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.

Compare related work with our research.

More »

Table 1 Expand

Fig 1.

Extraction methodology of time series data for training the model.

More »

Fig 1 Expand

Table 2.

Google trends keywords used to train the model.

More »

Table 2 Expand

Fig 2.

LSTM model structure.

More »

Fig 2 Expand

Fig 3.

Seq2Seq model structure.

More »

Fig 3 Expand

Fig 4.

Seq2Seq model structure.

More »

Fig 4 Expand

Fig 5.

LSTM, Seq2Seq + Attention model structure (LSTM: Top, Seq2Seq + Attention: Bottom).

More »

Fig 5 Expand

Fig 6.

Proposed model architecture.

More »

Fig 6 Expand

Fig 7.

Learning error and verification data error according to the number of model trainings (LSTM).

More »

Fig 7 Expand

Fig 8.

Learning error and verification data error according to the number of model trainings (Seq2Seq + Attention).

More »

Fig 8 Expand

Table 3.

Hyperparameter of model.

More »

Table 3 Expand

Fig 9.

Week 1 prediction using LSTM model.

More »

Fig 9 Expand

Fig 10.

Week 2 prediction using LSTM model.

More »

Fig 10 Expand

Fig 11.

Week 3 prediction using LSTM model.

More »

Fig 11 Expand

Fig 12.

Week 1 prediction using Seq2Seq model.

More »

Fig 12 Expand

Fig 13.

Week 2 prediction using Seq2Seq model.

More »

Fig 13 Expand

Fig 14.

Week 3 prediction using Seq2Seq model.

More »

Fig 14 Expand

Table 4.

LSTM model test set prediction accuracy evaluation.

More »

Table 4 Expand

Table 5.

Seq2Seq model test set prediction accuracy evaluation.

More »

Table 5 Expand