基于马尔科夫随机场和鲁棒误差函数的半监督分类研究

J4 ›› 2010, Vol. 45 ›› Issue (11): 1-4.

• 电子技术与信息 • 下一篇

基于马尔科夫随机场和鲁棒误差函数的半监督分类研究

梁军^1，2，陈龙²,周卫琪²，陶文倩¹，姚明²，胥正川³

1. 江苏大学计算机科学与通信工程学院, 江苏镇江 212013;
2. 江苏大学汽车与交通工程学院, 江苏镇江 212013; 3. 复旦大学管理学院, 上海 200433

收稿日期:2010-01-06 出版日期:2010-11-16 发布日期:2010-11-24
作者简介:梁军(1976-),男,副教授,博士研究生,主要研究领域为多agent理论与应用、机器学习、智能交通。Email:liangjun@ujs.edu.cn
基金资助:
国家自然科学基金资助项目(50875112,60841003,60702056);教育部人文社会科学研究项目(06JC630007);国家科技型中小企业技术创新基金资助项目(09C26213203797);江苏省高校自然科学指导性计划资助项目(08KJD580005,10KJD580001);江苏省汽车工程重点实验室开放基金资助项目(QC200705);江苏省自然科学基金资助项目(BK2010339)

Semi-supervised classification based on the Markov random field and robust error function

LIANG Jun^1,2, CHEN Long², ZHOU Wei-qi², TAO Wen-qian¹, YAO Ming², XU Zheng-chuan³

1. School of Computer Science ＆Telecommunication Engineering, Jiangsu University, Zhenjiang 212013, Jiangsu, China;
2. School of Automobile and Traffic Engineering, Jiangsu University, Zhenjiang 212013, Jiangsu, China;
3. School of Management, Fudan University, Shanghai 200433, China

Received:2010-01-06 Online:2010-11-16 Published:2010-11-24

摘要/Abstract

摘要：

为了克服由错误标记样本所引发的问题,提出半监督分类器模型。从标记数据和未标记数据中学习得到决策准则,并在马尔科夫随机场中,运用一个新的基于鲁棒误差函数的能量函数,分别设计基于迭代条件模型和马尔科夫链蒙特卡罗的两种算法来推断标记样本和未标记样本的类别。实验结果表明这两种方法对于现实世界的数据集来说是高效的,并具有很好的鲁棒性。

关键词: 半监督;分类;马尔科夫随机场;鲁棒误差函数

Abstract:

A model of semi-supervised classification was proposed to overcome the problem induced by mislabeled samples. A decision rule was learned from labeled and unlabeled data,and a new energy function based on robust error function was used in the Markov random field. Also two algorithms based on the iterative condition mode and the Markov chain Monte Carlo were designed to infer the label of both labeled and unlabeled samples. Experimental results demonstrated that the proposed methods were efficient for a real-world dataset.

Key words: semi-supervised; classification; Markov random field; robust error function

梁军1，2，陈龙2,周卫琪2，陶文倩1，姚明2，胥正川3. 基于马尔科夫随机场和鲁棒误差函数的半监督分类研究[J]. J4, 2010, 45(11): 1-4.

LIANG Jun1,2, CHEN Long2, ZHOU Wei-qi2, TAO Wen-qian1, YAO Ming2, XU Zheng-chuan3. Semi-supervised classification based on the Markov random field and robust error function[J]. J4, 2010, 45(11): 1-4.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于马尔科夫随机场和鲁棒误差函数的半监督分类研究

Semi-supervised classification based on the Markov random field and robust error function

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

多维度评价

本文评价

推荐阅读 0