| Titles |
|
English :
|
-Application of Artificial Neural Networks to Forecast Self-Sufficiency Ratio of Red Meat in Egypt
|
|
Arabic :
|
تطبيق الشبكات العصبية الاصطناعية للتنبؤ بنسبة الاكتفاء الذاتي للحوم الحمراء
|
|
| Abstract |
In this research work, an artificial neural network was utilized to forecast self-sufficiency ratio of red meat from Egyptian annual statistics. Multilayer Perceptron with the error backpropagation learning algorithm was used to build neural network model. The neural network was trained and tested with: years of red meat production, annually amount of red meat production, annually amount of consumed red meat, and average percapita of red meat as input parameters and self-sufficiency ratio of red meat as output parameter. The training data included periods from 1980 until 1999 while during testing process, periods from 2000 until 2005 was utilized.
The architecture of the neural network was consisted of three layers, the first layer for inputs, 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 0.9 with step size 1.0. The best results were achieved at 10000 training runs, which gave minimum mean squared error equals to 0.0004 during training process. The results during testing the neural network showed that the variation of observed and predicted self-sufficiency ratio of red meat was small and the linear correlation coefficient (r) and mean squared error (MSE) were 0.999 and 0.3901 respectively. Our study suggests that the neural network approach is very useful for forecasting self-sufficiency ratio of red meat although the relationship between it and relating variables was not seen.
|
| Publication year |
2001
|
| Pages |
6425 -6415
|
| Organization Name |
Agricultural Engineering Research Institute (AENRI)
|
| Country |
Egypt
|
| serial title |
مجلة العلوم الزراعية بكلية الزراعة جامعة المنصورة
|
| Volume |
26
. (10)
|
| Department |
Agriculture Power and Energy
|
| Author(s) from ARC |
|
| External authors (outside ARC) |
|
| Agris Categories |
Agricultural engineering
|
| Proposed Agrovoc |
Red Meat;
|
| Publication Type |
Journal
|