English

应用科学学报 ›› 2012, Vol. 30 ›› Issue (3): 287-293.doi: 10.3969/j.issn.0255-8297.2012.03.012

• 论文 • 上一篇    下一篇

过滤特征基因选择及演化硬件急性白血病分型

王进1;3， 丁凌1， 孙开伟1， 李钟浩2   

  1. 1. 重庆邮电大学计算机科学与技术学院，重庆400065
    2. 仁荷大学信息与通信工程系，韩国仁川402-751
    3. 重庆邮电大学计算智能重庆市重点实验室，重庆400065
  • 收稿日期:2011-02-28 修回日期:2011-06-02 出版日期:2012-05-30 发布日期:2012-05-30
  • 作者简介:王进，博士，教授，研究方向：演化硬件、模式识别、智能信息处理、生物信息处理，E-mail: wangjin_liips@yahoo.com.cn
  • 基金资助:

    国家自然科学基金(No.61075019)；重庆市自然科学基金(No.2009BB2080)；教育部留学回国人员科研启动基金(教外司留[No.2010]1174)；重庆邮电大学科研基金(No.A2009-06)资助

Molecular Classification of Acute Leukemia Using EHW with Filter-Based Gene Selection

WANG Jin1;3, DING Ling1, SUN Kai-wei1, LEE Chong-ho2   

  1. 1. College of Computer Science and Technology, Chongqing University of Posts and
    Telecommunications, Chongqing 400065, China
    2. Department of Information and Communication Engineering, Inha University,
    Incheon 402-751, Republic of Korea
    3. Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and
    Telecommunications, Chongqing 400065, China
  • Received:2011-02-28 Revised:2011-06-02 Online:2012-05-30 Published:2012-05-30

PDF

1213

被引次数

8

摘要：

 提出一种基于虚拟可重构结构的内部演化硬件癌症分子分型方法. 为有效处理DNA微阵列数据和便于硬件实现，对比研究了5 种基于过滤模式的信息基因选择方法. 演化硬件通过系统学习和系统分类两个阶段对经过特征选择的信息基因进行处理. 对急性白血病数据集的实验结果表明，基于信噪比信息基因选择方法的演化硬件分类器识别率最高. 演化硬件具有和其他传统模式识别方法可比的识别率，识别时间仅需0.12 ms.

关键词: 模式识别, 演化硬件, 特征选择, 虚拟可重构结构, 微阵列, 分子分型

Abstract:

A virtual reconfigurable architecture-based intrinsic evolvable hardware (EHW) is proposed for the molecular classification of cancer. To efficiently process DNA microarray datasets and cooperate with the hardware realization of EHW, five different filter-based gene selection methods are compared and discussed in this paper. The EHW classification system handles the selected informative genes through two stages: system
learning and system classification. Empirical studies on a human acute leukemia dataset demonstrate that classification accuracy of the gene selection scheme based on signal-to-noise ratio outperforms its competitors. Classification accuracy of the proposed EHW is high comparable with other state-of-the-art pattern recognition methods. The system recognition time is reduced to 0.12 ms.

Key words: pattern recognition, evolvable hardware, feature selection, virtual reconfigurable architecture, microarray, molecular classification

中图分类号: