Publication: Solving computational algorithm using CLONALNet technique based on artificial clonal selection
No Thumbnail Available
Date
2011
Authors
Samy J.A.L.A.
Krishnan P.S.A.L.
Kiong T.S.
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE Computer Society
Abstract
This paper discusses the approach of CLONALNet in determining the optimum fitness function and mean population by benchmarking it with CLONALG. By using this algorithm the steps to obtain the fitness function is optimized and processing time is reduced. CLONALNet is a hybrid or combination of both opt-aiNet (Optimize Artificial Immune Network) and CLONALG. CLONALNet enforces an algorithm that is much more robust in evaluating the fitness for each antibody cells since it initiates boundaries so that the initialization process doesn't run off as of previous CLONALG algorithm but still maintains the immune network interaction as in aiNet. Also included is the combination of steps which includes cloning, affinity maturation and selection steps into one single function to find the best group of clones. In recent studies done, the maximum value will be the optimum solution. The optimum result as suggested in this paper is the minimum value for fitness function referring to global optimum result which is zero. � 2011 IEEE.
Description
Keywords
CLONALNet , data acquisition , Gaussian , Multifunction , mutation rate , Clone cells , Cloning , Data acquisition , Affinity maturation , Artificial immune networks , CLONALNet , Computational algorithm , Fitness functions , Gaussians , Multifunction , Mutation rates , Health