基于灰粗糙支持向量机的连续多属性预测方法  

Continuous multi-attribute prediction method based on grey rough support vector machine

作　　者：王晨曦[1] 

机构地区：[1]漳州职业技术学院计算机工程系,福建漳州363000

出　　处：《合肥工业大学学报（自然科学版）》2012年第12期1652-1654,1724,共4页Journal of Hefei University of Technology：Natural Science

基　　金：福建省教育厅A类科技资助项目(JA12220)

摘　　要：文章对多属性且属性值为连续的决策系统进行预测,提出了灰粗糙支持向量机预测方法。首先采用灰色关联分析计算出条件属性相对于决策属性的重要度;并对连续属性进行离散化,结合Pawlak属性重要度与灰关联度进行约简;将约简后的条件属性作为影响因子,基于支持向量机对决策属性进行预测。实验结果表明,该方法是有效可行的。Aimed at the prediction of decision system with multi-attribute and continuous valued attrib- utes, a prediction method of grey rough support vector machine is proposed. Firstly, the significance of condition attribute relative to decision attribute is computed by using grey correlation analysis. Sec- ondly, attributes are reduced by using Pawlak＇ s attribute significance and grey correlation degree after continuous attributes are discretized. Finally, the reduced condition attributes are used as impact fac- tors to predict decision attribute based on support vector machine. The experimental results show that the method is valid and feasible.

关 键 词：灰关联分析 粗糙集 支持向量机 多属性 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]