Biomedical Engineering Reference
In-Depth Information
Fig. 3 Superimposition of
native TACR1 protein (red)
on D129Y mutant (green)
3 Methodology
3.1 Genetic Algorithm
GA proposed by J.H. Holland is one of the ef
cient optimization techniques which
is based on
'
Survival of the
ttest.
'
In this paper, we used GA to generate individual
classi
cation rules from the given set of training data items. The individual rule
consists of
'
if part
'
and
'
then part,
'
where
'
if part
'
is known as antecedent and
'
then
part
'
is known as consequent [
3
,
10
]. The rule representation is as follows.
If P then Q
where
P is the list of attributes involved in the rule formation.
Q is the class label of the rule.
Gene Representation:
In this approach, each individual is represented with conjunction of conditions
composing a given rule antecedent. Each gene represents a rule condition of the
form as follows.
A
i
Op
i
V
ij
where
A
i
represents the ith predictor attribute,
Op
i
comparison operator {<, >,
≤
,
≥
, =}, and
V
ij
denotes jth value of the ith attribute (Figs.
4
,
5
and
6
).
Search WWH ::
Custom Search