Research Article
Forecasting Computer Products Sales by Integrating Ensemble Empirical Mode Decomposition and Extreme Learning Machine
Table 4
The forecasting results of NB and DC using the single ELM, single SVR, single BPN, EMD-ELM, and the proposed EEMD-ELM models.
| Computer products | Models | RMSE | MAPE | MAD | Training time (s) |
| | Single ELM | 76.87 | 3.84% | 31.21 | 0.0382 | | Single SVR | 77.02 | 3.91% | 31.31 | 0.0903 | NB | Single BPN | 78.11 | 3.95% | 32.05 | 0.1103 | | EMD-ELM | 62.09 | 5.37% | 40.45 | 0.0713 | | EEMD-ELM | 56.33 | 3.53% | 28.01 | 0.0801 |
| | Single ELM | 22.94 | 5.53% | 16.31 | 0.0365 | | Single SVR | 23.02 | 5.59% | 16.65 | 0.0872 | DC | Single BPN | 22.96 | 5.54% | 16.31 | 0.0981 | | EMD-ELM | 22.38 | 4.53% | 15.88 | 0.0695 | | EEMD-ELM | 11.99 | 4.39% | 9.22 | 0.0797 |
|
|