面向模糊邻域动态特征交互的特征选择方法

徐久成; 牛武林; 段江豪; 张杉; 白晴

doi:10.16152/j.cnki.xdxbzr.2025-02-009

您当前的位置：

首页 >

文章列表页 >

面向模糊邻域动态特征交互的特征选择方法

不确定性与知识获取 | 更新时间：2025-04-21

- 面向模糊邻域动态特征交互的特征选择方法
- Feature selection method for dynamic feature interaction in fuzzy neighborhood system
- 西北大学学报（自然科学版） 2025年55卷第2期页码：320-332
- 作者机构：
  
  1.河南师范大学　计算机与信息工程学院，河南　新乡　 453007
  2.智慧商务与物联网技术河南省工程实验室，河南　新乡　 453007
- 作者简介：
  
  徐久成，男，博士，教授，从事粒计算、数据挖掘和生物信息学研究，xjc@htu.edu.cn。
- 基金信息：
  
  国家自然科学基金(61976082;62076089;62002103)
- DOI：10.16152/j.cnki.xdxbzr.2025-02-009
  中图分类号： TP181
- 收稿日期：2024-09-28，
  
  纸质出版日期：2025-04-25
- 稿件说明：
移动端阅览
徐久成, 牛武林, 段江豪, 等. 面向模糊邻域动态特征交互的特征选择方法[J]. 西北大学学报（自然科学版）, 2025,55(2):320-332.

XU Jiucheng, NIU Wulin, DUAN Jianghao, et al. Feature selection method for dynamic feature interaction in fuzzy neighborhood system[J]. Journal of northwest university (natural science edition), 2025, 55(2): 320-332.
徐久成, 牛武林, 段江豪, 等. 面向模糊邻域动态特征交互的特征选择方法[J]. 西北大学学报（自然科学版）, 2025,55(2):320-332. DOI： 10.16152/j.cnki.xdxbzr.2025-02-009.

XU Jiucheng, NIU Wulin, DUAN Jianghao, et al. Feature selection method for dynamic feature interaction in fuzzy neighborhood system[J]. Journal of northwest university (natural science edition), 2025, 55(2): 320-332. DOI： 10.16152/j.cnki.xdxbzr.2025-02-009.

摘要

针对大部分基于模糊邻域信息系统的特征选择方法，在选入特征时只是单调的按照特征顺序进行特征交互的问题，以及大多数特征度量函数仅从代数观或信息观的视角构造度量函数的缺陷，提出了一种基于模糊邻域动态特征交互的特征选择方法。首先，引入模糊邻域互信息计算特征相关度，并根据特征相关度将特征顺序重组。其次，分析特征动态交互的过程，通过模糊邻域互信息以及模糊邻域条件互信息，按照特征排序依次计算特征之间的冗余及动态交互程度。最后，为改善大多数特征度量函数构造视角单一的缺陷，提出一种多视角下的依赖模糊邻域混合互信息度量函数。在8个公共数据集上与现有的7种属性约简算法进行对比实验，实验结果表明，该算法消除了冗余特征，同时提高了数据分类的准确度。

Abstract

In order to solve the problem that most feature selection methods based on fuzzy neighborhood information system only monotonically interact with features according to the order of features when selecting features

and that most feature measurement functions only construct metric functions from the perspective of algebraic view or information view

a feature selection method based on dynamic feature interaction in fuzzy neighborhood is proposed. Firstly

fuzzy neighborhood mutual information is introduced to calculate the feature correlation degree and reorganize the feature order according to the feature correlation degree. Secondly

the process of dynamic interaction between features is analyzed

and the degree of redundancy and dynamic interaction between features is calculated according to the order of features through fuzzy neighborhood mutual information and fuzzy neighborhood conditional mutual information. Finally

in order to improve the defect of single perspective in the construction of most feature metric functions

a hybrid mutual information metric function relying on fuzzy neighborhoods from multiple perspectives is proposed. Experimental results show that the proposed algorithm eliminates redundant features and improves the accuracy of data classification while comparing with seven existing feature reduction algorithms on eight public datasets.

关键词

Keywords

references

AN S , HU Q H , WANG C Z , et al . Data reduction basedon NN-kNN measure for NN classification and regression [J ] . International Journal of Machine Learning and Cybernetics , 2022 , 13 ( 3 ): 765 - 781 .

WAN J H , CHEN H M , YUAN Z , et al . A novel hybrid feature selection method considering feature interaction in neighborhood rough set [J ] . Knowledge-Based Systems , 2021 , 227 ( 6 ): 107167 .

冉虹 , 候婷 , 贺龙雨 , 等 . 基于模糊邻域系统的模糊粗糙集模型 [J ] . 计算机科学 , 2022 , 49 ( S2 ): 330 - 334 .

RAN H , HOU T , HE L Y , et al . Fuzzy rough set model based on fuzzy neighborhood system [J ] . Computer Science , 2022 , 49 ( S2 ): 330 - 334 .

庞婧 , 姚炳学 , 李令强 . 基于模糊邻域系的α-粗糙集及其应用 [J ] . 模糊系统与数学 , 2022 , 36 ( 5 ): 158 - 165 .

PANG J , YAO B X , LI L Q . α-rough set based on fuzzy neighborhood system and its application [J ] . Fuzzy Systems and Mathematics , 2022 , 36 ( 5 ): 158 - 165 .

YUAN Z , CHEN H M , XIE P , et al . Attribute reduction methods in fuzzy rough set theory: An overview, comparative experiments, and new directions [J ] . Applied Soft Computing , 2021 , 107 : 107353 .

AKRAM M , ALI G , ALCANTUD J C , et al . Parameter reductions in N-soft sets and their applications in decision-making [J ] . Expert Systems , 2021 , 38 ( 1 ): e12601 .

ZHANG C , LI D Y , LIANG J Y . Multi-granularity three-way decisions with adjustable hesitant fuzzy linguistic multigranulation decision-theoretic rough sets over two universes [J ] . Information Sciences , 2020 , 507 : 665 - 683 .

SHI Z Q , XIE S R , LI L Q . Generalized fuzzy neighborhood system-based multigranulation variable precision fuzzy rough sets with double TOPSIS method to MADM [J ] . Information Sciences: An International Journal , 2023 , 643 : 119251 .

HU Q H , XIE Z X , YU D R . Hybrid attribute reduction based on a novel fuzzy-rough model and information granulation [J ] . Pattern Recognition , 2007 , 40 ( 12 ): 3509 - 3521 .

WANG Z H . Fundamental properties of fuzzy rough sets based on triangular norms and fuzzy implications: The properties characterized by fuzzy neighborhood and fuzzy topology [J ] . Complex & Intelligent Systems , 2024 , 10 ( 1 ): 1103 - 1114 .

杨洁 , 匡俊成 , 王国胤 , 等 . 代价敏感的多粒度邻域粗糙模糊集的近似表示 [J ] . 计算机科学 , 2023 , 50 ( 5 ): 137 - 145 .

YANG J , KUANG J C , WANG G Y , et al . Approximate representation of a cost-sensitive, multi-granularity neighborhood rough fuzzy set [J ] . Computer Science , 2023 , 50 ( 5 ): 137 - 145 .

DUCANGE P , FAZZOLARI M , MARCELLONI F . An overview of recent distributed algorithms for learning fuzzy models in Big Data classification [J ] . Journal of Big Data , 2020 , 7 ( 1 ): 1 - 29 .

WANG D , NIE F P , HUANG H . Feature selection via global redundancy minimization [J ] . IEEE Transactions on Knowledge and Data Engineering , 2015 , 27 ( 10 ): 2743 - 2755 .

TANG X C , DAI Y S , XIANG Y P . Feature selection based on feature interactions with application to text categorization [J ] . Expert Systems with Applications , 2019 , 120 : 207 - 216 .

HAGAR J D , WISSINK T L , KUHN D R , et al . Introducing combinatorial testing in a large organization [J ] . IEEE International Conference on Software Testing , 2015 , 48 ( 4 ): 64 - 72 .

WANG W J , GUO M , HAN T T , et al . A novel feature selection method considering feature interaction in neighborhood rough set [J ] . Intelligent Data Analysis , 2023 , 27 ( 2 ): 345 - 359 .

ZHOU P , LIP P , ZHAO S , et al . Feature interaction for streaming feature selection [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2021 , 32 ( 10 ): 4691 - 4702 .

LIN X H , LI C , REN W J , et al . A new feature selection method based on symmetrical uncertainty and interaction gain [J ] . Computational Biology and Chemistry , 2019 , 83 : 107149 .

孙敏杰 . 基于模糊邻域熵的特征基因选择方法研究 [D ] . 广州 : 广州大学 , 2023 : 7 - 11 .

XU J C , MENG X R , QU K L , et al . Feature selection using relative dependency complement mutual information in fitting fuzzy rough set model [J ] . Applied Intelligence , 2023 , 53 ( 15 ): 18239 - 18262 .

MA X , XU H , JU C H . Class-specific feature selection via maximal dynamic correlation change and minimal redundancy [J ] . Expert Systems with Applications , 2023 , 229 : 120455 .

CHEN D G , ZHANG L , ZHAO S Y , et al . A novel algorithm for finding reducts with fuzzy rough sets [J ] . IEEE Transactions on Fuzzy Systems , 2012 , 20 ( 2 ): 385 - 389 .

SUN L , WANG L Y , QIAN Y H , et al . Feature selection using Lebesgue and entropy measures for incomplete neighborhood decision systems [J ] . Knowledge-Based Systems , 2019 , 186 : 104942 .

TAN A H , WU W Z , QIAN Y H , et al . Intuitionistic fuzzy rough set-based granular structures and attribute subset selection [J ] . IEEE Transactions on Fuzzy Systems , 2019 , 27 ( 3 ): 527 - 539 .

SUN L , WANG L Y , DING W P , et al . Neighborhood multi-granulation rough sets-based attribute reduction using Lebesgue and entropy measures in incomplete neighborhood decision systems [J ] . Knowledge-Based Systems , 2020 , 192 : 105373 .

JENSEN R , SHEN Q . New approaches to fuzzy-rough feature selection [J ] . IEEE Transactions on Fuzzy Systems , 2009 , 17 ( 4 ): 824 - 838 .

XU J C , QU K L , MENG X R , et al . Feature selection based on multiview entropy measures in multiperspective rough set [J ] . International Journal of Intelligent Systems , 2022 , 37 ( 10 ): 7200 - 7234 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于互信息的特征选择在入侵检测中的优化

基于标记相关性和ReliefF的多标记特征选择

混合mRMR和改进磷虾群的肿瘤基因特征选择算法