基于模糊C-均值聚类的缺失数据填充方法

doi:10.13438/j.cnki.jdzk.2020.02.006

吉首大学学报（自然科学版）

基于模糊C-均值聚类的缺失数据填充方法

黄紫成，李影

（仰恩大学工程技术学院，福建泉州 362014）

出版日期:2020-03-25 发布日期:2020-09-08
作者简介:黄紫成（1984—），男，福建泉州人，仰恩大学工程技术学院讲师，硕士，主要从事机器学习、粗糙集研究.
基金资助:
福建省中青年教师教育科研项目（JT180671）；福建省科技厅软科学项目(2018R0097)

Missing Value Filling Method Based on Fuzzy C-Means Algorithm

HANG Zicheng, LI Ying

(College of Engineering Technology, Yang-En University, Quanzhou 362014, Fujian China)

Online:2020-03-25 Published:2020-09-08

摘要/Abstract

摘要：

针对缺失数据的有效填充问题，提出利用模糊C-均值聚类（FCM）算法的隶属度矩阵作为待填数据的加权权重.首先使用同一属性均值对缺失数据作预填充，再进行FCM以得到每个类别的隶属度矩阵，最后用该矩阵作为权重去乘以每个类别的属性均值，得到最终的填充数据.在UCI数据实验中，将FCM填充算法与k近邻（KNN）填充算法作对比分析，结果表明，FCM填充得到的均方根误差总体小于KNN填充.

关键词： 缺失数据, 模糊C-均值聚类, 隶属度矩阵, k近邻

Abstract:

For effective missing data filling, the membership matrix of fuzzy C-means algorithm is proposed as the weighted weight of the data to be filled in. Firstly, the missing data is pre-filled with the same attribute mean, then the membership matrix of each category is obtained by means of fuzzy C-means algorithm. Finally, the matrix is used as the weight to multiply the attribute mean of each category as the final filling data. In the UCI data experiment, compared with the KNN filling, the results show that the error in the method based on the fuzzy C-means algorithm filling is smaller than in the KNN filling.

Key words: missing value, fuzzy C-means algorithm, membership matrix, k-nearest neighbor

黄紫成，李影. 基于模糊C-均值聚类的缺失数据填充方法[J]. 吉首大学学报（自然科学版）, DOI: 10.13438/j.cnki.jdzk.2020.02.006.

HANG Zicheng, LI Ying. Missing Value Filling Method Based on Fuzzy C-Means Algorithm[J]. Journal of Jishou University（Natural Sciences Edition), DOI: 10.13438/j.cnki.jdzk.2020.02.006.

参考文献

[1] LIU Zhunga, PAN Quan, DEZERT JEAN, et al. Adaptive Imputation of Missing Values for Incomplete Pattern Classification[J]. Pattern Recognition, 2016, 52(2): 85-95.
[2] XUE Wenzhuo, HUI Li, PENG Yanguo, et al. Secure k Nearest Neighbors Query for High-Dimensional Vectors in Outsourced Environments[J]. IEEE Transactions on Big Data, 2018, 4(4): 586-599.
[3] WANG Jianmin, SONG Shaoxu, ZHU Xiaochen, et al. Efficient Recovery of Missing Events[J]. IEEE Transactions on Knowledge & Data Engineering, 2016, 28(11): 2943-2957.
[4] 谢霖铨,赵楠,徐浩,等.基于属性相关性的KNN近邻填补算法改进[J].江西理工大学学报,2019,40(1):95-101.
[5] 郝胜轩,宋宏,周晓锋.基于近邻噪声处理的KNN缺失数据填补算法[J].计算机仿真,2014,31(7):264-268.
[6] 杨涛,骆嘉伟,王艳,等.基于马氏距离的缺失值充填算法[J].计算机应用,2005,25(12):2868-2871.
[7] 马永军,汪睿,李亚军,等.利用聚类分析和离群点检测的数据填补方法[J].计算机工程与设计,2019,40(3):744-747;761.
[8] 李国和,杨绍伟,吴卫江,等.基于聚类的连续型数据缺失值充填方法[J].计算机工程,2019,45(9):32-39.
[9] 贺丹，陈松灿.基于凸差规划的不完整数据填充聚类[J].模式识别与人工智能，2017，30(1):81-88.
[10] PAN Ruilin, YANG Tingsheng, CAO Jianhua, et al. Missing Data Imputation By K Nearest Neighbors Based on Grey Relational Structure and Mutual Information[J]. Applied Intelligence, 2015, 43(3): 614-632.
[11] ZHANG Shichao. Nearest Neighbor Selection for Iteratively KNN Imputation[J]. Journal of Systems and Software, 2012, 85(11): 2541-2552.
[12] WANG CODE.K-Means聚类算法和模糊C-Means聚类算法[EB/OL].(2018-02-05)[2019-06-12].https:∥blog.csdn.net/wzl1997/article/details/79264560.
[13] YAN Dandan, YANG Youlong, LI Benhong. An Improved Fuzzy Classifier for Imbalanced Data[J]. Pattern Recognition, 2017, 32(3): 2315-2325.
[14] WU Shaochun, PANG Yijie, SHAO Sen, et al. Advanced Fuzzy C-Means Algorithm Based on Local Density and Distance[J]. Journal of Shanghai Jiaotong University (Science), 2018, 23(5): 636-642.

基于模糊C-均值聚类的缺失数据填充方法

Missing Value Filling Method Based on Fuzzy C-Means Algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价