Title :
Evaluation of neural network techniques in predicting and minimizing the mass of soil wastes in a sugar-beet harvesting season
Author :
Tummarello, G. ; Riva, G. ; Toscano, G. ; Piazza, F.
Author_Institution :
Area of Agric. Eng., Univ. of Ancona, Italy
fDate :
6/24/1905 12:00:00 AM
Abstract :
The unwanted soil collected during the harvesting of the sugar beets represents one of the main by-products of the sugar industry in Europe. In this study, we adopt different neural network predictors to be used as a base for an online harvesting optimization scheme. Our aim is to demonstrate the feasibility of a combinatory optimization of the harvesting schedule based on neural net predictions and a priori statistics in order to minimize the global value of soil tare for the season. Simulated results show the approach described has significant economical and ecological advantages
Keywords :
agriculture; forecasting theory; neural nets; optimisation; soil; time series; FIR filter; agriculture; neural network predictions; quantization; soil tare; soil waste reduction; sugar-beet harvesting; time series; Biological system modeling; Cleaning; Costs; Economic forecasting; Europe; Intelligent networks; Neural networks; Soil; Sugar industry; Sugar refining;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005510
