计算机工程与应用 ›› 2016, Vol. 52 ›› Issue (19): 94-96.

• 大数据与云计算 • 上一篇    下一篇

基于信息增益的最优组合因子Fisher判别法

毛临川,吴根秀,吴  恒,黄  梅   

  1. 江西师范大学 数学与信息科学学院,南昌 330022
  • 出版日期:2016-10-01 发布日期:2016-11-18

Optimal combination of factor Fisher discrimination method based on information gain

MAO Linchuan, WU Genxiu, WU Heng, HUANG Mei   

  1. School of Mathematics and Information Science, Jiangxi Normal University, Nanchang 330022, China
  • Online:2016-10-01 Published:2016-11-18

摘要: 线性判别分类器是一种有效的模式分析技术,其中以Fisher判别法准则应用最广,目前已有多种改进线性提取方法。引进信息增益,建立基于信息增益的最优组合因子判别分类器,实现最优组合因子判别分类器的优化。实验结果表明优化后的分类器有效剔除了冗余因子,具有良好的分类准确率。

关键词: 信息增益, 最优组合因子, 回代率

Abstract: Linear discriminant classifier is an effective model analysis technology, among them with Fisher discriminant criterion, the most widely used, there are many kinds of improved linear extraction method. This paper introduces the information gain, to establish the optimal combination of the factors based on the information gain discriminant classifier, quickly chooses the optimal discriminant classifier combination factor. Experiments show that the rapid selected classifier eliminates the redundancy factor effectively, and has good classification accuracy.

Key words: information gain, optimal combination factor, back substitution rate