Enhancing Photovoltaic Module Fault Diagnosis with Unmanned Aerial Vehicles and Deep Learning-Based Image Analysis

Table 12

Overall classification accuracy of ML classifiers for various pretrained networks.

Classifier	Test accuracy (%)
	AlexNet	DenseNet-201	GoogleNet	ResNet-50	VGG16	VGG19
IBK	99.84	100.00	99.80	99.68	99.52	99.84
Random forest	99.52	99.84	99.23	99.68	99.68	99.84
Bayes net	94.60	94.13	89.33	93.65	87.30	89.84

Boldface entries represent the highest values obtained.