摘要
借鉴已有的特征选取方法和粗糙集相关理论,本文提出了一种改进的基于粗糙集理论的特征选择方法,其主要思想是通过构造粒度函数将其应用于特征在分类中的重要性度量和约简,最后通过实验验证了该方法是有效的,并能够显著降低文本特征维数,提高分类的效率和精度。
By using the existing feature selection methods and relevant theory of rough set, this paper proposes an improved feature selection method based on rough set. The main idea of this method is to define granularity function and apply it to the importance measure and reduction of features in categorization. Finally, this method is proved to be effective by experiments. Besides, it can greatly reduce feature＇s dimension and effectively improve the accuracy and efficiency of categorization.
出处
《微计算机信息》
2012年第3期150-152,共3页
Control & Automation
基金
基金申请人:昝红英
项目名称:规则与统计相结合的现代汉语虚词用法自动识别研究
基金颁发部门:国家自然科学基金委(60970083)
关键词
文本分类
特征选取
粗糙集
粒度函数
启发式属性约简
Text Categorization
Feature Selection
Rough Set
Granularity Function
Heuristic Attribute Reduction
