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.

A Schematic diagram of the overall process.

More »

Fig 1 Expand

Fig 2.

Outlier situation.

More »

Fig 2 Expand

Fig 3.

Schematic diagram of the graphical convolutional network.

More »

Fig 3 Expand

Fig 4.

Feature node diagram structure.

More »

Fig 4 Expand

Fig 5.

Graphical attention network.

More »

Fig 5 Expand

Fig 6.

Model framework.

More »

Fig 6 Expand

Fig 7.

Example.

a introduces the Feature graph part, b introduces Gat layer calculation α12 part.

More »

Fig 7 Expand

Fig 8.

Characteristic heat map.

More »

Fig 8 Expand

Table 1.

Data set dimensions.

More »

Table 1 Expand

Table 2.

Comparison methods.

More »

Table 2 Expand

Table 3.

Comparison of F1-score, Precision, and Recall of anomaly detection models.

More »

Table 3 Expand

Fig 9.

Comparison with traditional methods.

More »

Fig 9 Expand

Fig 10.

Comparison with advanced methods.

More »

Fig 10 Expand

Fig 11.

F1-scores of different models with different sliding window sizes.

More »

Fig 11 Expand

Table 4.

F1-score under the model without different components.

More »

Table 4 Expand

Table 5.

Average training time.

More »

Table 5 Expand