Immunodominance and clonal selection inspired multiobjective clustering  

作　　者：Wenping Ma , Licheng Jiao, Maoguo Gong Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, Institute of Intelligent Information Processing, Xidian University, Xi’an 710071, China 

出　　处：《Progress in Natural Science:Materials International》2009年第6期751-758,共8页自然科学进展·国际材料（英文版）

基　　金：supported by the National Natural Science Foundation of China (Grant Nos.60703107,60703108);the National High Technology Research and Development Program (863 Program) of China (Grant Nos. 2006AA01Z107 and 2008AA12Z2475853);the National Basic Research Program (973 Program) of China(Grant No.2006CB705700);the Program for New Century Excellent Talents in University;the Program for Che-ung Kong Scholars and Innovative Research Team in University (Grant No.IRT0645)

摘　　要：The biological immune system is a highly parallel and distributed adaptive system. The information processing abilities of the immune system provide important insights into the field of computation. Based on immunodominance in the biological immune system and the clonal selection mechanism, a novel data mining method, Immune Dominance Clonal Multiobjective Clustering algorithm （IDCMC）, is presented. The algorithm divides an individual population into three sub-populations according to three different measurements, and adopts different evolution and selection strategies for each sub-population. The update of each sub-population, however, is not carried out in isolation. The periodic combination operation of the analysis of the three sub-populations represents considerable advantages in its global search ability. The clustering task is a multiobjective optimization problem, which is more robust with respect to the variety of cluster structures of different datasets than a single-objective clustering algorithm. In addition, the new algorithm can determine the number of clusters automatically, which should identify the most promising clustering solutions in the candidate set. The experimental results, using artificial datasets with different manifold structure and handwritten digit datasets, show that the IDCMC outperforms the PESA- II-based clustering method, the genetic algorithm-based clustering technique and the original K-Means algorithm in solving most of the problems tested.The biological immune system is a highly parallel and distributed adaptive system. The information processing abilities of the immune system provide important insights into the field of computation. Based on immunodominance in the biological immune system and the clonal selection mechanism, a novel data mining method, Immune Dominance Clonal Multiobjective Clustering algorithm (IDCMC), is presented. The algorithm divides an individual population into three sub-populations according to three different measurements, and adopts different evolution and selection strategies for each sub-population. The update of each sub-population, however, is not carried out in isolation. The periodic combination operation of the analysis of the three sub-populations represents considerable advantages in its global search ability. The clustering task is a multiobjective optimization problem, which is more robust with respect to the variety of cluster structures of different datasets than a single-objective clustering algorithm. In addition, the new algorithm can determine the number of clusters automatically, which should identify the most promising clustering solutions in the candidate set. The experimental results, using artificial datasets with different manifold structure and handwritten digit datasets, show that the IDCMC outperforms the PESA-Ⅱ-based clustering method, the genetic algorithm-based clustering technique and the original K-Means algorithm in solving most of the problems tested.

关 键 词：Artificial immune systems Multiobjective optimization CLUSTERING Unsupervised learning 

分 类 号：R392[医药卫生—免疫学] Q939.91[医药卫生—基础医学]