| Titles |
|
English :
|
Forecasting of Self-Sufficiency Ratio of Sugar in Egypt Using Artificial Neural Networks
|
|
Arabic :
|
التنبؤ بنسبة الاكتفاء الذاتي للسكر في جمهورية مصر العربية باستخدام الشبكات العصبية الاصطناعية
|
|
| Abstract |
In this research work, an artificial neural network was used to forecast self-sufficiency ratio of sugar in Egypt. Multilayer Perceptron with the error backpropagation learning algorithm was used to build neural network model. The data obtained from annual statistics. The neural network was trained and testing with, year of sugar production, annually amount of production, annually amount of consumed sugar, and average percapita of suger in Egypt during period of 1980-2005 as input parameters (independent variables) and self-sufficiency ratio of sugar in Egypt as output parameter (dependent variable).
The architecture of the neural network was consisted of three layers, the first layer for input, the second was hidden layer with 8 processing elements, and the third layer for output.
The hidden layer and the output layer had been hyperbolic tangent (Tanh) transfer function. The learning rate was 0.7 with step size 1.0. The best results were achieved at 1000 training runs, which gave minimum mean squared error equals to 0.0019 during training process. The results during testing process showed that the variation of observed and predicted self-sufficiency ratio of sugar was small and the linear correlation coefficient and root mean squared error were 0.999 and 0.756 % respectively.
|
| Publication year |
2001
|
| Pages |
245 - 235
|
| Organization Name |
Agricultural Engineering Research Institute (AENRI)
|
| Country |
Egypt
|
| serial title |
مجلة الإسكندرية للتبادل العلمى – مجلة دولية للعلوم والبيئة الزراعية
|
| Volume |
22
. (4)
|
| Department |
Agriculture Power and Energy
|
| Author(s) from ARC |
|
| External authors (outside ARC) |
|
| Agris Categories |
Agricultural engineering
|
| Proposed Agrovoc |
Artificial Neural Networks ;
|
| Publication Type |
Journal
|