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.

The architecture of the Multi-layer CNN model.

More »

Fig 1 Expand

Fig 2.

Data collection and analysis effect based on university virtual community.

More »

Fig 2 Expand

Table 1.

Mental health evaluation features.

More »

Table 1 Expand

Table 2.

Model parameter settings.

More »

Table 2 Expand

Fig 3.

Multi level CNN model training 3D surface graph.

More »

Fig 3 Expand

Table 3.

Training performance of multi-level CNN model under hyperparameter conditions.

More »

Table 3 Expand

Fig 4.

Comparison curve of accuracy between SVM and CNN models.

More »

Fig 4 Expand

Table 4.

Comparison of accuracy between SVM and CNN models experimental results.

More »

Table 4 Expand

Fig 5.

Density plot of random forest and CNN model results.

More »

Fig 5 Expand

Table 5.

Comparison results of Random Forest (RF) and Convolutional Neural Network (CNN) models.

More »

Table 5 Expand

Table 6.

Comparison of loss degree between GBDT and CNN models during training process.

More »

Table 6 Expand

Fig 6.

Comparison of loss functions between CNN and GBDT.

More »

Fig 6 Expand

Table 7.

Comparison of the accuracy of different models.

More »

Table 7 Expand

Fig 7.

Heat map of training loss changes for CNN networks at different levels.

More »

Fig 7 Expand

Table 8.

Statistics of training loss changes for CNN networks at different levels.

More »

Table 8 Expand

Fig 8.

t-SNE graph of CNN model before and after data augmentation.

More »

Fig 8 Expand

Table 9.

Performance comparison of various models.

More »

Table 9 Expand

Fig 9.

Comparison trend of CNN model accuracy under different loss functions.

More »

Fig 9 Expand

Fig 10.

Three dimensional mesh diagram of L2 regularization during CNN model training process.

More »

Fig 10 Expand

Fig 11.

Three dimensional heatmap of CNN model training loss under different training epochs.

More »

Fig 11 Expand

Fig 12.

Accuracy distribution of CNN models on different college datasets.

More »

Fig 12 Expand