首页 | 本学科首页   官方微博 | 高级检索  
     

遗传算法在储粮害虫特征选择中的应用
引用本文:张红涛,胡玉霞,邱道尹.遗传算法在储粮害虫特征选择中的应用[J].华北水利水电学院学报,2004,25(3):37-39.
作者姓名:张红涛  胡玉霞  邱道尹
作者单位:华北水利水电学院,河南,郑州,450011;郑州大学,电气工程学院,河南,郑州,450002
基金项目:中国科学院模式识别国家重点实验室开发基金资助项目(NLPR2000),河南省自然科学基金资助项目(0211030300).
摘    要:介绍了遗传算法在储粮害虫特征选择中的应用,对遗传算法的思想、实现步骤、参数选择分析及具体实现等进行了重点阐述.该算法有效地将粮虫的17维原始形态学特征降为10维,提高了分类的效率.在粮库现场系统能以86.5%的正确率将12种常见的粮虫区别开来.

关 键 词:储粮害虫  遗传算法  特征选择
文章编号:1002-5634(2004)03-0037-03
修稿时间:2004年2月20日

Application of Genetic Algorithm in Stored-grain Pests' Feature Selecting
ZHANG Hong-tao,HU Yu-xia,QIU Dao-yin.Application of Genetic Algorithm in Stored-grain Pests' Feature Selecting[J].Journal of North China Institute of Water Conservancy and Hydroelectric Power,2004,25(3):37-39.
Authors:ZHANG Hong-tao  HU Yu-xia  QIU Dao-yin
Affiliation:ZHANG Hong-tao~1,HU Yu-xia~2,QIU Dao-yin~1
Abstract:The application of genetic algorithm in stored-grain pest feature selecting is introduced briefly. The basic idea,steps,parameter selecting and material realization of the genetic algorithm are discussed in detail in feature selecting. The 17-dimension morphologic features of the stored-grain pests are compressed into 10 dimensions effectively and the classification efficiency is improved. The system can recognise the 12 kinds of familiar stored-grain pests in grain depot and the correct recognition ratio is over 86.5%.
Keywords:stored-grain pests  genetic algorithm  feature selecting
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号