期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：10
DOI：10.15680/IJIRCCE.2015.0310084
出版社：S&S Publications
摘要：The study reported the development of FFBPNN architecture and its corresponding software to predictthe rice production data in different districts of Tamilnadu, India. In order to get high accuracy of prediction, the curveexpert software was integrated into the FFBPNN software. The curve fitting software developed the best fitting modelsamong the 30 different linear and non linear models for Kuruvai, Samba and Kodai seasons of different districts ofTamilnadu. The test data and training data was fed as input to the FFBPNN software, it was found that the there waszero error between the observed data and the predicted data. The RMSE is zero and the ARE is also zero at 18thiteration. The curve expert produced the best fitting model to different districts during the three seasons. It was foundthat the best predicted models and their predicted data gives 1 to 9% higher than the observed data. It is due to naturalincrease in area of cultivation for every year or it may be improvement in rice production technology.
关键词：Neural Network; Curve Expert; Prediction of rice production; best fitting models
