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.

Literature summarized view.

More »

Table 1 Expand

Fig 1.

Proposed framework.

More »

Fig 1 Expand

Table 2.

Dataset features and descriptions.

More »

Table 2 Expand

Fig 2.

Feature importance score.

More »

Fig 2 Expand

Table 3.

Hyperparameter configuration for GNN-RMNet training.

More »

Table 3 Expand

Fig 3.

Correlation matrix of the features.

More »

Fig 3 Expand

Fig 4.

Feature importance score.

More »

Fig 4 Expand

Fig 5.

Driving speed distribution with common ranges and outliers.

More »

Fig 5 Expand

Fig 6.

Geographical distribution of trips with normal and anomalous events.

More »

Fig 6 Expand

Fig 7.

Geographical distribution of trips with normal and anomalous events.

More »

Fig 7 Expand

Fig 8.

Distribution of trip duration.

More »

Fig 8 Expand

Table 4.

Performance evaluation metrics comparison with methods.

More »

Table 4 Expand

Table 5.

Statistical analysis comparison of existing and proposed methods.

More »

Table 5 Expand

Fig 9.

Proposed GNN-RMNet training accuracy and loss.

More »

Fig 9 Expand

Table 6.

Interpretability metrics for normal vs. anomalous trips.

More »

Table 6 Expand

Fig 10.

GNN-RMNet model’s parameter sensitivity analysis.

More »

Fig 10 Expand