Real-World Applications - Immunological Computation: Theory and Applications - page 171

Chapter 7
Real-World Applications
Immunological computation (IC) techniques (or artifi cial immune systems) have
been used as a problem solver in a wide range of domains such as optimization, clas-
sifi cation, clustering, anomaly detection, machine learning, adaptive control, and
associative memories. h ey have also been used in conjunction with other methods
(hybridized) such as genetic algorithms (GAs), neural networks, fuzzy logic, and
swarm intelligence. IC includes real-world applications of computer security, fraud
detection, robotics, fault detection, data mining, text mining, image and pattern
recognition, bioinformatics, games, scheduling, etc.
First, a general description of the solution process of using immune-based mod-
els is presented followed by some general-purpose applications. Next, some applica-
tions of AISs are briefl y described to exhibit how these techniques can be used in
real-world problem solving.
7.1 Solving Problems Using
Immunological Computation
To apply an immunity-based model to solve a particular problem in a specifi c
domain, one should select the immune algorithm depending on the type of prob-
lem that needs to be solved. Accordingly, the fi rst step should be to identify the
elements involved in the problem and how they can be modeled as entities in a
particular AIS. To encode such entities, a representation scheme for these elements
should be chosen, such as a string representation, real-valued vector, or hybrid rep-
resentation. Subsequently, appropriate a nity/distance measures, which are to be
used to determine corresponding matching rules, should be defi ned. h e next step
171