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.

Comparison of dynamic graph methods and proposed models.

More »

Table 1 Expand

Table 2.

Summary of the related works.

More »

Table 2 Expand

Fig 1.

The Proposed STF-GGRU.

More »

Fig 1 Expand

Fig 2.

The spatial network of Sensors.

More »

Fig 2 Expand

Fig 3.

Recurrent patterns in time series data.

More »

Fig 3 Expand

Fig 4.

Integrated spatiotemporal feature extraction alignment.

More »

Fig 4 Expand

Fig 5.

Flowchart of the ISTFA array.

More »

Fig 5 Expand

Fig 6.

Graph Convolution Network Architecture [36].

More »

Fig 6 Expand

Fig 7.

Gated Recurrent Unit Network Architecture.

More »

Fig 7 Expand

Fig 8.

Fully connected layer for prediction module.

More »

Fig 8 Expand

Fig 9.

Flowchart of STF-GGRU implementation.

More »

Fig 9 Expand

Table 3.

PeMSD4 traffic flow prediction dataset.

More »

Table 3 Expand

Table 4.

PeMSD8 traffic flow prediction dataset.

More »

Table 4 Expand

Table 5.

Evaluation metrics of Benchmarks and STF-GGRU on PeMSD4.

More »

Table 5 Expand

Table 6.

Evaluation metrics of Benchmarks and STF-GGRU on PeMSD8.

More »

Table 6 Expand

Fig 10.

RMSE of STFFGRU and Baselines.

More »

Fig 10 Expand

Fig 11.

MAE of STFFGRU and Baselines.

More »

Fig 11 Expand

Fig 12.

MAPE of STFFGRU and Baseline.

More »

Fig 12 Expand

Fig 13.

Prediction for STF-GGRU and benchmark on PeMSD4.

More »

Fig 13 Expand

Fig 14.

Prediction for STF-GGRU and benchmark on PeMSD8.

More »

Fig 14 Expand

Fig 15.

Performance for STF-GGRU and Benchmark on all sensors On PeMSD8.

More »

Fig 15 Expand

Fig 16.

Performance for STF-GGRU and benchmark on all sensors On PeMSD8.

More »

Fig 16 Expand

Table 7.

Scalability performance of the proposed model.

More »

Table 7 Expand

Fig 17.

Traffic flow prediction results for Sensor 16 on the PeMSD4.

More »

Fig 17 Expand

Fig 18.

Traffic flow prediction results for Sensor 250 on the PeMSD4.

More »

Fig 18 Expand

Fig 19.

Traffic flow prediction results for Sensor 14 on the PeMSD8.

More »

Fig 19 Expand

Fig 20.

Traffic flow prediction results for Sensor 105 on the PeMSD8.

More »

Fig 20 Expand

Fig 21.

Prediction result for Sensor 250 on the PeMSD4 dataset during the 15:00–16:00 rush hour.

More »

Fig 21 Expand

Fig 22.

Prediction results for Sensor 160 on the PeMSD4 dataset during the rush hour period.

More »

Fig 22 Expand

Fig 23.

Prediction results for Sensor 14 on the PeMSD8 dataset during the rush hour.

More »

Fig 23 Expand

Fig 24.

Prediction result for Sensor 105 on the PeMSD8 dataset during the 14:00–15:00 period.

More »

Fig 24 Expand

Fig 25.

The highest traffic data PeMSD4 on 2-9-2018 (rush hour).

More »

Fig 25 Expand

Fig 26.

Model performance without Temporal Module.

More »

Fig 26 Expand

Fig 27.

Model performance without Spatial Module.

More »

Fig 27 Expand

Fig 28.

Model performance without ISTFA.

More »

Fig 28 Expand

Fig 29.

Model performance without CKA Module.

More »

Fig 29 Expand

Fig 30.

Model performance without DKNN Module.

More »

Fig 30 Expand