Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Summary data of split disease conditions.

More »

Table 1 Expand

Fig 1.

Samples of dataset classes.

More »

Fig 1 Expand

Table 2.

Summary of datasets used in the study.

More »

Table 2 Expand

Fig 2.

Channel attention module.

More »

Fig 2 Expand

Fig 3.

Spatial attention.

More »

Fig 3 Expand

Fig 4.

Channel, spatial attention (CBAM).

More »

Fig 4 Expand

Fig 5.

Learnable gated fusion CBAM (LGF-CBAM).

More »

Fig 5 Expand

Fig 6.

The proposed CNN model.

More »

Fig 6 Expand

Table 3.

Ablation study for optimizer selection.

More »

Table 3 Expand

Table 4.

Ablation study for activation function selection.

More »

Table 4 Expand

Fig 7.

Ablation study for batch size selection.

More »

Fig 7 Expand

Fig 8.

Ablation study for pooling operation selection.

More »

Fig 8 Expand

Table 5.

Selected hyperparameters for training the model.

More »

Table 5 Expand

Table 6.

Summary of feature extraction time for base models.

More »

Table 6 Expand

Table 7.

Training and inference time summary for base models.

More »

Table 7 Expand

Fig 9.

a: Accuracy for Pretrained Models. b. Model FPR for Pretrained Models. c. Model F1 score for Pretrained Models. d. Model PPV score for Pretrained Models. e. Model TPR score for Pretrained Models. f. Model Loss Score for Pretrained Models.

More »

Fig 9 Expand

Table 8.

Summary of evaluation on the base pretrained CNN models.

More »

Table 8 Expand

Table 9.

Statistical significance test on the base pretrained CNN models.

More »

Table 9 Expand

Fig 10.

Training and validation accuracy for the cocoa disease GH dataset.

More »

Fig 10 Expand

Fig 11.

Training and validation loss on the cocoa disease GH dataset.

More »

Fig 11 Expand

Fig 12.

Confusion matrix for the test dataset on the cocoa disease GH dataset.

More »

Fig 12 Expand

Table 10.

Summary of model performance metrics on the cocoa disease GH dataset.

More »

Table 10 Expand

Fig 13.

a: Grad-CAM visualizations of Healthy Cocoa Disease.b: Grad-CAM visualizations of Moni Cocoa Disease. c: Grad-CAM visualizations of Phyto Cocoa Disease.

More »

Fig 13 Expand

Table 11.

Performance comparison of the proposed LGF-CBAM model with baseline CBAM-based architectures on the Cocoa Disease GH dataset.

More »

Table 11 Expand

Fig 14.

a: Accuracy for All Datasets. b: Model FPR for all datasets. c: Model F1 Score for All Datasets. d: Model PPV Score for All Datasets. e:Model TPR Score, All Datasets. f: Model Loss Score for All Datasets.

More »

Fig 14 Expand

Table 12.

Summary of all dataset performance on the proposed model.

More »

Table 12 Expand

Table 13.

Cross-dataset performance.

More »

Table 13 Expand

Table 14.

Comparison of the proposed system with existing related systems.

More »

Table 14 Expand

Fig 15.

Comparison of cocoa diseases (YOLOv4) dataset.

More »

Fig 15 Expand

Fig 16.

Comparison on cacao disease in davao dataset.

More »

Fig 16 Expand

Fig 17.

Comparison on private datasets.

More »

Fig 17 Expand