首页> 外文会议>IEEE International Conference on Cloud Computing and Big Data Analysis >Attribute reduction algorithm based on indistinguishable degree
【24h】

Attribute reduction algorithm based on indistinguishable degree

机译:基于不可区分度的属性约简算法

获取原文

摘要

In order to overcome the shortcomings of computing attribute reduction based on discernibility matrix, an indistinguishable degree definition and the corresponding properties are introduced. By utilizing indistinguishable degree to depict the relative importance of attribute in information system, it proposes an effective indistinguishable degree algorithm for attribute reduction, which does not store discernibility matrix. In addition, an effective distinguish forest algorithm for attribute reduction is proposed to enhance the intuition about algorithm, and the effect about dig process. Besides, the example and experiments are used to illustrate the efficiency and feasibility of the proposed algorithm.
机译:为了克服基于可分辨矩阵计算属性约简的缺点,引入了难以区分的度定义和相应的性质。通过利用不可区分度来描述属性在信息系统中的相对重要性,提出了一种有效的不可区分度的属性约简算法,该算法不存储可分辨矩阵。提出了一种有效的区分森林的属性约简算法,以增强算法的直观性和挖掘过程的效果。此外,通过实例和实验说明了该算法的有效性和可行性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号