基于粗糙集的粮食产量SVM非线性组合预测模型.doc

文档介绍：
基于粗糙集的粮食产量 SVM 非线性组合预
测模型#
袁玉萍1,安增龙2**
5
10
(1. 黑龙江八一农垦大学理学院黑龙江大庆 163319;
2. 黑龙江八一农垦大学经济管理学院黑龙江大庆 163319)
摘要:针对粮食产量预测问题,引入支持向量机智能优化算法以及组合预测技术。利用基于
粗糙集理论的权系数确定方法,将权系数确定问题转化为标准粗糙集理论中属性重要性评价
问题,建立一种基于标准粗糙集理论的支持向量机组合预测方法;利用构建的组合预测模型
对黑龙江省粮食总产量的历史数据进行组合预测,分析表明所建立的组合预测模型对粮食产
量的预测精确度较高,与实际值具有很好的一致性,预测结果平均绝对误差比传统建模方法
明显降低。
关键词:农业系统工程;组合预测;粗糙集;支持向量机;权系数
中图分类号:S23
15
Study on SVM bination Forecasting Method
for Grain Yield Based on Rough Set Theory
YUAN Yuping1, AN Zenglong2
(1. Heilongjiang Bayi Agricultural University College of Sciences , Helongjiang Daqing, 163319;
20
25
30
2. Heilongjiang Bayi Agricultural University College of Economics&Management, Helongjiang
Daqing 163319)
Abstract: In this paper,aiming at it’s own prediction of grain output,draw into support vector
machine intelligent optimization algorithms bination prediction technique. Employ the method
of determining weight coefficient based on rough set theory. Establish bination forecasting
method on the basis of standard rough set theory. Use the SOM method of anizing neural
network to discretizationize attribute property in order to establish information systems and decision
table. Transform determining weight coefficient into the evaluation of attribute significance among
standard rough set theory,work out weight coefficient of single model bination prediction
model. Use bination pre