COVID-19 in Iran: Forecasting Pandemic Using Deep Learning
Table 3
Comparison of performance in the test stage on nine selected countries.
Model
BI
DI
Lag
MAPE
RMSE
NRMSE
RF
2.241
0.999988
111
0.00055
3.996
0.999712
199
0.000986
11.852
0.998976
283
0.001402
MLP
0.482
0.999991
20
0.000099
1.320
0.999722
109
0.00054
0.990
0.999801
65
0.000322
LSTM-R
1.549
0.999709
110.5
0.000547
1.210
0.999799
107.4
0.000532
1.325
0.999714
109.2
0.000541
LSTM-E
1.302
0.999790
108.1
0.000535
1.112
0.999800
105.9
0.000524
0.960
0.999853
59.2
0.000293
M-LSTM
0.641
0.999901
42.5
0.000210
0.524
0.999956
31.9
0.000158
0.481
0.999994
20.0
0.000099
represents only death cases as input and shows the confirmed cases along with death and recovered cases. BI: basic information; DI: detailed information. The performance is evaluated on death cases as output.
