基于改进蝙蝠优化自确定的模糊C-均值聚类算法

doi:10.3969/j.issn.1000-1158.2020.04.019

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (2224 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对模糊C-均值聚类算法敏感于初始聚类中心及聚类收敛慢、聚类数目手动设定等缺陷,提出了基于改进蝙蝠优化自确定的模糊C-均值聚类算法。该算法是基于密度峰值综合衡量聚类中心外围数据密集程度和聚类中心间距离,自动确定聚类中心和聚类数目,以此作为改进蝙蝠算法的初始中心;在原始蝙蝠算法中引入Levy飞行特征加强算法跳出局部最优能力;使用Powell局部搜索加快算法的收敛,利用改进的蝙蝠种群进行种群寻优,并将最优蝙蝠位置作为聚类C-均值新聚类中心,进行模糊聚类,以此循环交叉迭代多次最终获得聚类结果。将基于改进蝙蝠优化自确定的模糊C-均值聚类算法与其它两种聚类算法在标准数据集上进行仿真对比,实验结果表明:与其它两种算法相比,该算法收敛速度快、误差率低。

	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
	汤正华

关键词 ：计量学, 模糊C-均值聚类, 蝙蝠算法, Levy飞行, Powell局部搜索, 密度峰值, 自动确定

Abstract：For the fuzzy clustering C-means algorithm is sensitive to the initial clustering center and clustering slow convergence, manually set the number of clusters and other defects, self-defined fuzzy clustering C-means algorithm based on improved bat optimization was proposed.Based on the density peak value, the density of data and the distance between cluster centers were measured, so as to automatically determine the number of cluster centers and clusters, which was used as the initial center of the improved bat algorithm.The Levy flight characteristics were introduced to enhance the bat algorithm to jump out of the local optimum ability, and Powell local search was used to accelerate bat algorithm convergence.The improved bat population was used for population optimization, and the optimal bat position was used as the clustering C-means new clustering center, and fuzzy clustering was carried out to obtain the clustering results by repeated iterative iterations.Compared with the other two clustering algorithms on the standard dataset, the experimental results showed that the proposed clustering algorithm can converge quickly with lower error rate.

Key words： metrology fuzzy C-mean clustering bat algorithm levy flight powell Local Search density peak automatic determination

收稿日期: 2018-06-13

PACS:

TB973

基金资助:中共山东省委党校2019创新工程科研创新项目 (2019131)

作者简介: 汤正华(1982-),男,山东济南人,副教授,硕士,主要从事模式识别与人工智能、计算机网络安全方面的研究。Email: tangzhenghua82@sina.com

引用本文:

汤正华. 基于改进蝙蝠优化自确定的模糊C-均值聚类算法[J]. 计量学报, 2020, 41(4): 505-512.
TANG Zheng-hua. Self-Defined Fuzzy Clustering C-Means Algorithm Based on Improved Bat Optimization. Acta Metrologica Sinica, 2020, 41(4): 505-512.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2020.04.019 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2020/V41/I4/505

1 宋旭东, 朱文辉, 邱占芝. 大数据k-Means聚类挖掘优化算法[J].大连交通大学学报, 2015, 36(3): 91-94. SongX D , ZhuW H, QiuZ Z. Big Data K-Means Clustering Mining Optimization Algorithm[J].Journal of Dalian Jiaotong University, 2015, 36(3): 91-94.
2 DunnJ C. A Graph Theoretic Analysis of Pattern Classification via Tamuras Fuzzy Relation[J].IEEE Transactions on Systems Man & Cybernetics, 1974, 4(3): 310-313.
3 BezdekJ C. Pattern recognition with fuzzy objective function algorithms[M]. New York: Plenum Press, 1981: 203-239.
4 MehmoodR, BieR, DawoodH, et al. Fuzzy Clustering by Fast Search and Find of Density Peaks[C]//IEEE Computer Society. International Conference on Identification, Information, and Knowledge in the Internet of Things. Beijing, 2015: 258-261.
5 DingY, FuX. Kernel-based fuzzy c-means clustering algorithm based on genetic algorithm[J].Neurocomputing, 2016, 188: 233-238.
6 梁冰, 徐华. 基于改进人工蜂群的核模糊聚类算法[J].计算机应用, 2017, 39(9): 2600-2605. LiangB, XuH. Kernel fuzzy C-means clustering based on improved artificial bee colony algorithm[J].Journal of Computer Applications, 2017, 39(9): 2600-2605.
7 徐曼舒, 汪继文, 邱剑锋, 等. 基于改进人工蜂群的模糊C-均值聚类算法[J].计算机工程与科学, 2016, 38(6): 1238-1244. XuM S, WangJ W, QiuJ F, et al. A fuzzy C-means clustering algorithm based on improved artificial by colony[J].Computer Engineering and Science, 2016, 38(6): 1238-1244.
8 黄兴旺, 曾学文, 郭志川, 等. 采用改进二进制蝙蝠算法的任务调度算法[J].西安交通大学学报, 2017, 51(10): 65-70. HuangX W, ZengX W, GuoZ C, et al. A Task Scheduling Algorithm Based on an Improved Binary Bat Algorithm[J].Journal of Xian Jiaotong University, 2017, 51(10): 65-70.
9 RodriguezA, LaioA. Clustering by fastsearch and find of density peaks[J].Science, 2014, 344(6191): 1492-1496.
10 YangX S. Nature inspired meta-heuristic algorithms[M].2nd ed. Frome, UK: Luniver Press, 2010: 97-104.
11 冯辉宗, 彭丹, 袁荣棣. 基于PSO-SVM的发动机故障诊断研究[J].计算机测量与控制, 2014, 22(2): 355-357. FengH Z, PengD, YuanR D. Research on Automobile Engine Fault Diagnosis Based on PSO-SVM[J].Computer Measurement & Control, 2014, 22(2): 355-357.
12 高晋凯, 侯文, 杨冰倩, 等. 基于蚁群算法的模糊C均值聚类的改进研究[J].现代雷达, 2016, 38(11): 30-35. GaoJ K, HouW, YangB Q, et al. Improved Fuzzy C-means Clustering Based on Ant Colony Algorithm[J]. Modern Radar, 2016, 38(11): 30-35.
13 GionisA, MannilaH, TsaparasP. Clustering Aggregation[J].Acm Transactions on Knowledge Discovery from Data, 2005, 1(1): 341-352.
14 FrntiP, VirmajokiO. Iterative shrinking method for clustering problems[J].Pattern Recognition, 2006, 39(5): 761-775.
15 VeenmanC J, ReindersM J T, BackerE. A Maximum Variance Cluster Algorithm[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence, 2002, 24(9): 1273-1280.
16 田源, 王洪涛. 基于量子核聚类算法的图像边缘特征提取研究[J].计量学报, 2016, 37(6): 582-587. TianY, WangH T. Image Edge Feature Extraction Research Based on Quantum Kernel Clustering Algorithm[J].Acta Metrologica Sinica, 2016, 37(6): 582-587.
17 程一峰, 刘增力. 改进的K-奇异值分解图像去噪算法[J].计量学报, 2018, 39(3): 332-338. ChengY F, LiuZ L. Improved K-SVD Image Denoising Algorithm[J]. Acta Metrologica Sinica, 2018, 39(3): 332-338.
18 潘钊, 温银堂, 郑晓康, 等. 基于太赫兹图像的航天复合材料粘接缺陷检测方法研究[J]. 计量学报, 2018, 39(4): 471-475. PanZ, WenY T, ZhengX K, et al. Study on Nondestructive Testing for Bonding Defects in Aerospace Composite Based on Terahertz Image[J]. Acta Metrologica Sinica, 2018, 39(4): 471-475.
19 WuY Q, SongY, ZhouH C. State identification of boiler combustion flame images based on gray entropy multiple thresholding and support vector machine[J].Proceedings of the CSEE, 2013, 33(20): 66-73.
20 田小林, 焦李成, 缑水平. 基于PSO优化空间约束聚类的SAR 图像分割[J].电子学报, 2008, 36(3): 453-458. TianX L, JiaoL C, GouS P. SAR Image Segmentation Based on Spatially Constrained FCM Optimized by Particle Swarm Optimization[J]. Acta Electronica Sinica, 2008, 36(3): 453-458.