一种采用LLE降维和贝叶斯分类的多类标学习算法

Journal of Systems Engineering and Electronics ›› 2009, Vol. 31 ›› Issue (6): 1467-1472.

一种采用LLE降维和贝叶斯分类的多类标学习算法

李宏, 谢政, 向遥, 吴敏

中南大学信息科学与工程学院, 湖南, 长沙, 410083

收稿日期:2008-03-25 修回日期:2008-04-15 出版日期:2009-06-20 发布日期:2010-01-03
作者简介:李宏(1966- ),男,教授,博士后,主要研究方向为数据挖掘和图像处理.E-mail:lihongcsu@mail.csu.edu.cn
基金资助:
国家杰出青年科学基金项目(60425310);中南大学博士后基金项目资助课题

Multi-label learning by LLE dimension reduction and Bayesian classification

LI Hong, XIE Zheng, XIANG Yao, WU Min

School of Information Science and Engineering, Central South Univ., Changsha 410083, China

Received:2008-03-25 Revised:2008-04-15 Online:2009-06-20 Published:2010-01-03

摘要/Abstract

摘要： 多类标数据中的样本可能属于一个或多个类标,因此其分类问题较单类标分类更为复杂。提出一种新的多类标学习算法,首先针对多类标数据的特征属性维数高的特点,采用LLE算法对多类标数据的特征属性进行降维,提取能较完整描述数据的一组低维特征属性集;然后将多类标样本集按所属的类标进行划分,并采用贝叶斯分类模型来学习各组样本集的分类特性;根据各个分类模型的判定类标,综合得到多类标样本的最终类标集。将该算法分别应用到自然场景图像和基因数据的多类标分类学习中,实验结果表明,该算法针对不同的多类标数据集均能取得很好的分类效果,且相比于其他多类标算法有更高的性能。

Abstract: Samples of multi-label data may belong to more than one class,so its classification problem is much more complicated than single-label data.A novel multi-label learning algorithm is proposed.The feature attributes of multi-label data often have high dimensions,so an LLE algorithm is applied to decrease the dimension in order to extract a group of low dimensional feature attribute sets which could completely describe data.Then multi-label samples are partitioned in terms of their belonging classes,and the classification characteristics of each group are learned by using Bayesian classification model.After that,the final class-label set of multi-label samples is obtained according to the decision class-label of each classification model.The algorithm is applied to the multi-label classification learning of both nature scene image and gene data respectively.Experimental results show that the proposed algorithm can acquire good classification effects on different multi-label datasets and has better performance compared with the others.

中图分类号:

TP391.4

李宏, 谢政, 向遥, 吴敏. 一种采用LLE降维和贝叶斯分类的多类标学习算法[J]. Journal of Systems Engineering and Electronics, 2009, 31(6): 1467-1472.

LI Hong, XIE Zheng, XIANG Yao, WU Min. Multi-label learning by LLE dimension reduction and Bayesian classification[J]. Journal of Systems Engineering and Electronics, 2009, 31(6): 1467-1472.

参考文献

[1] Elisseeff A,Weston J.A kernel method for multi-labeled dassifcation[M].Dietterich T G,Becket S,Ghahramani Z Eds.Advances in Neural Information Processing Systems 14.MIT Press,Cambridge,MA,2002:681-687.
[2] McCallum A.Multi-label text classifcation with a mixture model trained by EM[C]//Working Notes of the AAAI Workshop on Text Learning,Orlando,1999:577-584.
[3] Amanda Clare,King Ross D.Knowledge discovery in multi-label phenotype data[C]//Proc.of ECML/PKDD,2001:462-470.
[4] Comité F D,Gilleron R,Tommasi M.Learning multi-label alternating decision tree from texts and data[C]//Perner P,Rosenfeld A Eds,Lecture Notes in Computer Science 2734,Springer,Berlin,2003:35-49.
[5] Li Hong,Zhao Rui,Chen Jian-er,et al.Research on multi-labeled decision trees[C]//ADMA,LNA I 4093,Springer-Verlag Berlin Heidelberg,2006:247-254.
[6] Freund Y,Schapire R E.A decision-theoretic generalization of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,1997,55(1):119-139.
[7] Zhang Minling,Zhou Zhihua.ML-kNN:A lazy learning approach to multi-label learning[J].Pattern Recognition(PRJ),2007,40(7):2038-2048.
[8] Brian F,Dejan K.Non-linear embedding and the underlying dimensionality of reflectance spectra and chromaticity histograms[C]//The IT&SID Ninth Color Imaging Conference:Color Science,Systems and Applications.Scottsdale:Society for Imaging Science and Technology,2001:126-129.
[9] Hedid A,Kouropteva O,Pietikainen O.Unsupervised learning using locally linear embedding:experiments with face poseanalysis[EB/OL].http://doi.ieeecomputersociety.org/10.1109/ ICPR.2002.1044625,2002.
[10] Dick D R,Robert P W.Locally linear embedding for classification[EB/OL].http://www.ph.tn.tudel ft.nl/～ dick/ ph-2002-01.pdf,2002.
[11] 张连文,郭海鹏.贝叶斯网引论[M].北京:科学出版杜,2006.
[12] Maron O,Ratan A L.Multiple-instance learning for natural scene classification[C]//Proc.of the 15th International Conference on Machine Learning,Madison,WI,1998:341-349.

[1]	徐义飞, 李晓冬, 李新德. 一种基于定位和非对称补偿的伪装目标分割方法[J]. 系统工程与电子技术, 2022, 44(9): 2707-2715.
[2]	张涛, 杨小冈, 卢瑞涛, 谢学立, 刘闯. 基于关键点的遥感图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(8): 2437-2447.
[3]	樊成, 王布宏, 田继伟. 基于多任务学习图卷积模型的航空网络节点分类[J]. 系统工程与电子技术, 2022, 44(7): 2341-2349.
[4]	赵晓枫, 徐叶斌, 吴飞, 牛家辉, 蔡伟, 张志利. 基于全局感知机制的地面红外目标检测方法[J]. 系统工程与电子技术, 2022, 44(5): 1461-1467.
[5]	王华超, 刘静, 程昊文, 彭喜衍. 基于模糊决策的快速星图识别[J]. 系统工程与电子技术, 2022, 44(5): 1447-1453.
[6]	王通典, 刘洁瑜, 吴宗收, 沈强, 姚二亮. 基于多尺度光流融合特征点视觉-惯性SLAM方法[J]. 系统工程与电子技术, 2022, 44(3): 977-985.
[7]	李洪瑶, 李小强, 韩心中, 谢学立, 席建祥. 基于决策融合的多无人机协同目标检测识别算法[J]. 系统工程与电子技术, 2022, 44(3): 746-754.
[8]	宋子壮, 杨嘉伟, 张东方, 王诗强, 张硕. 基于无锚框的红外多类别多目标实时跟踪网络[J]. 系统工程与电子技术, 2022, 44(2): 401-409.
[9]	范加利, 田少兵, 黄葵, 朱兴动. 基于Faster R-CNN的航母舰面多尺度目标检测算法[J]. 系统工程与电子技术, 2022, 44(1): 40-46.
[10]	吕鑫, 慕晓冬, 张钧. 基于改进麻雀搜索算法的多阈值图像分割[J]. 系统工程与电子技术, 2021, 43(2): 318-327.
[11]	徐国明, 袁宏武, 薛模根, 王峰. 全偏振参量低秩稀疏分解伪彩色图像融合[J]. 系统工程与电子技术, 2020, 42(11): 2450-2460.
[12]	向前, 王晓丹, 李睿, 来杰, 张国令. 基于DCNN的弹道中段目标HRRP图像识别[J]. 系统工程与电子技术, 2020, 42(11): 2426-2433.
[13]	罗钧, 刘建强, 庞亚男. 基于邻域搜索JADE的二维Otsu多阈值图像分割[J]. 系统工程与电子技术, 2020, 42(10): 2164-2171.
[14]	花思齐, 赵伟, 刘建业. 基于改进滤波器和图像多尺度变换的背景抑制算法[J]. 系统工程与电子技术, 2020, 42(8): 1679-1684.
[15]	黄秋实, 张雅声, 冯飞. 分布式星敏感器下空间目标航迹段关联算法[J]. 系统工程与电子技术, 2020, 42(5): 1007-1013.