Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (10): 27-29.

• 研究、探讨 • Previous Articles     Next Articles

Improved fuzzy C-means clustering algorithm

GUAN Qing,DENG Zhaohong,WANG Shitong   

  1. School of Information Technology,Jiangnan University,Wuxi,Jiangsu 214122,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-04-01 Published:2011-04-01


关 庆,邓赵红,王士同   

  1. 江南大学 信息工程学院,江苏 无锡 214122

Abstract: In order to overcome the Fuzzy C-Means(FCM) clustering algorithm falling into local minimum value and the shortcomings of the initial value of sensitivity,a improved ant colony algorithm based on quantum for fuzzy clustering is proposed.Quantum computing will combine theory and ant colony algorithm to improve the FCM algorithm.It uses quantum genetic algorithm to generate the initial pheromone distribution,and then updates using quantum gates quantum ants carry bits;later uses the ant colony algorithm for global search,parallel computing cluster and other characteristics to avoid falling into local optimal solution.The algorithm is verified to ensure the diversity of population,have a good global convergence and overcome the fuzzy C-means clustering algorithm deficiencies,and can effectively solve the premature convergence problem,so that the final clustering problem quickly and efficiently converges to the global optimal solution.

Key words: cluster analysis, Fuzzy C-Means(FCM) clustering, ant colony algorithm, quantum computing

摘要: 为了克服模糊C-均值(FCM)聚类算法易陷入局部极小值和对初始值敏感的缺点,提出了一种基于改进量子蚁群的模糊聚类算法。将量子计算原理和蚁群算法相结合来改进FCM算法。初期采用量子遗传算法生成信息素分布,后期利用蚁群算法的全局搜索性、并行计算性等特点避免聚类陷入局部最优解。实验证明该算法保证了种群的多样性,有较好的全局收敛性,克服了模糊C-均值聚类算法的不足,能有效解决未成熟收敛的问题,使聚类问题最终快速、有效地收敛到全局最优解。

关键词: 聚类分析, 模糊C-均值聚类, 蚁群算法, 量子计算