Research Article
A Statistical Image Feature-Based Deep Belief Network for Fire Detection
Table 8
Precision, recall, and F1-score of the comparison study for fire detection.
| Pattern | Proposed (%) | CDBN (%) | SVM (%) | Precision | Recall | F1-score | Precision | Recall | F1-score | Precision | Recall | F1-score |
| Fire | 94.33 | 90.76 | 92.51 | 84.34 | 86.27 | 85.29 | 75.53 | 75.35 | 75.44 | Nonfire | 90.97 | 94.47 | 92.69 | 84.65 | 82.54 | 83.59 | 74.58 | 74.76 | 74.67 | Average | 92.65 | 92.62 | 92.60 | 84.50 | 84.41 | 84.44 | 75.06 | 75.06 | 75.06 |
|
|