International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B3. Istanbul 2004
The immune system possesses several properties such as
self/nonself discrimination immunological memory, positive
/negative selection, immunological network, clonal selection
and learning which performs complex tasks.
3. ARTIFICIAL IMMUNE SYSTEM
3.1 Clonal Selection Theory
[n order to explain how an immune response is mounted when a
nonself antigenic pattern is recognized by a B cell, clonal
selection theory is been developed(F. M. Burnet, 1959). When a
B-cell receptor recognizes a nonself antigen with a certain
affinity, it is selected to proliferate and produce antibodies in
high volumes. The antibodies are soluble forms of the B-cell
receptors that are released from the B-cell surface to cope with
the invading nonself antigen. Antibodies bind to antigens
leading to their eventual elimination by other immune cells.
Proliferation in the case of immune cells is asexual, a mitotic
process; the cells divide themselves. During reproduction, the
B-cell clones undergo a hyper mutation process that, the Ag
stimulates the B cell to proliferate and mature into terminal Ab
secreting cells, named plasma cells. The process of cell division
generates a clone. In addition to proliferating and differentiating
into plasma cells, the activated B cells with high antigenic
affinities are selected to become memory cells with long life
spans. These memory cells circulate through the blood, lymph,
and tissues. When exposed to a second antigenic
stimulus ,commence to differentiate into plasma cells capable of
producing high-affinity Ab’s, preselected for the specific Ag
that had stimulated the primary response, Fig.l illustrates the
clonal selection, expansion, and affinity maturation processes.
= Os C med
Nar
Fig.1 Clonal selection principle
High affinity
memory cells
3.2 Clonal Selection Algorithm(CLONALG)
L.N.De Castro, F..J. Von zuben developed the Clonal Selection
Algorithm on the basis of clonal selection theory of the immune
system(L.N.De Castro, F. J. Von zuben, 2000b). It was proved
that can perform pattern recognition and adapt to solve multi-
modal optimization tasks. The CLONALG algorithm can be
described as follows:
1. Randomly initialize a population of individual(M);
2. For each pattern of P, present it to the population M and
determine its affinity with each element of the population M;
3. Select n of the best highest affinity elements of M and
generate copies of these individuals proportionally to their
affinity with the antigen. The higher the affinity, the higher the
number of copies, and vice-versa;
4. Mutate all these copies with a rate proportional to their
affinity with the input pattern: the higher the affinity, the
smaller the mutation rate;
5. Add these mutated individuals to the population M and
reselect m of these maturated individuals to be kept as
memories of the systems;
6. Repeat steps 2 to 5 until a certain criterion is met.
4. ARTIFICIAL IMMUNE CLASSIFICATION
ALGORITHM
Remote sensing image classification procedure involves two
steps. The first stage is the training of the system with a set of
sample data. Generally, sample data is obtained by selecting the
Region of Interest. In this paper, AIS is applied to train the
sample data. After the training is complete, the remote sensing
images are given for classification.
4.1 Training
As explained above, the training is done wet a set of sample
images. The sample images are obtained by selecting region of
interest(ROI). To every region of interest, The training
procedure is as follows:
|l. Initialization. Available Ab repertoire that can be
decomposed into several different subsets. Let Ab, represent
the set of memory cells. Ab; represent the set of remaining Ab.
Ab 7 Abi « Abi, (r*mzN). This is done by randomly choosing
training antigens to be added to the set of memory cells Ab;
and to the set of Ab. For each antigen Ag in the training set
perform the following steps.
2. Randomly choose an antigen Ag. in ROI and present it to
all. Ab's. Determine the vector aff , that contains the affinity
of Ag, to all the N Ab's in Ab. For the current investigation,
aes distance d; is the primary metric of affinity. The
Affinity aff, is defined as in equation(2) below:
aff; 5 -d; (2)
where | bm the number of remote sensing image bands.
3. Select the 5 highest affinity Ab’s from Ab to compose a new
set Ab}, of high affinity Ab’s in relation to Ag , and
In Ab
ton find the highest affinity memory cell, 7C,,,,., .
4. Clone the r selected Ab's based on their antigenic affinities,
generating the clone set Cl, The higher the antigenic affinity,
the higher the number of clones generated for each of the n
selected Ab's. The total number of clones generated N, IS
defined in equation(3) as follow:
n
N, = Y. round (P (3)
l
ixl
Interna
where
5. Allo
mutate
mutatic
are del
returns
random
equatio
where
6. Cal
relatioi
7. Sele
to Ag
the set
8. Dec
previo
trainin
set of 1
9. Rep
10. A
the avi
stoppit
If the
step 3.
