Improved Kernel Possibilistic Fuzzy Clustering Algorithm Based on Invasive Weed Optimization

doi:10.1007/s12204-015-1605-z

Abstract

Abstract: Fuzzy c-means (FCM) clustering algorithm is sensitive to noise points and outlier data, and the possibilistic fuzzy c-means (PFCM) clustering algorithm overcomes the problem well, but PFCM clustering algorithm has some problems: it is still sensitive to initial clustering centers and the clustering results are not good when the tested datasets with noise are very unequal. An improved kernel possibilistic fuzzy c-means algorithm based on invasive weed optimization (IWO-KPFCM) is proposed in this paper. This algorithm first uses invasive weed optimization (IWO) algorithm to seek the optimal solution as the initial clustering centers, and introduces kernel method to make the input data from the sample space map into the high-dimensional feature space. Then, the sample variance is introduced in the objection function to measure the compact degree of data. Finally, the improved algorithm is used to cluster data. The simulation results of the University of California-Irvine (UCI) data sets and artificial data sets show that the proposed algorithm has stronger ability to resist noise, higher cluster accuracy and faster convergence speed than the PFCM algorithm.

Key words: data mining|clustering algorithm| possibilistic fuzzy c-means (PFCM)| kernel possibilistic fuzzy c-means algorithm based on invasive weed optimization (IWO-KPFCM)

摘要：

Fuzzy c-means (FCM) clustering algorithm is sensitive to noise points and outlier data, and the possibilistic fuzzy c-means (PFCM) clustering algorithm overcomes the problem well, but PFCM clustering algorithm has some problems: it is still sensitive to initial clustering centers and the clustering results are not good when the tested datasets with noise are very unequal. An improved kernel possibilistic fuzzy c-means algorithm based on invasive weed optimization (IWO-KPFCM) is proposed in this paper. This algorithm first uses invasive weed optimization (IWO) algorithm to seek the optimal solution as the initial clustering centers, and introduces kernel method to make the input data from the sample space map into the high-dimensional feature space. Then, the sample variance is introduced in the objection function to measure the compact degree of data. Finally, the improved algorithm is used to cluster data. The simulation results of the University of California-Irvine (UCI) data sets and artificial data sets show that the proposed algorithm has stronger ability to resist noise, higher cluster accuracy and faster convergence speed than the PFCM algorithm.

关键词: data mining|clustering algorithm| possibilistic fuzzy c-means (PFCM)| kernel possibilistic fuzzy c-means algorithm based on invasive weed optimization (IWO-KPFCM)

CLC Number:

TP 274.2

ZHAO Xiao-qiang* (赵小强), ZHOU Jin-hu (周金虎). Improved Kernel Possibilistic Fuzzy Clustering Algorithm Based on Invasive Weed Optimization[J]. Journal of shanghai Jiaotong University (Science), 2015, 20(2): 164-170.

References 12

[1]	Krishnapuram R, Keller J M. A possibilistic approach to clustering [J]. IEEE Transactions on Fuzzy Systems, 1993, 1(2): 98-110.
[2]	Zhang Xiang, Wang Shi-tong. Mahalanobis distancebased possibilistic clustering algorithm and its analysis[J]. Journal of Data Acquisition & Processing, 2011,26(1): 101-105 (in Chinese).
[3]	Xie Z P, Wang S T, Chung F L. An enhanced possibilistic c-means clustering algorithm EPCM [J]. Soft Computing, 2008, 12: 593-611.
[4]	Pal N R, Pal K, Keller J M, et al. A possibilistic fuzzy c-means clustering algorithm [J]. IEEE Transactions on Fuzzy Systems, 2005, 13(4): 517-530.
[5]	Wu Xiao-hong, Zhou Jian-jiang. A novel possibilistic fuzzy c-means clustering [J]. Acta Electronica Sinica,2008, 36(10): 1996-2000 (in Chinese).
[6]	Mehrabian A R, Lucas C. A novel Numerical optimization algorithm inspired from weed colonization[J]. Ecological Informatics, 2006, 1(4): 355-366.
[7]	Roy S, Islam S M, Das S, et al. Multimodal optimization by artificial weed colonies enhanced with localized group search optimizers [J]. Applied Soft Computing,2012, 13: 27-46.
[8]	Han Yi, Cai Jian-hu, Li Yan-lai, et al. Invasive weed optimization and its advances [J]. Computer Science,2011, 38(3): 20-23 (in Chinese).
[9]	Chen Huan, Zhou Yong-quan, Zhao Guang-wei.Multi-population invasive weed optimization algorithm based on chaotic sequence [J]. Journal of Computer Applications, 2012, 32(7): 1958-1961 (in Chinese).
[10]	Han Xu-dong, Xia Shi-xiong, Liu Bing, et al. Kernelbased fast improved possibilistic c-means clustering algorithm[J]. Computer Engineering and Applications,2011, 47(6): 176-180 (in Chinese).
[11]	Yang Miin-Shen, Wu Kuo-Lung. Unsupervised possibilistic clustering [J]. Pattern Recognition, 2006, 39:5-21.
[12]	Zhao Xiao-qiang, Zhou Jin-hui, Yang Jia-min. A fuzzy clustering algorithm of data mining based on IWO [C]//Proceedings of the 32nd Chinese Control Conference. Xi’an, China: [s.n.], 2013: 7988-7993 (in Chinese).

[1]	XIAO Pengfei, NI He, JIN Jiashan. Sequential Prediction Method of Single Parameter for Thermal System Based on MWSA [J]. Journal of Shanghai Jiao Tong University, 2023, 57(1): 36-44.
[2]	CHEN Yun, SHEN Hao, WANG Jiayu, ZHAO Wenkai, PAN Zhijun, WANG Xiaohui, XIAO Yinjing. Real-Time Calculation of Carbon Emissions in County-Level Administrative Regions Based on ‘Energy Brain’ [J]. Journal of Shanghai Jiao Tong University, 2022, 56(9): 1111-1117.
[3]	WEI Zhifei, SONG Quanhong, LI Fang, YANG Qingyu, WANG Aihua. Research on Object Detection Algorithm Based on Neural Network Model Compression Technique [J]. Air & Space Defense, 2021, 4(4): 107-112.
[4]	HUANG Weikai, MA Xing, LIU Jin, LI Yuping, ZHENG Danli. Analysis of Tactical Missile Test Data Based on Improved K Means Clustering [J]. Air & Space Defense, 2019, 2(4): 69-74.
[5]	WU Shaochun (吴绍春), PANG Yijie (庞毅杰), SHAO Sen (邵森), JIANG Keyuan (江科元). Advanced Fuzzy C-Means Algorithm Based on Local Density and Distance [J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(5): 636-642.
[6]	LI Yangyang,SHI Licheng,WAN Weibing,ZHAO Qunfei. A Convolutional Neural Network-Based Method for 3D Object Detection [J]. Journal of Shanghai Jiaotong University, 2018, 52(1): 7-12.
[7]	XU Zewen1,2 (许泽文), LI Jianqiang1,2,3,4* (李建强), LIU Bo1 (刘博),BI Jing1 (毕敬), LI Rong1 (李蓉), MAO Rui3,4 (毛睿). Semi-Supervised Learning in Large Scale Text Categorization [J]. Journal of shanghai Jiaotong University (Science), 2017, 22(3): 291-302.
[8]	MAO Li1 (毛力), SONG Yi-chun1* (宋益春), LI Yin1 (李引),YANG Hong2 (杨弘), XIAO Wei2 (肖炜). Research of Improved Fuzzy c-means Algorithm Based on a New Metric Norm [J]. Journal of shanghai Jiaotong University (Science), 2015, 20(1): 51-55.
[9]	ZHANG Ying,JI Changgang,LI Junfu. A Routing Algorithm Based on Energy and Distance for Heterogeneous Sensor Networks with Multilevel Energies [J]. Journal of Shanghai Jiaotong University, 2014, 48(07): 953-958.
[10]	LONG Shun (龙舜), ZHU Wei-heng (朱蔚恒). Mining Evolving Association Rules for E-Business Recommendation [J]. Journal of shanghai Jiaotong University (Science), 2012, 17(2): 161-165.
[11]	QIU Wei-dong (邱卫东), JIN Ling (金凌), YANG Xiao-niu (杨小牛), YANG Hong-wa (杨红娃). Bit Stream Oriented Enumeration Tree Pruning Algorithm [J]. Journal of shanghai Jiaotong University (Science), 2011, 16(5): 567-570.
[12]	SHA Jian-Jun, PAN erShun. Soldering Parameter-Setting Approach Based on Improved Adaptive Neuro Fuzzy Inference Model [J]. Journal of Shanghai Jiaotong University, 2011, 45(12): 1741-1746.
[13]	LI Sike,MIAO Rui,ZHAO Yanzheng,JIANG Zhibin . Optimal Sensor Distribution in Multistation Manufacturing Systems for Variance Detection [J]. Journal of Shanghai Jiaotong University, 2010, 44(12): 1753-1757.