计算机工程与应用 ›› 2012, Vol. 48 ›› Issue (9): 131-133.

• 数据库、信号与信息处理 • 上一篇    下一篇

函数依赖判定可行域的人工鱼群属性约简

杜晓昕1,王 波2,戴学丰1   

  1. 1.齐齐哈尔大学 计算机与控制工程学院,黑龙江 齐齐哈尔 161006
    2.齐齐哈尔大学 教育与传媒学院,黑龙江 齐齐哈尔 161006
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2012-03-21 发布日期:2012-04-11

Artificial fish-swarm attribute reduction based on functional dependency to determine feasible region

DU Xiaoxin1, WANG Bo2, DAI Xuefeng1   

  1. 1.College of Computer and Control Engineering, Qiqihar University, Qiqihar, Heilongjiang 161006, China
    2.Education and Communication Institute, Qiqihar University, Qiqihar, Heilongjiang 161006, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2012-03-21 Published:2012-04-11

摘要: 针对基于互信息可行域判定算法的时间复杂度高,操作复杂等缺点,提出了利用函数依赖判定可行域和计算核属性的方法,该方法使用SQL语句实现,实现简单,运算速度快。利用人工鱼群算法具有获取全局极值的良好能力和对初值不敏感等优点,设计出了基于函数依赖判定可行域的人工鱼群属性约简算法。理论分析和试验结果表明,该算法具有可行性,能求取良好的约简结果。

关键词: 属性约简, 函数依赖, 人工鱼群算法, 可行域

Abstract: Aimed at the algorithm based on mutual information to determine feasible region, with the disadvantage of high time complexity and hard to operate, a new method based on functional dependency to determine feasible region and calculate core attribute is proposed. This method uses the SQL statement to achieve, is easy to implement and has fast computing speed. Artificial fish-swarm algorithm has the advantage of good ability to obtain global extremum and not sensitive to initial values, and artificial fish-swarm reduction algorithm based on functional dependency to determine feasible region is designed. Theoretical analysis and experimental results show that the algorithm is feasible, and can get good reduction result.

Key words: attribute reduction, functional dependency, artificial fish-swarm algorithm, feasible region