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.

Some related studies to the proposed work.

More »

Table 1 Expand

Fig 1.

The smart agriculture system’s IoT architecture.

More »

Fig 1 Expand

Fig 2.

The general framework for plant disease classification approach.

More »

Fig 2 Expand

Fig 3.

The main data flow diagram for the proposed framework and required tasks.

More »

Fig 3 Expand

Fig 4.

The Use case diagram for the implemented mobile application.

More »

Fig 4 Expand

Fig 5.

The main block diagram of the suggested framework.

More »

Fig 5 Expand

Table 2.

Used technologies and tools.

More »

Table 2 Expand

Table 3.

The trained dataset for 38 different classes of plant leaves.

More »

Table 3 Expand

Table 4.

The performance evaluation for different deep learning depicted approaches.

More »

Table 4 Expand

Fig 6.

Confusion matrix for 38-class plant disease classification based on the proposed ResNet-50-InceptionV3 model.

More »

Fig 6 Expand

Table 5.

Statistical test results.

More »

Table 5 Expand

Fig 7.

The Roc for the training process of the proposed ResNet 50 with the InceptionV3 algorithm.

More »

Fig 7 Expand

Fig 8.

The Roc for the training process of the proposed MobileNet-1 algorithm.

More »

Fig 8 Expand

Fig 9.

The Roc for the training process of the proposed MobileNet-2 algorithm.

More »

Fig 9 Expand

Fig 10.

The Roc for the training process of the CNN algorithm.

More »

Fig 10 Expand

Fig 11.

The implemented prototype for the proposed integrated IoT system.

More »

Fig 11 Expand