| 决策表最优特征子集的选择--基于粗集理论的启发式算法 |
| |
| 引用本文： | 潘韬,赵卫东,盛昭瀚.决策表最优特征子集的选择--基于粗集理论的启发式算法[J].东南大学学报(自然科学版),2000,30(5):118-122. |
| |
| 作者姓名： | 潘韬 赵卫东 盛昭瀚 |
| |
| 作者单位： | 东南大学经济管理学院，南京210096 |
| |
| 基金项目： | 江苏自然科学基金资助项目! (7760 5730 0 2 ) |
| |
| 摘 要： | 特征子集选择问题是机器学习的重要问题。而最优特征子集的选择是NP困难问题，因此需要启发式搜索指导求解。基于粗集理论，本文提出了一种新的决策表最优特征子集选择的启发式算法。和以往的方法相比，这种算法简单实用，在一定条件下能够以较高的效率得到最优特征子集。
|
| 关 键 词： | 最优特征选择 决策表 粗集 启发式算法 机器学习 |
Optimal Feature Subset Selection of Decision Tables |
| |
| Pan Tao,Zhao Weidong,Sheng Zhaohan.Optimal Feature Subset Selection of Decision Tables[J].Journal of Southeast University(Natural Science Edition),2000,30(5):118-122. |
| |
| Authors: | Pan Tao Zhao Weidong Sheng Zhaohan |
| |
| Abstract: | The feature subset selection is an important problem in machine learning, but the optimal feature subset selection is proves to be a NP hard one. Based on rough sets, a new heuristic algorithm is presented to solve the difficulty. To decision tables where the number of features reduces greatly after reduction, the algorithm is illustrated to be effective. Especially, it can give almost all the optimal solutions. |
| |
| Keywords: | optimal feature selection decision tables rough set |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
