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

Fig 1.

High-level study procedures.

More »

Fig 1 Expand

Fig 2.

Data distribution in each target class.

More »

Fig 2 Expand

Fig 3.

Sample leaf images.

More »

Fig 3 Expand

Table 1.

Samples of target label mapping.

More »

Table 1 Expand

Fig 4.

Architecture of proposed DWS-CNN (finetuned Mobile Net).

More »

Fig 4 Expand

Fig 5.

Standard convolution to produce one 8x8 output feature.

More »

Fig 5 Expand

Fig 6.

Standard convolution to produce 256 8x8 image features.

More »

Fig 6 Expand

Fig 7.

Depth-wise convolution to produce 3 channel 8x8 image feature.

More »

Fig 7 Expand

Fig 8.

Point-wise convolution to produce one 8x8 image feature.

More »

Fig 8 Expand

Fig 9.

Point-wise convolution to produce 256 8x8 image features.

More »

Fig 9 Expand

Table 2.

The parameters used in the study experiment.

More »

Table 2 Expand

Fig 10.

Accuracy and loss of a model for training and testing datasets.

More »

Fig 10 Expand

Table 3.

Testing accuracies of adopted models using learning rate 1*10-4.

More »

Table 3 Expand

Table 4.

Testing accuracies of adopted models using learning rate 1*10-3.

More »

Table 4 Expand

Table 5.

Correctly classified and misclassified classes performed by the proposed model (DWS-CNN).

More »

Table 5 Expand

Fig 11.

Confusion matrices of Proposed Model (Tuned DWS-CNN) for eight categories.

More »

Fig 11 Expand

Table 6.

Classification report of the proposed model (Fine-tuned DWS-CNN) for eight categories.

More »

Table 6 Expand

Fig 12.

F1_score value of the models using learning rate = 1*10-4 and batch size of 32.

More »

Fig 12 Expand

Table 7.

Testing accuracy of the models for each training.

More »

Table 7 Expand

Table 8.

Mean and standard deviation of accuracy and F1-score of each model.

More »

Table 8 Expand

Table 9.

Training time of proposed model and variants of CNN model.

More »

Table 9 Expand

Table 10.

Comparative analysis of previous work with the proposed method.

More »

Table 10 Expand

Fig 13.

Predicted medicinal plant using the proposed model.

More »

Fig 13 Expand