...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Computers >A Feature Selection Approach of Inconsistent Decision Systems in Rough Set
【24h】

A Feature Selection Approach of Inconsistent Decision Systems in Rough Set

机译：粗糙集中不一致决策系统的特征选择方法

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

—Feature selection has been widely discussed as an important preprocessing step in data mining applications since it reduces a model's complexity. In this paper, limitations of several representative reduction methods are analyzed firstly, and then by distinguishing consistent objects form inconsistent objects, decision inclusion degree and its probability distribution function as a new measure are presented for both inconsistent and consistent simplified decision systems. New definitions of distribution reduct and maximum distribution reduct for simplified decision systems are proposed. Many important propositions, properties, and conclusions for reduct are drawn. By using radix sorting and hash techniques, a heuristic distribution reduct algorithm for feature selection is constructed. Finally, compared with other feature selection algorithms on six UCI datasets, the proposed approach is effective and suitable for both consistent and inconsistent decision systems.
机译：- 自我选择已被广泛讨论为数据挖掘应用程序中的重要预处理步骤，因为它降低了模型的复杂性。在本文中，首先分析了几种代表性还原方法的局限，然后通过区分一致的物体形成不一致的物体，判断包含程度及其概率分布函数作为一种新的度量，既是不一致和一致的简化决策系统。提出了用于简化决策系统的分布式减减和最大分布式的新定义。绘制了许多重要的命题，属性和结论。通过使用基数排序和散列技术，构建了一种特征选择的启发式分布式算法。最后，与六个UCI数据集上的其他特征选择算法相比，所提出的方法是有效的，适用于一致和不一致的决策系统。

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