I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI)
Vo
l.
8
,
No
.
2
,
J
u
n
e
201
9
,
p
p
.
190
~
1
9
6
I
SS
N:
2
2
5
2
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
8
.i
2
.
p
p
190
-
1
9
6
190
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
AI
Sensitiv
ity
a
na
ly
sis
of a species
con
serv
ing
genetic al
g
o
rith
m
's
pa
ra
m
et
ers for
addres
sing
t
he
nic
he radius
probl
e
m
M
icha
el
Sco
t
t
B
r
o
w
n
Un
iv
e
rsit
y
o
f
M
a
r
y
lan
d
Un
iv
e
rsity
Co
ll
e
g
e
,
A
d
e
lp
h
i,
M
D
2
0
7
7
4
,
USA
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
29
,
2
0
1
9
R
ev
i
s
ed
A
pr
2
0
,
2
0
1
9
A
cc
ep
ted
A
pr
1
,
2
0
1
9
Nic
h
e
Ge
n
e
ti
c
A
lg
o
rit
h
m
s
(
N
GA
)
a
re
a
sp
e
c
ial
c
a
teg
o
r
y
o
f
G
e
n
e
ti
c
A
l
g
o
rit
h
m
s (
GA
)
th
a
t
so
lv
e
p
ro
b
l
e
m
s
w
it
h
m
u
lt
ip
le o
p
ti
m
a
.
T
h
e
s
e
a
lg
o
rit
h
m
s
p
re
se
rv
e
g
e
n
e
ti
c
d
iv
e
rsit
y
a
n
d
p
r
e
v
e
n
t
th
e
GA
f
ro
m
c
o
n
v
e
rg
in
g
o
n
a
sin
g
le
o
p
ti
m
a
.
M
a
n
y
N
GA
s
su
ff
e
r
f
ro
m
th
e
Nic
h
e
Ra
d
iu
s
P
ro
b
lem
(NRP
),
w
h
ich
is
th
e
p
ro
b
lem
o
f
c
o
rre
c
tl
y
se
tt
in
g
a
ra
d
iu
s
p
a
ra
m
e
ter
f
o
r
o
p
ti
m
a
l
re
s
u
lt
s.
W
h
il
e
th
e
se
lec
ti
o
n
o
f
th
e
ra
d
i
u
s
v
a
lu
e
h
a
s
b
e
e
n
w
id
e
ly
r
e
se
a
r
c
h
e
d
,
th
e
e
ff
e
c
ts
o
f
o
th
e
r
GA
p
a
ra
m
e
ters
o
n
g
e
n
e
ti
c
d
iv
e
rsity
is
n
o
t
we
ll
k
n
o
w
n
.
T
h
is
re
se
a
rc
h
i
s
a
p
a
ra
m
e
ter
se
n
siti
v
it
y
a
n
a
l
y
sis
o
n
t
h
e
o
th
e
r
p
a
ra
m
e
t
e
rs
in
a
GA
,
n
a
m
e
l
y
m
u
tatio
n
ra
te,
n
u
m
b
e
r
o
f
in
d
iv
id
u
a
ls an
d
n
u
m
b
e
r
o
f
g
e
n
e
ra
ti
o
n
s.
K
ey
w
o
r
d
s
:
Gen
etic
A
l
g
o
r
ith
m
Nich
e
R
ad
i
u
s
P
r
o
b
le
m
Sen
s
i
ti
v
it
y
An
al
y
s
is
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mic
h
ae
l Sco
tt B
r
o
w
n
,
Un
i
v
er
s
it
y
o
f
Ma
r
y
lan
d
U
n
iv
e
r
s
it
y
C
o
lleg
e,
A
d
elp
h
i,
MD
2
0
7
7
4
,
USA
.
E
m
ail:
m
ic
h
ae
l.b
r
o
w
n
@
u
m
u
c.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
B
ac
k
g
r
o
u
n
d
Nich
e
Gen
e
tic
A
lg
o
r
it
h
m
s
(
NG
A
s
)
h
a
v
e
b
ee
n
s
h
o
w
n
to
b
e
v
er
y
s
u
cc
es
s
f
u
l
s
o
l
v
i
n
g
o
p
ti
m
izatio
n
p
r
o
b
lem
s
i
n
m
u
lti
-
o
p
ti
m
a
d
o
m
ai
n
s
.
B
u
t
m
a
n
y
o
f
th
e
s
e
alg
o
r
ith
m
s
in
co
r
p
o
r
ate
a
r
a
d
iu
s
p
ar
am
eter
t
h
at
w
h
e
n
s
et
p
o
o
r
ly
p
r
o
d
u
ce
le
s
s
t
h
a
n
d
esira
b
le
r
es
u
lts
.
T
h
i
s
is
k
n
o
w
n
a
s
t
h
e
N
ich
e
R
a
d
i
u
s
P
r
o
b
lem
(
NR
P
)
.
So
m
e
alg
o
r
it
h
m
s
clai
m
to
ad
d
r
ess
th
e
NR
P
.
B
u
t,
th
e
p
o
ten
tial
o
f
alg
o
r
ith
m
s
t
h
at
s
u
f
f
er
f
r
o
m
N
R
P
w
ar
r
an
ts
ad
d
itio
n
al
r
esear
ch
in
t
h
i
s
ar
ea
.
T
h
e
P
r
o
b
lem
Mu
ch
r
e
s
ea
r
ch
h
as
b
ee
n
p
u
b
l
is
h
ed
co
n
ce
r
n
in
g
t
h
e
r
o
le
th
a
t
th
e
r
ad
iu
s
p
ar
a
m
eter
p
la
y
s
in
NG
As.
Fo
r
Fit
n
e
s
s
Sh
ar
i
n
g
NG
As
s
o
m
e
r
esear
c
h
i
n
d
icate
s
t
h
at
p
o
p
u
latio
n
s
ize
p
la
y
s
a
r
o
le
i
n
g
en
etic
d
i
v
er
s
it
y
[
1
]
.
L
itt
le
r
esear
ch
h
a
s
lo
o
k
ed
at
t
h
e
p
ar
a
m
eter
s
u
s
ed
in
NG
A
s
,
n
a
m
e
l
y
th
e
p
o
p
u
lat
io
n
s
ize,
n
u
m
b
er
o
f
i
n
d
iv
id
u
al
s
p
er
g
en
er
atio
n
an
d
m
u
tatio
n
r
ate.
T
h
is
r
esear
ch
co
n
d
u
ct
s
a
p
ar
am
eter
s
en
s
iti
v
it
y
an
al
y
s
is
o
n
th
e
s
e
o
th
er
p
ar
am
eter
s
u
s
in
g
a
p
o
p
u
lar
NGA
ca
lled
t
h
e
Sp
ec
ies
C
o
n
s
er
v
in
g
Ge
n
etic
A
l
g
o
r
ith
m
[
2
]
.
T
h
e
P
r
o
p
o
s
ed
So
lu
tio
n
T
h
is
r
esear
ch
w
ill
b
e
g
in
to
ad
d
r
es
s
h
o
w
NG
A
p
ar
a
m
ete
r
s
af
f
ec
t
th
eir
ab
il
it
y
to
lo
ca
te
o
p
ti
m
a.
L
ea
r
n
i
n
g
ab
o
u
t
t
h
e
ef
f
ec
ts
o
f
p
ar
am
eter
s
o
n
th
e
NR
P
is
i
m
p
o
r
tan
t
f
o
r
m
a
n
y
r
ea
s
o
n
s
.
W
h
e
n
d
o
in
g
r
esear
c
h
i
n
NG
A
s
th
i
s
r
esear
c
h
co
u
ld
b
e
u
s
ed
f
o
r
s
e
lecti
n
g
p
ar
a
m
et
er
v
al
u
es.
As
w
e
co
n
ti
n
u
e
t
o
ad
d
r
ess
th
e
NR
P
,
NG
A
s
t
h
at
s
u
f
f
er
f
r
o
m
NR
P
will b
e
m
o
r
e
u
s
e
f
u
l.
C
o
n
ti
n
u
ed
r
esear
ch
in
to
th
e
N
R
P
h
as
m
a
n
y
b
en
e
f
its
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
S
en
s
itivity a
n
a
lysi
s
o
f a
s
p
ec
ies co
n
s
ervin
g
g
en
etic
a
lg
o
r
ith
m'
s
p
a
r
a
mete
r
s
f
o
r
.
.
.
(
Mich
a
el
S
co
tt B
r
o
w
n
)
191
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
2
.
1
.
Niche
ra
diu
s
pro
ble
m
GAs
ar
e
w
ell
s
u
i
ted
f
o
r
f
i
n
d
in
g
o
p
ti
m
a
in
p
r
o
b
le
m
s
t
h
at
o
n
l
y
co
n
tain
a
s
i
n
g
le
o
p
ti
m
a
[
3
]
.
I
n
m
u
lti
-
o
p
ti
m
a
p
r
o
b
lem
s
tr
ad
itio
n
al
G
A
s
m
a
y
co
n
v
er
g
e
o
n
a
lo
ca
l
o
p
t
im
a
a
n
d
m
is
s
th
e
g
lo
b
al
o
p
tim
a.
A
s
p
ec
ial
s
u
b
s
et
o
f
G
A
s
,
ca
lled
N
ich
e
Gen
etic
A
lg
o
r
ith
ms
(
NG
A
s
)
,
i
s
s
p
ec
i
f
i
ca
ll
y
d
esi
g
n
ed
to
p
r
eser
v
e
o
p
ti
m
a
[
4
-
5
]
.
B
u
t
a
n
u
m
b
er
o
f
th
e
s
e
al
g
o
r
ith
m
s
h
av
e
a
r
a
d
iu
s
pa
r
a
m
eter
a
n
d
d
eter
m
i
n
in
g
a
g
o
o
d
v
alu
e
f
o
r
th
e
r
ad
iu
s
ca
n
b
e
p
r
o
b
lem
at
ic.
T
h
e
N
ich
e
R
a
d
iu
s
P
r
o
b
lem
(
NR
P
)
is
th
e
i
n
ab
ilit
y
to
s
elec
t
a
g
o
o
d
r
ad
iu
s
v
al
u
e
f
o
r
r
ad
iu
s
b
ased
NG
A
s
w
it
h
o
u
t
k
n
o
w
i
n
g
t
h
e
d
is
tan
ce
b
et
w
ee
n
o
p
ti
m
a
[
6
]
.
T
h
e
o
n
l
y
ef
f
ec
ti
v
e
w
a
y
to
d
eter
m
i
n
e
th
e
d
is
ta
n
ce
b
et
w
ee
n
o
p
ti
m
a
is
to
k
n
o
w
w
h
er
e
th
e
o
p
ti
m
a
ar
e
lo
ca
ted
.
B
u
t
if
w
e
k
n
e
w
th
e
lo
ca
tio
n
o
f
th
e
o
p
ti
m
a
t
h
er
e
w
o
u
ld
b
e
n
o
n
ee
d
to
r
u
n
th
e
NG
A
,
s
in
ce
o
p
ti
m
a
lo
ca
tio
n
is
th
e
p
u
r
p
o
s
e
o
f
th
e
NG
A
.
T
h
is
cr
ea
tes
a
p
ar
ad
o
x
i
n
t
h
at
N
G
A
s
ca
n
lo
ca
te
t
h
e
o
p
ti
m
a
ass
u
m
i
n
g
t
h
at
r
ad
iu
s
is
s
et
co
r
r
ec
tl
y
,
w
h
ic
h
r
eq
u
ir
es k
n
o
w
led
g
e
o
f
w
h
er
e
th
e
o
p
ti
m
a
ar
e
lo
ca
ted
.
NG
A
s
ar
e
g
o
o
d
at
s
o
lv
i
n
g
m
u
lti
-
o
p
ti
m
a
p
r
o
b
le
m
s
b
ec
a
u
s
e
th
e
y
p
r
eser
v
e
ar
ea
s
o
f
th
e
d
o
m
a
in
a
n
d
p
r
ev
en
t
g
lo
b
al
co
n
v
er
g
en
ce
.
B
y
p
r
eser
v
in
g
g
e
n
etic
d
iv
er
s
it
y
all
o
f
th
e
o
p
ti
m
a
ca
n
b
e
lo
ca
te
d
.
T
h
er
e
ar
e
NGA
s
th
a
t
ad
d
r
ess
t
h
e
N
R
P
.
C
M
A
-
E
S
[
7
-
9
]
,
G
A
S
[
1
0
-
1
1
]
,
DSGA
[
1
2
]
,
Fan
,
Sh
en
g
an
d
C
h
e
n
[
1
3
]
an
d
A
s
y
m
m
etr
ic
Sh
ar
i
n
g
[
1
4
-
1
5
]
all
ad
d
r
ess
th
is
p
r
o
b
le
m
t
o
s
o
m
e
d
eg
r
ee
.
B
u
t
it
i
s
i
m
p
o
r
tan
t
to
co
n
ti
n
u
e
to
d
o
r
esear
ch
o
n
t
h
e
N
R
P
b
ec
au
s
e
s
o
l
v
i
n
g
it
w
i
ll
p
r
o
v
id
e
u
s
w
it
h
m
o
r
e
u
s
e
f
u
l
NG
A
al
g
o
r
ith
m
s
.
On
e
s
u
ch
al
g
o
r
ith
m
t
h
at
co
u
l
d
b
en
ef
it
f
r
o
m
m
o
r
e
r
esear
ch
o
n
th
e
NR
P
is
th
e
Sp
ec
ie
s
C
o
n
s
er
v
i
n
g
Ge
n
etic
A
l
g
o
r
ith
m
(
S
C
G
A
)
[
2
]
.
SC
G
A
s
u
f
f
er
s
f
r
o
m
p
o
o
r
p
er
f
o
r
m
a
n
ce
w
h
e
n
t
h
e
r
ad
iu
s
i
s
in
co
r
r
ec
tl
y
s
elec
ted
[
2
]
.
2
.
2
.
Sp
ec
ies
co
ns
er
v
ing
g
enet
ic
a
lg
o
rit
h
m
SC
G
A
i
s
a
n
NG
A
t
h
at
atte
m
p
ts
to
co
n
s
er
v
e
ar
ea
s
o
f
t
h
e
d
o
m
a
in
[
2
]
.
T
h
e
p
o
p
u
latio
n
o
f
all
G
A
s
i
s
u
n
d
er
t
w
o
d
is
tin
c
t
p
r
ess
u
r
es.
T
h
er
e
is
an
e
x
p
lo
r
ativ
e
p
r
ess
u
r
e
f
o
u
n
d
in
m
u
tat
io
n
.
M
u
tatio
n
allo
w
s
th
e
G
A
to
ex
p
lo
r
e
n
e
w
ar
ea
s
o
f
t
h
e
d
o
m
a
in
.
T
h
er
e
is
also
an
e
x
p
lo
itativ
e
p
r
ess
u
r
e,
w
h
ic
h
is
f
o
u
n
d
in
s
e
lectio
n
.
T
h
is
p
r
ess
u
r
e
allo
w
s
th
e
G
A
to
ca
p
italize
o
n
f
it
ar
ea
s
o
f
th
e
d
o
m
ain
.
O
v
er
ti
m
e
t
h
e
ex
p
lo
itativ
e
p
r
ess
u
r
e
s
o
v
er
co
m
e
th
e
ex
p
lo
r
ativ
e
p
r
ess
u
r
es.
S
C
G
A
id
en
ti
f
ie
s
u
n
iq
u
e
ar
ea
s
o
f
th
e
d
o
m
ai
n
an
d
p
r
ev
en
ts
th
e
ex
p
lo
itativ
e
f
o
r
ce
s
f
r
o
m
eli
m
i
n
ati
n
g
th
e
m
u
n
til t
h
e
y
ca
n
b
e
ex
p
lo
r
ed
[
2
]
.
T
r
ad
itio
n
al
GAs
iter
ativ
el
y
p
er
f
o
r
m
s
th
r
ee
o
p
er
atio
n
s
:
s
elec
tio
n
,
cr
o
s
s
o
v
er
an
d
m
u
tatio
n
[
1
7
,
3
]
.
SC
G
A
e
n
h
an
ce
s
t
h
e
G
A
b
y
ad
d
in
g
t
w
o
ad
d
itio
n
al
o
p
er
atio
n
s
: seed
s
elec
tio
n
a
n
d
s
ee
d
co
n
s
er
v
atio
n
y
ie
ld
in
g
p
s
e
u
d
o
co
d
e
as f
o
llo
w
s
[
2
]
.
I
n
itial p
o
p
u
latio
n
B
eg
in
lo
o
p
u
n
t
il so
m
e
ter
m
i
n
a
te
co
n
d
itio
n
Seed
s
elec
tio
n
Selectio
n
C
r
o
s
s
o
v
er
Mu
tatio
n
Seed
co
n
s
er
v
atio
n
E
n
d
lo
o
p
T
h
e
s
ee
d
s
elec
t
io
n
o
p
er
atio
n
h
as
a
r
ad
iu
s
p
ar
a
m
eter
,
r
[
2
]
.
I
t
ev
alu
a
tes
ea
c
h
in
d
i
v
id
u
a
l
in
t
h
e
cu
r
r
en
t
p
o
p
u
latio
n
f
r
o
m
t
h
e
m
o
s
t
f
it
t
o
th
e
least
f
it.
Fo
r
ea
ch
i
n
d
iv
i
d
u
al
th
at
i
t
ev
al
u
ate
s
it
ch
ec
k
s
to
s
ee
if
t
h
er
e
i
s
an
o
th
er
s
ee
d
w
it
h
i
n
d
is
tan
ce
r
.
I
f
n
o
s
ee
d
ex
is
t
s
w
it
h
i
n
r
th
e
n
th
e
i
n
d
iv
id
u
al
is
m
ar
k
ed
as
a
s
ee
d
.
I
f
th
er
e
is
a
s
ee
d
w
it
h
in
r
th
e
n
th
e
in
d
i
v
id
u
al
i
s
n
o
t
a
s
ee
d
.
Seed
s
ar
e
lo
ca
ll
y
s
tr
o
n
g
i
n
d
iv
id
u
als
w
it
h
i
n
t
h
e
r
ad
iu
s
r
.
Seed
co
n
s
er
v
atio
n
e
n
s
u
r
es
th
a
t
s
e
ed
s
ar
e
r
ep
r
esen
ted
i
n
th
e
n
ex
t
g
e
n
er
atio
n
[
2
]
.
E
ac
h
s
e
e
d
w
i
ll
r
ep
lace
a
n
in
d
iv
id
u
al
in
t
h
e
n
e
x
t
g
e
n
er
at
io
n
.
T
h
e
o
p
e
r
atio
n
b
eg
in
s
b
y
ev
alu
a
tin
g
t
h
e
in
d
i
v
id
u
al
s
in
t
h
e
n
e
x
t
g
e
n
er
atio
n
w
it
h
i
n
d
is
ta
n
ce
r
o
f
th
e
s
ee
d
.
I
f
in
d
iv
id
u
als
ex
is
t
i
n
th
i
s
ar
ea
o
f
th
e
d
o
m
ai
n
th
e
s
ee
d
r
ep
lace
s
th
e
w
ea
k
e
s
t
in
d
iv
id
u
al
i
n
th
i
s
ar
ea
o
f
t
h
e
d
o
m
ai
n
.
I
f
t
h
e
n
e
x
t
g
en
er
atio
n
co
n
tain
s
n
o
i
n
d
iv
id
u
als
w
it
h
in
t
h
i
s
ar
ea
t
h
e
n
t
h
e
s
ee
d
r
ep
lace
s
th
e
g
lo
b
all
y
w
ea
k
est
i
n
d
i
v
id
u
al
i
n
t
h
e
n
e
x
t
g
e
n
er
atio
n
.
S
C
G
A
i
s
a
n
o
v
el
alg
o
r
it
h
m
t
h
a
t
p
r
eser
v
es
lo
ca
ll
y
s
tr
o
n
g
i
n
d
iv
id
u
als.
T
h
is
p
r
eser
v
e
s
t
h
eir
g
en
etic
tr
ait
s
an
d
allo
w
s
th
e
m
to
atte
m
p
t
to
f
i
n
d
lo
ca
l o
p
tim
a
[
2
]
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
3
.
1
.
Sens
it
iv
it
y
a
na
l
y
s
is
Sen
s
iti
v
it
y
An
al
y
s
i
s
is
t
h
e
s
tu
d
y
o
f
th
e
e
f
f
ec
t
th
at
p
a
r
a
m
e
ter
v
al
u
es
h
a
v
e
o
n
m
a
th
e
m
atica
l
m
o
d
el
s
[
1
8
]
.
Sen
s
iti
v
it
y
An
a
l
y
s
i
s
ca
n
h
elp
d
eter
m
in
e
w
h
ich
p
ar
a
m
e
ter
s
j
u
s
ti
f
y
f
u
r
t
h
er
in
v
est
ig
at
io
n
a
n
d
w
h
ic
h
p
ar
a
m
et
er
s
co
r
r
elate
with
t
h
e
o
u
tp
u
t.
T
h
er
e
ar
e
a
v
a
r
iet
y
o
f
m
et
h
o
d
s
to
p
er
f
o
r
m
s
en
s
it
iv
i
t
y
a
n
al
y
s
i
s
.
On
e
p
o
p
u
lar
m
eth
o
d
is
th
e
O
n
e
at
a
t
i
m
e
(
O
A
T
)
m
et
h
o
d
.
I
n
O
A
T
w
e
b
eg
i
n
w
it
h
a
b
ase
l
in
e
s
e
t
o
f
p
ar
a
m
e
ter
v
alu
e
s
.
P
ar
am
e
ter
v
al
u
es
ar
e
v
ar
ied
o
n
e
at
a
ti
m
e
w
h
ile
m
e
asu
r
i
n
g
t
h
e
ch
a
n
g
e
in
t
h
e
o
u
t
p
u
t.
I
n
th
i
s
r
esear
c
h
th
e
f
o
llo
w
i
n
g
p
ar
a
m
eter
v
al
u
es
w
er
e
s
elec
ted
f
o
r
t
h
e
b
as
e
ca
s
e.
T
h
e
p
o
p
u
latio
n
s
ize,
N
,
w
as
s
e
t
to
1
0
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
IJ
-
A
I
Vo
l.
8
,
No
.
2
,
J
u
n
e
201
9
:
190
–
1
9
6
192
T
h
e
g
en
e
m
u
ta
tio
n
r
ate,
M
,
w
a
s
s
et
to
0
.
0
1
.
T
h
e
n
u
m
b
er
o
f
g
en
er
atio
n
s
,
G
,
w
as
s
et
to
2
0
0
.
T
h
e
r
ad
iu
s
,
r
,
w
a
s
s
et
to
0
.
1
.
All
o
f
t
h
ese
v
alu
e
s
w
er
e
u
s
ed
in
p
r
io
r
r
esear
ch
o
n
S
C
G
A
[
2
,
1
2
]
.
T
h
e
v
ar
iatio
n
o
f
th
e
p
ar
am
eter
v
alu
e
s
w
ill
b
e
±
1
0
%,
±
2
0
%
an
d
±
4
0
%
co
m
p
ar
ed
to
th
e
b
ase
ca
s
e
v
alu
es.
Sin
ce
w
e
w
an
t
to
p
r
eser
v
e
g
e
n
etic
d
i
v
er
s
it
y
we
w
ill
m
ea
s
u
r
e
t
h
e
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
t
h
e
d
o
m
ai
n
s
v
alu
e
s
i
n
t
h
e
f
i
n
al
g
en
er
atio
n
w
ith
t
h
e
g
o
al
o
f
th
is
b
ein
g
h
i
g
h
.
A
lo
w
s
tan
d
a
r
d
d
ev
iatio
n
w
o
u
ld
in
d
icate
g
lo
b
al
co
n
v
er
g
en
ce
.
W
e
w
ill al
s
o
m
ea
s
u
r
e
th
e
a
v
er
ag
e
f
i
tn
e
s
s
o
f
t
h
e
f
in
a
l g
e
n
er
at
io
n
.
3
.
2
.
B
ench
m
a
r
ks
T
h
er
e
ar
e
a
n
u
m
b
er
o
f
w
id
el
y
u
s
ed
b
en
c
h
m
ar
k
s
f
o
r
m
u
lti
m
o
d
al
o
p
tim
izatio
n
p
r
o
b
lem
s
.
B
er
n
ier
[
1
6
]
g
en
er
alize
d
m
an
y
o
f
t
h
ese
f
u
n
ctio
n
s
i
n
to
eq
u
atio
n
1
.
(
)
=
−
2
s
in
(
)
6
(
1
)
Dif
f
er
e
n
t
v
al
u
es
f
o
r
R
,
c
,
p
an
d
k
w
il
l
y
ield
d
if
f
er
en
t
f
u
n
ctio
n
s
.
T
h
e
v
alu
e
o
f
c
d
eter
m
i
n
es
th
e
r
ate
o
f
d
ec
ay
o
f
th
e
o
s
cillatio
n
.
No
r
m
all
y
k
d
eter
m
i
n
es
t
h
e
n
u
m
b
er
o
f
o
p
ti
m
a
an
d
R
d
eter
m
i
n
e
s
th
e
r
a
n
g
e
v
al
u
e
o
f
th
e
o
p
ti
m
a.
So
m
e
f
o
r
m
o
f
th
is
eq
u
atio
n
h
a
s
b
ee
n
u
s
ed
in
m
a
n
y
r
esear
ch
p
ap
er
s
o
n
NG
A
s
[
1
9
-
2
1
,
1
]
.
T
h
e
b
en
ch
m
ar
k
s
u
s
ed
in
t
h
i
s
r
esear
ch
ar
e
s
h
o
w
n
i
n
eq
u
atio
n
s
F1
th
r
o
u
g
h
F3
.
A
ll
o
f
t
h
es
e
p
r
o
b
lem
s
ar
e
m
a
x
i
m
izatio
n
p
r
o
b
lem
s
w
h
er
e
th
e
v
al
u
e
o
f
x
is
b
et
w
ee
n
0
an
d
1
in
clu
s
iv
e.
A
ll
ar
e
f
o
r
m
s
o
f
(
1
)
an
d
h
av
e
b
ee
n
u
s
e
d
i
n
o
th
er
r
esear
ch
.
(
)
=
s
in
(
5
6
)
(
F1
)
(
)
=
s
in
(
5
3
)
6
(
F2
)
(
)
=
s
in
(
10
2
)
6
(
F3
)
T
h
ese
s
p
ec
if
ic
f
u
n
ctio
n
s
h
a
v
e
al
s
o
b
ee
n
u
s
ed
i
n
o
t
h
e
r
r
esear
ch
a
s
b
en
c
h
m
ar
k
s
[
1
6
,
1
2
]
.
Fu
n
ctio
n
1
is
a
s
in
e
f
u
n
ctio
n
w
it
h
o
p
ti
m
a
s
p
ac
ed
ev
e
n
l
y
t
h
r
o
u
g
h
o
u
t
t
h
e
d
o
m
ai
n
a
ll
w
i
t
h
t
h
e
s
a
m
e
r
an
g
e
v
alu
e
s
.
W
h
e
n
x
is
b
et
w
ee
n
0
a
n
d
1
th
e
f
u
n
c
tio
n
h
as 5
o
p
ti
m
a
.
A
g
r
ap
h
o
f
th
e
f
u
n
ct
io
n
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
1
.
Fig
u
r
e
1
.
Gr
ap
h
o
f
(
)
=
s
in
(
5
6
)
,
0
<=
x
<
=
1
Fu
n
ctio
n
2
a
ls
o
h
as
5
o
p
tim
a
w
h
e
n
x
r
an
g
e
s
b
et
w
ee
n
0
an
d
1
.
H
o
w
ev
er
,
u
n
li
k
e
F1
th
at
h
as
o
p
tim
a
ev
en
l
y
s
p
ac
ed
w
ith
i
n
t
h
e
d
o
m
ain
,
F2
o
p
tim
a
ar
e
in
cr
ea
s
in
g
l
y
clo
s
er
to
g
eth
er
as
x
i
n
cr
ea
s
e
s
.
Fig
u
r
e
2
s
h
o
w
s
a
g
r
ap
h
o
f
F2
.
Fig
u
r
e
2
.
Gr
ap
h
o
f
(
)
=
s
in
(
5
3
)
6
,
0
<=
x
<=
1
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
S
en
s
itivity a
n
a
lysi
s
o
f a
s
p
ec
ies co
n
s
ervin
g
g
en
etic
a
lg
o
r
ith
m'
s
p
a
r
a
mete
r
s
f
o
r
.
.
.
(
Mich
a
el
S
co
tt B
r
o
w
n
)
193
Fu
n
ctio
n
3
h
a
s
1
0
o
p
ti
m
a
w
h
e
n
x
r
an
g
es
b
et
w
ee
n
0
a
n
d
1
.
S
i
m
ilar
to
F2
,
th
e
s
e
o
p
ti
m
a
ap
p
ea
r
clo
s
er
to
g
eth
er
as
x
in
cr
ea
s
es.
Fi
g
u
r
e
3
s
h
o
w
s
a
g
r
ap
h
o
f
F3
.
Fig
u
r
e
3
.
Gr
ap
h
o
f
(
)
=
s
in
(
10
2
)
6
,
0
<=
x
<=
1
3
.
3
.
E
x
peri
m
ent
I
n
th
is
e
x
p
er
i
m
e
n
t
a
n
u
m
b
er
o
f
test
ca
s
es
w
er
e
ex
ec
u
ted
.
T
h
e
b
ase
ca
s
e
o
f
N
=
1
0
0
,
G
=
2
0
0
an
d
M
=
0
.
0
1
w
as
ex
ec
u
ted
a
n
d
is
u
s
ed
f
o
r
co
m
p
ar
is
o
n
ag
a
in
s
t
all
o
f
t
h
e
b
a
s
e
ca
s
e
s
.
E
ac
h
v
ar
iatio
n
o
f
±
1
0
%,
±
2
0
%
an
d
±
4
0
%
f
o
r
ea
ch
p
ar
am
eter
w
a
s
al
s
o
ex
ec
u
te
d
.
T
h
e
m
u
tatio
n
r
ate
is
a
g
en
e
m
u
tatio
n
r
ate.
I
t
is
e
v
al
u
ated
o
n
ea
c
h
g
e
n
e
o
f
ea
ch
i
n
d
iv
id
u
al
i
n
t
h
e
n
e
w
g
e
n
er
atio
n
.
A
m
u
ta
tio
n
r
ate
o
f
0
.
0
1
w
o
u
ld
m
ea
n
th
at
1
%
o
f
g
e
n
e
s
ar
e
s
elec
te
d
f
o
r
m
u
tatio
n
.
T
h
is
d
o
es
all
o
w
f
o
r
th
e
p
o
s
s
ib
ilit
y
th
a
t
m
u
ltip
le
g
en
e
s
i
n
a
n
in
d
iv
id
u
al
co
u
ld
b
e
m
u
ta
ted
.
T
h
e
m
o
d
eli
n
g
o
f
d
o
m
ai
n
v
alu
es
a
s
in
d
i
v
id
u
a
l
u
s
es
t
h
e
m
et
h
o
d
o
f
ev
e
n
l
y
d
iv
id
in
g
t
h
e
d
o
m
ai
n
[
2
2
]
.
T
h
e
r
an
g
e
o
f
d
o
m
ai
n
v
al
u
es
h
as
an
u
p
p
er
b
o
u
n
d
(
UB
)
o
f
1
an
d
th
e
lo
w
er
b
o
u
n
d
(
L
B
)
o
f
0
.
I
f
w
e
a
s
s
u
m
e
th
at
th
e
c
h
r
o
m
o
s
o
m
es
ar
e
b
n
-
1
b
n
…
b
1
b
0
,
th
e
f
o
llo
w
i
n
g
eq
u
atio
n
s
s
h
o
w
s
t
h
e
r
ep
r
esen
tatio
n
f
o
r
t
h
e
d
o
m
a
in
v
al
u
e
x
.
F
u
n
ct
io
n
2
s
h
o
w
s
t
h
e
eq
u
atio
n
f
o
r
co
n
v
er
t
in
g
i
n
d
iv
id
u
als
to
d
o
m
ai
n
v
a
lu
e
s
.
=
+
∑
2
−
1
=
0
2
−
1
(
−
)
(
2
)
T
h
is
eq
u
atio
n
m
a
k
es
a
n
in
d
i
v
id
u
al
o
f
all
0
'
s
b
e
th
e
L
B
an
d
an
i
n
d
i
v
id
u
al
o
f
all
1
'
s
b
e
th
e
UB
.
A
ll
d
o
m
a
in
v
al
u
es
i
n
b
et
w
ee
n
ar
e
d
iv
id
ed
ev
en
l
y
b
ased
u
p
o
n
th
e
n
u
m
b
er
o
f
ch
r
o
m
o
s
o
m
e
s
in
a
n
in
d
i
v
id
u
al.
I
n
th
is
r
esear
c
h
3
0
ch
r
o
m
o
s
o
m
es
w
er
e
u
s
ed
.
A
s
s
tated
ea
r
l
y
g
e
n
etic
d
iv
er
s
i
t
y
is
m
ea
s
u
r
ed
th
r
o
u
g
h
lar
g
er
v
alu
e
s
o
f
th
e
s
tan
d
ar
d
d
ev
iat
io
n
o
f
th
e
d
o
m
ai
n
v
al
u
es
i
n
th
e
f
i
n
al
g
e
n
er
atio
n
.
A
d
d
itio
n
all
y
,
t
h
is
r
esear
c
h
d
o
cu
m
en
ts
t
h
e
a
v
er
ag
e
f
it
n
es
s
o
f
t
h
e
f
in
a
l
g
e
n
er
atio
n
.
T
h
i
s
is
i
n
cl
u
d
ed
b
ec
au
s
e
it
i
s
n
o
t
ad
v
an
ta
g
eo
u
s
to
in
cr
ea
s
e
g
en
e
tic
d
iv
er
s
it
y
at
t
h
e
ex
p
en
s
e
o
f
f
it
n
es
s
.
T
h
is
w
o
u
ld
m
ea
n
th
a
t t
h
e
G
A
i
n
d
i
v
id
u
a
ls
h
a
v
e
n
o
t lo
ca
ted
th
e
o
p
ti
m
a.
Si
n
ce
G
A
s
ar
e
n
o
n
-
d
eter
m
i
n
is
t
ic
r
esu
lt
s
m
a
y
v
ar
y
f
o
r
e
ac
h
ex
ec
u
tio
n
o
f
th
e
alg
o
r
ith
m
.
Fo
r
ea
ch
co
m
b
i
n
atio
n
o
f
p
ar
a
m
eter
s
th
e
S
C
G
A
w
as
e
x
e
cu
ted
2
0
tim
e
s
an
d
all
r
esu
l
ts
w
er
e
av
er
a
g
ed
.
Stan
d
ar
d
d
ev
iatio
n
i
s
r
ea
ll
y
t
h
e
av
er
a
g
e
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
th
e
2
0
r
u
n
s
.
A
f
e
w
co
m
p
u
ted
v
al
u
es
ar
e
al
s
o
p
r
o
v
id
ed
.
T
h
e
d
if
f
er
e
n
ce
as
a
p
er
c
en
t
o
f
s
ta
n
d
ar
d
d
ev
iatio
n
is
ca
lcu
lated
f
o
r
ea
c
h
p
ar
a
m
et
er
s
et
co
m
p
ar
ed
to
th
e
b
ase
ca
s
e.
T
h
e
d
if
f
er
en
ce
as
a
p
er
ce
n
t
o
f
a
v
er
ag
e
f
i
tn
e
s
s
is
also
ca
lc
u
lated
.
T
h
i
s
m
a
k
es
it
ea
s
y
to
co
m
p
ar
e
a
p
ar
a
m
eter
s
et
to
t
h
e
b
ase
c
ase.
Fi
n
all
y
,
t
h
e
S
tu
d
e
n
t
T
-
T
est
is
p
er
f
o
r
m
ed
[
2
3
]
.
T
h
e
T
-
T
est
co
m
p
ar
es
t
h
e
s
tan
d
ar
d
d
ev
iatio
n
o
f
th
e
2
0
test
ca
s
e
s
f
o
r
th
e
b
ase
ca
s
e
to
ea
ch
s
et
o
f
p
ar
a
m
e
ter
s
.
T
h
e
p
v
a
lu
e
i
s
d
eter
m
i
n
ed
.
T
h
e
p
v
alu
e
th
r
es
h
o
ld
o
f
0
.
0
5
is
u
s
ed
to
d
eter
m
i
n
e
s
tat
is
tical
s
ig
n
i
f
ican
ce
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
E
x
p
er
i
m
e
n
t
r
esu
lts
ar
e
d
o
cu
m
en
ted
in
T
ab
les
1
th
r
o
u
g
h
9
.
T
ab
les
1
th
r
o
u
g
h
3
co
n
tai
n
r
esu
l
ts
f
o
r
f
u
n
ctio
n
F1
.
T
a
b
les
4
th
r
o
u
g
h
6
co
n
tain
r
esu
l
ts
f
o
r
f
u
n
c
t
io
n
F2
.
T
ab
les
7
th
r
o
u
g
h
9
co
n
tain
r
es
u
lts
f
o
r
f
u
n
ctio
n
F3
.
E
ac
h
tab
le
is
d
ed
icate
d
to
th
e
r
esu
lt
s
f
r
o
m
c
h
a
n
g
in
g
o
n
e
p
ar
a
m
e
ter
.
I
n
ea
ch
tab
le
t
h
e
f
ir
s
t
r
o
w
i
s
th
e
b
ase
ca
s
e
f
o
llo
w
ed
b
y
a
r
o
w
f
o
r
ea
ch
p
ar
a
m
eter
v
al
u
es
ch
an
g
ed
.
C
o
lu
m
n
SD
i
s
t
h
e
av
er
ag
e
o
f
s
ta
n
d
ar
d
d
ev
iatio
n
s
o
f
t
h
e
d
o
m
ain
v
al
u
es
o
f
t
h
e
f
i
n
al
g
e
n
er
atio
n
.
I
d
ea
ll
y
,
w
e
w
o
u
ld
li
k
e
th
i
s
to
b
e
lar
g
e
s
h
o
w
i
n
g
g
en
et
ic
d
iv
er
s
it
y
.
C
o
l
u
m
n
AF
is
t
h
e
a
v
er
ag
e
f
i
tn
e
s
s
o
f
t
h
e
f
i
n
al
g
en
er
atio
n
.
T
h
e
n
e
x
t
t
w
o
co
l
u
m
n
s
s
h
o
w
th
e
d
i
f
f
er
e
n
ce
as
a
p
er
ce
n
t o
f
t
h
e
b
ase
ca
s
e
to
t
h
e
p
ar
a
m
eter
s
et
v
a
lu
e
s
.
T
h
e
f
i
n
al
co
l
u
m
n
p
is
t
h
e
p
v
alu
e
f
r
o
m
th
e
T
-
T
est.
Usi
n
g
t
h
e
v
a
lu
e
o
f
p
e
q
u
al
to
0
.
0
5
as a
t
h
r
esh
o
ld
f
o
r
s
tati
s
tical
s
i
g
n
if
ica
n
ce
,
t
h
i
s
r
esear
ch
p
r
o
d
u
ce
s
v
er
y
m
i
x
ed
r
esu
lts
.
Fo
r
f
u
n
ct
io
n
F1
th
e
ca
s
es
o
f
N
=
6
0
,
M
=
0
.
0
0
8
an
d
M
=
0
.
0
0
6
p
r
o
d
u
ce
s
tatis
tica
ll
y
s
ig
n
i
f
ica
n
t
r
es
u
lts
.
M
=
0
.
0
0
9
co
m
e
s
v
er
y
clo
s
e
w
it
h
a
p
v
al
u
e
o
f
0
.
0
5
2
.
Fo
r
f
u
n
c
tio
n
F2
th
e
ca
s
e
s
o
f
G
=
2
4
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
IJ
-
A
I
Vo
l.
8
,
No
.
2
,
J
u
n
e
201
9
:
190
–
1
9
6
194
an
d
G
=
1
6
0
p
r
o
d
u
ce
s
tati
s
ti
ca
ll
y
s
i
g
n
i
f
ica
n
t
r
es
u
lts
.
Fo
r
F3
o
n
l
y
G
=
1
2
0
p
r
o
d
u
ce
s
ta
tis
ticall
y
s
i
g
n
if
ica
n
t
r
esu
lt
s
.
W
h
e
n
p
er
f
o
r
m
i
n
g
a
p
a
r
a
m
eter
s
e
n
s
iti
v
it
y
a
n
al
y
s
i
s
s
ta
tis
ticall
y
s
i
g
n
if
ica
n
t
r
es
u
lts
i
n
d
icate
a
co
r
r
el
atio
n
b
et
w
ee
n
th
e
p
ar
a
m
e
ter
an
d
g
e
n
etic
d
iv
er
s
it
y
.
T
ab
le
1
.
R
esu
lts
o
f
v
ar
y
in
g
N
f
o
r
F1
N
SD
AF
∆
∆
p
1
0
0
0
.
1
8
8
9
0
.
9
8
8
7
N
/
A
N
/
A
N
/
A
1
1
0
0
.
1
4
9
9
0
.
9
6
6
6
-
2
1
%
-
2%
0
.
6
7
1
2
0
0
.
2
8
0
4
0
.
9
5
1
6
4
8
%
-
4%
0
.
7
1
4
0
0
.
1
9
8
3
0
.
9
3
1
1
5%
-
6%
0
.
8
6
90
0
.
1
6
9
0
0
.
9
6
7
9
-
1
1
%
-
2%
0
.
1
2
80
0
.
2
4
5
1
0
.
9
7
2
3
3
0
%
-
2%
0
.
3
7
60
0
.
2
6
5
6
0
.
9
6
6
1
4
1
%
-
2%
0
.
0
3
9
T
ab
le
2
.
R
esu
lts
o
f
v
ar
y
in
g
G
f
o
r
F1
G
SD
AF
∆
∆
p
2
0
0
0
.
1
8
8
9
0
.
9
8
8
7
N
/
A
N
/
A
N
/
A
2
2
0
0
.
2
6
1
1
0
.
9
3
4
3
3
8
%
-
6%
0
.
9
2
2
4
0
0
.
2
5
2
4
0
.
9
4
2
8
3
4
%
-
5%
0
.
5
9
2
8
0
0
.
2
7
8
8
0
.
9
5
4
4
4
8
%
-
3%
0
.
9
3
1
8
0
0
.
2
2
2
5
0
.
9
8
1
2
1
8
%
-
1%
0
.
5
5
1
6
0
0
.
1
9
5
8
0
.
9
4
2
8
4%
-
5%
0
.
1
4
1
2
0
0
.
2
6
0
6
0
.
9
5
6
9
3
8
%
-
3%
0
.
5
T
ab
le
3
.
R
esu
lts
o
f
v
ar
y
in
g
M
f
o
r
F1
M
SD
AF
∆
∆
p
0
.
0
1
0
.
1
8
8
9
0
.
9
8
8
7
N
/
A
N
/
A
N
/
A
0
.
0
1
1
0
.
1
0
9
9
0
.
9
8
3
9
-
4
2
%
0%
0
.
8
7
0
.
0
1
2
0
.
1
7
3
8
0
.
9
8
6
1
-
8%
0%
0
.
8
8
0
.
0
1
4
0
.
1
4
5
7
0
.
9
6
5
0
-
2
3
%
-
2%
0
.
2
4
0
.
0
0
9
0
.
1
2
1
6
0
.
9
8
8
9
-
3
6
%
0%
0
.
0
5
2
0
.
0
0
8
0
.
2
3
5
0
0
.
9
7
5
8
2
4
%
-
1%
0
.
0
3
2
0
.
0
0
6
0
.
1
6
9
2
0
.
9
7
5
7
-
1
0
%
-
1%
0
.
0
2
7
T
ab
le
4
.
R
esu
lts
o
f
v
ar
y
in
g
N
f
o
r
F2
N
SD
AF
∆
∆
p
1
0
0
0
.
1
3
9
5
0
.
9
8
4
2
N
/
A
N
/
A
N
/
A
1
1
0
0
.
2
3
6
3
0
.
9
9
0
5
6
9
%
1%
0
.
1
7
1
2
0
0
.
1
1
9
0
0
.
9
9
1
2
-
1
5
%
1%
0
.
4
6
1
4
0
0
.
2
2
0
0
0
.
9
8
0
8
5
8
%
0%
0
.
8
8
90
0
.
0
9
4
3
0
.
9
8
8
8
-
3
2
%
0%
0
.
1
9
80
0
.
0
6
6
9
0
.
9
8
6
9
-
5
2
%
0%
0
.
3
1
60
0
.
1
7
4
7
0
.
9
8
3
0
2
5
%
0%
0
.
9
8
T
ab
le
5
.
R
esu
lts
o
f
v
ar
y
in
g
G
f
o
r
F2
G
SD
AF
∆
∆
p
2
0
0
0
.
1
3
9
4
5
2
8
0
.
9
841
N
/
A
N
/
A
N
/
A
2
2
0
0
.
0
6
9
3
4
0
9
0
.
9
8
9
7
-
5
0
%
1%
0
.
9
9
2
4
0
0
.
2
5
4
5
7
8
6
0
.
9
8
7
0
8
3
%
0%
0
.
0
4
7
2
8
0
0
.
1
9
8
6
7
3
1
0
.
9
8
9
3
4
2
%
1%
0
.
4
4
1
8
0
0
.
0
7
0
0
8
8
4
0
.
9
8
9
2
-
5
0
%
1%
0
.
6
3
1
6
0
0
.
1
5
2
9
7
8
1
0
.
9
8
8
8
1
0
%
0%
0
.
0
3
2
1
2
0
0
.
1
4
0
0
2
0
6
0
.
9
8
5
7
0%
0%
0
.
4
0
T
ab
le
6
.
R
esu
lts
o
f
v
ar
y
in
g
M
f
o
r
F2
M
SD
AF
∆
∆
p
0
.
0
1
0
.
1
3
9
5
0
.
9
8
4
2
N
/
A
N
/
A
N
/
A
0
.
0
1
1
0
.
1
8
6
0
0
.
9
4
7
0
3
3
%
-
4%
0
.
4
1
0
.
0
1
2
0
.
0
9
4
5
0
.
9
8
7
8
-
3
2
%
0%
0
.
2
6
0
.
0
1
4
0
.
1
5
8
0
0
.
9
7
8
8
1
3
%
-
1%
0
.
2
2
0
.
0
0
9
0
.
0
7
1
7
0
.
9
8
9
7
-
4
9
%
1%
0
.
5
7
0
.
0
0
8
0
.
1
0
4
2
0
.
9
8
9
0
-
2
5
%
0%
0
.
8
7
0
.
0
0
6
0
.
0
9
7
6
0
.
9
8
3
6
-
3
0
%
0%
0
.
8
5
T
ab
le
7
.
R
esu
lts
o
f
v
ar
y
in
g
N
f
o
r
F3
N
SD
AF
∆
∆
p
1
0
0
0
.
1
9
0
9
0
.
9
8
6
6
N
/
A
N
/
A
N
/
A
1
1
0
0
.
1
4
8
1
0
.
9
6
8
3
-
2
2
%
-
2%
0
.
4
6
1
2
0
0
.
1
8
3
3
0
.
9
6
0
8
-
4%
-
3%
0
.
2
9
1
4
0
0
.
1
5
8
6
0
.
9
6
7
0
-
1
7
%
-
2%
0
.
7
7
90
0
.
2
3
8
1
0
.
9
6
3
6
2
5
%
-
2%
0
.
2
9
80
0
.
0
9
7
8
0
.
9
8
4
0
-
4
9
%
0%
0
.
8
8
60
0
.
0
625
0
.
9
8
3
3
-
6
7
%
0%
0
.
0
7
T
ab
le
8
.
R
esu
lts
o
f
v
ar
y
in
g
G
f
o
r
F3
G
SD
AF
∆
∆
p
2
0
0
0
.
1
9
0
9
0
.
9
8
6
6
N
/
A
N
/
A
N
/
A
2
2
0
0
.
1
3
4
5
0
.
9
8
3
0
-
3
0
%
0%
0
.
5
2
2
4
0
0
.
3
7
1
7
0
.
9
3
8
9
9
5
%
-
5%
0
.
4
6
2
8
0
0
.
1
2
6
4
0
.
9
8
0
0
-
3
4
%
0%
0
.
9
1
1
8
0
0
.
1
8
4
1
0
.
9
5
8
5
-
4%
-
3%
0
.
1
0
1
6
0
0
.
1
1
5
7
0
.
9
7
2
9
-
3
9
%
-
1%
0
.
2
6
1
2
0
0
.
2
2
8
6
0
.
9
4
7
9
2
0
%
-
4%
0
.
0
2
T
ab
le
9
.
R
esu
lts
o
f
v
ar
y
in
g
M
f
o
r
F3
M
SD
AF
∆
∆
p
0
.
0
1
0
.
1
9
0
9
0
.
9
8
6
6
N
/
A
N
/
A
N
/
A
0
.
0
1
1
0
.
2
7
1
1
0
.
9
6
5
1
4
2
%
-
2%
0
.
1
2
0
.
0
1
2
0
.
3
0
1
3
0
.
9
6
1
0
5
8
%
-
3%
0
.
2
7
0
.
0
1
4
0
.
1
2
8
8
0
.
9
9
5
2
-
3
3
%
1%
0
.
2
2
0.
0
0
9
0
.
2
7
0
0
0
.
9
3
3
2
4
1
%
-
5%
0
.
2
4
0
.
0
0
8
0
.
1
5
0
1
0
.
9
8
4
8
-
2
1
%
0%
0
.
2
9
0
.
0
0
6
0
.
0
5
4
0
0
.
9
9
0
0
-
7
2
%
0%
0
.
9
6
5.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
o
n
l
y
b
e
g
i
n
s
t
o
ex
a
m
i
n
e
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
g
e
n
etic
d
iv
er
s
it
y
an
d
NG
A
p
ar
am
eter
s
.
Mo
r
e
r
esear
ch
n
ee
d
s
to
b
e
d
o
n
e.
T
h
is
g
i
v
e
s
r
is
e
to
n
u
m
er
o
u
s
ar
ea
s
o
f
ad
d
itio
n
al
r
esear
ch
.
T
h
is
r
esear
ch
o
n
l
y
u
s
ed
o
n
e
NG
A
al
g
o
r
ith
m
,
S
C
G
A
,
b
u
t
t
h
er
e
ar
e
o
th
er
N
G
A
s
th
at
co
u
ld
b
en
ef
it
f
r
o
m
t
h
i
s
r
esear
ch
.
An
al
g
o
r
ith
m
d
o
esn
't
n
ec
ess
ar
il
y
n
ee
d
to
u
s
e
th
e
t
er
m
r
ad
iu
s
to
b
e
a
ca
n
d
id
ate
f
o
r
f
u
r
th
er
r
esea
r
ch
.
T
h
e
Fit
n
e
s
s
S
h
ar
in
g
a
lg
o
r
it
h
m
[
1
9
]
also
s
u
f
f
er
s
f
r
o
m
t
h
e
NR
P
[
1
0
]
.
An
y
o
f
th
e
s
e
t
y
p
es
o
f
a
lg
o
r
it
h
m
s
w
o
u
ld
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
S
en
s
itivity a
n
a
lysi
s
o
f a
s
p
ec
ies co
n
s
ervin
g
g
en
etic
a
lg
o
r
ith
m'
s
p
a
r
a
mete
r
s
f
o
r
.
.
.
(
Mich
a
el
S
co
tt B
r
o
w
n
)
195
m
ak
e
a
g
o
o
d
s
u
b
j
ec
t
f
o
r
f
u
tu
r
e
r
esear
c
h
.
On
e
-
at
-
a
-
ti
m
e
is
n
o
t
th
e
o
n
l
y
s
e
n
s
itiv
it
y
an
al
y
s
is
m
et
h
o
d
.
T
h
er
e
ar
e
m
an
y
o
t
h
er
s
.
Di
f
f
e
r
en
tial
Se
n
s
i
tiv
it
y
An
al
y
s
is
d
ev
elo
p
s
s
e
n
s
it
iv
i
t
y
co
e
f
f
ic
ien
t
s
th
at
r
ep
r
ese
n
t
t
h
e
r
atio
o
f
ch
an
g
e
o
f
o
u
tp
u
t
to
in
p
u
t
[
2
4
]
.
I
n
Sen
s
iti
v
it
y
I
n
d
e
x
th
e
o
u
tp
u
t
p
er
ce
n
t
d
if
f
er
e
n
c
e
is
co
m
p
u
ted
b
ased
o
n
ev
al
u
ati
n
g
ea
c
h
p
ar
a
m
et
er
v
alu
e
f
r
o
m
a
m
i
n
i
m
u
m
to
m
a
x
i
m
u
m
v
al
u
e
[
2
5
]
.
A
n
d
th
er
e
ar
e
m
a
n
y
o
th
er
m
e
th
o
d
s
[
1
8
]
.
Usi
n
g
o
th
er
s
e
n
s
it
iv
i
t
y
an
al
y
s
is
m
e
th
o
d
s
i
s
a
n
i
m
p
o
r
tan
t
ar
ea
o
f
f
u
t
u
r
e
r
esear
c
h
.
T
h
is
r
esear
ch
o
n
l
y
u
s
ed
3
b
en
ch
m
ar
k
f
u
n
c
tio
n
s
s
h
o
w
n
i
n
eq
u
atio
n
s
F1
,
F2
an
d
F3
.
B
u
t
th
er
e
ar
e
o
th
er
b
en
ch
m
ar
k
f
u
n
ctio
n
s
.
T
h
ese
f
u
n
ct
io
n
s
co
m
e
f
r
o
m
a
s
e
t
o
f
f
u
n
ctio
n
s
u
s
ed
b
y
B
er
n
ier
[
1
6
]
an
d
B
r
o
w
n
[
1
2
]
.
T
h
er
e
ar
e
o
th
er
b
en
ch
m
ar
k
f
u
n
ctio
n
s
in
t
h
e
s
e
t.
T
h
er
e
ar
e
o
th
e
r
in
ter
esti
n
g
f
u
n
ctio
n
s
u
s
ed
i
n
o
th
er
G
A
r
esear
c
h
.
T
h
e
A
c
k
l
e
y
f
u
n
ctio
n
w
as
u
s
ed
in
L
in
g
et.
al.
[
2
6
]
an
d
R
ag
h
u
w
an
s
h
i
an
d
Ka
k
d
e
[
2
7
]
.
S
h
u
b
er
t
w
a
s
u
s
ed
in
An
d
o
an
d
Ko
b
ay
a
s
h
i
[
2
8
]
.
R
o
s
en
b
r
o
ck
w
a
s
u
s
ed
in
R
a
g
h
u
w
an
s
h
i
an
d
Ka
k
d
e
[
2
9
]
.
A
d
d
itio
n
al
r
esear
c
h
w
it
h
o
th
er
b
en
ch
m
ar
k
f
u
n
ctio
n
s
w
o
u
ld
b
e
b
en
ef
icial.
P
er
h
ap
s
o
th
er
p
ar
a
m
eter
s
o
f
t
h
e
e
x
p
er
i
m
e
n
t
co
u
ld
p
r
o
d
u
ce
m
o
r
e
d
ec
is
i
v
e
r
esu
lt
s
.
E
v
en
th
o
u
g
h
t
h
e
b
ase
ca
s
e
v
a
lu
es
ar
e
u
s
ed
i
n
o
t
h
er
r
esear
c
h
,
th
e
y
m
a
y
n
o
t
b
e
th
e
o
p
ti
m
al
s
et
o
f
v
al
u
e
s
f
o
r
co
m
p
ar
is
o
n
.
P
er
h
ap
s
u
s
in
g
m
o
r
e
t
h
a
n
2
0
tr
ials
co
u
ld
p
r
o
d
u
ce
d
if
f
er
e
n
t
r
es
u
lts
o
r
p
o
s
s
ib
l
y
c
h
a
n
g
in
g
t
h
e
±
1
0
%,
±
2
0
%
an
d
±
4
0
%
f
o
r
ea
ch
p
ar
a
m
et
er
co
u
ld
g
iv
e
cle
ar
er
r
esu
lts
.
T
h
is
r
esear
c
h
s
h
o
ws
th
at
i
n
s
o
m
e
ca
s
e
s
th
e
G
A
p
ar
am
e
ter
s
o
f
n
u
m
b
er
o
f
in
d
iv
id
u
al
s
,
n
u
m
b
er
o
f
g
e
n
er
atio
n
s
a
n
d
m
u
ta
tio
n
r
ate
ca
n
af
f
ec
t
th
e
g
e
n
etic
d
iv
er
s
it
y
.
B
u
t
n
o
d
ef
in
i
tiv
e
c
o
n
clu
s
io
n
s
ca
n
b
e
m
ad
e.
O
n
e
p
o
s
s
ib
le
co
n
cl
u
s
io
n
i
s
t
h
at
h
o
w
G
A
p
ar
a
m
eter
s
af
f
ec
t
g
en
e
tic
d
i
v
er
s
it
y
i
s
d
if
f
er
en
t
f
o
r
ea
c
h
f
u
n
ctio
n
.
T
h
is
th
eo
r
y
i
s
s
u
p
p
o
r
ted
b
y
o
b
s
er
v
at
io
n
th
at
th
e
m
u
ta
tio
n
r
ate
i
n
t
w
o
ca
s
es
a
f
f
ec
t
s
g
e
n
etic
d
i
v
er
s
it
y
in
F1
,
b
u
t
n
o
t
F2
o
r
F3
.
An
d
th
e
n
u
m
b
er
o
f
g
en
er
atio
n
s
af
f
ec
t
s
g
e
n
etic
d
iv
er
s
it
y
in
F2
a
n
d
F3
,
b
u
t
n
o
t
F1
.
R
esu
lt
s
s
h
o
w
t
h
at
all
th
r
e
e
p
ar
am
eter
s
af
f
ec
t
g
en
et
ic
d
i
v
er
s
it
y
i
n
a
s
tat
is
tica
ll
y
s
i
g
n
i
f
ica
n
t
w
a
y
i
n
at
least
o
n
e
test
ca
s
e.
P
r
eser
v
in
g
g
e
n
e
tic
d
iv
er
s
it
y
is
k
e
y
to
ad
d
r
ess
in
g
th
e
NR
P
.
T
h
is
r
esear
ch
atte
m
p
ts
to
ex
a
m
i
n
e
f
ac
to
r
s
th
at
at
tr
i
b
u
te
to
g
en
e
tic
d
iv
er
s
it
y
,
o
th
er
t
h
a
n
th
e
r
ad
iu
s
p
ar
a
m
eter
.
Ma
n
y
n
e
w
ar
ea
s
o
f
r
esear
c
h
h
av
e
b
e
en
s
u
g
g
e
s
ted
th
a
t
w
ill
h
elp
u
s
lear
n
m
o
r
e
ab
o
u
t
g
en
et
ic
d
iv
er
s
it
y
.
RE
F
E
R
E
NC
E
S
[1
]
A
.
D.
Cio
p
p
a
,
C
.
De
S
tef
a
n
o
a
n
d
A
.
M
a
rc
e
ll
i,
“
On
t
h
e
Ro
le
o
f
P
o
p
u
lati
o
n
S
ize
a
n
d
Nic
h
e
Ra
d
iu
s
i
n
F
it
n
e
ss
S
h
a
rin
g
”
,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Evo
lu
ti
o
n
a
ry
Co
mp
u
t
a
ti
o
n
,
2
0
0
4
,
8
(6
)
,
p
p
.
5
8
0
-
5
9
2
.
[2
]
J.
P
.
L
i,
M
.
E.
Ba
laz
s,
G
.
T
.
P
a
rk
s
a
n
d
P
.
J.
Clark
so
n
,
“
A
sp
e
c
i
e
s
c
o
n
se
rv
in
g
g
e
n
e
ti
c
a
l
g
o
rit
h
m
f
o
r
m
u
lt
im
o
d
a
l
f
u
n
c
ti
o
n
o
p
t
im
iza
ti
o
n
”
,
Evo
lu
ti
o
n
a
ry
c
o
mp
u
t
a
ti
o
n
,
2
0
0
2
,
1
0
(
3
),
p
p
.
2
0
7
-
2
3
4
.
[3
]
J.
H.
Ho
ll
a
n
d
,
“
A
d
a
p
tatio
n
i
n
n
a
t
u
ra
l
a
n
d
a
rti
f
icia
l
s
y
ste
m
s:
a
n
in
tro
d
u
c
to
ry
a
n
a
l
y
si
s
w
it
h
a
p
p
li
c
a
ti
o
n
s
to
b
io
l
o
g
y
,
c
o
n
tro
l,
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
c
e
”
,
U M
ich
ig
a
n
Pre
ss
,
1
9
7
5
.
[4
]
O.
M
.
S
h
ir,
“
Nic
h
i
n
g
in
Ev
o
l
u
ti
o
n
a
ry
A
lg
o
rit
h
m
s”
,
Ha
n
d
b
o
o
k
o
n
Na
tu
ra
l
C
o
mp
u
ti
n
g
.
S
p
ri
n
g
e
r
Be
rli
n
He
id
e
l
b
e
rg
,
2
0
1
2
,
p
p
.
1
0
3
5
-
1
0
6
9
.
[5
]
K.
De
Jo
n
g
,
“
A
n
a
n
a
l
y
si
s
o
f
th
e
b
e
h
a
v
io
r
o
f
a
c
las
s
o
f
g
e
n
e
ti
c
a
d
a
p
ti
v
e
s
y
ste
m
s
”
,
Do
c
to
ra
l
Diss
e
rta
t
io
n
.
Un
iv
e
rsit
y
o
f
M
ich
ig
a
n
,
1
9
7
5
.
[6
]
M
.
S
.
Br
o
w
n
a
n
d
J.
Yo
u
n
g
,
“
Rep
li
c
a
ti
o
n
o
f
t
h
e
Nich
e
Ra
d
iu
s
Pro
b
lem
u
si
n
g
C
lu
ste
rin
g
Ge
n
e
ti
c
Al
g
o
rit
h
ms
[
Ab
stra
c
t
]
”
,
In
T
h
e
T
w
e
n
t
y
-
S
e
v
e
n
th
I
n
tern
a
ti
o
n
a
l
F
lairs Co
n
f
e
re
n
c
e
,
2
0
1
4
.
[7
]
O.
M
.
S
h
ir
a
n
d
T
.
Ba
c
k
,
“
Nic
h
e
Ra
d
iu
s
A
d
a
p
tatio
n
in
th
e
C
M
A
-
ES
Nic
h
in
g
A
lg
o
rit
h
m
“
,
Pa
ra
ll
e
l
P
ro
b
lem
S
o
lvin
g
fro
m Na
t
u
re
-
PP
S
N
I
X
,
2
0
0
6
,
p
p
.
1
4
2
-
1
5
1
.
[8
]
O.
M
.
S
h
ir,
M
.
Emm
e
rich
a
n
d
T
.
Ba
c
k
,
“
A
d
a
p
ti
v
e
Nic
h
e
Ra
d
ii
a
n
d
Nic
h
e
S
h
a
p
e
s
A
p
p
ro
a
c
h
e
s
f
o
r
Nic
h
in
g
w
it
h
th
e
CM
A
-
ES
”
,
Evo
lu
ti
o
n
a
ry
Co
mp
u
t
a
ti
o
n
,
2
0
1
0
,
1
8
(1
)
,
p
p
.
9
7
-
1
2
6
.
[9
]
O.
M
.
S
h
ir,
M
.
Emm
e
rich
a
n
d
T.
Ba
c
k
,
“
S
e
lf
-
Ad
a
p
ti
v
e
Nich
in
g
CM
A
-
ES
wit
h
M
a
h
a
la
n
o
b
is
M
e
tric
”
,
2
0
0
7
IEE
E
Co
n
g
re
ss
o
n
Ev
o
lu
ti
o
n
a
ry
Co
m
p
u
tatio
n
,
2
0
0
7
,
p
p
.
8
2
0
-
8
2
7
.
[1
0
]
M
.
Je
las
it
y
a
n
d
J.
Do
m
b
i,
“
GA
S
,
a
n
A
p
p
ro
a
c
h
to
a
S
o
lu
t
io
n
o
f
th
e
Nic
h
e
Ra
d
iu
s
P
ro
b
lem
”
,
G
e
n
e
ti
c
Al
g
o
rit
h
ms
in
En
g
i
n
e
e
rin
g
S
y
ste
ms
:
In
n
o
v
a
ti
o
n
s a
n
d
Ap
p
li
c
a
ti
o
n
s
,
1
9
9
5
,
4
1
4
,
p
p
.
4
2
4
-
4
2
9
.
[1
1
]
M
.
Je
las
it
y
a
n
d
J.
Do
m
b
i,
“
GA
S
,
a
Co
n
c
e
p
t
o
n
M
o
d
e
li
n
g
S
p
e
c
ies
in
Ge
n
e
ti
c
A
lg
o
rit
h
m
s
”
,
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
,
1
9
8
8
,
9
9
(1
),
p
p
.
1
-
1
9
.
[1
2
]
M
.
S
.
Bro
w
n
,
“
A
S
p
e
c
ies
-
Co
n
se
rv
in
g
G
e
n
e
ti
c
A
lg
o
rit
h
m
f
o
r
M
u
lt
im
o
d
a
l
Op
ti
m
iza
ti
o
n
.
D
o
c
to
ra
l
Diss
e
rtatio
n
”
,
No
v
a
S
o
u
t
h
e
a
ste
rn
Un
iv
e
rsity
,
2
0
1
0
.
[1
3
]
D.
F
a
n
,
W
.
S
h
e
n
g
a
n
d
S
.
Ch
e
n
,
2
0
1
3
.
“
A
Div
e
rs
e
Nich
e
Ra
d
ii
Nich
in
g
T
e
c
h
n
i
q
u
e
fo
r
M
u
lt
i
mo
d
a
l
F
u
n
c
t
i
o
n
Op
ti
miza
ti
o
n
”
,
C
h
i
n
e
se
A
u
to
m
a
ti
o
n
C
o
n
g
re
ss
,
Ch
a
n
g
sh
a
,
C
h
in
a
,
2
0
1
3
,
p
p
.
7
0
-
7
4
.
[1
4
]
V
.
v
a
n
d
e
r
G
o
e
s,
A
s
y
m
m
e
tri
c
S
h
a
rin
g
,
2
0
0
8
.
[1
5
]
V
.
v
a
n
d
e
r
G
o
e
s,
O.
M
.
S
h
ir
a
n
d
T
.
Ba
c
k
,
“
Nich
e
Ra
d
iu
s
Ad
a
p
ta
ti
o
n
wit
h
Asy
mm
e
tric
S
h
a
rin
g
”
,
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
P
a
ra
ll
e
l
P
r
o
b
lem
S
o
lv
in
g
f
ro
m
Na
tu
re
,
2
0
0
8
,
p
p
.
1
9
5
-
2
0
4
.
[1
6
]
L
.
B
e
rn
ier,
“
A
G
e
n
e
ti
c
A
lg
o
rit
h
m
w
it
h
S
e
lf
-
a
d
a
p
ti
v
e
Nic
h
e
S
izin
g
”
,
Ottaw
a
:
Na
ti
o
n
a
l
L
ib
ra
r
y
o
f
Ca
n
a
d
a
,
1
9
9
5
.
[1
7
]
H.
J.
Bre
m
e
r
m
a
n
n
,
“
T
h
e
e
v
o
lu
ti
o
n
o
f
in
telli
g
e
n
c
e
:
T
h
e
n
e
rv
o
u
s
s
y
ste
m
a
s
a
m
o
d
e
l
o
f
it
s
e
n
v
iro
n
m
e
n
t”,.
(T
e
c
h
n
ica
l
Re
p
o
rt
No
.
1
,
Co
n
trac
t
No
.
4
4
7
,
I
ss
u
e
1
7
)
U
n
iv
e
rsity
o
f
W
a
sh
in
g
to
n
,
De
p
a
rtm
e
n
t
o
f
M
a
th
e
m
a
ti
c
s,
1
9
5
8
.
[1
8
]
D.
M
.
Ha
m
b
y
,
“
A
Re
v
ie
w
o
f
T
e
c
h
n
iq
u
e
s
f
o
r
P
a
ra
m
e
ter
S
e
n
siti
v
it
y
A
n
a
l
y
sis
o
f
En
v
iro
n
m
e
n
tal
M
o
d
e
ls”
,
En
v
iro
n
me
n
ta
l
M
o
n
it
o
rin
g
a
n
d
A
ss
e
ss
m
e
n
t
,
1
9
9
4
,
3
2
,
p
p
.
1
3
5
-
1
5
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
IJ
-
A
I
Vo
l.
8
,
No
.
2
,
J
u
n
e
201
9
:
190
–
1
9
6
196
[1
9
]
D.
E.
G
o
ld
b
e
rg
a
n
d
J.
Rich
a
rd
so
n
,
“
Ge
n
e
ti
c
a
l
g
o
rit
h
ms
wit
h
sh
a
rin
g
fo
r
mu
lt
imo
d
a
l
fu
n
c
t
io
n
o
p
ti
miz
a
ti
o
n
”
,
In
G
e
n
e
ti
c
a
lg
o
rit
h
m
s
a
n
d
th
e
ir
a
p
p
li
c
a
ti
o
n
s:
P
r
o
c
e
e
d
in
g
s
o
f
th
e
S
e
c
o
n
d
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
G
e
n
e
ti
c
A
l
g
o
rit
h
m
s,
Hill
sd
a
le,
NJ
:
L
a
w
re
n
c
e
Erl
b
a
u
m
,
Ju
ly
1
9
8
7
,
p
p
.
4
1
-
4
9
.
[2
0
]
C.
G
.
L
e
e
,
,
D.
H.
Ch
o
a
n
d
H.
K.
Ju
n
g
,
“
Nic
h
in
g
g
e
n
e
ti
c
a
lg
o
rit
h
m
w
it
h
re
stricte
d
c
o
m
p
e
ti
ti
o
n
se
lec
ti
o
n
f
o
r
m
u
lt
i
m
o
d
a
l
f
u
n
c
ti
o
n
o
p
ti
m
iza
ti
o
n
”
,
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
ma
g
n
e
ti
c
s
,
1
9
9
9
,
3
5
(3
)
,
p
p
.
1
7
2
2
-
1
7
2
5
.
[2
1
]
B.
L
.
M
il
ler
a
n
d
M
.
J.
S
h
a
w,
“
Ge
n
e
ti
c
a
lg
o
rith
ms
wit
h
d
y
n
a
mi
c
n
ich
e
sh
a
ri
n
g
f
o
r
mu
lt
i
mo
d
a
l
f
u
n
c
ti
o
n
o
p
ti
miz
a
ti
o
n
”,
P
r
o
c
e
e
d
in
g
s o
f
IE
EE
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
E
v
o
lu
ti
o
n
a
ry
Co
m
p
u
tatio
n
,
1
9
9
6
,
p
p
.
7
8
6
-
7
9
1
.
[2
2
]
C.
Z.
Ja
n
ik
o
w
a
n
d
Z.
M
ich
a
lew
i
c
z
,
“
A
n
e
x
p
e
ri
m
e
n
tal
c
o
m
p
a
riso
n
o
f
b
in
a
ry
a
n
d
f
lo
a
ti
n
g
p
o
in
t
re
p
re
se
n
tatio
n
s
i
n
g
e
n
e
ti
c
a
lg
o
rit
h
m
s”
,
In
ICGA,
Ju
l
y
1
9
9
1
,
p
p
.
3
1
-
3
6
.
[2
3
]
S
tu
d
e
n
t,
“
T
h
e
p
r
o
b
a
b
le erro
r
o
f
a
m
e
a
n
”
,
Bio
m
e
tri
k
a
,
1
9
0
8
,
p
p
.
1
-
2
5
.
[2
4
]
T
.
J.
Krie
g
e
r,
C.
Du
rsto
n
a
n
d
D.
C.
A
lb
rig
h
t,
,
“
S
tatisti
c
a
l
d
e
term
in
a
ti
o
n
o
f
e
ff
e
c
ti
v
e
v
a
riab
le
s
in
se
n
siti
v
it
y
a
n
a
ly
sis”
,
T
ra
n
sa
c
ti
o
n
s
o
f
t
h
e
Am
e
ric
a
n
Nu
c
lea
r
S
o
c
iety
,
1
9
7
8
,
2
8
.
[2
5
]
F
.
O.
Ho
f
fm
a
n
a
n
d
C.
W
.
M
il
l
e
r,
“
Un
c
e
rta
in
ti
e
s
in
e
n
v
ir
o
n
me
n
ta
l
r
a
d
i
o
lo
g
ica
l
a
ss
e
ss
me
n
t
mo
d
e
ls
a
n
d
th
e
ir
imp
li
c
a
ti
o
n
s
”,
In
P
r
o
c
e
e
d
in
g
s
o
f
th
e
Nin
e
tee
n
t
h
A
n
n
u
a
l
M
e
e
ti
n
g
o
f
th
e
Na
ti
o
n
a
l
C
o
u
n
c
il
o
n
Ra
d
i
a
ti
o
n
P
ro
t
e
c
ti
o
n
a
n
d
M
e
a
su
re
m
e
n
ts,
A
p
ril
1
9
8
3
,
p
p
.
6
-
7.
[2
6
]
Q.
L
in
g
,
G
.
W
a
,
Z.
Ya
n
g
a
n
d
Q.
W
a
n
g
,
“
Cro
w
d
in
g
Clu
ste
rin
g
Ge
n
e
ti
c
A
lg
o
rit
h
m
f
o
r
M
u
lt
i
m
o
d
a
l
F
u
n
c
ti
o
n
Op
ti
m
iza
ti
o
n
”
,
Ap
p
li
e
d
S
o
ft
Co
m
p
u
ti
n
g
,
2
0
0
8
,
8
,
p
p
.
8
8
-
9
5
.
[2
7
]
M
.
M
.
Ra
g
h
u
w
a
n
sh
i
a
n
d
O.
G
.
Ka
k
d
e
,
“
Distrib
u
ted
Qu
a
si
S
tea
d
y
-
S
tate
Ge
n
e
ti
c
A
l
g
o
rit
h
m
w
i
th
Nic
h
e
s
a
n
d
S
p
e
c
ies
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ta
ti
o
n
a
l
In
telli
g
e
n
c
e
Res
e
a
rc
h
,
2
0
0
7
a
,
3
(2
),
p
p
.
1
5
5
-
1
6
4
.
[2
8
]
S
.
A
n
d
o
a
n
d
S
.
Ko
b
a
y
a
sh
i,
“
Fi
tn
e
ss
-
b
a
se
d
Ne
ig
h
b
o
r
S
e
lec
ti
o
n
fo
r
M
u
lt
imo
d
a
l
F
u
n
c
ti
o
n
Op
ti
miz
a
ti
o
n
”
P
ro
c
e
e
d
in
g
o
f
th
e
2
0
0
5
Co
n
f
e
re
n
c
e
o
n
G
e
n
e
ti
c
a
n
d
Ev
o
l
u
ti
o
n
a
ry
Co
m
p
u
tatio
n
,
W
a
sh
in
g
to
n
DC,
2
0
0
5
,
1
5
7
3
-
1
5
7
4
.
[2
9
]
M
.
M
.
Ra
g
h
u
w
a
n
sh
i
a
n
d
O.
G
.
Ka
k
d
e
,
“
Distrib
u
ted
Qu
a
si
S
tea
d
y
-
S
tate
Ge
n
e
ti
c
A
l
g
o
rit
h
m
w
i
th
Nic
h
e
s
a
n
d
S
p
e
c
ies
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ta
ti
o
n
a
l
In
telli
g
e
n
c
e
Res
e
a
rc
h
,
2
0
0
7
b
,
3
(2
),
p
p
.
1
5
5
-
1
6
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.