Research Article
Fault-Level Grading of Photovoltaic Cells Employing Lightweight Deep Learning Models
Table 6
Binary classification results of deep ANN with 0.5 as threshold using augmented data: (a) GLCM features and (b) LBP features.
| ā | Actual class | Healthy | Full faulty |
| (a) GLCM features | Predicted class | Healthy | 249 | 38 | Full faulty | 22 | 85 | Classwise accuracy | 91.9% | 69.1% | Overall accuracy | 84.8% |
| (b) LBP features | Predicted class | Healthy | 247 | 38 | Full faulty | 24 | 85 | Classwise accuracy | 91.1% | 69.1% | Overall accuracy | 84.3% |
|
|