计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (30): 121-122.DOI: 10.3778/j.issn.1002-8331.2009.30.037

• 数据库、信号与信息处理 • 上一篇    下一篇

一种新的应用于文本特征子集优化的GATS算法

姜沛佩,刘培玉   

  1. 山东师范大学 信息科学与工程学院,济南 250014
  • 收稿日期:2009-04-22 修回日期:2009-07-16 出版日期:2009-10-21 发布日期:2009-10-21
  • 通讯作者: 姜沛佩

New optimization GATS algorithm method used in text features subsets

JIANG Pei-pei,LIU Pei-yu   

  1. School of Information Science and Engineering,Shandong Normal University,Jinan 250014,China
  • Received:2009-04-22 Revised:2009-07-16 Online:2009-10-21 Published:2009-10-21
  • Contact: JIANG Pei-pei

摘要: 针对文本分类中特征子集优化问题,将禁忌搜索算法引入到遗传算法中对遗传算法的核心算子——交叉算子进行改进形成禁忌交叉算子,改进后的算法称为GATS(遗传禁忌搜索算法),并将其应用在文本分类中来实现空间降维。实验证明,应用此方法进行文本特征项的选取不仅能够保持GA和TS算法本身的优点,还能在一定程度上提高文本分类的准确率。

关键词: 遗传算法, 禁忌搜索, 遗传禁忌搜索算法, 禁忌交叉算子

Abstract: For feature subset optimization problems in text categorization,taboo search algorithm is introduced in genetic algorithm for its core operator to form tabu crossover operator,the improved algorithm called the GATS(genetic tabu search algorithm),and it be applied to text categorization to realize the dimensionality reduction of the feature space.The experiments show that the application of this method to select the characteristics of the text can not only maintain the advantages of the GA and the TS algorithm themselves,but also to some extent to improve the classification accuracy of the text.

Key words: genetic algorithm, tabu search, Genetic Tabu Search Algorithm(GATS), Tabu Search Recombination(TSR)

中图分类号: