الفهرس 
abstractOnly 14 pages are availabe for public view
 |  | from | 16 |  |  |
| | | from | 16 | | |
Abstract
The late 1970‟s showed considerable interest in biology as a source of inspiration for solving computational problems [1]. Models of the central nervous system have driven artificial neural networks. Darwin theory spawned evolutionary simulations in natural selection [2].
Immunology can be defined as the study of the defense mechanisms that confer resistance against diseases. The system whose main function is to protect human bodies against the constant attack of external microorganisms is called the immune system. The immune system specifically recognizes and selectively eliminates foreign invaders by a process known as the immune response [3, 4]. The biological immune systems, like human nervous systems and Darwin evolutionary theory, offer a number of attractive features such as ability to remember, classify, recognize and neutralize the effect of foreign particles [5]. The biological immune system is a robust, complex, adaptive system that defends the body from foreign pathogens (instances). It is also able to categorize all cells (or molecules) within the body as self-cells or non-self cells [4]. A non-self cell is anything that can initiate an immune response; examples are a virus, bacteria, or splinter, however a self-cell; are human organism‟s own cells [6]. The immune system (IS) is composed of a complex set of cells, molecules and organs that have the capability of performing a lot of complex tasks [7].
The immune system can be divided into two major branches: The innate and adaptive immune systems. The innate immune system is an unchanging mechanism that detects and destroys certain invading organisms [5], while the adaptive immune system responds to previously unknown foreign cells and builds a response to them that can remain in the body over a long period of time [8]. This remarkable information processing biological system has caught the attention of computer science in recent years. A new field of research was developed under a new branch of computational intelligence called Artificial Immune System (AIS) where its basic idea and algorithms are inspired and based on the biological immune system (IS) by Hunt et al. [9], Dasgupta [7, 10], McCoy et al. [11], Forrest et al. [12], and Hofmeyr et al. [13]. Artificial Immune Systems (AIS) is a sub-field of Computational Intelligence motivated by immunology which to applied theoretical immunological models to machine learning and automated problem solving. Artificial immune systems are aimed to solve real-world problems, and therefore are mainly related to the areas of computer science and engineering [3]. Computer engineering, computer scientists and researchers are interested in studying the capability of immune system [14]. Modern Artificial Immune systems are inspired by one of three subfields: clone selection, negative selection and immune network algorithms. The techniques are commonly used for clustering, pattern recognition, classification, optimization, and other similar machine learning problem domains.
Artificial immune systems are applied to solve problems in many domain areas, however the theoretical immunology is intended to simulate, complement, and/or improve experimental analyses of the immune system [8]. Artificial immune systems are not only
2
related to create the abstract or metaphorical models of the biological immune system, they also include those mathematical theoretical immunology models being applied to tasks such as optimization, control, and autonomous robot navigation [3]. One of the oldest models among of natural computing is cellular automata (CA), dating back over half a century. The first cellular automata (CA) studies by John von Neumann [15, 16] in the late 1939s were biologically motivated [17]. Von Neumann wanted to examine synthetic computing devices analogous to human brain in which the processing units and memory are not separated from each other, that are massively parallel and that are capable of repair and building themselves given the necessary raw material [17]. The goal of cellular automata model is to design self-replicating artificial systems that are also computationally universal. Cellular automata (CA) are a mathematical models for systems in which many simple components act together to produce complicated patterns of behavior [18]. Each site takes on possible values, and is updated in discrete time steps according to some rules that depend on the value of sites in some neighborhood around. Cellular automata can be considered as an information processing systems [17]. Cellular automata evolution is to perform some computation on the sequence of site values given as the initial state. It is conjectured that cellular automata are generically capable of universal computation, so that they can implement arbitrary information-processing procedures. One of the most popular applications of cellular automata (CA) models is called „simulation games‟, of which John Horton Conway‟s “Game of Life” [19]. The popularity of cellular automata (CA) models was achieved in the 1980‟s through the work of Stephen Wolfram [18, 20]. Based on empirical experiments using computers, an extensive classification of cellular automata (CA) models was given as mathematical models for self-organizing statistical systems. Wolfram related cellular automata to all disciplines of different scientific fields (e.g., sociology, biology, physics, mathematics,. . ., etc.) [20]. Traffic system simulation using cellular automata is also one of the most popular simulation approaches of using cellular automata (CA) models [21]. There are many designs of traffic system approaches using cellular automata [22] starting from the one lane traffic system simulation up to designing a whole city traffic system simulation [22, 24]. 1.1 BACKGROUND AND PROBLEM There were some approaches tried to combine artificial immune system and cellular automata such as Xiaoping Liu et al. [25] and Ramin Javadzadeh et al [26]. Those methods are all different at representation, and the basic idea of combination, the application that those methods can be applied on. The model.