| 改进支持向量分类用于蝶类自动鉴别 |
| |
| 引用本文： | 陈渊,丰锋,袁哲明.改进支持向量分类用于蝶类自动鉴别[J].昆虫学报,2011,54(5):609-614. |
| |
| 作者姓名： | 陈渊 丰锋 袁哲明 |
| |
| 作者单位： | 1. 湖南省作物种质创新与资源利用重点实验室,长沙410128;湖南农业大学生物安全科学技术学院,长沙410128
2. 湖南农业大学生物安全科学技术学院,长沙,410128 |
| |
| 基金项目： | 湖南省杰出青年基金，湖南省教育厅青年基金，湖南省2008年高校科技创新团队项目 |
| |
| 摘 要： | 昆虫自动识别是重要的新兴研究领域, 其中特征筛选与恰当地将多分类转化为二分类是两个关键步骤。本文基于支持向量分类, 提出了一种新的多类昆虫自动鉴别方法: 先以初始样本互作转换将多分类转化为二分类, 再以可交换核函数消除互作样本中初始样本排列顺序不同的影响, 继以非线性筛选去除无关特征与冗余特征并给出各保留特征相对重要性排序, 最后以简单投票决策校正独立预测结果。新方法应用于2科7种蝶类自动鉴别, 以前翅9个翅脉交叉点距离为初始特征, 种、科阶元26、24个随机初始测试样本均获得了100%的准确鉴别。新方法在昆虫自动识别等多分类领域有广泛应用前景。
|
| 关 键 词： | 支持向量分类 蝴蝶 自动识别 特征筛选 互作转换 |
| 收稿时间： | 2011-01-20; |
Automatic identification of butterfly species with an improved support vector classification |
| |
| CHEN Yuan,FENG Feng,YUAN Zhe-Ming.Automatic identification of butterfly species with an improved support vector classification[J].Acta Entomologica Sinica,2011,54(5):609-614. |
| |
| Authors: | CHEN Yuan FENG Feng YUAN Zhe-Ming |
| |
| Institution: | CHEN Yuan1,2,FENG Feng2,YUAN Zhe-Ming1,2(1.Hunan Provincial Key Laboratory of Crop Germplasm Innovation and Utilization,Hunan Agricultural University,Changsha 410128,China,2.College of Bio-safety Science and Technology,China) |
| |
| Abstract: | Automatic identification of insects is an important and emerging area of research.The screening features and transforming multi-class classification into two-class classification properly are two key procedures in the process.In this article,a novel method for automatic identification of multi-class insects was developed based on support vector classification(SVC).Firstly,the initial multi-class samples were transformed into two-class samples with interaction transformation.Secondly,a symmetrical kernel fun... |
| |
| Keywords: | Support vector classification(SVC) butterfly automatic identification screening features interaction transformation |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《昆虫学报》浏览原始摘要信息 |
| 点击此处可从《昆虫学报》下载免费的PDF全文 |
|
