B Cell–Inspired Algorithms - Immunological Computation: Theory and Applications - page 118

In clonal selection algorithms, each antibody and antigen is represented by a set
of attributes { x 1 , x 2 , …, x n }. h us, antibodies and antigens may be represented as
either n -dimensional points in a metric space such as Euclidean space or use binary
encoding of the attributes; however, other representations are also used.
h e antigenic a nity of each antibody is typically defi ned based on a metric,
usually, the Euclidean distance. Also, some operators are defi ned to introduce
genetic variation to the antibodies based on their antigenic a nities. First, a
cloning operator is defi ned to make exact copies (clones) of those antibodies having
higher antigenic a nities; the higher the antigenic a nity, the higher the number
of clones an antibody can generate. h en some genetic variation is introduced to
these antibodies (through a mutation operator) to allow them for better matching
with the antigens.
A lthough severa l variations of clona l selection a lgorithms have been introduced,
most algorithms have similar features as that of the basic clonal selection algorithm
(De Castro and Von Zuben, 2000) presented in Figure 5.1 (the diff erent steps of
the fl ow diagram are shown in Figure 5.2).
During the a nity maturation process, when mutated antibodies are added to
the current population to reselect the best individuals and keep them as the mem-
ory of current antigen, it is necessary to compute the a nities of the new antibodies
toward the antigen; therefore, the whole set of antibodies need to be ranked, and
subsequently, a selection process needs to be performed.

(6)

N d

P r
M

(1)

Select

(2)

P n

(5)

Clone

Re-select

(3)

C

Maturate

(4)

C *

Figure 5.1 Generic clonal selection algorithm.