) | 7.5 | 5.7 | 3.8 | 0 | SE | 0.92 | 0.94 | 0.96 | 1.0 | SP | 0.88 | 0.94 | 0.95 | 1.0 | ACC (%) | 91.5 | 94.3 | 95.7 | 100 | AUC | 0.93 | 0.95 | 0.97 | 1.0 |
|
|