[1]李京政,杨习贝,王平心,等.模糊粗糙集的稳定约简方法[J].南京理工大学学报(自然科学版),2018,42(01):68.[doi:10.14177/j.cnki.32-1397n.2018.42.01.010]
 Li Jingzheng,Yang Xibei,Wang Pingxin,et al.Stable attribute reduction approach for fuzzy rough set[J].Journal of Nanjing University of Science and Technology,2018,42(01):68.[doi:10.14177/j.cnki.32-1397n.2018.42.01.010]
点击复制

模糊粗糙集的稳定约简方法()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
42卷
期数:
2018年01期
页码:
68
栏目:
出版日期:
2018-02-28

文章信息/Info

Title:
Stable attribute reduction approach for fuzzy rough set
文章编号:
1005-9830(2018)01-0068-08
作者:
李京政1杨习贝12王平心3陈向坚1
1.江苏科技大学 计算机学院,江苏 镇江 212003; 2.南京理工大学 经济管理学院,江苏 南京 210094; 3.江苏科技大学 数理学院,江苏 镇江 212003
Author(s):
Li Jingzheng1Yang Xibei12Wang Pingxin3Chen Xiangjian1
1.School of Computer Science,Jiangsu University of Science and Technology,Zhenjiang 212003,China; 2.School of Economics & Management,Nanjing University of Science and Technology,Nanjing 210094,China; 3.School of Mathematics and Physics,Jiangsu Unive
关键词:
属性约简 数据扰动 模糊粗糙集 稳定性
Keywords:
attribute reduction data perturbation fuzzy rough sets stability
分类号:
TP18
DOI:
10.14177/j.cnki.32-1397n.2018.42.01.010
摘要:
属性约简是粗糙集理论研究的核心内容。目前已有的研究成果往往是根据分类性能、代价或不确定性等一些度量来定义及求解约简,并未充分考虑数据扰动有可能对约简结果产生的波动影响。为解决这一问题,提出了一种可以求解稳定约简的启发式算法框架:首先,在全体样本集上利用多次聚类进行多重采样以得到若干边界样本集合; 其次,利用集成策略,对每一个属性在所有边界样本集合上求得的重要度进行融合; 最后,选择重要度较高的属性加入到约简集合中。在8个UCI数据集上将新算法与传统算法进行对比分析,实验结果表明当数据发生扰动时,所提出的方法不仅能够有效地提升求解约简的时间效率与约简结果的稳定性,而且依据约简所求得分类结果的稳定性也有显著增强。
Abstract:
Attribute reduction plays a core role in rough set theory.Presently,most of the results of such topic are based on the measurements such that classification performances,costs,uncertainties and so on.Those do not carefully take the fluctuations of reducts into account if data perturbations happen.To fill this gap,a heuristic framework for generating stable reduct is proposed.Firstly,multiple boundary sample sets are induced by multiple clusterings’ technique.Secondly,the fused significance for each attribute can be computed using the multiple significances of such attribute obtained in all boundary sample sets.Finally,the attribute with greatest fused significance is selected and then added into the pool set.The proposed algorithm is tested on several UCI data sets and the experimental results indicate that by comparing with traditional heuristic algorithms,this approach can not only effectively improve the time efficiency for computing reduct and the stability of the reduct,but also advance the classification stability based on the reduct.

参考文献/References:

[1] Pawlak Z.Rough sets-Theoretical aspects of reasoning about data[M].Dordrecht,Boston,London:Kluwer Academic Publishers,1991. [2]Pawlak Z.Rough sets[J].International Journal of Computer & Information Sciences,1982,11(5):341-356. [3]Dubois D,Prade H.Rough fuzzy sets and fuzzy rough sets[J].International Journal of General Systems,1990,17(2):191-209. [4]Jensen R,Shen Q.Fuzzy-rough sets assisted attribute selection[J].IEEE Transactions on Fuzzy Systems,2007,15(1):73-89. [5]Wang Xizhao,Tsang E C,Zhao Suyun,et al.Learning fuzzy rules from fuzzy samples based on rough set technique[J].Information Sciences,2007,177(20):4493-4514. [6]Wu Weizhi.Attribute reduction based on evidence theory in incomplete decision systems[J].Information Sciences,2008,178(5):1355-1371. [7]Yang Xibei,Qi Yunsong,Song Xiaoning,et al.Test cost sensitive multigranulation rough set:model and minimal cost selection[J].Information Sciences,2013,250(11):184-199. [8]Qian Yuhua,Liang Jiye,Pedrycz W,et al.Positive approximation:an accelerator for attribute reduction in rough set theory[J].Artificial Intelligence,2010,174(9-10):597-618. [9]Liu Xiaodong,Pedrycz W,Chai Tianyou,et al.The development of fuzzy rough sets with the use of structures and algebras of axiomatic fuzzy sets[J].IEEE Transactions on Knowledge & Data Engineering,2009,21(3):443-462. [10]Hu Qinghua,Yu Daren,Pedrycz W,et al.Kernelized fuzzy rough sets and their applications[J].IEEE Transactions on Knowledge & Data Engineering,2011,23(11):1649-1667. [11]王宇,杨志荣,杨习贝.决策粗糙集属性约简:一种局部视角方法[J].南京理工大学学报,2016,40(4):444-449. Wang Yu,Yang Zhirong,Yang Xibei.Local attribute reduction approach based on decision-theoretic rough set[J].Journal of Nanjing University of Science and Technology,2016,40(4):444-449. [12]黄颖,李芳芳.基于粗集理论的物流供应商选择研究[J].江苏科技大学学报(自然科学版),2008,22(6):67-71. Huang Ying,Li Fangfang.Research on logistics suppliers selection based on rough sets theory[J].Journal of Jiangsu University of Science and Technology(Natural Science Edition),2008,22(6):67-71. [13]王熙照,王婷婷,翟俊海.基于样例选取的属性约简算法[J].计算机研究与发展,2012,49(11):2305-2310. Wang Xizhao,Wang Tingting,Zhai Junhai.An attribute reduction algorithm based on instance selection[J].Journal of Computer Research and Development,2012,49(11):2305-2310. [14]Saeys Y,Abeel T,Peer Y V D.Robust feature selection using ensemble feature selection techniques[J].Lecture Notes in Computer Science,2008,5212:313-325. [15]Li Yun,Si J,Zhou Guojing,et al.FREL:a stable feature selection algorithm[J].IEEE Transactions on Neural Networks & Learning Systems,2014,26:1388-1402. [16]Wu Xindong,Kumar V,Quinlan J R,et al.Top 10 algorithms in data mining[J].Knowledge and Information Systems,2008,14(1):1-37. [17]钱晓东,曹阳.基于社区极大类发现的大数据并行聚类算法[J].南京理工大学学报,2016,40(1):117-123. Qian Xiaodong,Cao Yang.Large data parallel clustering algorithm based on discovery of maximal class in the community[J].Journal of Nanjing University of Science and Technology,2016,40(1):117-123. [18]刘芝怡,陈功.基于改进k-means算法的RFAT客户细分研究[J].南京理工大学学报,2014,38(4):531-536. Liu Zhiyi,Chen Gong.RFAT customer segmentation based on improved k-means algorithm[J].Journal of Nanjing University of Science and Technology,2014,38(4):531-536. [19]Ju Hengrong,Yang Xibei,Song Xiaoning.Dynamic updating multigranulation fuzzy rough set:approxima-tions and reducts[J].International Journal of Machine Learning & Cybernetics,2014,5(6):981-990. [20]杨习贝,徐苏平,戚湧,等.基于多特征空间的粗糙数据分析方法[J].江苏科技大学学报(自然科学版),2016,30(4):370-373. Yang Xibei,Xu Suping,Qi Yong,et al.Rough data analysis method based on multi-feature space[J].Journal of Jiangsu University of Science and Technology(Natural Science Edition),2016,30(4):370-373. [21]Hu Qinghua,Zhang Lei,Chen Degang,et al.Gaussian kernel based fuzzy rough sets:model,uncertainty measures and applications[J].International Journal of Approximate Reasoning,2010,51(4):453-471. [22]Rao C R,Wu Y.Linear model selection by cross-validation[J].Journal of Statistical Planning and Inference,2003,128(1):231-240. [23]杨春,殷绪成,赫红卫,等.基于差异性的分类器集成:有效性分析及优化集成[J].自动化学报,2014,40(4):660-674. Yang Chun,Yin Xucheng,He Hongwei,et al.Classifier ensemble based on diversity:effectiveness analysis and optimization integration[J].Acta Automatica Sinica,2014,40(4):660-674. [24]Kuncheva L I,Whitaker C J.Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy[J].Machine Learning,2003,51(2):181-207. [25]Yule G U.On the association of attributes in statistics[J].Philosophical Transactions of the Royal Society A:Mathematical,Physical & Engineering Sciences,1900,194:257-319. [26]Li Shengqiao,Harner E J,Adjeroh D A.Random KNN feature selection-a fast and stable alternative to random forests[J].BMC Bioinformatics,2011,12(1):450-459. [27]胡清华,于达仁,谢宗霞.基于邻域粒化和粗糙逼近的数值属性约简[J].软件学报,2008,19(3):640-649. Hu Qinghua,Yu Daren,Xie Zongxia,et al.Numerical attribute reduction based on neighborhood granulation and rough approximation[J].Journal of Software,2008,19(3):640-649. [28]Zhou Bing.Multi-class decision-theoretic rough sets[J].International Journal of Approximate Reasoning,2014,55(1):211-224. [29]Dou Huili,Yang Xibei,Song Xiaoning,et al.Decision-theoretic rough set:a multicost strategy[J].Knowledge-Based Systems,2016,91:71-83. [30]Hu Qinghua,Zhang Lei,An Shuang,et al.On robust fuzzy rough set models[J].IEEE Transactions on Fuzzy Systems,2012,20(4):636-651. [31]Zhang Minling,Zhou Zhihua.A review on multi-label learning algorithms[J].IEEE Transactions on Knowledge & Data Engineering,2014,26(8):1819-1837. [32]Xu Suping,Yang Xibei,Yu Hualong,et al.Multi-label learning with label-specific feature reduction[J].Knowledge-Based Systems,2016,104:52-61.

相似文献/References:

[1]王 宇,杨志荣,杨习贝.决策粗糙集属性约简:一种局部视角方法[J].南京理工大学学报(自然科学版),2016,40(04):444.[doi:10.14177/j.cnki.32-1397n.2016.40.04.011]
 Wang Yu,Yang Zhirong,Yang Xibei.Local attribute reduction approach based on decision-theoretic rough set[J].Journal of Nanjing University of Science and Technology,2016,40(01):444.[doi:10.14177/j.cnki.32-1397n.2016.40.04.011]
[2]方 宇,高 磊,刘忠慧,等.基于三支决策的广义代价敏感近似属性约简[J].南京理工大学学报(自然科学版),2019,43(04):481.[doi:10.14177/j.cnki.32-1397n.2019.43.04.015]
 Fang Yu,Gao Lei,Liu Zhonghui,et al.Generalized cost-sensitive approximate attributereduction based on three-way decisions[J].Journal of Nanjing University of Science and Technology,2019,43(01):481.[doi:10.14177/j.cnki.32-1397n.2019.43.04.015]

备注/Memo

备注/Memo:
收稿日期:2017-02-06 修回日期:2017-06-22 基金项目:国家自然科学基金(61572242,61503160,61502211); 江苏省高校哲学社会科学基金(2015SJD769); 中国博士后科学基金(2014M550293); 江苏省青蓝工程人才项目 作者简介:李京政(1993-),男,硕士生,主要研究方向:粗糙集理论、机器学习,E-mail:maxlijingzheng@163.com; 通讯作者:杨习贝(1980-),男,博士,副教授,主要研究方向:粗糙集理论、粒计算、机器学习,E-mail:zhenjiangyangxibei@163.com. 引文格式:李京政,杨习贝,王平心,等. 模糊粗糙集的稳定约简方法[J]. 南京理工大学学报,2018,42(1):68-75. 投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2018-02-28