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.

Sample images from the four distinct waste material datasets.

More »

Fig 1 Expand

Table 1.

An overview of the datasets.

More »

Table 1 Expand

Table 2.

Unique waste classes throughout the 7 datasets.

More »

Table 2 Expand

Fig 2.

Customized DenseNet-201 with Squeeze and Excitation Integrated Parallel CNN Architecture.

More »

Fig 2 Expand

Fig 3.

Squeeze and Excitation Mechanism.

More »

Fig 3 Expand

Table 3.

Experimental setup for the proposed classification model.

More »

Table 3 Expand

Fig 4.

Accuracy & loss curves of the DenseNet201-Infused Parallel SE-CNN for Waste Classification V2 dataset.

More »

Fig 4 Expand

Fig 5.

Confusion matrix for Waste Classification V2 dataset.

More »

Fig 5 Expand

Table 4.

Classwise metrics overview for Waste classification V2 dataset.

More »

Table 4 Expand

Fig 6.

Overall Metrics overview for Waste Classification V2 dataset.

More »

Fig 6 Expand

Fig 7.

ROC curve for Waste Classification V2 dataset.

More »

Fig 7 Expand

Fig 8.

Accuracy & loss curves of the DenseNet201-Infused Parallel SE-CNN for Waste Classification dataset.

More »

Fig 8 Expand

Fig 9.

Confusion Matrix for Waste Classification dataset.

More »

Fig 9 Expand

Table 5.

Classwise metrics overview for the waste classification dataset.

More »

Table 5 Expand

Fig 10.

Overall Metrics overview for Waste Classification dataset.

More »

Fig 10 Expand

Fig 11.

ROC Curve for Waste Classification dataset.

More »

Fig 11 Expand

Fig 12.

Accuracy & loss curves of the DenseNet201-Infused Parallel SE-CNN for OpenRecycle Dataset.

More »

Fig 12 Expand

Fig 13.

Confusion Matrix for OpenRecycle Dataset.

More »

Fig 13 Expand

Table 6.

Classwise metrics overview for the OpenRecycle dataset.

More »

Table 6 Expand

Fig 14.

Overall Metrics overview for the OpenRecycle dataset.

More »

Fig 14 Expand

Fig 15.

ROC Curve for OpenRecycle Dataset.

More »

Fig 15 Expand

Fig 16.

Accuracy & loss curves of the DenseNet201-Infused Parallel SE-CNN for TrashNet Dataset.

More »

Fig 16 Expand

Fig 17.

Confusion Matrix for TrashNet Dataset.

More »

Fig 17 Expand

Table 7.

Classwise metrics overview for the TrashNet dataset.

More »

Table 7 Expand

Table 8.

Classwise metrics overview after data augmentation for TrashNet dataset.

More »

Table 8 Expand

Fig 18.

Overall Metrics overview for TrashNet dataset.

More »

Fig 18 Expand

Fig 19.

ROC Curve for TrashNet Dataset.

More »

Fig 19 Expand

Table 9.

Robustness evaluation of model under adversarial attacks, noisy data, and environmental conditions.

More »

Table 9 Expand

Table 10.

Performance metrics of the model across three additional datasets.

More »

Table 10 Expand

Table 11.

Comparative analysis of classification performance with different deep CNN models.

More »

Table 11 Expand

Table 12.

ML classifiers performance comparison across datasets.

More »

Table 12 Expand

Table 13.

Comparative analysis of classification performance among models from prior studies.

More »

Table 13 Expand

Table 14.

Impact of parallel CNN Branches and SE attention on model performance.

More »

Table 14 Expand

Table 15.

Empirical time complexity analysis across datasets.

More »

Table 15 Expand

Table 16.

Energy consumption and carbon emissions for different datasets.

More »

Table 16 Expand

Table 17.

Empirical benchmarking of model complexity and computational requirements across architectures.

More »

Table 17 Expand

Fig 20.

Explainability of Proposed Model Using Grad-CAM.

More »

Fig 20 Expand

Fig 21.

Interface of the Website.

More »

Fig 21 Expand

Fig 22.

Uploading an image and predicting via website.

More »

Fig 22 Expand

Fig 23.

Gradio Deployment.

More »

Fig 23 Expand