|
A hybridization of feedforward neural network and differential evolutionto forecast fertilizer consumption emphasizingon selecting optimal architecture |
|---|---|
| รหัสดีโอไอ | |
| Creator | Thoranin Sujjaviriyasup |
| Title | A hybridization of feedforward neural network and differential evolutionto forecast fertilizer consumption emphasizingon selecting optimal architecture |
| Publisher | Research and Development Office, Prince of Songkla University |
| Publication Year | 2564 |
| Journal Title | Songklanakarin Journal of Science and Technology (SJST) |
| Journal Vol. | 43 |
| Journal No. | 4 |
| Page no. | 1160-1168 |
| Keyword | time series analysis, combined model, agro - industry, parameter selection, optimization technique |
| URL Website | https://rdo.psu.ac.th/sjstweb/index.php |
| ISSN | 0125-3395 |
| Abstract | A fertilizer marketing or producing sector has played an important role in agricultural productivity and also foodsecurity around the world for many years. However, the demand of fertilizer consumption is uncertain and difficult to beforecasted by using simple approaches. Therefore, an accuracy of future demand concerning fertilizer is very interesting task tosupport decision making. In this research, a hybrid model of feedforward neural networks and differential evolution emphasizingon architectural evolution is developed to forecast ten datasets of fertilizer consumption and is compared with conventionalmodels based on five accuracy measures. The empirical results indicated that the developed model can provide more accuracythan conventional models at 0.05 significance levels. Furthermore, the capability of the developed model can also provide thehighest precision compared with both ARIMA and SVR models. Consequently, the developed model can be a promising tool topredict future demands of fertilizer consumption. |
