CASIA OpenIR  > 毕业生  > 博士学位论文
One-class问题研究及应用
其他题名One-class Problem Study and Application
齐红威
学位类型工学博士
导师王珏
2004-05-01
学位授予单位中国科学院研究生院
学位授予地点中国科学院自动化研究所
学位专业模式识别与智能系统
关键词One-class问题 非监督学习 半监督学习 信息描述 分类 统计学习算法 股票市场 说话人识别 Web/text Mining One-class Problem Un-supervised Learning Semi-supervised Learning Information Description Classification Statistical l
摘要0ne-class问题包括0ne-class描述问题和one-class分类问题,给定一组没 有标签的样本集,前者指如何描述它包含的内在信息(与异常信息或噪音信息 相对应),而后者指如果把此样本集作为目标类,如何与其它所有无关类(当然 也包括outliers)分类的问题。0ne-class问题的研究无论是在模式识别还是在 信息处理领域都具有重要意义。 论文的丰要内容包括: (1)概述分析了one一class问题的研究内容及研究意义,并首次把0ne—class 问题分为one—class摧述问题和one—class分类问题,并给出了这两种问题的潜 在应用。 (2)提出了一种解决One—class描述问题的模型:基于方差的信息分解模型 (variance—based Information Decomposing Model,VIDM), 并为此模型引 入了基于主成分分析的算法和基于主曲线的算法。 (3)用股票异常收益检测和说话人识别的特征提取两个实验验证了VIDM模 犁及其算法的有效性。 (4)用SvM方法研究one—class分类和out¨er检测问题。在将0ne—class分类 问题理解为一种函数估计问题的基础上,首次定义了_11—0ne—class和11一out¨er 问题的泛化错误,进而定义了线性町分性和边缘,得到了求解。ne—class问题的 最大边缘、软边缘和~一软边缘算法。 (5)首次在one-class分类问题中引入半监督学习的思想,提出了一种半监 督的one-class分类算法(semi v SVM),此方法在易趣拍卖网站中的商品分类上取得了很好的效果。
其他摘要One-class problem includes one-class description and one-class classification. Given a dataset without label, the former means how to describe the intrinsic information (opposite to abnormal information or noise information) of the dataset, and the latter means that if we thought the data in the dataset as target samples, then how to divide them with all the outlying samples (includes outliers). It is significant to study one-class problem not only to pattern recognition but also to Information science. The main contents involved in the thesis are the following: (1) Firstly we give the contents and significance about the research of one-class problem, and then divide the one-class problem into one-class description and one-class classification. We show the potential applications of the one-class problem at last. (2) We present a model to solve the problem of one-class description: Variance-based Information Decomposing Model (VIDM), and introduce algorithms based on the Principal Component Analysis and the Principal Curves to the VIDM. (3) Making experiments on abnormal returns detection and feature extraction of speaker recognition to show the practicality of the VIDM and its algorithms. (4) One-class classification and outlier problems are investigated by using the idea of SVM. Based on regarding a one-class problem as the one to estimate a function, the generalization error is defined for the first time. The linear separability, margin and optimal linear classifier are then defined and the regular SVM is reformulated into that for one-class problems. (5) Through integrating the idea of semi-supervised learning into the problem of one-class classification, a kind of semi-one-class classification algorithm is presented (Semi-v-SVM). This algorithm is verified by the experiment of merchandise classification in auction website of"eachnet" (www.eachnet.com).
馆藏号XWLW808
其他标识符808
语种中文
文献类型学位论文
条目标识符http://ir.ia.ac.cn/handle/173211/5798
专题毕业生_博士学位论文
推荐引用方式
GB/T 7714
齐红威. One-class问题研究及应用[D]. 中国科学院自动化研究所. 中国科学院研究生院,2004.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[齐红威]的文章
百度学术
百度学术中相似的文章
[齐红威]的文章
必应学术
必应学术中相似的文章
[齐红威]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。