您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2026, Vol. 56 ›› Issue (1): 35-48.doi: 10.6040/j.issn.1672-3961.0.2024.200

• 机器学习与数据挖掘 • 上一篇    

基于数据权重的鲁棒性模糊粗糙集与属性约简

李璐1,王鑫2   

  1. 1.安徽建筑大学数理学院, 安徽 合肥 230601;2.安徽建筑大学经济与管理学院, 安徽 合肥 230601
  • 发布日期:2026-02-03
  • 作者简介:李璐(1980— ),女,副教授,硕士,主要研究方向为数据挖掘、粗糙集. E-mail:lilu@ahjzu.edu.cn
  • 基金资助:
    安徽省高校省级自然科学研究项目基金资助项目(KJ2021JD20)

Robust fuzzy rough set and attribute reduction based on data weights

LI Lu1, WANG Xin2   

  1. LI Lu1, WANG Xin2(1. School of Mathematics and Physics, Anhui Jianzhu University, Hefei 230601, Anhui, China;
    2. School of Economics and Management, Anhui Jianzhu University, Hefei 230601, Anhui, China
  • Published:2026-02-03

PDF (PC)

5

摘要： 提出一种鲁棒性模糊粗糙集模型和属性约简算法。考虑数据样本的局部密度并进行量化,利用量化结果评估样本在数据集整体中的噪声程度;通过噪声程度衡量样本的权重,定义一种样本集之间的距离度量,并将样本之间的模糊相似性替换为样本集之间的模糊相似性,提升模糊相似关系的鲁棒性,建立一种鲁棒性模糊粗糙集模型;基于所提出的鲁棒性模糊粗糙集定义属性与类之间的依赖度,以评估属性子集的显著性,并设计一种鲁棒性模糊粗糙集的属性约简算法。试验结果表明,所设计的属性约简算法比现有的算法具有更强的鲁棒性和优越性。

关键词: 模糊粗糙集, 鲁棒性, 噪声数据, 样本权重, 模糊依赖度, 属性约简

Abstract: A robust fuzzy rough set model and attribute reduction algorithm were proposed in this paper. This article considered the local density of data samples and quantifies them, using the quantization results to evaluate the noise level of the samples in the overall dataset. The weight of the samples was measured by the level of noise, and a distance measure between sample sets was defined. The fuzzy similarity between samples was replaced by the fuzzy similarity between sample sets, which improved the robustness of the fuzzy similarity and established a robust fuzzy rough set model. Based on the proposed robust fuzzy rough set, the dependency between attributes and classes was defined to evaluate the significance of attribute subsets, and a robust fuzzy rough set attribute reduction algorithm was designed. The experimental results showed that the designed attribute reduction algorithm had stronger robustness and superiority than existing algorithms.

Key words: fuzzy rough set, robustness, noise data, sample weight, fuzzy dependency degree, attribute reduction

中图分类号: 

  • TP181
[1] 宋苏洋, 叶军, 曾广财, 等. 基于优化可辨识矩阵的多粒度粗糙集属性约简算法[J]. 山东大学学报(理学版), 2024, 59(5): 52-62. SONG Suyang, YE Jun, ZENG Guangcai, et al.Multi-granularity rough set attribute reduction algorithm based on optimized discernibility matrix[J]. Journal of Shandong University(Natural Science), 2024, 59(5): 52-62.
[2] YANG J, QIN X D, WANG G Y, et al. Attribute reduction for hierarchical classification based on improved fuzzy rough set[J]. Information Sciences, 2024, 677: 120900.
[3] CHEN Y P, DING W P, JU H R, et al. A distributed attribute reduction based on neighborhood evidential conflict with Apache Spark[J]. Information Sciences, 2024, 668: 120521.
[4] CUI S G, LI G S, SANG B B, et al. Distance metric learning-based multi-granularity neighborhood rough sets for attribute reduction[J]. Applied Soft Computing, 2024, 159: 111656.
[5] DUBOIS D, PRADE H. Rough fuzzy sets and fuzzy rough sets[J]. International Journal of General Systems, 1990, 17(2/3): 191-209.
[6] KOU G, YANG P, PENG Y, et al. Evaluation of feature selection methods for text classification with small datasets using multiple criteria decision-making methods[J]. Applied Soft Computing, 2020, 86: 105836.
[7] HU Q H, ZHANG L, AN S, et al. On robust fuzzy rough set models[J]. IEEE Transactions on Fuzzy Systems, 2012, 20(4): 636-651.
[8] WANG C Y, WAN L J. New results on granular variable precision fuzzy rough sets based on fuzzy(co)implications[J]. Fuzzy Sets and Systems, 2021, 423: 149-169.
[9] AN S, HU Q H, WANG C Z. Probability granular distance-based fuzzy rough set model[J]. Applied Soft Computing, 2021, 102: 107064.
[10] WANG C Z, HUANG Y, SHAO M W, et al. Fuzzy rough set-based attribute reduction using distance measures[J]. Knowledge-Based Systems, 2019, 164: 205-212.
[11] YANG X L, CHEN H M, LI T R, et al. A noise-aware fuzzy rough set approach for feature selection[J]. Knowledge-Based Systems, 2022, 250: 109092.
[12] ZHANG X H, OU Q Q, WANG J Q. Variable precision fuzzy rough sets based on overlap functions with application to tumor classification[J]. Information Sciences, 2024, 666: 120451.
[13] ZOU D D, XU Y L, LI L Q, et al. Novel variable precision fuzzy rough sets and three-way decision model with three strategies[J]. Information Sciences, 2023, 629: 222-248.
[14] LIANG P, LEI D F, CHIN K S, et al. Feature selection based on robust fuzzy rough sets using kernel-based similarity and relative classification uncertainty measures[J]. Knowledge-Based Systems, 2022, 255: 109795.
[15] SANG B B, CHEN H M, WAN J H, et al. Self-adaptive weighted interaction feature selection based on robust fuzzy dominance rough sets for monotonic classification[J]. Knowledge-Based Systems, 2022, 253(11): 109523.
[16] BAI H X, JING J H, LI D Y, et al. A fuzzy rough sets-based data-driven approach for quantifying local and overall fuzzy relations between variables for spatial data[J]. Applied Soft Computing, 2024, 162: 111848.
[17] THEERENS A, CORNELIS C. On the granular representation of fuzzy quantifier-based fuzzy rough sets[J]. Information Sciences, 2024, 665: 120385.
[18] SHU T X, LIN Y J, GUO L. Online hierarchical streaming feature selection based on adaptive neighborhood rough set[J]. Applied Soft Computing, 2024, 152: 111276.
[19] WANG Z H, CHEN H M, YANG X L, et al. Fuzzy rough dimensionality reduction: a feature set partition-based approach[J]. Information Sciences, 2023, 644: 119266.
[1] 邱利芹,王磊,于越,孙雅慧. 知识粒度视角下区间值决策信息系统的增量式属性约简[J]. 山东大学学报 (工学版), 2025, 55(6): 45-57.
[2] 陈宝国,邓明,陈金林. 基于权重邻域熵的数值型信息系统属性约简算法[J]. 山东大学学报 (工学版), 2024, 54(1): 33-44.
[3] 季雨瑄,叶军,杨震宇,敖家欣,王磊. 结合分辨矩阵改进的邻域粗糙集属性约简算法[J]. 山东大学学报 (工学版), 2022, 52(4): 99-109.
[4] 王一宾,李田力,程玉胜,钱坤. 基于核极限学习机自编码器的标记分布学习[J]. 山东大学学报 (工学版), 2020, 50(3): 58-65.
[5] 王换,周忠眉. 一种基于聚类的过抽样算法[J]. 山东大学学报(工学版), 2018, 48(3): 134-139.
[6] 侯明冬,王印松,田杰. 积分时滞对象的一种内模PID鲁棒控制方法[J]. 山东大学学报(工学版), 2016, 46(5): 64-67.
[7] 景运革,李天瑞. 基于知识粒度的增量约简算法[J]. 山东大学学报(工学版), 2016, 46(1): 1-9.
[8] 张井岗,马文廷,赵志诚. 串级时滞过程的二自由度Smith预估控制[J]. 山东大学学报 (工学版), 2015, 45(5): 43-50.
[9] 辛丽玲, 何威, 于剑, 贾彩燕. 一种基于密度差异的离群点检测算法[J]. 山东大学学报(工学版), 2015, 45(3): 7-14.
[10] 葛凯蓉, 常发亮, 董文会. 基于局部敏感直方图的稀疏表达跟踪算法[J]. 山东大学学报(工学版), 2014, 44(5): 14-19.
[11] 谢志华. 一种新的血流建模方法及其在红外人脸识别中的应用[J]. 山东大学学报(工学版), 2013, 43(5): 1-5.
[12] 施珺,朱敏. 一种基于灰色系统和支持向量机的预测优化模型[J]. 山东大学学报(工学版), 2012, 42(5): 7-11.
[13] 赵占山1,2, 张静3, 孙连坤1, 丁刚1. 有限时间收敛的滑模自适应控制器设计[J]. 山东大学学报(工学版), 2012, 42(4): 74-78.
[14] 翟俊海,高原原,王熙照,陈俊芬. 基于划分子集的属性约简算法[J]. 山东大学学报(工学版), 2011, 41(4): 24-28.
[15] 周长辉1, 胡永健2,余绍鹏1. 鲁棒的源扫描仪辨识算法设计[J]. 山东大学学报(工学版), 2011, 41(2): 62-65.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发