Fault-Level Grading of Photovoltaic Cells Employing Lightweight Deep Learning Models

Table 3

Binary classification results of deep ANN using original data: (a) GLCM features and (b) LBP features.

		Actual class
		Healthy	Full faulty
(a) GLCM features
Predicted class	Healthy	178	32
	Full faulty	48	75
Classwise accuracy		78.7%	70.1%
Overall accuracy		75.9%
(b) LBP features
Predicted class	Healthy	178	32
	Full faulty	48	75
Class-wise accuracy		78.7%	70.1%
Overall accuracy		75.9%