J4 ›› 2010, Vol. 37 ›› Issue (1): 18-22.doi: 10.3969/j.issn.1001-2400.2010.01.004

• 研究论文 • 上一篇    下一篇

用于非监督特征选择的免疫克隆多目标优化算法

尚荣华;焦李成;吴建设;马文萍;李阳阳   

  1. (西安电子科技大学 智能感知与图像理解教育部重点实验室,陕西 西安  710071)
  • 收稿日期:2008-12-16 出版日期:2010-02-20 发布日期:2010-03-29
  • 通讯作者: 尚荣华
  • 作者简介:尚荣华(1979-),女,讲师,博士,E-mail: rhshang@mail.xidian.edu.cn.
  • 基金资助:

    国家“863”计划资助项目(2009AA12Z210);陕西省“13115”科技创新工程重大科技专项资助项目(2008ZDKG-37);国家自然科学基金资助项目(60703107,60703108,60803098);陕西省自然科学基金资助项目(2007F32);国家教育部博士点基金资助项目(20070701022);中国博士后科学基金特别资助项目(200801426);中国博士后科学基金资助项目(20080431228);教育部长江学者和创新团队支持计划资助项目(IRT0645)

Immune clonal multi-objective algorithm for unsupervised feature selection

SHANG Rong-hua;JIAO Li-cheng;WU Jian-she;MA Wen-ping;LI Yang-yang   

  1. (Ministry of Education Key Lab. of Intelligent Perception and Image Understanding, Xidian Univ., Xi'an  710071, China)
  • Received:2008-12-16 Online:2010-02-20 Published:2010-03-29
  • Contact: SHANG Rong-hua

摘要:

提出一种基于免疫克隆多目标优化算法的特征选择方法,先将非监督特征选择问题归结为多目标优化问题,然后构造相应的问题模型和目标函数.最后,采用免疫克隆多目标优化算法,通过增加相关特征的显著性,减小不相关特征的显著性来实现每个特征显著性的优化,达到特征选择的目的.UCI数据集的仿真实验表明,该算法降低了错误识别率,验证了其在非监督特征选择中的应用潜力.

关键词: 非监督特征选择, 克隆选择, 多目标优化

Abstract:

The unsupervised feature selection is transferred into a multiobjective optimization problem, and the immune clonal selection algorithm for multi-objective optimization is applied to solve it. Firstly, the unsupervised feature selection problem is translated into multi-objective problem. Secondly, the model and the objective functions are constructed. Lastly, each feature of significance is optimized by increasing the significance of the related features and decreasing the significance of the unrelated features. Experimental results on UCI data sets show that the error recognition rate is decreased and that the effectiveness and potential of the method are validated.

Key words: unsupervised feature selection, clonal selection, multi-objective optimization