Table 10 Performance comparison with state-of-the-art models (SOTA).

From: Advanced deep learning framework for soil texture classification

Method

Accuracy

F1-score

Precision

Recall

AUC

Kappa

MobileNetV2

0.915

0.872

0.885

0.861

0.934

0.871

EfficientNet-B0

0.932

0.891

0.902

0.878

0.947

0.889

ResNet50

0.945

0.905

0.917

0.896

0.956

0.902

VGG-19 + Attention

0.951

0.912

0.928

0.899

0.963

0.912

Proposed ATFEM (Ours)

0.981

0.896

0.902

0.877

0.981

0.948

Back to article page