基于粗糙集的粮食产量组合预测模型

Study on Integrated Forecasting Methods for Grain Yield Based on Rough Set Theory

为预测粮食总产量,建立了基于粗糙集的粮食产量组合预测模型。通过建立预测模型与预测对象的关系数据模型,离散化属性数据值来建立知识表达系统和决策表,并依据粗糙集理论计算出预测对象对预测模型的依赖度、预测模型的重要度以及组合预测模型中各单一模型的权系数。利用浙江省粮食总产量的历史数据建立了粮食产量组合预测模型,分析表明所建模型有较好的预测效果。

Combined forecasting of grain yield based on rough set theory was put forward in order to enhance the precision of prediction result of grain yield. The relative data model between forecast objective and forecast model, and knowledge system and decision table was established respectively by means of converting continuous attribute values into discrete attribute values. Then, the weight of combination forecast was calculated by computing both dependence and significance of between forecast model and forecast objective according to estimating dependence and significance of attributes in rough set theory. Finally, the combined forecasting model of grain model was established in terms of statistic of grain yield from 1980 to 2002 in Zhejiang Province, China, and results of analysis shows that the combined forecasting model has higher forecasting precision.