自适应半径选择的近邻邻域分类器

doi:10.16451/j.cnki.issn1003-6059.202211004

摘要
图/表
参考文献(0)
相关文章 (10)

全文: PDF (738 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

在邻域粗糙集中,邻域分类器简单高效.然而,邻域半径作为决定邻域分类器分类性能的关键因素,构建方式存在不足.一方面,邻域半径的构建由于未经过训练过程而缺乏通用性;另一方面,当数据样本分布不均出现空邻域时可导致分类器失效.针对上述问题,文中提出自适应半径选择的近邻邻域分类器(Near Neighborhood Classifier with Adaptive Radius Selection, NNC-AR).首先,基于K近邻算法为训练样本构建训练邻域半径.然后,为了克服传统方法选取邻域半径参数的主观性,对待测试样本定义自适应的近邻邻域半径.最后,为分类器失效的部分测试样本定义新的近似邻域半径,有效提升分类器的泛化能力.实验表明,NNC-AR的F1值和分类精度均较高.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张清华
	肖嘉瑜
	艾志华
	王国胤

关键词 ：邻域粗糙集, 邻域分类器, 邻域半径, 自适应半径

Abstract：

In neighborhood rough sets, the neighborhood classifier is an intuitive and effective classification method in data mining. However, the neighborhood radius, as a key factor to determine the classification performance of the neighborhood classifier, has some defects in construction. The construction of the neighborhood radius is not universal due to the lack of the training stage. When the data samples are not uniformly distributed and then empty neighborhoods appear, the classifier fails. Aiming at these problems, a near neighborhood classifier with adaptive radius selection(NNC-AR) is proposed. Firstly, for training samples, a training neighborhood radius based on K-nearest neighbor is defined. For test samples, an adaptive neighborhood radius is defined to overcome the subjectivity of the artificial parameter in the traditional neighborhood radius. Finally, for the test samples with classifier failure, an approximate neighborhood radius is defined to improve the generalization ability of the classifier. The experimental results show that the F1 score and classification accuracy of NNC-AR model are significantly improved.

Key words： Key Words Neighborhood Rough Set Neighborhood Classifier Neighborhood Radius Adaptive Radius

收稿日期: 2022-09-29

ZTFLH:

TP 18

基金资助:

国家重点研发计划项目(No.2020YFC2003502)、国家自然科学基金项目(No.62276038)资助

通讯作者: 张清华,博士,教授,主要研究方向为粗糙集、模糊集、粒计算、三支决策等.E-mail:zhangqh@cqupt.edu.cn.

作者简介: 肖嘉瑜,硕士研究生,主要研究方向为智能信息处理、数据挖掘.E-mail:xiaojiayuhhh@163.com.艾志华,硕士研究生,主要研究方向为智能信息处理、数据挖掘.E-mail:azh15213138308@163.com.王国胤,博士,教授,主要研究方向为粗糙集、粒计算、认知计算、数据挖掘、智能信息处理等.E-mail:wanggy@cqupt.edu.cn.

引用本文:

张清华, 肖嘉瑜, 艾志华, 王国胤. 自适应半径选择的近邻邻域分类器[J]. 模式识别与人工智能, 2022, 35(11): 989-998. ZHANG Qinghua, XIAO Jiayu, AI Zhihua, WANG Guoyin. Near Neighborhood Classifier with Adaptive Radius Selection. Pattern Recognition and Artificial Intelligence, 2022, 35(11): 989-998.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202211004 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2022/V35/I11/989

[1] PAWLAK Z. Rough Sets. International Journal of Computer and Information Sciences, 1982, 11(5): 341-356.
[2] WEI W, LIANG J Y.Information Fusion in Rough Set Theory: An Overview. Information Fusion, 2019, 48: 107-118.
[3] 杨洁,王国胤,张清华,等.多粒度云模型的相似性度量.模式识别与人工智能, 2018, 31(8): 677-692.
(YANG J, WANG G Y, ZHANG Q H, et al. Similarity Measure of Multi-granularity Cloud Model. Pattern Recognition and Artificial Intelligence, 2018, 31(8): 677-692.)
[4] 邓大勇,姚坤,肖春水.全粒度粗糙集的不确定性.模式识别与人工智能, 2018, 31(9): 809-815.
(DENG D Y, YAO K, XIAO C S.Uncertainty of Entire-Granulation Rough Sets. Pattern Recognition and Artificial Intelligence, 2018, 31(9): 809-815.)
[5] 王佳琪,苗夺谦,张红云.基于可变多粒度概率粗糙集的分类模型.模式识别与人工智能, 2017, 30(8): 710-717.
(WANG J Q, MIAO D Q, ZHANG H Y.Classification Model Based on Variable Multi-granulation Probabilistic Rough Set. Pattern Recognition and Artificial Intelligence, 2017, 30(8): 710-717.)
[6] AGGARWAL M.Rough Information Set and Its Applications in Decision Making. IEEE Transactions on Fuzzy Systems, 2017, 25(2): 265-276.
[7] DONG H B, LI T, DING R, et al. A Novel Hybrid Genetic Algorithm with Granular Information for Feature Selection and Optimization. Applied Soft Computing, 2018, 65: 33-36.
[8] SHE Y H, HE X L, SHI H X, et al. A Multiple-Valued Logic Approach for Multigranulation Rough Set Model. International Journal of Approximate Reasoning, 2017, 82: 270-284.
[9] YAO Y Y, ZHANG X Y. Class-Specific Attribute Reducts in Rough Set Theory. Information Sciences, 2017, 418/419: 601-618.
[10] 梁美社,米据生,侯成军,等.基于局部广义多粒度粗糙集的多标记最优粒度选择.模式识别与人工智能, 2019, 32(8): 718-725.
(LIANG M S, MI J S, HOU C J, et al. Optimal Granulation Selection for Multi-label Data Based on Local Generalized Multi-granulation Rough Set. Pattern Recognition and Artificial Intelligence, 2019, 32(8): 718-725.)
[11] BAI H X, LI D Y, GE Y, et al. Spatial Rough Set-Based Geographical Detectors for Nominal Target Variables. Information Sciences, 2022, 586: 525-539.
[12] 陈玉洪,张清华,杨洁.基于区间阴影集的密度峰值聚类算法.模式识别与人工智能, 2019, 32(6): 531-544.
(CHEN Y H, ZHANG Q H, YANG J.Density Peak Clustering Algorithm Based on Interval Shadowed Sets. Pattern Recognition and Artificial Intelligence, 2019, 32(6): 531-544.)
[13] WU C Y, ZHANG Q H, CHENG Y L, et al. Novel Three-Way Generative Classifier with Weighted Scoring Distribution. Information Sciences, 2021, 579: 732-750.
[14] ZHANG Q H, CHENG Y L, ZHAO F, et al. Optimal Scale Combination Selection Integrating Three-Way Decision with Hasse Diagram. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(8): 3675-3689.
[15] ZHANG Q H, YANG C C, WANG G Y.A Sequential Three-Way Decision Model with Intuitionistic Fuzzy Numbers. IEEE Tran-sactions on Systems, Man, and Cybernetics(Systems), 2021, 51(5): 2640-2652.
[16] 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.
[17] DAI J H, HU Q H, HU H, et al. Neighbor Inconsistent Pair Selection for Attribute Reduction by Rough Set Approach. IEEE Transactions on Fuzzy Systems, 2018, 26(2): 937-950.
[18] LIU K Y, YANG X B, FUJITA H, et al. An Efficient Selector for Multi-granularity Attribute Reduction. Information Sciences, 2019, 505: 457-472.
[19] YANG J L, YAO Y Y.A Three-Way Decision Based Construction of Shadowed Sets from Atanassov Intuitionistic Fuzzy Sets. Information Sciences, 2021, 577: 1-21.
[20] HU Q H, ZHANG L J, ZHOU Y C, et al. Large-Scale Multimodality Attribute Reduction with Multi-kernel Fuzzy Rough Sets. IEEE Transactions on Fuzzy Systems, 2018, 26(1): 226-238.
[21] ZHANG Q H, ZHANG P, WANG G Y.Research on Approximation Set of Rough Set Based on Fuzzy Similarity. Journal of Intelligent and Fuzzy Systems, 2017, 32(3): 2549-2562.
[22] ZHANG Q H, AI Z H, ZHANG J Z, et al. A Novel Fast Constructing Neighborhood Covering Algorithm for Efficient Classification. Knowledge-Based Systems, 2021, 225. DOI: 10.1016/j.knosys.2021.107104.
[23] 孙林,黄金旭,徐久成,等.基于自适应鲸鱼优化算法和容错邻域粗糙集的特征选择算法.模式识别与人工智能, 2022, 35(2): 150-165.
(SUN L, HUANG J X, XU J C, et al. Feature Selection Based on Adaptive Whale Optimization Algorithm and Fault-Tolerance Neighborhood Rough Sets. Pattern Recognition and Artificial Intelligence, 2022, 35(2): 150-165.)
[24] 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.)
[25] 胡清华,赵辉,于达仁.基于邻域粗糙集的符号与数值属性快速约简算法.模式识别与人工智能, 2008, 21(6): 732-738.
(HU Q H, ZHAO H, YU D R.Efficient Symbolic and Numerical Attribute Reduction with Neighborhood Rough Sets. Pattern Recognition and Artificial Intelligence, 2008, 21(6): 732-738.)
[26] 徐波,张贤勇,冯山.邻域粗糙集的加权依赖度及其启发式约简算法.模式识别与人工智能, 2018, 31(3): 256-264.
(XU B, ZHANG X Y, FENG S.Weighted Dependence of Neighborhood Rough Sets and Its Heuristic Reduction Algorithm. Pattern Recognition and Artificial Intelligence, 2018, 31(3): 256-264.)
[27] WANG C Z, HUANG Y, SHAO M W, et al. Feature Selection Based on Neighborhood Self-Information. IEEE Transactions on Cybernetics, 2020, 50(9): 4031-4042.
[28] 夏鸿斌,陆炜,刘渊.基于异构邻域聚合的协同过滤推荐算法.模式识别与人工智能, 2021, 34(8): 712-722.
(XIA H B, LU W, LIU Y.Collaborative Filtering with Heterogeneous Neighborhood Aggregation. Pattern Recognition and Artificial Intelligence, 2021, 34(8): 712-722.)
[29] YUE X D, CHEN Y F, MIAO D Q, et al. Fuzzy Neighborhood Covering for Three-Way Classification. Information Sciences, 2020, 507: 795-808.
[30] 薛占熬,司小朦,袁艺林,等.多粒度邻域粗糙直觉模糊集模型.模式识别与人工智能, 2017, 30(1): 11-20.
(XUE Z A, SI X M, YUAN Y L, et al. Model of Multi-granulation Neighborhood Rough Intuitionistic Fuzzy Sets. Pattern Recognition and Artificial Intelligence, 2017, 30(1): 11-20.)
[31] WANG C Z, HU Q H, WANG X Z, et al. Feature Selection Based on Neighborhood Discrimination Index. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(7): 2986-2999.
[32] 白盛兴,林耀进,王晨曦,等.基于邻域粗糙集的大规模层次分类在线流特征选择.模式识别与人工智能, 2019, 32(9): 811-820.
(BAI S X, LIN Y J, WANG C X, et al. Large-Scale Hierarchical Classification Online Streaming Feature Selection Based on Neighborhood Rough Set. Pattern Recognition and Artificial Intelligence, 2019, 32(9): 811-820.)
[33] HU Q H, YU D R, XIE Z X. Neighborhood Classifiers. Expert Systems with Applications, 2008, 34(2): 866-876.
[34] 徐苏平,杨习贝,于化龙,等.一种基于邻域协同表达的分类方法.计算机科学, 2017, 44(9): 234-238.
(XU S P, YANG X B, YU H L, et al. Neighborhood Collaborative Representation Based Classification Method. Computer Science, 2017, 44(9): 234-238.)
[35] 亓慧,杨习贝,史颖.一种扩充粒化的序列邻域分类方法.山西大学学报(自然科学版), 2020, 43(4): 885-889.
(QI H, YANG X B, SHI Y.An Expanded Granulation Based Sequential Neighborhood Classification Method. Journal of Shanxi University(Natural Science Edition), 2020, 43(4): 885-889.)
[36] RAO X S, SONG J J, YANG X B, et al. Neighborhood Classifier for Label Noise // Proc of the International Conference on Machine Learning and Cybernetics. Washington, USA: IEEE, 2019. DOI: 10.1109/ICMLC48188.2019.8949200.
[37] KUMAR S U, INBARANI H H.A Novel Neighborhood Rough Set Based Classification Approach for Medical Diagnosis. Procedia Computer Science, 2015, 47: 351-359.
[38] WANG Y D, PAN Z B, PAN Y W.A Training Data Set Cleaning Method by Classification Ability Ranking for the k-Nearest Neighbor Classifier. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(5): 1544-1556.
[39] KIM K.Normalized Class Coherence Change-Based kNN for Cla-ssification of Imbalanced Data. Pattern Recognition, 2021, 120. DOI: 10.1016/j.patcog.2021.108126.
[40] XIAO J Y, ZHANG Q H, AI Z H, et al. A Fast Neighborhood Classifier Based on Hash Bucket with Application to Medical Diagnosis. International Journal of Approximate Reasoning, 2022, 148: 177-132.
[41] WILSON D R, MARTINEZ T R.Improved Heterogeneous Distance Functions. Journal of Artificial Intelligence Research, 1997, 6: 1-34.