南京大学学报(自然科学版) ›› 2021, Vol. 57 ›› Issue (2): 262–271.doi: 10.13232/j.cnki.jnju.2021.02.011

• • 上一篇    

基于合理粒度的局部邻域决策粗糙计算方法

孙颖, 蔡天使, 张毅, 鞠恒荣, 丁卫平()   

  1. 南通大学信息科学技术学院，南通，226019
  • 收稿日期:2020-10-19 出版日期:2021-03-23 发布日期:2021-03-23
  • 通讯作者: 丁卫平 E-mail:dwp9988@163.com
  • 作者简介:E⁃mail：dwp9988@163.com
  • 基金资助:
    国家自然科学基金(62006128);江苏省自然科学基金(BK20191445);江苏省双创博士计划，江苏省研究生科研与实践创新计划(SJCX20_1150);江苏省大学生创新训练项目(202010304023Z);南通大学人才引进项目(03081198);江苏高校“青蓝工程”，江苏省高等学校自然科学研究面上项目(20KJB520009);南通市科技计划项目(JC2020141)

Justifiable granularity based local neighborhood decision⁃theoretic rough set approach

Ying Sun, Tianshi Cai, Yi Zhang, Hengrong Ju, Weiping Ding()   

  1. School of Information Science and Technology，Nantong University，Nantong，226019，China
  • Received:2020-10-19 Online:2021-03-23 Published:2021-03-23
  • Contact: Weiping Ding E-mail:dwp9988@163.com

RichHTML

16450

PDF (PC)

866

摘要：

信息粒度和近似方法是粗糙集理论进行数据描述的两个关键.现实中数据分布情况复杂多变，现有的模型缺乏对不同数据区域进行区分的能力，且易受到异常数据的干扰，导致最终分类决策的失误.为此提出基于合理粒度的局部邻域决策粗糙集模型.首先，根据邻域中对象的个数和类别识别一些极端情况（例如离群点和标签噪声点），分别给出不同分布情况下数据点的粗糙隶属度；其次，为已识别的标签噪声数据提供一组伪标记，用伪标记对原始标签进行修正；最后引入合理粒度准则，构造由信息覆盖性函数和特殊性函数融合的新的评估标准，并通过粒子群优化算法对其进行优化，得到最佳邻域半径.实验结果表明，该方法为复杂数据处理提供了一种有效的解决方案.

关键词: 合理粒度, 异常数据, 粒子群优化算法, 局部邻域决策粗糙集模型

Abstract:

Justifiable information granularity and feasible approximation methods are the two basic keys of rough set data description. In reality，the data distribution is complex and diverse，and the existing models cannot correctly classify the data in high?density areas and sparse?density areas，as well as label noise data，resulting in final decision errors. In this regard，this paper proposes a rough set model of neighborhood decision based on justifiable granularity. Firstly，according to the number and categories of objects in the neighborhood，some extreme cases are identified，such as outliers and label noise data，and the rough membership of data under different distributions is given. Secondly，a set of pseudo?labels are provided for the identified label noise data，and the original labels are corrected with the pseudo?labels. Finally，the principle of justifiable granularity is introduced，and a new evaluation standard combining information coverage and specificity is established. The particle swarm algorithm is used to optimize it to obtain the best neighborhood radius. Experimental results show that this method provides an effective solution for complex data processing.

Key words: justifiable granularity, abnormal data, particle swarm optimization algorithm, local neighborhood decision rough set model

中图分类号: 

  • TP18

图1

几种数据分布情况"

图2

不同的邻域粒度选择"

表1

风机齿轮箱运行状态信息表"

编号C1C2C3D
x10.560.420.03正常
x20.520.430.04正常
x30.980.040.56非正常
x40.990.020.53非正常
x50.140.030.15非正常
x60.880.120.46正常
x70.830.090.54非正常
x80.650.530.03正常
x90.480.410.02正常
x100.910.110.49非正常

表2

六个UCI数据集的描述"

序号数据集名称样本属性决策
1BA137252
2Cardiotocography21262310
3Glass Identification214107
4Ionosphere351342
5Sonar208602
6WDBC569312

图3

本文算法在六个UCI数据集上不同噪声比下的近似质量比较"

图4

本文算法在六个UCI数据集上在不同噪声比下的NN比较"

1 Pawlak Z. Rough sets. International Journal of Computer and Information Sciences，1982，11(5)：341-356.
2 Pawlak Z，Wong S K M，Ziarko W. Rough sets：Probabilistic versus deterministic approach. International Journal of Man?Machine Studies，1988，29(1)：81-95.
3 Yao Y Y，Wong S K M. A decision theoretic framework for approximating concepts. International Journal of Man?Machine Studies，1992，37(6)：793-809.
4 Yao Y Y. Three?way decisions with probabilistic rough sets. Information Sciences，2010，180(3)：341-353.
5 Li W W，Huang Z Q，Jia X Y，et al. Neighborhood based decision?theoretic rough set models. International Journal of Approximate Reasoning，2016，69：1-17.
6 Qian Y H，Liang X Y，Wang Q，et al. Local rough set：A solution to rough data analysis in big data. International Journal of Approximate Reasoning，2018，97：38-63.
7 Wang Q，Qian Y H，Liang X Y，et al. Local neighborhood rough set. Knowledge?Based Systems，2018，153：53-64.
8 Qian Y H，Liang X Y，Lin G P，et al. Local multigranulation decision?theoretic rough sets. International Journal of Approximate Reasoning，2017，82：119-137.
9 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. Knowledge?Based Systems，2020，192：105373.
10 Yang X B，Liang S C，Yu H L，et al. Pseudo?label neighborhood rough set：measures and attribute reductions. International Journal of Approximate Reasoning，2019，105：112-129.
11 Hu Q H，Liu J F，Yu D R. Mixed feature selection based on granulation and approximation. Knowledge?Based Systems，2008，21(4)：294-304.
12 Hu Q H，Yu D R，Liu J F，et al. Neighborhood rough set based heterogeneous feature subset selection. Information Sciences，2008，178(18)：3577-3594.
13 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. 软件学报，2008，19(3)：640-649.
Hu Q H，Yu D R，Xie Z X. Numerical attribute reduction based on neighborhood granulation and rough approximation. Journal of Software，2008，19(3)：640-649.
14 Ouyang T H，Pedrycz W，Pizzi N J. Record linkage based on a three?way decision with the use of granular descriptors. Expert Systems with Applications，2019，122：16-26.
15 Wang C Z，Shi Y P，Fan X D，et al. Attribute reduction based on k?nearest neighborhood rough sets. International Journal of Approximate Reasoning，2019，106：18-31.
16 Pedrycz W，Homenda W. Building the fundamentals of granular computing：a principle of justifiable granularity. Applied Soft Computing，2013，13(10)：4209-4218.
17 Ju H R，Pedrycz W，Li H X，et al. Sequential three?way classifier with justifiable granularity. Knowledge?Based Systems，2019，163：103-119.
18 Zhang B W，Pedrycz W，Wang X M，et al. Design of interval type?2 information granules based on the principle of justifiable granularity. IEEE Transactions on Fuzzy Systems，2020，doi：10.1109/TFUZZ.2020.3023758.
19 Fu C，Lu W，Pedrycz W，et al. Fuzzy granular classification based on the principle of justifiable granularity. Knowledge?Based Systems，2019，170：89-101.
20 Venter G，Sobieszczanski?Sobieski J. Particle swarm optimization. AIAA Journal，2003，41(8)：1583-1589.
21 Hu X H，Cercone N. Learning in relational databases：a rough set approach. Computational Intelligence，1995，11(2)：323-338.
22 胡建秀，曾建潮. 微粒群算法中惯性权重的调整策略. 计算机工程，2007，33(11)：193-195.
Hu J X，Zeng J C. Selection on inertia weight of particle swarm optimization. Computer Engineering，2007，33(11)：193-195.
[1] 李子龙,周勇,鲍蓉. AdaBoost图像到类距离学习的图像分类方法[J]. 南京大学学报(自然科学版), 2020, 56(1): 51-56.
[2] 吴家豪1，彭志平2*，崔得龙2，李启锐2，何杰光2. 基于多Agent系统的粒子群遗传优化云工作流调度算法[J]. 南京大学学报(自然科学版), 2017, 53(6): 1114-.
[3] 周文猛1，杨一品1，周余1，于耀1，金苏文2，都思丹1*. 基于Kinect的无标记手部姿态估计系统[J]. 南京大学学报(自然科学版), 2015, 51(2): 297-.
[4]   韩飞**，杨春生，刘清 .  一种改进的基于梯度搜索的粒子群优化算法*[J]. 南京大学学报(自然科学版), 2013, 49(2): 196-201.
[5]  刘杨1，田学锋2，詹志辉1**
.  粒子群优化算法惯量权重控制方法的研究*
[J]. 南京大学学报(自然科学版), 2011, 47(4): 364-371.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!

版权所有 © 2021 《南京大学学报(自然科学)》

地址：江苏省南京市鼓楼区汉口路22号，南京大学学报编辑部，210093

电话：025-83592704 , 传真：025-83592704        技术支持：北京玛格泰克科技发展有限公司