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.

Spatio-temporal network prediction task.

More »

Fig 1 Expand

Fig 2.

Efficient Channel Attention Mechanism.

More »

Fig 2 Expand

Fig 3.

Framework of Transformer-based Hypergraph Convolutional Traffic Flow Prediction Model(The model architecture employs three stacked S-T Blocks).

More »

Fig 3 Expand

Fig 4.

Constructing a hypergraph.

More »

Fig 4 Expand

Table 1.

Table caption Nulla mi mi, venenatis sed ipsum varius, volutpat euismod diam.

More »

Table 1 Expand

Table 2.

Information of PeMSD4 dataset and PeMSD8 dataset.

More »

Table 2 Expand

Table 3.

Performance of different models on the PeMSD4 and PeMSD8 datasets. Results are presented as mean ± standard deviation (5 independent runs).

More »

Table 3 Expand

Table 4.

Paired t-test results between TSHGCN and the strongest baseline model.

More »

Table 4 Expand

Fig 5.

Hypergraph visualization.

More »

Fig 5 Expand

Fig 6.

Sensitivity Analysis of Hypergraph Neighborhood Size Parameter k.

More »

Fig 6 Expand

Fig 7.

Sensitivity Analysis of Hypergraph Convolutional Layer Count L.

More »

Fig 7 Expand

Table 5.

Ablation Study Results on PeMSD4 and PeMSD8 Datasets.

More »

Table 5 Expand

Fig 8.

Heatmap Analysis of Joint Effects of Hypergraph Parameters k and L.

More »

Fig 8 Expand

Fig 9.

Hyperedge Weight Spatiotemporal Dynamic Evolution.

More »

Fig 9 Expand

Fig 10.

Ablation experiment on PeMSD4 and PeMSD8 datasets.

More »

Fig 10 Expand

Table 6.

Ablation Study Results on PeMSD4 and PeMSD8 Datasets.

More »

Table 6 Expand