区间型符号数据的特征选择方法

doi:10.12005/orms.2015.0009

运筹与管理 ›› 2015, Vol. 24 ›› Issue (1): 67-74.DOI: 10.12005/orms.2015.0009

区间型符号数据的特征选择方法

郭崇慧, 刘永超

大连理工大学系统工程研究所,辽宁大连 116024

收稿日期:2013-08-27 出版日期:2015-02-12
作者简介:郭崇慧(1973-),男,博士,教授,博士生导师,主要研究方向:数据挖掘与知识发现, 决策理论与方法等。刘永超(1989-),男,硕士研究生,研究方向:符号数据挖掘。
基金资助:
国家自然科学基金资助项目(71171030,71031002);教育部新世纪优秀人才支持计划(NCET-11-0050)

A Feature Selection Method for Symbolic Interval Data

GUO Chong-hui, LIU Yong-chao

Institute of Systems Engineering, Dalian University of Technology, Dalian 116024, China

Received:2013-08-27 Online:2015-02-12

摘要/Abstract

摘要： 对区间型符号数据进行特征选择,可以降低数据的维数,提取数据的关键特征。针对区间型符号数据的特征选择问题,本文提出了一种新的特征选择方法。首先,该方法使用区间数Hausdorff距离和区间数欧氏距离度量区间数的相似性,通过建立使得样本点与样本类中心相似性最大的优化模型来估计区间型符号数据的特征权重。其次,基于特征权重构建相应的分类器来评价所估计特征权重的优劣。最后,为了验证本文方法的有效性,分别在人工生成数据集和真实数据集上进行了数值实验,数值实验结果表明,本文方法可以有效地去除无关特征,识别出与类标号有关的特征。

关键词: 符号数据分析, 特征选择, 最近邻分类器, 区间型数据

Abstract: Feature selection for symbolic interval data can reduce the dimension of data and extract the key features of data.In order to deal with the feature selection problem, a new method is proposed in this paper. Firstly, Hausdorff distance and Euclidean distance are utilized to measure the similarity between two interval numbers, and an optimization model, which aims to maximize the similarity between each sample and its class center, is established to estimate the feature weights for symbolic interval data. Next, based on the estimated feature selection weights, a classifier is constructed to evaluate the goodness of the weights. Finally, in order to verify the effectiveness of the proposed method, numerical experiments are done in artificially generated data sets and real data sets, respectively. The numerical experiments results show that the proposed algrithm can eliminate irrelevant features and identify features which are relevant to the class labels.

Key words: symbolic data analysis, feature selection, nearest neighbor classifier, interval data

中图分类号:

O235

郭崇慧, 刘永超. 区间型符号数据的特征选择方法[J]. 运筹与管理, 2015, 24(1): 67-74.

GUO Chong-hui, LIU Yong-chao. A Feature Selection Method for Symbolic Interval Data[J]. Operations Research and Management Science, 2015, 24(1): 67-74.

参考文献

[1] Bock H H, Diday E. Analysis of symbolic data: exploratory methods for extracting statistical information from complex data[M]. Springer, 1999.
[2] 李汶华,郭均鹏.区间型符号数据回归分析及其应用[J].管理科学学报,2010,13(4):38-43.
[3] 胡艳,王惠文.一种海量数据分析技术-符号数据分析及应用[J].北京航空航天大学学报,2004,17(2):40-44.
[4] Douzal-Chouakria A, Billard L, Diday E. Principal component analysis for interval-valued observations[J]. Statistical Analysis and Data Mining, 2011, 4(2): 229-246.
[5] Lauro C N, Palumbo F. Principal componment analysis of interval data: a symbolic data analysis approach[J]. Computational Statisics, 2000, 15(1): 73-87.
[6] Gioia F, Lauro C N. Principal component analysis on interval data[J]. Computational Statistics, 2006, 21(2): 343-363.
[7] Lima Neto E A, de Carvalho F A T. Centre and range method for fitting a linear regression model to symbolic interval data[J]. Computational Statistics & Data Analysis, 2008, 52(3): 1500-1515.
[8] Domingues M A O, de Souza R M C R, Cysneiros F J A. A robust method for linear regression of symbolic interval data[J]. Pattern Recognition Letters, 2010, 31(13): 1991-1996.
[9] Lima Neto E A, de Carvalho F A T. Constrained linear regression models for symbolic interval-valued variables[J]. Computational Statistics & Data Analysis, 2010, 54(2): 333-347.
[10] 张伟斌,刘文江.区间型数据的模糊c均值聚类算法[J].计算机工程,2008,34(11):26-28.
[11] De Souza R M C R, de Carvalho F A T. Clustering of interval data based on city-block distances[J]. Pattern Recognition Letters, 2004, 25(3): 353-365.
[12] Chavent M, de Carvalho F A T, Lechevallier Y, et al. New clustering methods for interval data[J]. Computational statistics, 2006, 21(2): 211-229.
[13] De Carvalho F D A T, de Souza R M C R, Chavent M, et al. Adaptive Hausdorff distances and dynamic clustering of symbolic interval data[J]. Pattern Recognition Letters, 2006, 27(3): 167-179.
[14] De Carvalho F A T, Lechevallier Y. Partitional clustering algorithms for symbolic interval data based on single adaptive distances[J]. Pattern Recognition, 2009, 42: 1223-1236.
[15] Hedjazi L, Aguilar-Martin J, Lann M L. Similarity-margin based feature selection for symbolic interval data[J]. Pattern Recognition Letters , 2011, 32(4): 578-585.
[16] 谢信喜,王士同.适用于区间数据的基于相互距离的相似性传播聚类[J].计算机应用,2008,28(6):1441-1443.

区间型符号数据的特征选择方法

A Feature Selection Method for Symbolic Interval Data

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics