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.

The unfolding diagram of the forward propagation of the RNN.

More »

Fig 1 Expand

Table 1.

Criteria of MAPE and RMSPE.

More »

Table 1 Expand

Fig 2.

Decomposition of the number of PTB cases in Urumqi from January 2014 to December 2018.

More »

Fig 2 Expand

Fig 3.

ACF and PACF diagrams after first-order difference of PTB cases in Urumqi.

More »

Fig 3 Expand

Table 2.

The evaluations of goodness-of-fit for plausible ARIMA models.

More »

Table 2 Expand

Table 3.

Parameters estimation for ARIMA (1,1,2)×(0,0,1)12 model.

More »

Table 3 Expand

Table 4.

White noise test of residuals for ARIMA (1,1,2)×(0,0,1)12 model.

More »

Table 4 Expand

Table 5.

The optimal models for each air pollutant.

More »

Table 5 Expand

Fig 4.

Cross-correlations between the pre-whitened PTB cases and air pollutants.

More »

Fig 4 Expand

Table 6.

The residual and parameter tests of ARIMAX models.

More »

Table 6 Expand

Fig 5.

Spearman ranks correlation coefficients between the PTB cases and air pollutants with a lag of 1 to 12 months.

Notes *: P < 0.05 **: P < 0.01 ***: P < 0.001.

More »

Fig 5 Expand

Fig 6.

Epoch-error plots of the RNN9 after three training cycles.

(A) First cycle, (B) Second cycle, (C) Third cycle.

More »

Fig 6 Expand

Table 7.

Training results of RNN1-RNN5 models.

More »

Table 7 Expand

Table 8.

Training results of RNN models with incorporating air pollutants (O3, PM2.5, PM10, SO2, and NO2).

More »

Table 8 Expand

Fig 7.

Distances between OBS and simulation results by ARIMA, ARIMAX, and RNN models.

More »

Fig 7 Expand

Fig 8.

The fitting results of ARIMA, ARIMAX, and RNN models.

More »

Fig 8 Expand

Fig 9.

The fitting and predicting results of the ARIMAX(1,1,2)×(0,1,1)12+PM2.5(lag = 12)model.

More »

Fig 9 Expand