期刊名称：International Journal of Intelligent Systems and Applications
印刷版ISSN：2074-904X
电子版ISSN：2074-9058
出版年度：2014
卷号：6
期号：12
页码：55-61
DOI：10.5815/ijisa.2014.12.08
出版社：MECS Publisher
摘要：Hybrid back propagation based genetic algorithm approach is a popular way to train neural networks for weather prediction. The major drawback of this method is that weather parameters were assumed to be independent of each other and their temporal relation with one another was not considered. So in the present research a modified time series based weather prediction model is proposed to eliminate the problems incurred in hybrid BP/GA technique. The results are very encouraging; the proposed temporal weather prediction model outperforms the previous models while performing for dynamic and chaotic weather conditions.
关键词：Temporal Weather Forecasting; Time Series Prediction; Artificial Neural Networks; Back Propagation Algorithm; Genetic Algorithms
