A parallelized artificial immune network for fuzzy clustering

Abstract

An artificial immune network (AIN), AINFCM, has been successfully used for fuzzy clustering to overcome the shortage of FCM algorithm that is sensitive to the selection of initial centres. However, as a stochastic searching algorithm, the runtime of AINFCM goes up especially when dealing with large quantities of data or generating much more antibodies for clone selection. In this paper, the PAINFCM is proposed for parallel affinity calculation of antibodies according to time complexity of AINFCM algorithm. Subsequently, a coarse-grained version of PAINFCM algorithm was proposed to parallelize clone expansion. Experiments indicated that the PAINFCM improves efficiency of AIN. Furthermore, it provides a good balance between global searching ability and run time of the AIN.

Keywords:

• AIN
• fuzzy clustering
• parallel computing
• clone selection
• artificial immune system

AMS Subject Classification: :

• 68T01
• 68W10

Acknowledgements

The authors express their most sincere appreciation to Prof. Lai C.-H. from Greenwich University for many helpful suggestions and modifications to improve the paper. The authors acknowledge support from innovation team project of Jiangnan University JNIRT0702.