首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于近红外光谱和系统聚类法的蝗虫识别模型研究
引用本文:熊雪梅, 王一鸣.基于近红外光谱和系统聚类法的蝗虫识别模型研究[J].激光与红外,2007,37(3):237-239.
作者姓名:熊雪梅  王一鸣
作者单位:中国农业大学信息与电气工程学院,北京,100083
基金项目:科技部科研院所社会公益研究专项基金
摘    要:以蝗虫的近红外光谱图作为分析的对象,采用聚类分析方法对蝗虫进行快速的识别研究.结果表明:矢量归一化预处理后的光谱数据经最长距离法进行聚类分析,分类结果正确率为100%.此法可为蝗虫自动侦测系统中识别蝗虫提供一种可靠、简便的手段,盲样检测的准确率可达91.67%.

关 键 词:近红外光谱  聚类分析  蝗虫  近红外光谱  系统聚类法  蝗虫  识别模型  研究  Cluster  Analysis  Near  Infrared  Spectra  Based  Model  准确率  检测  盲样  手段  侦测系统  自动  正确率  分类结果  聚类分析方法  最长距离法  光谱数据
文章编号:1001-5078(2007)03-0237-03
修稿时间:2006-08-242006-10-12

Locusts Detection Model Based on Near Infrared Spectra and Cluster Analysis
XIONG Xue-mei; WANG Yi-ming.Locusts Detection Model Based on Near Infrared Spectra and Cluster Analysis[J].Laser & Infrared,2007,37(3):237-239.
Authors:XIONG Xue-mei; WANG Yi-ming
Institution:College of Information and Electrical Engineering; China agricultural university; Beijing 100083; China
Abstract:The objective of this study was to develop a rapid, real-time method for the detection of locusts.Near infrared spectra(NIR) in the range of 3996~12489.5cm-1 were recorded and the range of 3996~11502cm-1 was selected.Models were established by using the cluster analysis method.Different methods were compared.The study showed that complete-linkage model gave better results than single-linkage and other methods with the correctly classification rate of 91.67% for the test data set.Results indicate that NIR me...
Keywords:near infrared spectra  cluster analysis  locust
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《激光与红外》浏览原始摘要信息
点击此处可从《激光与红外》下载免费的PDF全文
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