您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（理学版）》

《山东大学学报(理学版)》 ›› 2020, Vol. 55 ›› Issue (3): 107-112.doi: 10.6040/j.issn.1671-9352.4.2019.192

• • 上一篇    

分段二次方转换函数驱动的高斯核模糊C均值聚类

唐益明1,2*,张征1,芦启明1   

  1. 合肥工业大学 1.计算机与信息学院, 2.情感计算与先进智能机器安徽省重点实验室, 安徽 合肥 230601
  • 发布日期:2020-03-27
  • 作者简介:唐益明(1982— ),男,博士,副研究员,研究方向为机器学习、情感计算、图像处理. E-mail:tym608@163.com*通信作者
  • 基金资助:
    国家自然科学基金资助项目(61673156,61432004,U1613217,61672202);中国博士后科学基金资助项目(2014T70585);安徽省自然科学基金资助项目(1408085MKL15,1508085QF129);国家“863”高技术研究发展计划资助项目(2012AA011103)

Gaussian kernel fuzzy C-means clustering driven by piecewise quadratic transfer function

TANG Yi-ming1,2*, ZHANG Zheng1, LU Qi-ming1   

  1. 1. School of Computer and Information, 2. Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine, Hefei University of Technology, Hefei 230601, Anhui, China
  • Published:2020-03-27

PDF (PC)

503

摘要： 基于转换数据的模糊聚类算法存在转换模式单一、聚散效果不明显的问题,提出了分段二次方转换函数驱动的高斯核模糊C均值聚类算法。首先,通过分段二次方转换函数将原先分段线性数据转化的策略进行了相应的拓展,使数据转化的模式更加细腻,使得同类型的数据更好地聚集在一起,非同类型的数据进行远离。其次,我们引入了高斯核函数,将数据从低维空间映射到高维空间来进行聚类划分。最后,将这些集成到模糊聚类的框架之中,形成了所提算法。通过对比实验表明,所提算法明显优于相关的4种算法。

关键词: 模糊C均值聚类算法, 高斯核函数, 非线性数据转换, 二次方函数

Abstract: As for the fuzzy C-Means algorithm based on transformed data, whose conversion mode is single while the effect of non-distribution is not obvious. For these reasons, the Gaussian kernel fuzzy C-means algorithm driven by piecewise quadratic transfer function is proposed. Firstly, the strategy of transforming the original piecewise linear data is extended by the piecewise quadratic conversion function, which makes the data conversion mode more delicate, so that the same type of data is better gathered together, and different types of data keep away. Secondly, we introduce a Gaussian kernel function to map data from low-dimensional space to high-dimensional space for clustering. Finally, the piecewise quadratic conversion function and Gaussian kernel function are integrated into the framework of fuzzy clustering to form the proposed algorithm. The comparison experiments show that the proposed algorithm is significantly better than the related four algorithms.

Key words: fuzzy C-means clustering, Gaussian kernel, nonlinear data transformation, quadratic function

中图分类号: 

  • O159
[1] RATHORE P, KUMAR D, BEZDEK J C, et al. A rapid hybrid clustering algorithm for large volumes of high dimensional data[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(4):641-654.
[2] HUANG Dong, WANG Changdong, LAI Jianhuang. Locally weighted ensemble clustering[J]. IEEE Transactions on Cybernetics, 2018, 48(5):1460-1473.
[3] TANG Yiming, HU Xianghui, PEDRYCZ W, et al. DVPFCM: density viewpoint-induced possibilistic fuzzy C-means[J]. Neurocomputing, 2019, 329(1):407-423.
[4] DING Ruxi, WANG Xueqing, SHANG Kun, et al. Sparse representation-based intuitionistic fuzzy clustering approach to find the group intra-relations and group leaders for large-scale decision making[J]. IEEE Transactions on Fuzzy Systems, 2019, 27(3):559-573.
[5] TANG Yiming, YANG Xuezhi, LIU Xiaoping et al. Double fuzzy implications-based restriction inference algorithm[J]. Iranian Journal of Fuzzy Systems, 2015, 12(6):17-40.
[6] TANG Yiming, LIU Xiaoping. Differently implicational universal triple I method of(1, 2, 2)type[J]. Computers & Mathematics with Applications, 2010, 59(6):1965-1984.
[7] DUNN J C. A fuzzy relative of the ISO DATA process and its use in detecting compact well-separated clusters[J]. Journal of Cybernetics and Systems, 1973, 3(3):33-57.
[8] BEZDEK J C. Pattern recognition with fuzzy objective function algorithms[M]. New York: Plenum Press, 1981.
[9] KELLER J M, KRISHNAPURAM R. A possibilistic approach to clustering[J]. IEEE Transactions on Fuzzy Systems, 1993, 1(2):98-110.
[10] ZHANG Jiangshe, LEUNG Yiuwing.Improved possibilistic C-means clustering algorithms[J]. IEEE Transaction on Fuzzy Systems, 2004, 12(2):209-217.
[11] PAL N R, PAL K, KELLER J M, et al. Possibilistic fuzzy C-means clustering algorithm[J]. IEEE Transactions on Fuzzy Systems, 2005, 13(4):107-116.
[12] CHEN Songchan, ZHANG Daoqiang. Fuzzy clustering using kernel method[C] // Proc of the 2002 International Conference on Control and Automation. London: ICCA, 2002: 162-163.
[13] YANG Minshen, TSAI H S. A Gaussian kernel-based fuzzy C-means algorithm with a spatial bias correction[J]. Pattern Recognition Letters, 2008, 29(12):1713-1725.
[14] GONEN M, ALPAYDIN E. Localized multiple kernel learning[C] // Proc of the 25th International Conference on Machine Learning(ICML 2008). Helsinki: ACM 2008: 352-359.
[15] TZORTZIS G, LIKAS A. The global kernel k-means algorithm for clustering in feature space[J]. IEEE Transactions on Neural Networks, 2009, 20(7):1181-1194.
[16] ZHU Xiubin, PEDRYCZA W, LI Zhiwu. Fuzzy clustering with nonlinearly transformed data[J]. Applied Soft Computing, 2017, 61(1):364-376.
[17] TANG Yiming, YANG Xuezhi. Symmetric implicational method of fuzzy reasoning[J]. International Journal of Approximate Reasoning, 2013, 54(8):1034-1048.
[18] TANG Yiming, REN Fuji. Fuzzy systems based on universal triple I method and their response functions[J]. International Journal of Information Technology & Decision Making, 2017, 16(2):443-471.
[19] TANG Yiming, PEDRYCZ W. On the α(u,v)-symmetric implicational method for R- and(S, N)-implications[J]. International Journal of Approximate Reasoning, 2018, 92(1):212-231.
[1] 郝秀梅,李宁宁. P-信息隐藏挖掘的数量特征及应用[J]. 《山东大学学报(理学版)》, 2019, 54(9): 9-14.
[2] 孙倩倩,李小南. 区间毕达哥拉斯模糊集的信息度量及其应用[J]. 《山东大学学报(理学版)》, 2019, 54(9): 43-53.
[3] 张廷海,覃锋. 基于重叠函数和分组函数的蕴涵分配性[J]. 《山东大学学报(理学版)》, 2019, 54(9): 36-42.
[4] 程亚菲,赵彬. 模糊蕴涵关于合取2-一致模满足输入律的刻画[J]. 《山东大学学报(理学版)》, 2019, 54(8): 20-32.
[5] 于晓丹,董丽,吴聪,孔祥智. 软关联环[J]. 山东大学学报（理学版）, 2018, 53(4): 31-35.
[6] 刘莉君. 布尔代数上triple-δ-导子的特征及性质[J]. 山东大学学报（理学版）, 2017, 52(11): 95-99.
[7] 张琬迪,宋晓秋,吴尚伟. 一类模糊积分微分方程的模糊微分变换法[J]. 山东大学学报（理学版）, 2017, 52(10): 42-49.
[8] 刘莉君. 剩余格上n-重正蕴涵滤子的特征及刻画[J]. 山东大学学报（理学版）, 2017, 52(8): 48-52.
[9] 彭家寅. BL-代数的扰动模糊理想[J]. 山东大学学报（理学版）, 2016, 51(10): 78-94.
[10] 卢威,宋晓秋,黄雷雷. 基于模糊积分的Hermite-Hadamard和Sandaor类型的不等式[J]. 山东大学学报（理学版）, 2016, 51(8): 22-28.
[11] 彭家寅. 格蕴涵代数的不分明化滤子[J]. 山东大学学报（理学版）, 2016, 51(2): 119-126.
[12] 彭家寅. 关联模糊集理论的伪BL-代数的软滤子[J]. 山东大学学报（理学版）, 2015, 50(08): 40-45.
[13] 索春凤, 王贵君. 最大交互数对非齐次T-S模糊系统的潜在影响[J]. 山东大学学报（理学版）, 2015, 50(08): 14-19.
[14] 沈冲, 姚卫. 模糊完备格上模糊G-理想和模糊Galois伴随之间的一一对应[J]. 山东大学学报（理学版）, 2015, 50(04): 36-41.
[15] 杨永伟, 贺鹏飞, 李毅君. BL-代数中的落影模糊理想[J]. 山东大学学报（理学版）, 2015, 50(02): 83-89.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(理学版)》编辑部　
地址: 山东省济南市山大南路27号山东大学中心校区（250100）　电话: +86-0531-88366917　E-mail: xblxb@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