Proceedings of 2010 IEEE Student Conference on Research and Development (SCOReD 2010),
13 - 14 Dec 2010, Putrajaya, Malaysia
Hybrid Artifcial Immune System-Genetic Algorithm
optimization based on mathematical test fnctions
Mohammed Obaid Ali
I
, S. P. Koh
l
,K. H. Chong \ David F. w. Yap
2
,
Department of Electronics and Communication Engineering
I
Universiti Tenaga Nasional (UNITEN)
43009 Kajang, Selangor Darul Ehsan, Malaysia
2
Universiti Teknikal Malaysia Melaka(UTeM)
Hang Tuah Jaya,76100 Durian Tunggal, Melaka, Malaysia
I
{engin mohammed2020@ahoo.com},
I
{johnnykoh,chongkh@uniten.edu.my} ,z {david.yap@utem.edu.my}
Abstract- This paper demonstrates a hybrid between two
optimization methods that are Artifcial Immune System
(AIS) and Genetic Algorithm (GA). The capability of
overcoming the shortcomings of individual algorithms
without losing their advantages makes the hybrid techniques
superior to the stand-alone ones based on the dominant
purpose of hybridization. The improvement of the results that
enable to get it if GA and AIS work separately is the main
objective of this hybrid. The hybrid includes two processes;
frstly, AIS is the attraction among the researchers as the
algorithm. This enables it to develop local searching ability
and efciency yet the convergence rate for AIS is preferably
not precise compared to the GA. Secondly, a Genetic
Algorithm is typically initializing population randomly. The
last generation of AIS will be the input to the next process of
the hybrid which is the GA in this hybrid AIS-GA. Hybrid
makes GA enters the stage of standard solutions more rapidly
and more accurate compared with GA initialized population
at random. To diferentiate between the results in terms of
achieving the minimum value for these fnctions, eight
mathematical test fnctions are being used to make
comparison.
Kewords: Hybrid, Artifcial Immune System (AIS), Genetic
Algorithm (GA) optimization mathematical test fnctions.
I. INTRODUCTION
Generally, optimization theory is the core of mathematical
results and numerical methods. Its fnction is for searching
and discovering the best resolution fom a collection of
options without having to accurately enumerate and evaluate
all likely options [1]. The process of optimization lies at the
beginning of engineering itself. The usual fnction of an
engineer is to improve designs and create new ones with
more effcient and less expensive systems as well as to
elaborate plans and procedures for the existing systems [2].
The competency of optimization techniques to identif the
fnest case without having to test all potential cases that
comes through the use of a simple level of mathematics and
at the cost of executing iterative numerical calculations using
acutely defned logical process or algorithms applied on
computing machines [3]. Adeptness with basic-matrix
manipulation, linear algebra and calculus are needed to
develop the optimization methodology [4]. It is essential to
characterize the breaches of the engineering system to be
optimized to apply the mathematical results and numerical
978-1-4244-8648-9/101$26.00 ©2010 IEEE 256
methods of optimization theory to defnite engineering
problems[5,6,7].
II. ARTIFICIAL IMMUNE SYSTEM
People ofen t to nature whenever seeking new ideas to
solve computational problems that has become much
complex. The vertebrae immune system has been greatly
attended to as it is a good potential source of inspiration. It is
thought of as the possibility to glean different insights and
alterative solutions, compared to other biological-based
methods. Due to a wide variety of problems ranging fom
optimization, fault tolerance, data mining, bioinformatics and
robotic systems being opposed with the development of
solutions, the feld of Artifcial Immune System (AIS) has
become popular with its high distribution. It is also highly
adaptive, self-organizing in nature, capable of maintaining
memories of past encounters while continually able to lea
about upcoming encounters that has never been approached.
From over the past few years, AIS-based works span fom
theoretical modeling and simulation to more variety of
application. Interest in the AIS feld has been increasing
among many of new works inclusive in this feld of research
today [8, 9, 10].
The artifcial immune system (AIS) applies a leaing
method infuenced by the human immune system. The human
immune system is an amazing natural defense mechanism
that defends and leas about foreign substances [11]. The
AIS objective using idea based on immunology for the
growth of systems are capable of doing numerous tasks in
various areas of research [12, 13].
The detection of harmfl foreign element which is called
pathogens that attacks us is the main task of our immune
system. Our immune system defends us fom the pathogens.
Bacteria and viruses are the examples of such pathogens. An
atigen is a molecule that can be recognized by our immune
system. Such molecule triggers a specifc reaction fom our
immune system. An important role is played by the
Lymphocytes which are a special type of cells in our immune
system. There are two types of lymphocytes exist which is
the B cells or B lymphocytes and T cells or T lymphocytes.
When detecting the antigen, the B cells that best match the
antigens are cloned.