基于自适应局部保持投影的无监督特征选择方法

doi:10.3969/j.issn.0253-2778.2018.04.004

中国科学技术大学学报 ›› 2018, Vol. 48 ›› Issue (4): 290-297.DOI: 10.3969/j.issn.0253-2778.2018.04.004

基于自适应局部保持投影的无监督特征选择方法

严菲，王晓栋

厦门理工学院计算机与信息工程学院，福建厦门 361024

收稿日期:2017-05-25 修回日期:2017-06-24 出版日期:2018-04-30 发布日期:2018-04-30
通讯作者: 严菲
作者简介:严菲（通讯作者），女，硕士/实验师，研究方向：模式识别、数据挖掘. E-mail: 275223188@qq.com
基金资助:
国家自然科学基金(61502405)，福建省自然基金面上项目(2017J01511)，福建省中青年教师教育科研项目((JAT160357,JAT170417)资助.

Unsupervised feature selection method based on adaptive locality preserving projection

YAN Fei, WANG Xiaodong

College of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China）

Received:2017-05-25 Revised:2017-06-24 Online:2018-04-30 Published:2018-04-30

摘要/Abstract

摘要： 基于谱图的无监督特征选择方法在原始高维空间构建图，易受噪声或冗余特征干扰.为此提出一种基于自适应局部保持投影的无监督特征选择方法，利用全局线性回归函数建立特征选择模型，结合自适应局部保持投影提高模型准确度，引入l2,1约束提升特征之间可区分度，避免噪声干扰.最后通过实验验证了该方法的有效性.

关键词: 特征选择, 无监督学习, 线性回归, 局部保持投影, l2, 1范数

Abstract: The unsupervised feature selection method based on spectrogram is constructed in the original high dimensional data space, which is easily disturbed by noise or redundant features. To overcome these deficiencies, an unsupervised feature selection method based on adaptive locality preserving projection is proposed. Global linear regression function is utilized to construct feature selection model, and the adaptive local preserving projection is adopted to improve model accuracy. Then the l2,1-norm constraint is added to improve the distinguishability of different features and avoid noise interference. A comparison with several state-of-the-art feature selection methods demostrate the effectiveness of the proposed method.

Key words: feature selection, unsupervised learning, linear regression, locality preserving projection, l2,1-norm

中图分类号:

TP391.4

严菲，王晓栋. 基于自适应局部保持投影的无监督特征选择方法[J]. 中国科学技术大学学报, 2018, 48(4): 290-297.

YAN Fei, WANG Xiaodong. Unsupervised feature selection method based on adaptive locality preserving projection[J]. Journal of University of Science and Technology of China, 2018, 48(4): 290-297.

参考文献

［1］
NIE F, CAI X, HUANG H, et al. Efficient and robust feature selection via joint l2,1-norms minimization[C]// Advances in Neural Information Processing Systems. Chicago: IEEE Press, 2010:1813-1821.
[2] YANG Y, MA Z, HAUPTMANN A G, et al. Feature selection for multimedia analysis by sharing information among multiple tasks[J]. IEEE Transactions on Multimedia, 2013, 15(3): 661-669.
[3] CHANG X, NIE F, YANG Y, et al. A convex formulation for semi-supervised multi-label feature selection[C]// 28th AAAI Conference on Artificial Intelligence. Québec, Canada: AAAI Press, 2014:1171-1177.
[4] 王晓栋, 严菲, 谢勇,等. 基于稀疏图表示的特征选择方法研究[J]. 计算机工程与科学, 2015, 37(12): 2372-2378.
WANG X D, YAN F, XIE Y, et al. A feature selection method based on sparse graph representation[J]. Computer Engineering & Science, 2015, 37(12): 2372-2378.
[5] REN Y, ZHANG G, YU G, et al. Local and global structure preserving based feature selection[J]. Neurocomputing, 2012, 89(10):147-157.
[6] HE X, CAI D, NIYOGI P. Laplacian score for feature selection[J]. Advances in Neural Information Processing Systems, 2005, 18: 507-514.
[7] YANG Y, SHEN H T, MA Z, et al. l2,1-norm regularized discriminative feature selection for unsupervised learning[C]// International Joint Conference on Artificial Intelligence. Barcelona, Spain: AAAI Press, 2011: 1589-1594.
[8] LI Z, YANG Y, LIU J, et al. Unsupervised feature selection using nonnegative spectral analysis[C]// 26th AAAI Conference on Artificial Intelligence. New York: AAAI Press, 2012:1026-1032.
[9] ZHAO Z, LIU H. Spectral feature selection for supervised and unsupervised learning[C]// Proceedings of the 24th International Conference on Machine Learning. Corvalis, USA: ACM Press, 2007: 1151-1157.
[10] CAI D, ZHANG C, HE X. Unsupervised feature selection for multi-cluster data[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington: ACM Press, 2010: 333-342.
[11] WANG X D, ZHANG X, ZENG Z, et al. Unsupervised spectral feature selection with l2-norm graph[J]. Neurocomputing, 2016, 200(C): 47-54.
[12] HOU C, NIE F, LI X, et al. Joint embedding learning and sparse regression: A framework for unsupervised feature selection[J]. IEEE Transactions on Cybernetics, 2014, 44(6): 793-804.
[13] ZHANG Z, BAI L, LIANG Y, et al. Unsupervised Feature Selection by Graph Optimization[M]// Image Analysis and Processing – ICIAP, Springer, 2015.
[14] HE X, NIYOGI P. Locality preserving projections (LPP)[J]. Advances in Neural Information Processing Systems, 2002, 16(1): 186-197.
[15] NIE F, WANG X, HUANG H. Clustering and projected clustering with adaptive neighbors[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Québec, Canada: ACM Press, 2014: 977-986.
[16] LYONS M J, BUDYNEK J, AKAMATSU S. Automatic classification of single facial images [J]. IEEE Transactions on Pattern Analysis, 1999, 21(12): 1357-1362.

()
(

[1]	文泽波，康宇，曹洋，魏梦，宋卫国. 基于随机森林特征选择的视频烟雾检测[J]. 中国科学技术大学学报, 2017, 47(8): 653-664.
[2]	徐子伟，王鹏，陈宗海. 一种基于Fisher比率和预测风险准则的电信客户流失预测分步特征选择方法[J]. 中国科学技术大学学报, 2017, 47(8): 686-694.
[3]	李权威，宛田宾，秦俊，廖光煊. 基于Dignet无监督学习聚类算法的智能火灾探测[J]. 中国科学技术大学学报, 2009, 39(7): 769-776.

基于自适应局部保持投影的无监督特征选择方法

Unsupervised feature selection method based on adaptive locality preserving projection

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价