Research Article
Novel FTLRNN with Gamma Memory for Short-Term and Long-Term Predictions of Chaotic Time Series
Table 10
Performance of MLPNN and FTLRNN for testing data set for monthly sunspot time series.
| (month) | MLP neural network | FTLRNN | MSE | NMSE | | MSE | NMSE | |
| 1 | 0.00247 | 0.04533 | 0.97569 | 0.002227 | 0.04162 | 0.98163 | 6 | 0.01229 | 0.2234 | 0.8917 | 0.00554 | 0.1008 | 0.9528 | 12 | 0.02387 | 0.43132 | 0.77184 | 0.01693 | 0.30599 | 0.8550 | 18 | 0.03989 | 0.7174 | 0.5741 | 0.02266 | 0.4075 | 0.7977 | 24 | 0.0538 | 0.9658 | 0.3584 | 0.03059 | 0.54899 | 0.71497 |
|
|