电子学报 ›› 2016, Vol. 44 ›› Issue (4): 995-1002.DOI: 10.3969/j.issn.0372-2112.2016.04.034

• 科研通信 • 上一篇    下一篇

基于近邻信息和PSO算法的集成特征选取

刘全金1,2, 赵志敏1, 李颖新3,4, 俞晓磊5   

  1. 1. 南京航空航天大学理学院, 江苏南京 210016;
    2. 安庆师范学院物理与电气工程学院, 安徽安庆 246011;
    3. 北京经纬纺机新技术有限公司, 北京 100176;
    4. 北京市轻纺机械机器视觉工程技术研究中心, 北京 100176;
    5. 江苏省标准化研究院, 江苏南京 210029
  • 收稿日期:2014-10-24 修回日期:2014-12-16 出版日期:2016-04-25
    • 通讯作者:
    • 赵志敏
    • 作者简介:
    • 刘全金 男,1971年12月生于安徽六安,南京航空航天大学理学院博士研究生,安庆师范学院教授,主要研究方向:机器学习、信息处理. E-mail:liuquanjing666@126.com;李颖新 男,1972年9月生于河北迁安,北京经纬纺机新技术有限公司高级工程师,博士,主要研究方向:机器视觉、机器学习与数据挖掘、生物信息学. E-mail:linterlee@126.com;俞晓磊 男,1981年10月生于江苏南京,江苏省标准化研究院高级工程师、南京理工大学博士后,主要研究方向:通信与射频信号处理、电子信号检测技术. E-mail:nuaaxiaoleiyu@126.com
    • 基金资助:
    • 国家自然科学基金 (No.61475071,No.61173068,No.10172043); 教育部博士点基金 (No.20093218110024); 江苏省自然科学基金青年基金 (No.BK20141032); 国家质检总局科技项目 (No.2013QK194); 安徽省自然科学基金 (No.1608085QF157)

Ensemble Feature Selection Method Based on Neighborhood Information and PSO Algorithm

LIU Quan-jin1,2, ZHAO Zhi-min1, LI Ying-xin3,4, YU Xiao-lei55   

  1. 1. College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu 210016, China;
    2. Department of Physics, Anqing Normal College, Anqing, Anhui 246011, China;
    3. Beijing Jingwei Textile Machinery New Technology Co Ltd, Beijing 100176, China;
    4. Beijing Light Industry and Textile Machinery Engineering Research Center for Machine Vision, Beijing 100176, China;
    5. Jiangsu Institute of Standardization, Nanjing, Jiangsu 210029, China
  • Received:2014-10-24 Revised:2014-12-16 Online:2016-04-25 Published:2016-04-25
    • Supported by:
    • National Natural Science Foundation of China (No.61475071, No.61173068, No.10172043); Ph.D. Programs Foundation of Ministry of Education of China (No.20093218110024); Natural Science Foundation of Jiangsu Province Youth Fund (No.BK20141032); Science and Technology Project of AQSIQ (No.2013QK194); Natural Science Foundation of Anhui Province (No.1608085QF157)

摘要:

提出了一种新的PSO特征选取方法.以粒子对应特征组合的同类近邻样本和异类近邻样本间的距离关系作为类别可分性和粒子适应度函数.以适应度函数加权的群体历史最佳、粒子历史最佳和粒子邻域内最佳个体信息共同指导粒子运动方向,搜索类内紧密、类间分离的最佳特征组合;同时,利用加权集成方法对PSO特征选取方法进行集成,以提高特征选取方法的稳定性和鲁棒性.在5个高维数据集上的特征选取实验结果表明集成PSO特征选取方法的有效性和可行性.

关键词: 特征选取, PSO, 集成方法, 分类

Abstract:

A new PSO algorithm is proposed in this paper for feature selection.Distances within the same class and between different classes are used as the index for distinguishing different classes,and thus can be used to construct the fitness function of particles in PSO.The direction of particles for searching optimal features which can result in close intra-class distance and far inter-class distance is determined by the current best solution of the particle and the optimal individual in particle neighborhood,weighted by the fitness function.Meanwhile,the PSO algorithm is aggregated by the weighted voting method to improve its stability and robustness.The experiment results on 5 high dimensional datasets show that the ensemble PSO algorithm is effective and feasible.

Key words: feature selection, PSO(particle swarm optimization), ensemble method, classification

中图分类号: