I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
,
p
p
.
1508
~
1
5
1
7
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
3
.
pp
1
5
0
8
-
1
5
1
7
1508
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Tuni
ng
featur
e se
lection to
enha
nce
ma
chine learni
ng
predictions
o
f
ba
ndg
a
p and
ef
f
icie
ncy
in
cha
lco
g
eni
de
pero
v
skites
O
s
ph
a
nie
M
ent
a
ri
P
rim
a
dia
nti
1
,
Ry
a
n Nur
I
m
a
n
1
,
M
uh
a
m
m
a
d Z
im
a
m
ul Adli
1
,
Ag
un
g
M
uh
a
m
a
d T
o
ha
1
,
Ag
un
g
Su
ry
a
Wibo
wo
2
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
I
sl
a
m N
u
sa
n
t
a
r
a
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
Te
l
k
o
m
U
n
i
v
e
r
si
t
y
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
2
3
,
2
0
2
5
R
ev
is
ed
Ma
r
1
8
,
2
0
2
6
Acc
ep
ted
Ma
r
2
6
,
2
0
2
6
S
o
lar
c
e
ll
tec
h
n
o
lo
g
y
h
a
s
a
d
v
a
n
c
e
d
ra
p
i
d
ly
i
n
e
fficie
n
c
y
a
n
d
m
a
teria
l
in
n
o
v
a
ti
o
n
.
As
a
re
n
e
wa
b
le
e
n
e
rg
y
so
u
rc
e
,
so
lar
c
e
ll
s
h
e
lp
m
it
ig
a
te
th
e
g
lo
b
a
l
e
n
e
rg
y
c
risis.
P
e
ro
v
sk
it
e
-
b
a
se
d
so
lar
c
e
ll
s
h
a
v
e
re
c
e
n
tl
y
a
c
h
iev
e
d
e
fficie
n
c
ies
a
b
o
v
e
2
5
%
,
su
r
p
a
ss
in
g
c
o
n
v
e
n
t
io
n
a
l
sili
c
o
n
c
e
ll
s.
Am
o
n
g
e
m
e
rg
in
g
m
a
teria
ls,
c
h
a
lco
g
e
n
id
e
p
e
ro
v
sk
it
e
s
sh
o
w
g
re
a
t
p
r
o
m
i
se
d
u
e
to
th
e
ir
su
p
e
rio
r
sta
b
il
it
y
c
o
m
p
a
re
d
t
o
h
a
li
d
e
p
e
ro
v
sk
it
e
s.
Ho
we
v
e
r,
t
h
e
y
re
m
a
in
in
th
e
e
x
p
l
o
ra
ti
o
n
sta
g
e
,
m
a
k
in
g
a
c
c
u
ra
te
p
re
d
ictio
n
s
o
f
th
e
ir
e
lec
tri
c
a
l
p
ro
p
e
rti
e
s,
e
sp
e
c
ially
b
a
n
d
g
a
p
,
e
ss
e
n
ti
a
l
f
o
r
a
ss
e
ss
in
g
p
o
ten
ti
a
l
in
so
lar
c
e
ll
a
p
p
li
c
a
ti
o
n
s.
T
h
is
stu
d
y
p
re
d
icts
b
a
n
d
g
a
p
v
a
l
u
e
s
u
sin
g
c
o
m
p
u
tati
o
n
a
l
m
e
th
o
d
s,
e
m
p
h
a
siz
in
g
e
fficie
n
c
y
a
n
d
c
o
st
re
d
u
c
ti
o
n
c
o
m
p
a
re
d
t
o
e
x
p
e
rime
n
tal
a
p
p
ro
a
c
h
e
s.
Ke
y
fe
a
tu
re
s
d
e
riv
e
d
fro
m
c
o
ll
e
c
ted
d
a
ta
in
c
lu
d
e
o
x
i
d
a
ti
o
n
sta
te,
e
lec
tro
n
e
g
a
ti
v
it
y
,
c
o
o
r
d
in
a
ti
o
n
n
u
m
b
e
r,
io
n
ic
ra
d
iu
s,
a
n
d
d
e
n
sity
.
S
e
v
e
ra
l
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
lg
o
rit
h
m
s:
Ad
a
Bo
o
st
Re
g
re
ss
o
r,
g
ra
d
ie
n
t
b
o
o
stin
g
re
g
re
ss
o
r,
su
p
p
o
rt
v
e
c
to
r
re
g
re
ss
o
r
,
Ca
tBo
o
st
Re
g
re
ss
o
r,
a
n
d
k
-
n
e
i
g
h
b
o
r
re
g
re
ss
o
r
,
we
re
imp
lem
e
n
ted
u
sin
g
P
y
t
h
o
n
.
Th
e
re
se
a
rc
h
p
ro
c
e
ss
in
v
o
lv
e
d
d
a
ta
c
o
ll
e
c
ti
o
n
,
p
re
p
r
o
c
e
ss
in
g
(fe
a
tu
r
e
sc
a
li
n
g
,
fu
sio
n
,
re
d
u
c
ti
o
n
,
a
n
d
se
lec
ti
o
n
)
,
m
o
d
e
l
train
in
g
a
n
d
tes
ti
n
g
wi
th
5
-
fo
ld
c
ro
ss
-
v
a
li
d
a
ti
o
n
,
a
n
d
h
y
p
e
rp
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
t
o
a
c
h
iev
e
o
p
ti
m
a
l
re
su
lt
s.
Am
o
n
g
th
e
tes
ted
m
o
d
e
ls,
Ca
tBo
o
st
Re
g
re
ss
o
r
y
iel
d
e
d
th
e
b
e
st
p
e
rfo
rm
a
n
c
e
,
a
c
h
iev
i
n
g
a
c
o
e
ffi
c
ien
t
o
f
d
e
term
in
a
ti
o
n
(R
²
)
o
f
6
9
.
3
4
%
,
a
m
e
a
n
a
b
so
lu
te
e
rro
r
(
M
AE)
o
f
2
3
.
1
%
,
a
n
d
ro
o
t
-
mean
-
sq
u
a
re
e
rro
r
(RM
S
E)
o
f
2
9
.
4
9
%
,
d
e
m
o
n
stra
ti
n
g
i
ts
e
ffe
c
ti
v
e
n
e
ss
in
p
re
d
ictin
g
c
h
a
lco
g
e
n
i
d
e
p
e
ro
v
s
k
it
e
b
a
n
d
g
a
p
s.
K
ey
w
o
r
d
s
:
B
an
d
g
ap
C
atB
o
o
s
t
R
eg
r
ess
o
r
Featu
r
e
f
u
s
io
n
Featu
r
e
s
elec
tio
n
Ma
ch
in
e
lear
n
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ag
u
n
g
Su
r
y
a
W
ib
o
wo
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
T
elk
o
m
Un
iv
er
s
ity
J
l.
T
elek
o
m
u
n
ik
asi T
er
u
s
an
B
u
ah
b
atu
No
.
1
,
Su
k
ap
u
r
a,
Kec
.
Day
eu
h
k
o
l
o
t,
Kab
.
B
an
d
u
n
g
,
J
awa
B
ar
at
,
I
n
d
o
n
esia
E
m
ail: a
g
u
n
g
s
w@
telk
o
m
u
n
iv
er
s
ity
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
is
in
g
g
lo
b
al
d
em
an
d
f
o
r
s
u
s
tain
ab
le
en
er
g
y
h
as
ac
ce
ler
ated
th
e
s
ea
r
c
h
f
o
r
a
d
v
an
ce
d
m
ater
ials
f
o
r
n
ex
t
-
g
e
n
er
atio
n
p
h
o
to
v
o
l
taic
(
PV)
tech
n
o
lo
g
y
.
So
lar
en
er
g
y
is
wid
ely
r
ec
o
g
n
ize
d
as
a
clea
n
an
d
en
v
ir
o
n
m
en
tally
f
r
ien
d
ly
s
o
u
r
ce
,
d
r
iv
in
g
ef
f
o
r
ts
to
ef
f
icien
tl
y
co
n
v
er
t
s
u
n
lig
h
t
in
to
u
s
ab
le
en
er
g
y
[
1
]
.
I
n
th
is
co
n
tex
t,
p
e
r
o
v
s
k
ite
m
ater
ials
h
av
e
em
er
g
ed
as
p
r
o
m
is
in
g
ca
n
d
id
ates
d
u
e
to
th
eir
s
tr
u
ctu
r
al
f
lex
i
b
ilit
y
,
r
ea
s
o
n
ab
le
ef
f
icien
c
y
,
an
d
p
o
ten
tial f
o
r
en
h
an
ce
d
s
tab
ilit
y
an
d
en
v
i
r
o
n
m
e
n
tal
co
m
p
ati
b
ilit
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Tu
n
in
g
fea
t
u
r
e
s
elec
tio
n
to
en
h
a
n
ce
ma
c
h
in
e
lea
r
n
in
g
p
r
ed
i
ctio
n
s
o
f
…
(
Osp
h
a
n
ie
Men
t
a
r
i P
r
ima
d
ia
n
ti
)
1509
T
h
e
p
er
o
v
s
k
ite
f
am
ily
,
with
th
e
g
en
er
al
f
o
r
m
u
la
AB
X₃
[
1
]
,
h
as
a
f
lex
ib
le
c
r
y
s
tal
s
tr
u
ctu
r
e
th
at
allo
ws
s
u
b
s
titu
tio
n
s
at
m
u
ltip
le
s
ites
,
lead
in
g
to
d
i
v
er
s
e
elec
tr
o
n
ic
p
r
o
p
er
ties
.
W
h
ile
h
alid
e
p
er
o
v
s
k
ites
o
f
f
er
h
ig
h
p
h
o
to
v
o
ltaic
p
er
f
o
r
m
an
c
e,
th
ey
s
u
f
f
er
f
r
o
m
in
s
tab
ilit
y
an
d
to
x
icity
.
I
n
co
n
tr
ast,
ch
alc
o
g
en
id
e
p
e
r
o
v
s
k
ites
(
C
Ps
)
p
r
o
v
id
e
b
etter
s
tab
ilit
y
,
n
o
n
-
to
x
icity
,
a
n
d
tu
n
ab
le
b
an
d
g
ap
s
.
T
h
eir
s
tr
o
n
g
lig
h
t
a
b
s
o
r
p
tio
n
an
d
s
tr
u
ctu
r
al
in
teg
r
ity
m
ak
e
th
em
p
r
o
m
is
e
f
o
r
s
o
lar
ce
lls
an
d
o
th
er
ap
p
licatio
n
s
,
s
u
p
p
o
r
tin
g
th
e
d
e
v
elo
p
m
en
t
o
f
n
ex
t
-
g
en
er
atio
n
s
u
s
tain
ab
le
PV te
c
h
n
o
lo
g
ies.
Per
o
v
s
k
ite
s
tr
u
ctu
r
es
a
r
e
wid
ely
u
s
ed
b
ey
o
n
d
s
o
lar
ce
lls
,
in
clu
d
in
g
i
n
o
p
to
elec
tr
o
n
ics,
m
ag
n
eto
r
esis
tan
ce
,
s
u
p
er
co
n
d
u
ctiv
ity
,
d
ielec
tr
ic,
an
d
p
iezo
e
lectr
ic
d
ev
ices,
d
u
e
to
th
eir
f
lex
ib
le
s
tr
u
ctu
r
e
an
d
p
h
y
s
ical
p
r
o
p
e
r
ties
.
C
h
alco
g
en
id
e
p
er
o
v
s
k
ites
ar
e
s
tab
le,
lead
-
f
r
ee
m
ater
ials
with
s
tr
o
n
g
o
p
to
elec
tr
o
n
ic
p
er
f
o
r
m
an
ce
[
2
]
.
Ad
d
itio
n
al
ly
,
s
tu
d
ies
o
n
L
aSr
Mn
O₃
an
d
L
aBaMn
O₃
s
h
o
w
th
eir
ef
f
ec
tiv
en
ess
in
m
ag
n
eto
r
esis
tan
ce
ap
p
licatio
n
s
u
n
d
er
v
a
r
y
in
g
tem
p
er
at
u
r
es
an
d
m
ag
n
etic
f
ield
s
[
3
]
.
Stu
d
ies
s
h
o
w
th
at
p
er
o
v
s
k
ite
s
tr
u
ctu
r
es
ex
h
ib
it
d
iv
er
s
e
ad
v
an
ce
d
p
r
o
p
er
ties
.
Me
tallic
co
m
p
o
u
n
d
s
s
u
ch
as
B
a
-
La
-
Cu
-
O
d
em
o
n
s
tr
ate
s
u
p
er
co
n
d
u
ctiv
ity
b
e
h
av
io
r
[
4
]
.
R
esear
ch
o
n
B
aT
iO₃
h
ig
h
lig
h
ts
its
ap
p
licatio
n
as
a
d
ielec
tr
ic
m
a
ter
ial,
im
p
r
o
v
i
n
g
e
n
er
g
y
s
to
r
a
g
e
ef
f
icien
cy
th
r
o
u
g
h
n
an
o
s
tr
u
ctu
r
e
en
g
in
ee
r
in
g
[
5
]
.
A
d
d
itio
n
ally
,
p
er
o
v
s
k
ites
lik
e
B
aT
iO₃
an
d
B
iFeO₃
ar
e
wid
ely
u
s
ed
in
p
iezo
elec
tr
ic
d
ev
ices,
e
n
ab
lin
g
ef
f
icien
t c
o
n
v
er
s
io
n
b
etwe
en
m
ec
h
an
ical
an
d
elec
tr
ical
en
er
g
y
[
6
]
.
C
h
alco
g
en
id
e
p
er
o
v
s
k
ites
h
a
v
e
em
er
g
ed
as
p
r
o
m
is
in
g
alt
er
n
ativ
es
d
u
e
to
th
eir
s
u
p
er
i
o
r
th
e
r
m
al
s
tab
ilit
y
an
d
tu
n
ab
le
elec
tr
ical
p
r
o
p
er
ties
,
en
h
an
cin
g
en
er
g
y
c
o
n
v
er
s
io
n
e
f
f
icien
cy
.
T
h
ey
a
r
e
co
n
s
id
er
ed
s
tab
le
an
d
ef
f
ec
tiv
e
m
ater
ials
f
o
r
s
o
lar
ce
ll
ap
p
licatio
n
s
,
th
o
u
g
h
t
h
eir
d
e
v
elo
p
m
e
n
t
r
e
m
ain
s
lim
ited
[
7
]
.
Ho
wev
e
r
,
s
tu
d
ies
o
n
t
h
eir
elec
tr
ical
an
d
o
p
tical
p
r
o
p
er
ties
,
p
ar
ticu
lar
ly
b
an
d
g
ap
,
ar
e
s
till
s
ca
r
ce
,
a
n
d
b
o
th
ex
p
er
im
en
tal
m
eth
o
d
s
an
d
d
en
s
ity
f
u
n
ctio
n
a
l th
eo
r
y
(
DFT)
ap
p
r
o
ac
h
es f
ac
e
ch
allen
g
es in
co
s
t,
tim
e,
a
n
d
ac
cu
r
ac
y
[
8
]
.
T
h
e
d
is
co
v
e
r
y
o
f
n
ew
ch
alc
o
g
en
id
e
p
er
o
v
s
k
ites
is
co
s
tly
an
d
tim
e
-
co
n
s
u
m
in
g
,
m
a
k
in
g
m
ac
h
i
n
e
lear
n
in
g
(
ML
)
a
v
al
u
ab
le
alt
er
n
ativ
e.
Pre
v
io
u
s
s
tu
d
ies
a
p
p
lied
ML
f
o
r
b
a
n
d
g
a
p
p
r
ed
ic
tio
n
,
s
u
ch
as
u
s
in
g
r
an
d
o
m
f
o
r
est
f
o
r
B
aZ
r
S₃
wi
th
o
u
t
c
o
m
p
ar
i
n
g
m
u
ltip
le
m
o
d
els
[
9
]
,
an
d
c
o
m
b
in
in
g
DF
T
-
b
ased
d
escr
ip
to
r
s
with
ML
m
eth
o
d
s
with
o
u
t
f
e
atu
r
e
s
elec
tio
n
[
1
0
]
.
Oth
er
w
o
r
k
u
s
ed
g
r
ap
h
n
eu
r
al
n
etwo
r
k
s
b
u
t
also
lack
ed
f
ea
tu
r
e
s
elec
tio
n
d
esp
ite
ac
h
iev
in
g
g
o
o
d
ac
cu
r
ac
y
[
1
1
]
.
Ad
d
i
tio
n
ally
,
s
tu
d
ies o
n
d
if
f
er
en
t p
er
o
v
s
k
ite
m
ater
ials
h
ig
h
lig
h
t
th
e
im
p
o
r
tan
ce
o
f
f
ea
tu
r
e
e
n
g
in
ee
r
in
g
,
s
u
c
h
as
o
x
id
atio
n
s
tate,
elec
tr
o
n
eg
at
iv
ity
,
co
o
r
d
in
atio
n
n
u
m
b
er
,
an
d
io
n
ic
r
a
d
ii,
to
im
p
r
o
v
e
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
[
1
2
]
.
T
h
is
s
tu
d
y
f
o
cu
s
es
o
n
p
r
ed
ic
tin
g
b
an
d
g
a
p
s
an
d
ef
f
icien
cy
o
f
ch
alco
g
en
id
e
p
e
r
o
v
s
k
ites
u
s
in
g
ML
with
k
ey
f
ea
tu
r
es
s
u
ch
as
io
n
ic
r
ad
iu
s
,
elec
tr
o
n
eg
ativ
ity
,
o
x
id
atio
n
s
tate,
an
d
c
o
o
r
d
i
n
atio
n
n
u
m
b
er
.
B
y
ap
p
ly
in
g
f
ea
tu
r
e
f
u
s
io
n
an
d
s
elec
tio
n
,
ML
en
ab
les
f
ast
an
d
ac
cu
r
ate
p
r
ed
ictio
n
o
f
b
a
n
d
g
ap
en
er
g
y
,
a
cr
itical
f
ac
to
r
i
n
s
o
lar
ce
ll
p
e
r
f
o
r
m
an
c
e.
C
o
m
p
ar
e
d
to
co
n
v
en
tio
n
al
m
eth
o
d
s
,
t
h
is
ap
p
r
o
ac
h
is
m
o
r
e
ef
f
icien
t
an
d
co
s
t
-
ef
f
ec
tiv
e,
s
u
p
p
o
r
tin
g
th
e
d
esig
n
o
f
s
u
s
tain
ab
le,
h
ig
h
-
e
f
f
icien
cy
s
o
lar
ce
lls
.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
d
escr
ib
es
th
e
m
ater
ials
an
d
m
eth
o
d
s
u
s
ed
in
th
e
s
tu
d
y
.
T
h
e
d
ataset
is
a
b
alan
ce
d
co
llectio
n
co
m
p
iled
f
r
o
m
p
u
b
lis
h
ed
p
ee
r
-
r
ev
iewe
d
ar
t
icles
[
1
3
]
–
[
2
0
]
an
d
v
er
if
ie
d
d
atab
ases
.
T
h
e
m
eth
o
d
o
l
o
g
y
f
o
cu
s
es
o
n
p
r
ed
ictin
g
b
an
d
g
ap
a
n
d
ef
f
icien
cy
u
s
in
g
f
ea
tu
r
e
f
u
s
io
n
an
d
f
ea
t
u
r
e
s
elec
tio
n
.
Key
s
tep
s
in
clu
d
e
d
ata
p
r
e
p
r
o
ce
s
s
in
g
to
r
ed
u
ce
d
im
en
s
io
n
a
lity
an
d
id
e
n
tify
im
p
o
r
tan
t
f
ea
tu
r
es,
d
ataset
au
g
m
en
tatio
n
to
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
,
an
d
h
y
p
e
r
p
ar
am
eter
o
p
tim
izatio
n
u
s
in
g
OPTU
NA.
T
h
is
au
to
m
ated
o
p
tim
izatio
n
en
h
an
ce
s
m
o
d
el
ac
cu
r
ac
y
an
d
g
en
er
aliza
tio
n
.
2
.
1
.
Da
t
a
s
et
a
nd
f
ea
t
ures
W
e
co
m
p
iled
a
d
ataset
to
talin
g
1
1
8
co
m
p
o
u
n
d
s
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
,
in
clu
d
in
g
AFlo
wlib
[
2
1
]
,
Ma
ter
ials
Pro
ject
[
2
2
]
,
Pu
b
C
h
em
[
2
3
]
,
W
eb
E
lem
e
n
ts
,
C
h
em
g
lo
b
e,
an
d
p
u
b
lis
h
ed
jo
u
r
n
a
l
ar
ticles
[
1
3
]
–
[
2
0
]
.
W
e
u
s
ed
f
iv
e
k
ey
f
ea
tu
r
es:
a_
io
n
s
,
b
_
io
n
s
,
an
d
x
_
io
n
s
,
as
s
h
o
wn
in
T
ab
le
1
.
T
h
ese
d
escr
ip
to
r
s
(
elec
tr
o
n
eg
ativ
ity
,
io
n
ic
r
a
d
iu
s
,
o
x
id
atio
n
s
tate,
d
e
n
s
ity
,
an
d
co
o
r
d
in
atio
n
n
u
m
b
er
)
lin
k
a
to
m
ic
p
r
o
p
er
ties
to
elec
tr
o
n
ic
b
e
h
av
io
r
.
T
h
eir
in
t
eg
r
atio
n
i
n
th
e
ML
m
o
d
el
ca
p
tu
r
es
ch
em
ical
a
n
d
s
tr
u
ctu
r
a
l
ef
f
ec
ts
,
en
a
b
lin
g
ac
cu
r
ate
b
an
d
g
ap
p
r
ed
ictio
n
f
o
r
o
p
tim
izin
g
ch
alco
g
en
id
e
p
e
r
o
v
s
k
ite
s
o
lar
ce
lls
.
T
ab
le
1
.
Su
m
m
a
r
y
o
f
f
ea
tu
r
es a
n
d
r
ef
e
r
en
ce
s
F
e
a
t
u
r
e
s
N
u
mb
e
r
o
f
f
e
a
t
u
r
e
s
R
e
f
e
r
e
n
c
e
El
e
c
t
r
o
n
e
g
a
t
i
v
i
t
y
3
W
e
b
e
l
E
m
e
n
t
s
I
o
n
i
c
r
a
d
i
i
3
C
h
e
mg
l
o
b
e
.
o
r
g
O
x
i
d
a
t
i
o
n
st
a
t
e
3
[
2
3
]
D
e
n
si
t
y
3
C
h
e
mg
l
o
b
e
.
o
r
g
C
o
o
r
d
i
n
a
t
i
o
n
n
u
m
b
e
r
3
C
h
e
mg
l
o
b
e
.
o
r
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
0
8
-
1
5
1
7
1510
All
s
elec
ted
f
ea
tu
r
es
in
f
lu
en
ce
b
an
d
g
a
p
an
d
e
f
f
icien
cy
.
E
lectr
o
n
eg
ativ
ity
d
if
f
er
en
ce
s
af
f
e
ct
b
o
n
d
in
g
(
io
n
ic
v
s
.
c
o
v
alen
t)
,
io
n
ic
r
ad
ii
d
eter
m
in
e
lattice
s
tr
u
ctu
r
e,
a
n
d
o
x
id
atio
n
s
tates
d
ef
in
e
elec
tr
o
n
ic
co
n
f
ig
u
r
atio
n
s
.
Den
s
ity
r
ef
le
cts
ato
m
ic
p
ac
k
in
g
,
wh
ile
c
o
o
r
d
in
atio
n
n
u
m
b
e
r
d
escr
ib
e
s
th
e
lo
ca
l
b
o
n
d
in
g
en
v
ir
o
n
m
en
t.
T
o
g
eth
er
,
th
ese
f
ea
tu
r
es c
ap
tu
r
e
k
ey
c
h
em
ical
an
d
s
tr
u
ctu
r
al
f
ac
to
r
s
f
o
r
ac
cu
r
ate
p
r
ed
ictio
n
.
2
.
2
.
ML
pro
ce
s
s
ing
Fig
u
r
e
1
p
r
esen
ts
th
e
ML
wo
r
k
f
lo
w,
s
tar
tin
g
with
d
ata
co
llectio
n
a
n
d
p
r
ep
r
o
ce
s
s
in
g
.
Mo
d
el
p
er
f
o
r
m
an
ce
d
ep
e
n
d
s
o
n
d
at
a
q
u
ality
an
d
q
u
an
tity
,
u
s
in
g
d
ata
f
r
o
m
th
e
Ma
ter
ials
Pro
ject
[
2
2
]
an
d
p
r
io
r
s
tu
d
ies
[
1
3
]
–
[
2
0
]
.
Data
p
r
o
ce
s
s
in
g
in
clu
d
es
clea
n
in
g
to
en
s
u
r
e
ac
cu
r
ac
y
.
Featu
r
e
f
u
s
io
n
in
teg
r
ates
m
u
ltip
le
f
ea
tu
r
es
[
2
4
]
,
wh
ile
f
ilter
-
b
as
ed
f
ea
tu
r
e
s
elec
tio
n
r
em
o
v
es
ir
r
elev
an
t
d
ata,
im
p
r
o
v
in
g
ef
f
icien
cy
,
ac
c
u
r
ac
y
,
an
d
in
ter
p
r
etab
ilit
y
[
2
5
]
.
Fig
u
r
e
1
.
R
esear
ch
m
eth
o
d
o
l
o
g
y
wo
r
k
f
lo
w
I
n
th
e
m
o
d
elin
g
s
tag
e,
m
u
lt
ip
le
ML
alg
o
r
ith
m
s
:
Ad
aBo
o
s
t,
Gr
ad
ien
t
B
o
o
s
tin
g
,
s
u
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
SVR
)
,
C
atB
o
o
s
t,
a
n
d
k
-
n
e
ar
est n
eig
h
b
o
r
(
KNN)
ar
e
im
p
lem
en
ted
in
Py
th
o
n
[
1
2
]
.
Hy
p
er
p
ar
am
eter
tu
n
in
g
is
ap
p
lied
to
im
p
r
o
v
e
p
er
f
o
r
m
a
n
ce
,
u
s
in
g
OPTU
NA
with
B
ay
esian
o
p
tim
izatio
n
(
T
PE)
[
2
6
]
,
[
2
7
]
.
T
h
e
f
in
al
s
tag
e
in
clu
d
es
ev
alu
atio
n
an
d
in
ter
p
r
etatio
n
u
s
in
g
r
o
o
t
-
m
ea
n
-
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
,
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
an
d
co
ef
f
icien
t
o
f
d
et
er
m
in
atio
n
(
R²
)
m
etr
ics
[
2
8
]
–
[
3
0
]
,
wh
ile
Sh
ap
ley
ad
d
itiv
e
e
x
p
lan
atio
n
(
SHAP)
ex
p
lain
s
th
e
co
n
t
r
ib
u
tio
n
o
f
ea
ch
f
ea
tu
r
e
t
o
th
e
m
o
d
el
p
r
ed
ict
io
n
s
[
3
1
]
.
I
n
Fig
u
r
e
2
we
id
en
tifie
d
f
iv
e
ch
ar
ac
ter
is
tics
:
o
x
id
atio
n
s
tate
(
OS)
,
elec
tr
o
n
eg
a
tiv
ity
(
E
)
,
co
o
r
d
in
atio
n
n
u
m
b
er
(
C
N)
,
i
o
n
ic
r
ad
iu
s
(
I
R
)
,
an
d
d
en
s
ity
(
D)
,
ea
ch
ex
h
i
b
itin
g
s
ev
er
al
n
u
m
er
ical
r
an
g
es,
in
clu
d
in
g
:
a.
Ox
id
atio
n
s
tate
(
OS)
r
an
g
es f
r
o
m
-
2
t
o
+6
.
b.
E
lectr
o
n
eg
ativ
ity
(
E
)
r
a
n
g
es f
r
o
m
0
.
7
9
to
3
.
4
4
.
c.
C
o
o
r
d
in
atio
n
n
u
m
b
er
(
C
N)
r
a
n
g
es f
r
o
m
2
to
1
2
d.
I
o
n
ic
r
a
d
iu
s
(
I
R
)
r
an
g
es f
r
o
m
1
.
7
E
-
1
1
to
2
.
2
E
-
1
0
.
e.
Den
s
ity
(
D)
r
an
g
es f
r
o
m
0
.
0
0
1
4
2
9
t
o
1
8
.
9
.
E
ac
h
f
ea
tu
r
e
g
r
o
u
p
co
m
p
r
is
es
th
r
ee
v
alu
es
o
r
r
e
p
r
esen
tatio
n
s
,
f
o
llo
wed
b
y
th
e
u
s
e
o
f
n
o
r
m
aliza
tio
n
.
Prio
r
to
am
alg
am
atio
n
,
ea
ch
f
ea
tu
r
e
u
n
d
er
wen
t
n
o
r
m
aliza
tio
n
v
ia
a
m
in
/m
ax
s
ca
ler
,
wh
ich
ad
ju
s
ts
v
alu
es
to
a
r
an
g
e
b
etwe
en
0
an
d
1
to
elim
in
ate
d
is
cr
ep
an
cies
in
s
ca
le.
Min
-
Ma
x
Scaler
is
a
n
o
r
m
ali
za
tio
n
tech
n
iq
u
e
th
a
t
s
ca
les
all
s
ig
n
al
v
alu
es
to
a
r
an
g
e
b
etwe
en
0
a
n
d
1
.
As
in
(
1
)
an
d
(
2
)
d
elin
ea
te
th
e
Min
-
Ma
x
Scaler
n
o
r
m
alizin
g
tec
h
n
iq
u
e
[
3
2
]
.
=
(
−
.
)
(
.
−
)
(
1
)
=
∗
(
−
)
+
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Tu
n
in
g
fea
t
u
r
e
s
elec
tio
n
to
en
h
a
n
ce
ma
c
h
in
e
lea
r
n
in
g
p
r
ed
i
ctio
n
s
o
f
…
(
Osp
h
a
n
ie
Men
t
a
r
i P
r
ima
d
ia
n
ti
)
1511
T
h
e
d
ata
wer
e
n
o
r
m
alize
d
u
s
i
n
g
th
e
m
in
-
m
a
x
s
ca
lin
g
m
eth
o
d
p
r
esen
ted
in
(1
)
–
(
2
)
.
Featu
r
e
f
u
s
io
n
p
r
o
d
u
ce
d
1
5
f
ea
tu
r
es,
af
ter
wh
ich
m
o
n
o
to
n
ic
d
ata
wer
e
r
em
o
v
e
d
.
Featu
r
e
r
ed
u
ctio
n
u
s
in
g
a
v
ar
ian
ce
th
r
esh
o
ld
r
e
d
u
ce
d
t
h
e
s
et
to
1
4
f
ea
tu
r
es,
f
o
llo
wed
b
y
f
ilter
-
b
ased
s
elec
tio
n
to
r
etain
th
e
m
o
s
t
r
elev
an
t
o
n
es.
Fin
ally
,
8
f
ea
tu
r
es
wer
e
u
s
ed
f
o
r
tr
ain
in
g
an
d
test
in
g
.
T
h
is
s
tu
d
y
ap
p
lies
m
u
ltip
le
ML
r
eg
r
ess
io
n
m
o
d
els
to
p
r
ed
ict
b
an
d
g
ap
an
d
e
f
f
icien
c
y
,
as d
escr
ib
ed
in
th
e
f
o
llo
win
g
s
ec
tio
n
s
.
Fig
u
r
e
2
.
T
h
e
d
ata
p
r
o
ce
s
s
in
g
em
p
lo
y
ed
f
o
r
th
is
r
esear
ch
2
.
3
.
Ca
t
B
o
o
s
t
Reg
re
s
s
o
r
T
h
e
ca
teg
o
r
ical
b
o
o
s
tin
g
(
C
atB
o
o
s
t)
r
eg
r
ess
o
r
r
ep
r
esen
ts
an
en
s
em
b
le
tech
n
iq
u
e
d
e
r
iv
ed
f
r
o
m
g
r
ad
ien
t
b
o
o
s
tin
g
[
3
3
]
.
C
atB
o
o
s
t
is
an
en
s
em
b
le
m
ac
h
in
e
lear
n
in
g
m
et
h
o
d
b
ased
o
n
g
r
ad
ien
t
b
o
o
s
tin
g
d
ec
is
io
n
tr
ee
s
(
GB
DT
)
,
p
ar
ticu
lar
ly
well
-
s
u
ited
f
o
r
h
a
n
d
lin
g
h
eter
o
g
en
eo
u
s
an
d
c
ateg
o
r
ical
f
ea
tu
r
es
[
3
4
]
–
[
3
6
]
.
T
h
e
C
atB
o
o
s
t
alg
o
r
ith
m
n
atu
r
ally
in
te
g
r
ates
a
m
eth
o
d
f
o
r
ef
f
ec
tiv
ely
tr
an
s
f
o
r
m
in
g
n
o
n
-
n
u
m
er
ical
d
ata
in
to
n
u
m
e
r
ical
f
o
r
m
ats
with
o
u
t
r
eq
u
ir
in
g
p
ar
a
m
etr
ic
ad
ju
s
tm
en
ts
,
p
r
o
d
u
cin
g
f
a
v
o
r
ab
le
o
u
tco
m
es
in
a
s
in
g
le
r
u
n
[
3
7
]
.
Similar
to
o
th
er
g
r
ad
ie
n
t
b
o
o
s
tin
g
m
eth
o
d
s
,
C
atB
o
o
s
t
co
n
s
tr
u
cts
n
ew
tr
ee
s
wh
ile
ad
d
r
ess
in
g
th
e
o
v
er
f
itti
n
g
c
h
allen
g
es
ty
p
ical
o
f
co
n
v
e
n
tio
n
al
alg
o
r
ith
m
s
.
I
t
ap
p
lies
a
r
an
d
o
m
p
e
r
m
u
tatio
n
s
tr
ateg
y
to
o
r
g
an
ize
th
e
d
ata
an
d
th
e
n
en
co
d
es
ea
ch
ca
teg
o
r
ical
f
ea
t
u
r
e
with
n
u
m
er
ical
v
alu
es
[
3
8
]
.
B
y
ap
p
ly
in
g
p
r
io
r
ity
f
ac
to
r
s
an
d
weig
h
t
co
ef
f
icien
t
s
,
th
e
im
p
ac
t
o
f
lo
w
-
f
r
e
q
u
en
c
y
an
d
n
o
is
y
d
ata
is
m
in
im
ized
.
E
q
u
atio
n
s
(
3
)
a
n
d
(
4
)
wer
e
em
p
lo
y
e
d
f
o
r
tr
ain
in
g
th
e
d
ataset.
=
(
,
)
(
3
)
L
e
t
j
=
t
h
e
n
u
m
b
e
r
o
f
s
a
m
p
l
e
s
(
1
,
2
,
…
n
)
,
X
j
=
j
th
g
o
a
l
v
a
l
u
e
o
f
X
(
x
j
1
,
x
j
2
,
…
x
j
i
)
,
a
n
d
Y
j
=
j
th
t
a
r
g
e
t
v
a
l
u
e
o
f
Y
.
=
∑
(
=
=
1
)
+
∑
(
=
=
1
)
+
(
4
)
w
h
er
e
φ
r
ep
r
esen
ts
th
e
in
d
icato
r
f
u
n
ctio
n
,
α
d
en
o
tes th
e
in
itial we
ig
h
t,
an
d
s
ig
n
if
ies th
e
s
tar
tin
g
v
alu
e.
2
.
4
.
Ada
B
o
o
s
t
R
eg
re
s
s
o
r
Ad
aBo
o
s
tR
eg
r
ess
o
r
[
3
9
]
is
a
co
m
m
o
n
ly
u
tili
ze
d
ML
r
eg
r
ess
io
n
tech
n
iq
u
e
r
ec
o
g
n
iz
ed
f
o
r
its
p
r
o
f
icien
c
y
in
r
eliab
ly
p
r
ed
i
ctin
g
tar
g
et
v
ar
iab
les.
I
t
is
p
ar
t
o
f
th
e
b
o
o
s
tin
g
al
g
o
r
it
h
m
f
am
ily
,
wh
ich
in
cr
em
en
tally
r
ef
in
es
wea
k
m
o
d
els
to
th
e
d
ata
p
r
io
r
to
am
alg
am
atin
g
th
em
in
to
a
m
o
r
e
r
o
b
u
s
t
m
o
d
el.
T
h
e
b
o
o
s
tin
g
tech
n
iq
u
e
e
f
f
ec
tiv
ely
r
ed
u
ce
s
b
ias an
d
im
p
r
o
v
es th
e
m
o
d
el'
s
p
r
ed
ictiv
e
ca
p
ac
ity
.
2
.
5
.
G
ra
dientBo
o
s
t
ing
R
eg
re
s
s
o
r
T
h
e
Gr
ad
ien
tB
o
o
s
tin
g
R
eg
r
ess
o
r
[
4
0
]
f
o
r
m
s
a
n
en
s
em
b
le
m
o
d
el
th
r
o
u
g
h
th
e
s
tep
wis
e
in
teg
r
atio
n
o
f
p
r
ed
icto
r
s
,
wh
e
r
e
ea
ch
o
n
e
en
h
an
ce
s
th
e
p
r
ec
ed
in
g
p
er
f
o
r
m
an
ce
.
I
n
co
n
tr
ast
to
Ad
aBo
o
s
t,
it
ap
p
lies
g
r
a
d
ien
t
d
escen
t
to
tar
g
et
r
esid
u
al
er
r
o
r
s
o
f
ea
r
lier
lear
n
er
s
,
th
er
e
b
y
cr
ea
tin
g
a
r
o
b
u
s
t
f
r
am
ewo
r
k
f
o
r
m
i
n
im
izin
g
p
r
ed
ictio
n
e
r
r
o
r
s
o
v
er
s
u
cc
ess
iv
e
iter
atio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
0
8
-
1
5
1
7
1512
2
.
6
.
K
Neig
hb
o
rs
R
eg
re
s
s
o
r
KNe
ig
h
b
o
r
s
R
eg
r
ess
o
r
[
4
1
]
e
m
p
lo
y
s
s
im
ilar
ity
-
b
ased
p
r
e
d
i
ctio
n
b
y
lo
ca
tin
g
t
h
e
k
-
n
ea
r
es
t
n
eig
h
b
o
r
s
o
f
a
g
iv
en
d
ata
p
o
i
n
t
u
s
in
g
a
d
is
tan
ce
m
ea
s
u
r
e
lik
e
E
u
clid
e
an
d
is
tan
ce
.
T
h
e
p
r
e
d
icted
v
a
lu
e
is
th
en
d
e
r
iv
ed
f
r
o
m
th
e
av
er
a
g
e
tar
g
et
v
alu
e
s
o
f
th
o
s
e
n
eig
h
b
o
r
s
.
I
n
o
u
r
wo
r
k
,
we
r
ef
in
ed
th
e
h
y
p
er
p
ar
a
m
eter
s
—
n
u
m
b
er
o
f
n
eig
h
b
o
r
s
,
leaf
s
ize,
,
an
d
n
u
m
b
er
o
f
task
s
—
wh
ile
k
ee
p
in
g
th
e
o
th
er
s
at
d
e
f
au
lt,
as
th
ey
co
n
tr
ib
u
ted
litt
le
to
p
er
f
o
r
m
an
ce
im
p
r
o
v
e
m
en
t.
2
.
7
.
Su
pp
o
rt
v
ec
t
o
r
re
g
re
s
s
io
n
Su
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
(
S
VR
)
[
4
2
]
is
a
ML
ap
p
r
o
ac
h
th
at
u
tili
ze
s
a
lin
ea
r
f
u
n
ctio
n
to
r
ep
r
esen
t
d
ata
in
a
v
ec
to
r
s
p
ac
e.
T
h
e
SVR
m
o
d
el
aim
s
to
m
in
im
ize
t
h
e
ag
g
r
eg
ate
o
f
th
e
d
is
tan
ce
s
b
etwe
en
th
e
ac
tu
al
p
lace
m
en
ts
o
f
all
s
am
p
les
an
d
th
is
lin
ea
r
f
u
n
ctio
n
,
r
ef
er
r
e
d
to
as
th
e
lo
s
s
f
u
n
ctio
n
.
T
h
e
SVR
alg
o
r
ith
m
d
eter
m
in
es th
e
o
p
tim
al
p
ar
am
eter
s
o
f
a
lin
ea
r
f
u
n
ctio
n
b
y
m
in
im
izin
g
th
e
ass
o
ciate
d
lo
s
s
f
u
n
ctio
n
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
r
esu
lts
an
d
d
is
cu
s
s
io
n
o
f
M
L
m
o
d
els
f
o
r
b
an
d
g
ap
p
r
e
d
ictio
n
in
ch
alco
g
en
id
e
p
e
r
o
v
s
k
ites
.
R
esu
lts
ar
e
s
h
o
wn
th
r
o
u
g
h
f
ig
u
r
es,
g
r
ap
h
s
,
an
d
tab
les
f
o
r
clea
r
co
m
p
ar
is
o
n
[
1
2
]
.
T
h
e
d
is
cu
s
s
io
n
h
ig
h
lig
h
ts
th
e
ef
f
ec
ts
o
f
f
ea
tu
r
e
s
elec
tio
n
,
f
e
atu
r
e
f
u
s
io
n
,
an
d
h
y
p
e
r
p
ar
am
e
ter
o
p
tim
izatio
n
o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
in
clu
d
in
g
ev
alu
atio
n
m
etr
ics,
f
ea
tu
r
e
im
p
o
r
tan
ce
,
a
n
d
alg
o
r
ith
m
c
o
m
p
ar
is
o
n
s
3
.
1
.
E
v
a
lua
t
i
o
n
m
et
ric
T
ab
les
2
a
n
d
3
d
is
p
lay
th
e
r
esu
lts
o
f
o
u
r
s
im
u
latio
n
c
o
n
c
er
n
in
g
b
an
d
g
ap
an
d
e
f
f
icien
c
y
.
T
a
b
le
2
illu
s
tr
ates
th
e
r
esu
lts
o
f
th
e
b
an
d
g
ap
s
im
u
latio
n
,
w
h
ich
co
m
p
a
r
es
s
ix
r
e
g
r
ess
io
n
m
o
d
els
u
s
in
g
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
b
est
m
o
d
el
f
r
o
m
t
h
e
b
an
d
g
ap
s
im
u
lati
o
n
was
th
e
C
atB
o
o
s
t
R
eg
r
ess
o
r
,
wh
ic
h
ac
h
iev
ed
th
e
lo
west
MA
E
o
f
0
.
2
3
1
0
e
V
an
d
R
MSE
o
f
0
.
2
9
4
9
eV,
alo
n
g
with
th
e
h
i
g
h
est
R
²
o
f
0
.
6
9
3
4
u
n
d
er
5
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
.
T
h
is
in
d
icat
es
C
at
B
o
o
s
t
d
eliv
er
ed
th
e
m
o
s
t
ac
cu
r
ate
an
d
d
ep
e
n
d
ab
le
f
o
r
ec
asts
am
o
n
g
all
m
o
d
els.
On
th
e
o
th
er
h
an
d
,
A
d
aBo
o
s
t
R
eg
r
ess
o
r
also
d
id
r
e
lativ
ely
well
MA
E
0
.
2
7
0
8
,
R
²
0
.
6
1
6
,
b
u
t
n
o
t
as
s
tr
o
n
g
as
C
atB
o
o
s
t.
KNe
ig
h
b
o
r
s
an
d
R
an
d
o
m
Fo
r
est
ex
h
i
b
ited
in
f
er
io
r
r
esu
lts
with
g
r
ea
ter
m
is
tak
es
an
d
s
u
b
s
tan
tially
lo
wer
R
²
v
alu
es,
s
u
g
g
esti
n
g
p
o
o
r
g
en
er
aliz
atio
n
.
Su
p
p
o
r
t
v
ec
to
r
r
eg
r
es
s
o
r
with
Gr
ad
ien
t
B
o
o
s
tin
g
th
e
r
e
g
r
ess
o
r
s
h
o
we
d
r
ea
s
o
n
a
b
le
p
er
f
o
r
m
a
n
ce
,
b
e
tter
th
an
R
an
d
o
m
Fo
r
est/
KNe
ig
h
b
o
r
s
b
u
t
b
elo
w
C
atB
o
o
s
t.
T
ab
le
2
.
R
esu
lts
o
f
b
an
d
g
ap
s
i
m
u
latio
n
M
e
t
h
o
d
s
M
A
E
(
e
V
)
R
M
S
E
(
e
V
)
R2
C
a
t
b
o
o
s
t
R
e
g
r
e
ss
o
r
0
.
2
3
1
0
.
2
9
4
9
0
.
6
9
3
4
A
d
a
b
o
o
st
R
e
g
r
e
ss
o
r
0
.
2
7
0
8
0
.
2
9
4
9
0
.
6
1
6
K
n
e
i
g
h
b
o
r
sR
e
g
r
e
sso
r
0
.
3
5
5
6
0
.
4
1
1
9
0
.
4
0
2
R
a
n
d
o
mF
o
r
e
st
R
e
g
r
e
ss
o
r
0
.
3
5
3
7
0
.
4
4
2
8
0
.
2
6
2
6
S
u
p
p
o
r
t
V
e
c
t
o
r
R
e
g
r
e
ss
o
r
0
.
2
8
6
7
0
.
3
6
7
9
0
.
5
2
2
8
G
r
a
d
i
e
n
t
B
o
o
st
i
n
g
R
e
g
r
e
ss
o
r
0
.
3
0
5
9
0
.
3
6
0
.
5
4
3
2
T
ab
le
3
s
h
o
ws
th
e
r
esu
lts
o
f
th
e
ef
f
icien
c
y
s
im
u
latio
n
f
o
r
f
o
r
ec
asti
n
g
s
o
lar
ce
lls
.
T
h
e
b
est
m
o
d
el
f
r
o
m
th
e
ef
f
icien
c
y
s
im
u
latio
n
was
th
e
C
a
tB
o
o
s
t
R
eg
r
ess
o
r
as
th
e
b
est
p
er
f
o
r
m
er
,
ac
h
iev
in
g
a
m
in
im
u
m
MA
E
o
f
0
.
2
2
9
0
eV,
a
m
i
n
im
u
m
R
MSE
o
f
0
.
2
9
5
9
eV,
an
d
a
m
ax
im
u
m
R
²
o
f
0
.
6
9
1
4
.
T
h
is
s
h
o
ws
g
o
o
d
p
r
ed
ictio
n
ac
cu
r
ac
y
an
d
co
n
s
t
an
t
r
eliab
ilit
y
.
Oth
er
o
b
s
er
v
ati
o
n
s
wer
e
th
at
t
h
e
Ad
aBo
o
s
t
R
eg
r
ess
o
r
p
er
f
o
r
m
e
d
s
ec
o
n
d
-
b
est
with
MA
E
0
.
2
3
8
3
an
d
R
²
0
.
6
6
2
4
,
clo
s
e
to
C
atB
o
o
s
t.
Gr
ad
ien
t
B
o
o
s
tin
g
R
eg
r
ess
o
r
ag
ain
d
em
o
n
s
tr
ated
m
o
d
est p
er
f
o
r
m
an
ce
with
an
R
²
o
f
0
.
5
4
5
0
.
K
Neig
h
b
o
r
s
,
R
an
d
o
m
Fo
r
est,
an
d
SVR
d
em
o
n
s
tr
ated
wo
r
s
e
ac
cu
r
ac
y
with
lar
g
er
m
i
s
tak
es a
n
d
lo
w
R
²,
s
u
g
g
esti
n
g
th
ey
ar
e
less
ap
p
r
o
p
r
iate
f
o
r
th
is
task
.
T
ab
le
3
.
Ou
tco
m
es o
f
ef
f
icien
cy
s
im
u
latio
n
M
e
t
h
o
d
s
M
A
E
(
e
V
)
R
M
S
E
(
e
V
)
R
2
C
a
t
b
o
o
s
t
R
e
g
r
e
ss
o
r
0
.
2
2
9
0
0
.
2
9
5
9
0
.
6
9
1
4
A
d
a
b
o
o
st
R
e
g
r
e
ss
o
r
0
.
2
3
8
3
0
.
3
3
0
1
0
.
6
6
2
4
K
n
e
i
g
h
b
o
r
sR
e
g
r
e
sso
r
0
.
3
4
6
3
0
.
4
0
3
4
0
.
4
6
3
8
R
a
n
d
o
mF
o
r
e
st
R
e
g
r
e
ss
o
r
0
.
3
4
6
0
0
.
4
3
7
2
0
.
3
5
9
7
S
u
p
p
o
r
t
V
e
c
t
o
r
R
e
g
r
e
ss
o
r
0
.
3
1
3
2
0
.
6
3
2
9
0
.
3
9
2
9
G
r
a
d
i
e
n
t
B
o
o
st
i
n
g
R
e
g
r
e
ss
o
r
0
.
3
0
5
1
0
.
3
6
0
0
0
.
5
4
5
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Tu
n
in
g
fea
t
u
r
e
s
elec
tio
n
to
en
h
a
n
ce
ma
c
h
in
e
lea
r
n
in
g
p
r
ed
i
ctio
n
s
o
f
…
(
Osp
h
a
n
ie
Men
t
a
r
i P
r
ima
d
ia
n
ti
)
1513
T
ab
le
4
co
m
p
a
r
es
th
e
m
eth
o
d
s
an
d
f
in
d
in
g
s
o
f
Kh
an
et
a
l
.
[
1
2
]
a
n
d
o
u
r
cu
r
r
en
t
in
v
esti
g
a
tio
n
wh
ile
em
p
lo
y
in
g
C
atB
o
o
s
t
R
eg
r
ess
o
r
f
o
r
b
a
n
d
g
a
p
s
im
u
latio
n
Kh
an
et
a
l
.
[
1
2
]
.
Me
th
o
d
Kh
a
n
et
a
l
.
[
1
2
]
ap
p
lied
s
tr
o
n
g
p
r
ed
ictiv
e
ac
c
u
r
ac
y
.
H
o
wev
er
,
i
n
o
u
r
in
v
esti
g
atio
n
,
we
s
im
u
lated
C
atB
o
o
s
t
R
eg
r
ess
o
r
esp
ec
ially
f
o
r
ch
alco
g
en
id
e
p
e
r
o
v
s
k
ites
,
wh
ich
ar
e
th
e
f
u
tu
r
e
p
er
o
v
s
k
ites
,
u
s
in
g
th
e
Njem
a
et
a
l
.
p
u
b
licatio
n
[
1
]
.
T
h
en
,
u
n
lik
e
Kh
a
n
et
a
l
.
[
1
2
]
,
we
u
s
ed
f
ea
tu
r
e
f
u
s
io
n
an
d
f
ea
tu
r
e
s
elec
tio
n
to
f
o
cu
s
s
o
lely
o
n
th
e
m
o
s
t
im
p
o
r
tan
t
d
escr
ip
to
r
s
(
elec
tr
o
n
e
g
ativ
ity
,
io
n
ic
r
ad
ii,
o
x
id
atio
n
s
tate,
d
en
s
ity
,
an
d
c
o
o
r
d
in
atio
n
n
u
m
b
er
)
.
T
h
e
f
in
d
in
g
s
y
ield
ed
R
²
=
0
.
6
9
3
4
.
Alth
o
u
g
h
lo
wer
th
an
Kh
an
et
a
l
.
[
1
2
]
,
th
is
r
ef
lects
th
e
in
cr
ea
s
ed
d
if
f
icu
lty
o
f
p
r
ed
ictin
g
ch
alco
g
en
id
e
p
er
o
v
s
k
ites
,
wh
ich
ar
e
less
r
esear
ch
ed
an
d
m
a
y
h
av
e
m
o
r
e
c
o
m
p
lex
elec
tr
o
n
ic
in
ter
ac
tio
n
s
.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
o
u
r
r
e
s
ea
r
ch
an
d
Kh
a
n
et
a
l
[
1
2
]
M
e
t
h
o
d
s
D
i
f
f
e
r
e
n
c
e
s
R
e
f
.
C
a
t
b
o
o
s
t
R
e
g
r
e
ss
o
r
f
o
r
B
a
n
d
g
a
p
si
m
u
l
a
t
i
o
n
P
e
r
o
v
sk
i
t
e
s
[
1
2
]
C
a
t
b
o
o
s
t
R
e
g
r
e
ss
o
r
f
o
r
B
a
n
d
g
a
p
si
m
u
l
a
t
i
o
n
[
o
u
r
w
o
r
k
]
F
e
a
t
u
r
e
F
u
s
i
o
n
Th
i
s
st
u
d
y
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
Th
i
s
st
u
d
y
C
h
a
l
c
o
g
e
n
i
d
e
Th
i
s
st
u
d
y
Fig
u
r
e
3
ex
p
lain
s
th
at
C
atB
o
o
s
t
R
eg
r
ess
o
r
ex
h
ib
its
th
e
s
tr
o
n
g
est
p
r
ed
ictiv
e
ca
p
ab
ilit
y
—
its
p
r
ed
ictio
n
s
ar
e
clo
s
est
to
th
e
d
iag
o
n
al,
ag
r
ee
in
g
with
p
r
e
v
io
u
s
m
ea
s
u
r
es
(
lo
west
MA
E
an
d
h
ig
h
est
R
²)
.
Ad
aBo
o
s
t
R
eg
r
ess
o
r
is
th
e
s
ec
o
n
d
-
b
est
p
er
f
o
r
m
an
ce
,
with
d
ec
en
t
alig
n
m
en
t
b
u
t
s
o
m
e
wh
at
less
ac
cu
r
ac
y
.
KNe
ig
h
b
o
r
s
an
d
r
a
n
d
o
m
f
o
r
est
r
eg
r
ess
o
r
s
p
er
f
o
r
m
b
a
d
ly
,
d
em
o
n
s
tr
atin
g
s
ig
n
if
ican
t
p
r
ed
ictio
n
er
r
o
r
s
an
d
p
o
o
r
alig
n
m
en
t.
Su
p
p
o
r
t
v
ec
t
o
r
an
d
g
r
ad
ie
n
t
b
o
o
s
tin
g
r
e
g
r
ess
o
r
s
o
f
f
er
m
o
d
er
ate
p
r
e
d
ictiv
e
p
o
wer
b
u
t
ar
e
less
d
ep
en
d
a
b
le
th
an
b
o
o
s
tin
g
-
b
as
ed
ap
p
r
o
ac
h
es.
T
h
e
r
ed
lin
e
g
iv
es
a
b
en
ch
m
ar
k
:
th
e
clo
s
er
th
e
s
ca
tter
p
o
in
ts
lie
to
th
is
lin
e,
th
e
b
etter
th
e
m
o
d
el.
C
atB
o
o
s
t d
ef
in
itely
o
u
tp
er
f
o
r
m
s
o
th
er
s
.
Fig
u
r
e
3
.
An
al
y
s
is
o
f
th
e
ex
p
e
r
im
en
tal
v
er
s
u
s
p
r
e
d
icted
b
an
d
g
ap
v
alu
es u
tili
zin
g
o
u
r
ML
m
o
d
els
3
.
2
.
F
e
a
t
ure
im
po
rt
a
nce
wit
h f
ilte
r
re
g
re
s
s
io
n a
nd
Sh
a
pl
ey
a
dd
it
iv
e
ex
pla
na
t
io
n
T
h
is
wo
r
k
u
s
ed
f
ea
tu
r
e
im
p
o
r
t
an
ce
with
f
ilter
r
eg
r
ess
io
n
,
with
wh
ich
we
r
ated
o
u
r
f
ea
tu
r
es
as
s
h
o
wn
in
Fig
u
r
e
4.
Fig
u
r
e
4
(
a
)
h
ig
h
lig
h
ts
f
ea
tu
r
e
im
p
o
r
ta
n
ce
.
E
lect
r
o
n
eg
ativ
ity
(
E
C
)
is
th
e
m
o
s
t
in
f
lu
en
tial,
d
ir
ec
tly
af
f
ec
tin
g
b
o
n
d
in
g
a
n
d
b
an
d
g
ap
.
Den
s
ity
(
DC
)
an
d
co
o
r
d
i
n
atio
n
n
u
m
b
er
(
C
NA)
also
p
lay
m
ajo
r
r
o
les
b
y
in
f
lu
en
cin
g
at
o
m
ic
p
ac
k
in
g
an
d
elec
tr
o
n
ic
s
tr
u
ctu
r
e.
M
o
d
e
r
ate
f
ea
tu
r
es
in
clu
d
e
E
A
an
d
OSA,
wh
ich
im
p
ac
t
lo
ca
l
b
o
n
d
in
g
.
L
o
we
r
-
im
p
ac
t f
ea
tu
r
es
—
OSB
,
I
R
A,
an
d
I
R
C
—
h
av
e
s
m
aller
co
n
tr
ib
u
tio
n
s
,
m
ain
ly
r
e
f
in
in
g
th
e
p
r
ed
ictio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
0
8
-
1
5
1
7
1514
Fig
u
r
e
4
(
b
)
s
h
o
ws
th
at
elec
tr
o
n
eg
ativ
ity
(
E
C
)
h
as
th
e
s
tr
o
n
g
est
im
p
ac
t
o
n
b
an
d
g
a
p
,
wh
er
e
h
ig
h
er
v
alu
es
in
cr
ea
s
e
p
r
ed
ictio
n
s
.
C
o
o
r
d
in
atio
n
n
u
m
b
er
(
C
NA)
also
s
ig
n
if
ican
tly
r
aises
b
an
d
g
ap
v
alu
es.
Den
s
ity
(
DC
)
an
d
io
n
ic
r
ad
iu
s
(
I
R
A)
h
av
e
m
o
d
er
ate
ef
f
ec
ts
,
wh
ile
o
x
id
atio
n
s
tates (
OS
B
,
OS
A)
,
io
n
ic
r
ad
iu
s
C
(
I
R
C
)
,
an
d
elec
tr
o
n
eg
ativ
ity
A
(
E
A)
co
n
tr
ib
u
te
less
.
Ov
er
all,
elec
tr
o
n
eg
ativ
ity
an
d
co
o
r
d
in
atio
n
n
u
m
b
er
ar
e
t
h
e
m
o
s
t
in
f
lu
en
tial f
ac
to
r
s
.
(
a)
(
b
)
Fig
u
r
e
4
.
Vis
u
al
s
u
m
m
ar
y
o
f
th
e
f
ea
tu
r
e
i
n
f
lu
en
ce
,
with
(
a)
u
tili
zin
g
SHAP v
alu
es f
o
r
r
an
k
in
g
f
ea
tu
r
e
im
p
o
r
tan
ce
in
o
u
r
ML
an
d
(
b
)
C
at
B
o
o
s
t
R
eg
r
ess
o
r
b
an
d
g
ap
3
.
4
.
H
y
perpa
ra
m
e
t
er
t
un
ing
w
it
h O
P
T
UNA
I
n
th
is
wo
r
k
,
we
u
s
ed
OPTU
NAto
tu
n
e
th
e
h
y
p
er
p
a
r
am
ete
r
s
o
f
v
ar
io
u
s
ML
m
o
d
els,
as
s
h
o
wn
in
T
ab
le
5
.
T
ab
le
5
s
u
m
m
ar
ize
s
OPTU
NA
-
b
ased
h
y
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
f
o
r
ea
ch
m
o
d
el,
b
ala
n
cin
g
co
m
p
lex
ity
an
d
g
en
er
aliza
tio
n
.
C
atB
o
o
s
t
an
d
Gr
ad
ien
t
B
o
o
s
tin
g
u
s
e
lo
w
lear
n
in
g
r
ates
wi
th
m
an
y
iter
atio
n
s
f
o
r
h
ig
h
er
ac
cu
r
ac
y
.
Ad
aBo
o
s
t
u
s
es
f
ewe
r
es
tim
ato
r
s
to
r
ed
u
ce
o
v
e
r
f
itti
n
g
,
KNN
u
s
es
a
lar
g
e
k
(
3
1
)
f
o
r
s
m
o
o
th
er
p
r
ed
ictio
n
s
,
R
an
d
o
m
Fo
r
est
b
alan
ce
s
tr
ee
d
ep
th
an
d
s
ize,
an
d
SVR
em
p
lo
y
s
a
n
o
n
-
lin
ea
r
k
er
n
el
t
o
ca
p
tu
r
e
co
m
p
lex
r
elatio
n
s
h
ip
s
.
T
ab
le
5
.
H
y
p
er
p
ar
a
m
eter
tu
n
i
n
g
s
ettin
g
s
with
OPTU
NA
M
e
t
h
o
d
s
H
y
p
e
r
p
a
r
a
me
t
e
r
s
C
a
t
b
o
o
s
t
R
e
g
r
e
ss
o
r
'i
t
e
r
a
t
i
o
n
s':
5
0
7
,
'
d
e
p
t
h
'
:
6
,
'
l
e
a
r
n
i
n
g
_
r
a
t
e
'
:
0
.
0
0
3
5
5
8
9
3
0
4
5
9
7
6
5
5
3
8
2
,
'l
2
_
l
e
a
f
_
r
e
g
'
:
0
.
0
9
1
5
3
9
5
2
1
7
2
2
8
1
1
0
6
,
'r
a
n
d
o
m
_
s
t
r
e
n
g
t
h
'
:
0
.
0
1
3
4
1
6
1
5
9
8
7
5
3
8
3
1
8
5
,
'b
a
g
g
i
n
g
_
t
e
m
p
e
r
a
t
u
r
e
':
0
.
1
3
7
0
0
7
7
9
1
5
0
1
4
8
4
3
2
,
'
b
o
r
d
e
r
_
c
o
u
n
t
':
5
1
A
d
a
b
o
o
st
R
e
g
r
e
ss
o
r
'n
_
e
st
i
ma
t
o
r
s'
:
4
9
,
'
l
e
a
r
n
i
n
g
_
r
a
t
e
'
:
0
.
0
9
1
4
0
8
9
6
2
0
9
0
9
0
7
4
7
,
'r
a
n
d
o
m_
s
t
a
t
e
'
:
4
0
K
n
e
i
g
h
b
o
r
sR
e
g
r
e
sso
r
'n
_
n
e
i
g
h
b
o
r
s':
3
1
,
'
l
e
a
f
_
si
z
e
'
:
7
1
,
'
p
':
1
,
'n
_
j
o
b
s':
5
R
a
n
d
o
mF
o
r
e
st
R
e
g
r
e
ss
o
r
'n
_
e
st
i
ma
t
o
r
s'
:
1
6
3
,
'ma
x
_
d
e
p
t
h
'
:
1
6
,
'
mi
n
_
sa
mp
l
e
s
_
s
p
l
i
t
':
2
,
'm
i
n
_
sa
mp
l
e
s
_
l
e
a
f
'
:
2
S
u
p
p
o
r
t
V
e
c
t
o
r
R
e
g
r
e
ss
o
r
'co
e
f
0
':
8
.
3
5
5
8
1
4
6
6
3
8
0
8
5
2
5
,
'
t
o
l
':
0
.
8
1
2
2
8
2
2
3
2
3
3
0
6
1
3
7
,
'e
p
si
l
o
n
':
0
.
3
8
8
4
5
5
7
9
1
5
5
5
0
4
0
3
,
'C
':
2
.
4
2
7
5
9
9
7
1
6
3
3
3
2
3
1
,
'
d
e
g
r
e
e
'
:
8
,
'
max
_
i
t
e
r
':
8
0
,
'c
a
c
h
e
_
si
z
e
'
:
3
5
9
G
r
a
d
i
e
n
t
B
o
o
st
i
n
g
R
e
g
r
e
ss
o
r
'l
e
a
r
n
i
n
g
_
r
a
t
e
'
:
0
.
0
0
2
6
0
2
4
9
3
3
8
5
1
5
2
4
5
5
5
,
'a
l
p
h
a
'
:
0
.
6
8
8
8
9
4
0
2
5
9
0
9
4
0
4
2
,
'
n
_
e
s
t
i
m
a
t
o
r
s':
4
4
4
,
'min
_
sa
mp
l
e
s
_
l
e
a
f
':
0
.
0
3
2
8
8
3
1
3
5
1
5
7
0
2
6
8
6
,
'm
i
n
_
sa
mp
l
e
s
_
s
p
l
i
t
':
0
.
3
6
8
5
7
3
3
0
7
5
3
3
9
9
4
4
,
'min
_
w
e
i
g
h
t
_
f
r
a
c
t
i
o
n
_
l
e
a
f
':
0
.
0
6
5
6
7
9
3
4
5
8
4
6
2
9
0
6
2
,
'm
a
x
_
d
e
p
t
h
':
4
0
,
'min
_
i
mp
u
r
i
t
y
_
d
e
c
r
e
a
s
e
':
0
.
0
2
2
5
3
2
3
1
3
1
8
1
0
2
5
4
8
8
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
in
v
o
lv
e
d
p
r
e
d
ictin
g
th
e
b
an
d
g
ap
a
n
d
ef
f
icien
cy
o
f
ch
alco
g
en
id
e
p
er
o
v
s
k
ite
s
o
lar
ce
lls
th
r
o
u
g
h
th
e
ap
p
licatio
n
o
f
v
ar
io
u
s
ML
m
o
d
els,
s
u
ch
as
Ad
aBo
o
s
t
R
eg
r
ess
o
r
,
C
at
B
o
o
s
t
R
eg
r
ess
o
r
,
Gr
ad
ien
t
B
o
o
s
tin
g
R
eg
r
ess
o
r
,
KNe
ig
h
b
o
r
s
R
eg
r
ess
o
r
,
an
d
SVR
.
T
o
test
th
e
s
u
cc
es
s
o
f
th
e
ML
m
o
d
els,
we
ap
p
lied
th
r
ee
p
e
r
f
o
r
m
an
ce
m
etr
ics:
R
MSE
,
MA
E
,
an
d
R
².
Am
o
n
g
all
th
e
m
o
d
els,
C
atB
o
o
s
tR
eg
r
ess
o
r
d
is
p
lay
ed
th
e
b
est
p
er
f
o
r
m
an
ce
o
n
b
a
n
d
g
ap
an
d
ef
f
icien
cy
f
o
r
ec
asts
.
T
h
e
C
atB
o
o
s
t
R
eg
r
ess
o
r
ac
h
iev
ed
t
h
e
b
est
p
er
f
o
r
m
an
ce
i
n
th
e
b
an
d
g
ap
s
im
u
latio
n
,
o
b
tain
in
g
th
e
lo
we
s
t
MA
E
o
f
0
.
2
3
1
0
eV
an
d
R
MSE
o
f
0
.
2
9
4
9
eV,
alo
n
g
with
th
e
h
i
g
h
est
R
²
v
al
u
e
o
f
0
.
6
9
3
4
.
Fo
r
th
e
e
f
f
icien
cy
s
im
u
latio
n
,
C
atB
o
o
s
t
g
av
e
th
e
m
o
s
t
ac
cu
r
ate
an
d
d
e
p
en
d
a
b
le
f
o
r
ec
asts
am
o
n
g
all
m
o
d
els.
lo
west
R
MSE
o
f
0
.
2
9
5
9
eV,
a
n
d
t
h
e
h
ig
h
est
R
²
o
f
0
.
6
9
1
4
.
Go
o
d
f
o
r
ec
ast
ac
cu
r
ac
y
an
d
co
n
tin
u
o
u
s
r
eliab
ilit
y
.
B
o
th
b
an
d
g
ap
a
n
d
e
f
f
icien
cy
f
o
r
ec
asts
h
ig
h
lig
h
t
elec
tr
o
n
eg
ativ
ity
(
E
C
)
an
d
c
o
o
r
d
in
atio
n
n
u
m
b
er
(
C
NA/C
AN)
as
th
e
m
o
s
t
s
ig
n
if
ican
t
asp
ec
ts
.
T
h
en
,
d
e
n
s
ity
an
d
io
n
ic
r
a
d
ii
s
er
v
e
as
s
ec
o
n
d
ar
y
y
et
c
r
u
cial
s
tr
u
ctu
r
al
d
escr
ip
to
r
s
.
Af
ter
t
h
at,
o
x
id
ati
o
n
s
tatu
s
in
f
lu
e
n
ce
s
p
r
ed
ictio
n
s
m
o
d
er
ately
,
co
n
s
is
ten
t
with
its
in
v
o
lv
em
en
t
in
o
r
b
ital
en
er
g
ies.
T
h
e
SHAP
v
alu
es
f
o
r
b
a
n
d
g
a
p
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Tu
n
in
g
fea
t
u
r
e
s
elec
tio
n
to
en
h
a
n
ce
ma
c
h
in
e
lea
r
n
in
g
p
r
ed
i
ctio
n
s
o
f
…
(
Osp
h
a
n
ie
Men
t
a
r
i P
r
ima
d
ia
n
ti
)
1515
an
d
ef
f
icien
cy
g
i
v
e
in
ter
p
r
eta
b
ilit
y
,
in
d
icatin
g
th
at
th
e
m
o
d
el’
s
d
ec
is
io
n
s
f
it
wi
th
estab
l
is
h
ed
p
h
y
s
ical
an
d
ch
em
ical
p
r
in
cip
les o
f
p
er
o
v
s
k
ites
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
ac
k
n
o
wled
g
e
th
e
Dep
ar
tm
e
n
t o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
,
I
s
lam
ic
Nu
s
an
tar
a
Un
iv
er
s
ity
,
B
an
d
u
n
g
,
an
d
th
e
I
n
d
o
n
esian
Go
v
e
r
n
m
en
t
u
n
d
er
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
an
d
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
(
Kem
d
ik
tis
ain
tek
)
f
o
r
t
h
eir
s
u
p
p
o
r
t o
f
th
is
wo
r
k
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
wo
r
k
was
f
u
n
d
e
d
b
y
th
e
I
n
d
o
n
esian
Go
v
er
n
m
en
t
u
n
d
er
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
a
n
d
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
(
Kem
d
ik
tis
ain
tek
)
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
ass
u
m
es
f
u
ll
r
esp
o
n
s
ib
ilit
y
f
o
r
all
co
r
r
esp
o
n
d
en
ce
ass
o
ciate
d
with
th
is
p
u
b
licatio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Osp
h
an
ie
Me
n
tar
i
Prim
ad
ian
ti
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
y
an
Nu
r
I
m
a
n
✓
✓
✓
Mu
h
am
m
ad
Z
im
am
u
l
Ad
li
✓
✓
✓
Ag
u
n
g
M
u
h
am
ad
T
o
h
a
✓
✓
Ag
u
n
g
Su
r
y
a
W
ib
o
wo
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
ar
e
a
v
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
G
.
N
j
e
ma
a
n
d
J.
K
.
K
i
b
e
t
,
“
A
r
e
v
i
e
w
o
f
c
h
a
l
c
o
g
e
n
i
d
e
-
b
a
se
d
p
e
r
o
v
sk
i
t
e
s
a
s
t
h
e
n
e
x
t
n
o
v
e
l
m
a
t
e
r
i
a
l
s
:
S
o
l
a
r
c
e
l
l
a
n
d
o
p
t
o
e
l
e
c
t
r
o
n
i
c
a
p
p
l
i
c
a
t
i
o
n
s,
c
a
t
a
l
y
s
i
s
a
n
d
f
u
t
u
r
e
p
e
r
sp
e
c
t
i
v
e
s
,
”
N
e
x
t
N
a
n
o
t
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
,
p
.
1
0
0
1
0
2
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
x
n
a
n
o
.
2
0
2
4
.
1
0
0
1
0
2
.
[
2
]
M
.
K
u
m
a
r
,
A
.
S
i
n
g
h
,
D
.
G
i
l
l
,
a
n
d
S
.
B
h
a
t
t
a
c
h
a
r
y
a
,
“
O
p
t
o
e
l
e
c
t
r
o
n
i
c
p
r
o
p
e
r
t
i
e
s
o
f
c
h
a
l
c
o
g
e
n
i
d
e
p
e
r
o
v
s
k
i
t
e
s
b
y
m
a
n
y
-
body
p
e
r
t
u
r
b
a
t
i
o
n
t
h
e
o
r
y
,
”
J
o
u
r
n
a
l
o
f
P
h
y
s
i
c
a
l
C
h
e
m
i
s
t
r
y
L
e
t
t
e
r
s
,
v
o
l
.
1
2
,
n
o
.
2
2
,
p
p
.
5
3
0
1
–
5
3
0
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
2
1
/
a
c
s.
j
p
c
l
e
t
t
.
1
c
0
1
0
3
4
.
[
3
]
Z.
J.
R
a
z
i
,
S
.
A
.
S
e
b
t
,
a
n
d
A
.
K
h
a
j
e
h
n
e
z
h
a
d
,
“
M
a
g
n
e
t
o
r
e
s
i
st
a
n
c
e
t
e
m
p
e
r
a
t
u
r
e
d
e
p
e
n
d
e
n
c
e
o
f
LSM
O
a
n
d
L
B
M
O
p
e
r
o
v
s
k
i
t
e
man
g
a
n
i
t
e
s
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
ret
i
c
a
l
a
n
d
A
p
p
l
i
e
d
P
h
y
si
c
s
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
2
4
3
–
2
4
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
0
9
4
-
0
1
8
-
0
3
1
0
-
3.
[
4
]
J.
G
.
B
e
d
n
o
r
z
a
n
d
K
.
A
.
M
u
l
l
e
r
,
“
P
o
ssi
b
l
e
h
i
g
h
Tc
s
u
p
e
r
c
o
n
d
u
c
t
i
v
i
t
y
i
n
t
h
e
B
a
-
La
-
Cu
-
O
s
y
s
t
e
m,
”
Z
e
i
t
s
c
h
ri
f
t
f
o
r
P
h
y
s
i
k
B
C
o
n
d
e
n
se
d
Ma
t
t
e
r
,
v
o
l
.
6
4
,
n
o
.
2
,
p
p
.
1
8
9
–
1
9
3
,
J
u
n
.
1
9
8
6
,
d
o
i
:
1
0
.
1
0
0
7
/
B
F
0
1
3
0
3
7
0
1
.
[
5
]
X
.
Ji
a
n
g
e
t
a
l
.
,
“
S
u
p
e
r
i
o
r
e
n
e
r
g
y
st
o
r
a
g
e
B
a
T
i
O
3
-
b
a
s
e
d
a
mo
r
p
h
o
u
s
d
i
e
l
e
c
t
r
i
c
f
i
l
m
w
i
t
h
p
o
l
y
mo
r
p
h
i
c
h
e
x
a
g
o
n
a
l
a
n
d
c
u
b
i
c
n
a
n
o
s
t
r
u
c
t
u
r
e
s
,
”
C
h
e
m
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
4
3
1
,
p
.
1
3
3
4
4
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
e
j
.
2
0
2
1
.
1
3
3
4
4
7
.
[
6
]
J.
W
u
,
“
P
e
r
o
v
sk
i
t
e
l
e
a
d
-
f
r
e
e
p
i
e
z
o
e
l
e
c
t
r
i
c
c
e
r
a
m
i
c
s
,
”
J
o
u
rn
a
l
o
f
A
p
p
l
i
e
d
Ph
y
si
c
s
,
v
o
l
.
1
2
7
,
n
o
.
1
9
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
0
0
6
2
6
1
.
[
7
]
M
.
S
u
h
a
i
l
,
H
.
A
b
b
a
s,
M
.
B
.
K
h
a
n
,
a
n
d
Z.
H
.
K
h
a
n
,
“
C
h
a
l
c
o
g
e
n
i
d
e
p
e
r
o
v
s
k
i
t
e
s f
o
r
p
h
o
t
o
v
o
l
t
a
i
c
a
p
p
l
i
c
a
t
i
o
n
s
:
a
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
N
a
n
o
p
a
rt
i
c
l
e
Re
s
e
a
r
c
h
,
v
o
l
.
2
4
,
n
o
.
7
,
p
.
1
4
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
5
1
-
022
-
0
5
5
2
5
-
0.
[
8
]
B
.
K
a
d
u
k
,
T.
K
o
w
a
l
c
z
y
k
,
a
n
d
T
.
V
a
n
V
o
o
r
h
i
s,
“
C
o
n
s
t
r
a
i
n
e
d
d
e
n
si
t
y
f
u
n
c
t
i
o
n
a
l
t
h
e
o
r
y
,
”
C
h
e
m
i
c
a
l
R
e
v
i
e
w
s
,
v
o
l
.
1
1
2
,
n
o
.
1
,
p
p
.
3
2
1
–
3
7
0
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
2
1
/
c
r
2
0
0
1
4
8
b
.
[
9
]
S
.
S
h
a
r
ma
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
a
i
d
e
d
b
a
n
d
g
a
p
e
n
g
i
n
e
e
r
i
n
g
o
f
B
a
Zr
S
3
C
h
a
l
c
o
g
e
n
i
d
e
P
e
r
o
v
s
k
i
t
e
,
”
A
C
S
A
p
p
l
i
e
d
Ma
t
e
r
i
a
l
s
a
n
d
I
n
t
e
rf
a
c
e
s
,
v
o
l
.
1
5
,
n
o
.
1
5
,
p
p
.
1
8
9
6
2
–
1
8
9
7
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
2
1
/
a
c
s
a
m
i
.
3
c
0
0
6
1
8
.
[
1
0
]
J.
Y
a
n
g
a
n
d
A
.
M
a
n
n
o
d
i
-
K
a
n
a
k
k
i
t
h
o
d
i
,
“
H
i
g
h
-
t
h
r
o
u
g
h
p
u
t
c
o
m
p
u
t
a
t
i
o
n
s
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
h
a
l
i
d
e
p
e
r
o
v
sk
i
t
e
d
i
sc
o
v
e
r
y
,
”
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
5
0
8
-
1
5
1
7
1516
MR
S
B
u
l
l
e
t
i
n
,
v
o
l
.
4
7
,
n
o
.
9
,
p
p
.
9
4
0
–
9
4
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
5
5
7
/
s
4
3
5
7
7
-
022
-
0
0
4
1
4
-
2.
[
1
1
]
P
.
O
mp
r
a
k
a
sh
,
B
.
M
a
n
i
k
a
n
d
a
n
,
A
.
S
a
n
d
e
e
p
,
R
.
S
h
r
i
v
a
s
t
a
v
a
,
P
.
V
i
sw
e
s
h
,
a
n
d
D
.
B
.
P
a
n
e
m
a
n
g
a
l
o
r
e
,
“
G
r
a
p
h
r
e
p
r
e
s
e
n
t
a
t
i
o
n
a
l
l
e
a
r
n
i
n
g
f
o
r
b
a
n
d
g
a
p
p
r
e
d
i
c
t
i
o
n
i
n
v
a
r
i
e
d
p
e
r
o
v
s
k
i
t
e
c
r
y
s
t
a
l
s,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
Ma
t
e
r
i
a
l
s
S
c
i
e
n
c
e
,
v
o
l
.
1
9
6
,
p
.
1
1
0
5
3
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
mat
sci
.
2
0
2
1
.
1
1
0
5
3
0
.
[
1
2
]
A
.
K
h
a
n
,
J
.
K
a
n
d
e
l
,
H
.
T
a
y
a
r
a
,
a
n
d
K
.
T.
C
h
o
n
g
,
“
P
r
e
d
i
c
t
i
n
g
t
h
e
b
a
n
d
g
a
p
a
n
d
e
f
f
i
c
i
e
n
c
y
o
f
p
e
r
o
v
s
k
i
t
e
s
o
l
a
r
c
e
l
l
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s,
”
M
o
l
e
c
u
l
a
r
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
4
3
,
n
o
.
2
,
p
.
e
2
0
2
3
0
0
2
1
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
2
/
m
i
n
f
.
2
0
2
3
0
0
2
1
7
.
[
1
3
]
S
.
O
’
B
r
i
e
n
,
L.
B
r
u
s
,
a
n
d
C
.
B
.
M
u
r
r
a
y
,
“
S
y
n
t
h
e
s
i
s
o
f
mo
n
o
d
i
s
p
e
r
se
n
a
n
o
p
a
r
t
i
c
l
e
s
o
f
b
a
r
i
u
m
t
i
t
a
n
a
t
e
:
T
o
w
a
r
d
a
g
e
n
e
r
a
l
i
z
e
d
st
r
a
t
e
g
y
o
f
o
x
i
d
e
n
a
n
o
p
a
r
t
i
c
l
e
sy
n
t
h
e
si
s,”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
r
i
c
a
n
C
h
e
m
i
c
a
l
S
o
c
i
e
t
y
,
v
o
l
.
1
2
3
,
n
o
.
4
8
,
p
p
.
1
2
0
8
5
–
1
2
0
8
6
,
2
0
0
1
,
d
o
i
:
1
0
.
1
0
2
1
/
j
a
0
1
1
4
1
4
a
.
[
1
4
]
M
.
B
u
f
f
i
e
r
e
,
D
.
S
.
D
h
a
w
a
l
e
,
a
n
d
F
.
E
l
-
M
e
l
l
o
u
h
i
,
“
C
h
a
l
c
o
g
e
n
i
d
e
ma
t
e
r
i
a
l
s
a
n
d
d
e
r
i
v
a
t
i
v
e
s
f
o
r
p
h
o
t
o
v
o
l
t
a
i
c
a
p
p
l
i
c
a
t
i
o
n
s,
”
E
n
e
r
g
y
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
,
n
o
.
1
1
,
p
.
1
9
0
0
8
1
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
2
/
e
n
t
e
.
2
0
1
9
0
0
8
1
9
.
[
1
5
]
N
.
S
a
t
a
,
M
.
I
sh
i
g
a
me
,
a
n
d
S
.
S
h
i
n
,
“
O
p
t
i
c
a
l
a
b
so
r
p
t
i
o
n
s
p
e
c
t
r
a
o
f
a
c
c
e
p
t
o
r
-
d
o
p
e
d
S
r
Zr
O
3
a
n
d
S
r
Ti
O
3
p
e
r
o
v
sk
i
t
e
-
t
y
p
e
p
r
o
t
o
n
c
o
n
d
u
c
t
o
r
s,”
S
o
l
i
d
S
t
a
t
e
I
o
n
i
c
s
,
v
o
l
.
8
6
–
8
8
,
n
o
.
P
A
R
T
1
,
p
p
.
6
2
9
–
6
3
2
,
1
9
9
6
,
d
o
i
:
1
0
.
1
0
1
6
/
0
1
6
7
-
2
7
3
8
(
9
6
)
0
0
2
2
6
-
3.
[
1
6
]
Y
.
G
a
n
,
N
.
M
i
a
o
,
P
.
La
n
,
J.
Zh
o
u
,
S
.
R
.
El
l
i
o
t
t
,
a
n
d
Z.
S
u
n
,
“
R
o
b
u
s
t
d
e
s
i
g
n
o
f
h
i
g
h
-
p
e
r
f
o
r
ma
n
c
e
o
p
t
o
e
l
e
c
t
r
o
n
i
c
c
h
a
l
c
o
g
e
n
i
d
e
c
r
y
st
a
l
s
f
r
o
m
h
i
g
h
-
t
h
r
o
u
g
h
p
u
t
c
o
m
p
u
t
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
r
i
c
a
n
C
h
e
m
i
c
a
l
S
o
c
i
e
t
y
,
v
o
l
.
1
4
4
,
n
o
.
1
3
,
p
p
.
5
8
7
8
–
5
8
8
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
2
1
/
j
a
c
s.
1
c
1
2
6
2
0
.
[
1
7
]
Y
.
Z
h
a
n
g
,
T.
S
h
i
m
a
d
a
,
T.
K
i
t
a
m
u
r
a
,
a
n
d
J.
W
a
n
g
,
“
F
e
r
r
o
e
l
e
c
t
r
i
c
i
t
y
i
n
R
u
d
d
l
e
s
d
e
n
–
P
o
p
p
e
r
c
h
a
l
c
o
g
e
n
i
d
e
p
e
r
o
v
s
k
i
t
e
s
f
o
r
p
h
o
t
o
v
o
l
t
a
i
c
a
p
p
l
i
c
a
t
i
o
n
:
t
h
e
r
o
l
e
o
f
t
o
l
e
r
a
n
c
e
f
a
c
t
o
r
,
”
T
h
e
J
o
u
r
n
a
l
o
f
Ph
y
s
i
c
a
l
C
h
e
m
i
st
r
y
L
e
t
t
e
rs
,
v
o
l
.
8
,
n
o
.
2
3
,
p
p
.
5
8
3
4
–
5
8
3
9
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
2
1
/
a
c
s.
j
p
c
l
e
t
t
.
7
b
0
2
5
9
1
.
[
1
8
]
N
.
A
.
M
o
r
o
z
e
t
a
l
.
,
“
I
n
si
g
h
t
s
o
n
t
h
e
sy
n
t
h
e
si
s,
c
r
y
st
a
l
a
n
d
e
l
e
c
t
r
o
n
i
c
st
r
u
c
t
u
r
e
s
,
a
n
d
o
p
t
i
c
a
l
a
n
d
t
h
e
r
m
o
e
l
e
c
t
r
i
c
p
r
o
p
e
r
t
i
e
s
o
f
Sr
1
–
x
Sb
x
H
f
S
e
3
o
r
t
h
o
r
h
o
m
b
i
c
p
e
r
o
v
sk
i
t
e
,
”
I
n
o
rg
a
n
i
c
C
h
e
m
i
s
t
ry
,
v
o
l
.
5
7
,
n
o
.
1
2
,
p
p
.
7
4
0
2
–
7
4
1
1
,
Ju
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
2
1
/
a
c
s.i
n
o
r
g
c
h
e
m.
8
b
0
1
0
3
8
.
[
1
9
]
K
.
K
u
h
a
r
e
t
a
l
.
,
“
S
u
l
f
i
d
e
p
e
r
o
v
s
k
i
t
e
s
f
o
r
s
o
l
a
r
e
n
e
r
g
y
c
o
n
v
e
r
s
i
o
n
a
p
p
l
i
c
a
t
i
o
n
s:
c
o
m
p
u
t
a
t
i
o
n
a
l
sc
r
e
e
n
i
n
g
a
n
d
s
y
n
t
h
e
si
s
o
f
t
h
e
s
e
l
e
c
t
e
d
c
o
m
p
o
u
n
d
L
a
Y
S
3
,
”
E
n
e
r
g
y
&
E
n
v
i
r
o
n
m
e
n
t
a
l
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
n
o
.
1
2
,
p
p
.
2
5
7
9
–
2
5
9
3
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
3
9
/
C
7
EE
0
2
7
0
2
H
.
[
2
0
]
Y
.
N
i
s
h
i
g
a
k
i
e
t
a
l
.
,
“
E
x
t
r
a
o
r
d
i
n
a
r
y
st
r
o
n
g
b
a
n
d
-
e
d
g
e
a
b
s
o
r
p
t
i
o
n
i
n
d
i
st
o
r
t
e
d
c
h
a
l
c
o
g
e
n
i
d
e
p
e
r
o
v
s
k
i
t
e
s
,
”
S
o
l
a
r
R
RL
,
v
o
l
.
4
,
n
o
.
5
,
p
.
1
9
0
0
5
5
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
2
/
s
o
l
r
.
2
0
1
9
0
0
5
5
5
.
[
2
1
]
S
.
C
u
r
t
a
r
o
l
o
e
t
a
l
.
,
“
A
F
LO
W
LI
B
.
O
R
G
:
A
d
i
s
t
r
i
b
u
t
e
d
m
a
t
e
r
i
a
l
s p
r
o
p
e
r
t
i
e
s
r
e
p
o
si
t
o
r
y
f
r
o
m h
i
g
h
-
t
h
r
o
u
g
h
p
u
t
a
b
i
n
i
t
i
o
c
a
l
c
u
l
a
t
i
o
n
s,”
C
o
m
p
u
t
a
t
i
o
n
a
l
Ma
t
e
r
i
a
l
s
S
c
i
e
n
c
e
,
v
o
l
.
5
8
,
p
p
.
2
2
7
–
2
3
5
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mm
a
t
s
c
i
.
2
0
1
2
.
0
2
.
0
0
2
.
[
2
2
]
A
.
Ja
i
n
e
t
a
l
.
,
“
C
o
mm
e
n
t
a
r
y
:
T
h
e
M
a
t
e
r
i
a
l
s
P
r
o
j
e
c
t
:
A
m
a
t
e
r
i
a
l
s
g
e
n
o
m
e
a
p
p
r
o
a
c
h
t
o
a
c
c
e
l
e
r
a
t
i
n
g
ma
t
e
r
i
a
l
s
i
n
n
o
v
a
t
i
o
n
,
”
APL
Ma
t
e
r
i
a
l
s
,
v
o
l
.
1
,
n
o
.
1
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
6
3
/
1
.
4
8
1
2
3
2
3
.
[
2
3
]
S
.
K
i
m
e
t
a
l
.
,
“
P
u
b
C
h
e
m
2
0
1
9
u
p
d
a
t
e
:
I
mp
r
o
v
e
d
a
c
c
e
ss
t
o
c
h
e
m
i
c
a
l
d
a
t
a
,
”
N
u
c
l
e
i
c
Ac
i
d
s
R
e
se
a
rc
h
,
v
o
l
.
4
7
,
n
o
.
D
1
,
p
p
.
D
1
1
0
2
--
D
1
1
0
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
9
3
/
n
a
r
/
g
k
y
1
0
3
3
.
[
2
4
]
Y
.
D
a
i
,
F
.
G
i
e
s
e
k
e
,
S
.
O
e
h
mc
k
e
,
Y
.
W
u
,
a
n
d
K
.
B
a
r
n
a
r
d
,
“
A
t
t
e
n
t
i
o
n
a
l
f
e
a
t
u
r
e
f
u
si
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
1
I
E
EE
W
i
n
t
e
r
C
o
n
f
e
re
n
c
e
o
n
A
p
p
l
i
c
a
t
i
o
n
s
o
f
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
WA
C
V
2
0
2
1
,
2
0
2
1
,
p
p
.
3
5
5
9
–
3
5
6
8
,
d
o
i
:
1
0
.
1
1
0
9
/
W
A
C
V
4
8
6
3
0
.
2
0
2
1
.
0
0
3
6
0
.
[
2
5
]
J.
C
a
i
,
J.
L
u
o
,
S
.
W
a
n
g
,
a
n
d
S
.
Y
a
n
g
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
i
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
A
n
e
w
p
e
r
s
p
e
c
t
i
v
e
,
”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
3
0
0
,
p
p
.
7
0
–
7
9
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.2
0
1
7
.
1
1
.
0
7
7
.
[
2
6
]
P
.
S
c
h
r
a
t
z
,
J.
M
u
e
n
c
h
o
w
,
E.
I
t
u
r
r
i
t
x
a
,
J.
R
i
c
h
t
e
r
,
a
n
d
A
.
B
r
e
n
n
i
n
g
,
“
H
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
a
n
d
p
e
r
f
o
r
m
a
n
c
e
a
sses
sme
n
t
o
f
st
a
t
i
st
i
c
a
l
a
n
d
m
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
u
si
n
g
s
p
a
t
i
a
l
d
a
t
a
,
”
Ec
o
l
o
g
i
c
a
l
M
o
d
e
l
l
i
n
g
,
v
o
l
.
4
0
6
,
p
p
.
1
0
9
–
1
2
0
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
o
l
m
o
d
e
l
.
2
0
1
9
.
0
6
.
0
0
2
.
[
2
7
]
T.
A
k
i
b
a
,
S
.
S
a
n
o
,
T.
Y
a
n
a
se
,
T
.
O
h
t
a
,
a
n
d
M
.
K
o
y
a
m
a
,
“
O
p
t
u
n
a
:
a
n
e
x
t
-
g
e
n
e
r
a
t
i
o
n
h
y
p
e
r
p
a
r
a
me
t
e
r
o
p
t
i
mi
z
a
t
i
o
n
f
r
a
m
e
w
o
r
k
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
S
I
G
K
D
D
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
s
c
o
v
e
r
y
a
n
d
D
a
t
a
Mi
n
i
n
g
,
J
u
l
.
2
0
1
9
,
p
p
.
2
6
2
3
–
2
6
3
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
2
9
2
5
0
0
.
3
3
3
0
7
0
1
.
[
2
8
]
J.
Z
h
o
u
,
A
.
H
.
G
a
n
d
o
m
i
,
F
.
C
h
e
n
,
a
n
d
A
.
H
o
l
z
i
n
g
e
r
,
“
Ev
a
l
u
a
t
i
n
g
t
h
e
q
u
a
l
i
t
y
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
e
x
p
l
a
n
a
t
i
o
n
s:
A
s
u
r
v
e
y
o
n
met
h
o
d
s
a
n
d
met
r
i
c
s
,
”
El
e
c
t
r
o
n
i
c
s (S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
5
,
p
p
.
1
–
1
9
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
0
0
5
0
5
9
3
.
[
2
9
]
C
.
J.
W
i
l
l
m
o
t
t
a
n
d
K
.
M
a
t
s
u
u
r
a
,
“
A
d
v
a
n
t
a
g
e
s
o
f
t
h
e
m
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
(
M
A
E)
o
v
e
r
t
h
e
r
o
o
t
m
e
a
n
s
q
u
a
r
e
e
r
r
o
r
(
R
M
S
E)
i
n
a
ssess
i
n
g
a
v
e
r
a
g
e
m
o
d
e
l
p
e
r
f
o
r
m
a
n
c
e
,
”
C
l
i
m
a
t
e
Re
se
a
r
c
h
,
v
o
l
.
3
0
,
n
o
.
1
,
p
p
.
7
9
–
8
2
,
2
0
0
5
.
[
3
0
]
A
.
C
l
a
r
k
e
,
“
D
o
y
o
u
k
n
o
w
y
o
u
r
o
b
l
i
g
a
t
i
o
n
s
?
,
”
J
o
u
rn
a
l
o
f
t
h
e
I
ri
s
h
D
e
n
t
a
l
As
so
c
i
a
t
i
o
n
,
v
o
l
.
5
3
,
n
o
.
1
,
p
p
.
4
8
–
4
9
,
2
0
0
7
.
[
3
1
]
Y
.
N
o
h
a
r
a
,
K
.
M
a
t
s
u
m
o
t
o
,
H
.
S
o
e
j
i
ma,
a
n
d
N
.
N
a
k
a
s
h
i
ma,
“
E
x
p
l
a
n
a
t
i
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
u
si
n
g
S
h
a
p
l
e
y
a
d
d
i
t
i
v
e
e
x
p
l
a
n
a
t
i
o
n
a
n
d
a
p
p
l
i
c
a
t
i
o
n
f
o
r
r
e
a
l
d
a
t
a
i
n
h
o
sp
i
t
a
l
,
”
C
o
m
p
u
t
e
r M
e
t
h
o
d
s
a
n
d
Pr
o
g
r
a
m
s i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
2
1
4
,
p
.
1
0
6
5
8
4
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
2
1
.
1
0
6
5
8
4
.
[
3
2
]
S
.
T.
Ja
a
f
a
r
a
n
d
M
.
M
o
h
a
mm
a
d
i
,
“
Ep
i
l
e
p
t
i
c
s
e
i
z
u
r
e
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
U
H
D
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
4
1
–
5
0
,
2
0
1
9
,
d
o
i
:
1
0
.
2
1
9
2
8
/
u
h
d
j
st
.
v
3
n
2
y
2
0
1
9
.
p
p
4
1
-
5
0
.
[
3
3
]
J.
M
.
A
h
n
,
J
.
K
i
m
,
a
n
d
J
.
K
i
m
,
“
En
se
mb
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
o
f
G
r
a
d
i
e
n
t
B
o
o
st
i
n
g
(
X
G
B
o
o
s
t
,
L
i
g
h
t
G
B
M
,
C
a
t
B
o
o
s
t
)
a
n
d
a
t
t
e
n
t
i
o
n
-
b
a
se
d
C
N
N
-
LSTM
f
o
r
h
a
r
m
f
u
l
a
l
g
a
l
b
l
o
o
ms f
o
r
e
c
a
st
i
n
g
,
”
T
o
x
i
n
s
,
v
o
l
.
1
5
,
n
o
.
1
0
,
p
.
6
0
8
,
2
0
2
3
.
[
3
4
]
J.
T.
H
a
n
c
o
c
k
a
n
d
T.
M
.
K
h
o
s
h
g
o
f
t
a
a
r
,
“
C
a
t
B
o
o
st
f
o
r
b
i
g
d
a
t
a
:
a
n
i
n
t
e
r
d
i
sci
p
l
i
n
a
r
y
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
B
i
g
D
a
t
a
,
v
o
l
.
7
,
n
o
.
1
,
p
.
9
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
0
-
0
0
3
6
9
-
8.
[
3
5
]
R
.
S
.
A
j
i
n
,
S
.
S
e
g
o
n
i
,
a
n
d
R
.
F
a
n
t
i
,
“
O
p
t
i
mi
z
a
t
i
o
n
o
f
S
V
R
a
n
d
C
a
t
B
o
o
st
m
o
d
e
l
s
u
s
i
n
g
m
e
t
a
h
e
u
r
i
st
i
c
a
l
g
o
r
i
t
h
ms
t
o
a
ss
e
ss
l
a
n
d
s
l
i
d
e
su
sc
e
p
t
i
b
i
l
i
t
y
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
4
,
n
o
.
1
,
p
.
2
4
8
5
1
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
4
-
7
2
6
6
3
-
x.
[
3
6
]
Y
.
Zh
a
n
g
,
Z.
Z
h
a
o
,
a
n
d
J.
Zh
e
n
g
,
“
C
a
t
B
o
o
st
:
A
n
e
w
a
p
p
r
o
a
c
h
f
o
r
e
st
i
ma
t
i
n
g
d
a
i
l
y
r
e
f
e
r
e
n
c
e
c
r
o
p
e
v
a
p
o
t
r
a
n
s
p
i
r
a
t
i
o
n
i
n
a
r
i
d
a
n
d
semi
-
a
r
i
d
r
e
g
i
o
n
s
o
f
N
o
r
t
h
e
r
n
C
h
i
n
a
,
”
J
o
u
r
n
a
l
o
f
H
y
d
ro
l
o
g
y
,
v
o
l
.
5
8
8
,
p
.
1
2
5
0
8
7
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
h
y
d
r
o
l
.
2
0
2
0
.
1
2
5
0
8
7
.
[
3
7
]
N
.
S
.
B
h
a
t
i
a
n
d
M
.
K
h
a
r
i
,
“
A
n
e
w
i
n
t
r
u
si
o
n
d
e
t
e
c
t
i
o
n
s
c
h
e
me
u
si
n
g
C
a
t
B
o
o
s
t
c
l
a
ss
i
f
i
e
r
,
”
i
n
F
o
rt
h
c
o
m
i
n
g
N
e
t
w
o
rks
a
n
d
S
u
s
t
a
i
n
a
b
i
l
i
t
y
i
n
t
h
e
I
o
T
Era
,
F
i
rst
EAI
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
,
F
o
N
e
S
–
I
o
T
2
0
2
0
,
Vi
r
t
u
a
l
E
v
e
n
t
,
2
0
2
0
,
p
p
.
1
6
9
–
176
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
6
9
4
3
1
-
9
_
1
3
.
[
3
8
]
N
.
P
r
a
sa
n
n
a
V
e
n
k
a
t
e
sh
,
R
.
P
r
a
d
e
e
p
K
u
mar,
B
.
C
h
a
k
r
a
v
a
r
t
h
y
N
e
e
l
a
p
u
,
K
.
P
a
l
,
a
n
d
J.
S
i
v
a
r
a
ma
n
,
“
C
a
t
B
o
o
s
t
-
b
a
s
e
d
i
mp
r
o
v
e
d
d
e
t
e
c
t
i
o
n
o
f
P
-
w
a
v
e
c
h
a
n
g
e
s
i
n
si
n
u
s
r
h
y
t
h
m
a
n
d
t
a
c
h
y
c
a
r
d
i
a
c
o
n
d
i
t
i
o
n
s
:
a
l
e
a
d
s
e
l
e
c
t
i
o
n
st
u
d
y
,
”
P
h
y
s
i
c
a
l
a
n
d
En
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
s
i
n
Me
d
i
c
i
n
e
,
v
o
l
.
4
6
,
n
o
.
2
,
p
p
.
9
2
5
–
9
4
4
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
4
6
-
0
2
3
-
0
1
2
7
4
-
z.
[
3
9
]
D
.
P
.
S
o
l
o
m
a
t
i
n
e
a
n
d
D
.
L
.
S
h
r
e
s
t
h
a
,
“
A
d
a
B
o
o
s
t
.
R
T
:
a
b
o
o
s
t
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
r
e
g
r
e
s
s
i
o
n
p
r
o
b
l
e
m
s
,
”
i
n
2
0
0
4
I
E
E
E
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
s
(
I
E
E
E
C
a
t
.
N
o
.
0
4
C
H
3
7
5
4
1
)
,
2
0
0
4
,
v
o
l
.
2
,
p
p
.
1
1
6
3
–
1
1
6
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
J
C
N
N
.
2
0
0
4
.
1
3
8
0
1
0
2
.
[
4
0
]
T.
D
u
a
n
e
t
a
l
.
,
“
N
G
B
o
o
st
:
n
a
t
u
r
a
l
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
f
o
r
p
r
o
b
a
b
i
l
i
st
i
c
p
r
e
d
i
c
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
3
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
,
P
MLR
,
2
0
2
0
,
p
p
.
2
6
9
0
–
2
7
0
0
.
[
4
1
]
O
.
K
r
a
mer,
“
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s,”
i
n
D
i
m
e
n
s
i
o
n
a
l
i
t
y
R
e
d
u
c
t
i
o
n
w
i
t
h
U
n
s
u
p
e
rv
i
se
d
N
e
a
res
t
N
e
i
g
h
b
o
rs
,
B
e
r
l
i
n
,
G
e
r
m
a
n
y
:
S
p
r
i
n
g
e
r
,
2
0
1
3
,
p
p
.
1
3
–
2
3
.
[
4
2
]
A
.
J.
S
mo
l
a
a
n
d
B
.
S
c
h
ö
l
k
o
p
f
,
“
A
t
u
t
o
r
i
a
l
o
n
su
p
p
o
r
t
v
e
c
t
o
r
r
e
g
r
e
ss
i
o
n
,
”
S
t
a
t
i
st
i
c
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
1
9
9
–
2
2
2
,
2
0
0
4
,
d
o
i
:
1
0
.
1
0
2
3
/
B
:
S
TC
O
.
0
0
0
0
0
3
5
3
0
1
.
4
9
5
4
9
.
8
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Tu
n
in
g
fea
t
u
r
e
s
elec
tio
n
to
en
h
a
n
ce
ma
c
h
in
e
lea
r
n
in
g
p
r
ed
i
ctio
n
s
o
f
…
(
Osp
h
a
n
ie
Men
t
a
r
i P
r
ima
d
ia
n
ti
)
1517
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
O
sph
a
n
ie
Menta
r
i
Prim
a
d
i
a
n
t
i
re
c
e
iv
e
d
th
e
B.
E
n
g
.
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
fr
o
m
Telk
o
m
Un
i
v
e
rsity
,
I
n
d
o
n
e
sia
in
2
0
1
2
a
n
d
t
h
e
m
a
ste
r’s
d
e
g
re
e
s
in
e
lec
tri
c
e
n
g
in
e
e
rin
g
fro
m
U
n
iv
e
rsit
y
o
f
I
n
d
o
n
e
sia
,
In
d
o
n
e
sia
,
i
n
2
0
1
7
.
Cu
rr
e
n
tl
y
,
sh
e
is
a
lec
tu
re
r
a
t
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
,
U
n
iv
e
rsit
y
Isla
m
Nu
sa
n
tar
a
,
Ba
n
d
u
n
g
Un
i
v
e
rsity
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
re
n
e
wa
b
le
e
n
e
rg
y
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
b
io
in
f
o
rm
a
ti
c
e
sp
e
c
ially
m
o
lec
u
lar
a
n
d
to
x
icity
.
S
h
e
will
c
o
n
ti
n
u
e
h
e
r
P
h
.
D.
s
o
o
n
i
n
e
lec
tri
c
a
l
e
n
g
i
n
e
e
rin
g
in
I
n
d
o
n
e
sia
.
S
h
e
li
k
e
s
g
o
in
g
t
o
n
a
tu
re
p
lac
e
s,
re
a
d
s
s
o
m
e
b
o
o
k
s,
li
ste
n
t
o
m
u
si
c
in
leisu
re
ti
m
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
o
s
p
h
a
n
ie
8
8
@
m
a
il
.
c
o
m
.
Ry
a
n
Nur
Im
a
n
is
c
u
rre
n
tl
y
a
P
h
.
D.
stu
d
e
n
t
in
m
a
teria
ls
c
h
e
m
istry
a
t
Ka
n
a
z
a
w
a
Un
iv
e
rsity
,
Ja
p
a
n
.
His
re
se
a
rc
h
i
n
tere
sts
in
c
lu
d
e
se
m
ico
n
d
u
c
ti
n
g
d
e
v
ice
s,
m
a
g
n
e
ti
c
m
a
teria
ls,
a
n
d
c
a
rb
o
n
-
b
a
se
d
m
a
teria
ls.
He
is
a
lec
tu
re
r
in
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
a
t
Un
iv
e
rsitas
Isla
m
Nu
sa
n
tara
,
In
d
o
n
e
sia
.
Mu
h
a
m
m
a
d
Zi
m
a
m
u
l
Ad
li
h
a
s
a
stro
n
g
re
se
a
rc
h
in
tere
st
in
se
n
so
rs,
b
io
se
n
so
rs,
n
a
n
o
m
a
teria
ls,
a
n
d
n
a
n
o
tec
h
n
o
l
o
g
y
.
He
is
c
u
rre
n
t
ly
a
P
h
.
D.
stu
d
e
n
t
a
t
t
h
e
Ba
n
d
u
n
g
In
sti
tu
te
o
f
Tec
h
n
o
l
o
g
y
(IT
B),
Ba
n
d
u
n
g
,
I
n
d
o
n
e
sia
.
In
a
d
d
i
ti
o
n
to
h
is
a
c
a
d
e
m
ic
p
u
rsu
it
s,
h
e
se
rv
e
s
a
s
th
e
h
e
a
d
o
f
t
h
e
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
S
t
u
d
y
P
r
o
g
ra
m
a
t
UN
INU
S
Un
iv
e
rsity
,
In
d
o
n
e
sia
.
He
is
a
lso
a
c
ti
v
e
ly
in
v
o
l
v
e
d
i
n
o
rg
a
n
iza
ti
o
n
a
l
a
c
ti
v
it
ies
,
i
n
c
lu
d
in
g
Na
h
d
latu
l
Ula
m
a
in
Ba
n
d
u
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
z
ima
m
u
lad
li
@
u
n
i
n
u
s.a
c
.
i
d
.
Ag
u
n
g
M
u
h
a
m
a
d
To
h
a
re
c
e
iv
e
d
h
is
m
a
ste
r’s
d
e
g
re
e
in
e
le
c
tri
c
a
l
e
n
g
in
e
e
rin
g
fro
m
t
h
e
Ba
n
d
u
n
g
In
sti
tu
te
o
f
T
e
c
h
n
o
l
o
g
y
(IT
B)
,
I
n
d
o
n
e
sia
.
He
is
c
u
rre
n
tl
y
a
lec
tu
re
r
in
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
a
t
U
n
iv
e
rsitas
Isla
m
Nu
sa
n
tara
,
In
d
o
n
e
sia
.
Ou
tsid
e
h
is
a
c
a
d
e
m
ic
a
c
ti
v
it
ies
,
h
e
e
n
jo
y
s
n
a
tu
re
,
p
a
rti
c
u
larly
m
o
u
n
tain
e
n
v
i
ro
n
m
e
n
ts.
He
is
a
d
e
v
o
ted
fa
m
il
y
m
a
n
,
with
o
n
e
so
n
,
a
n
d
e
n
jo
y
s
s
p
e
n
d
i
n
g
q
u
a
li
ty
t
ime
with
h
is
fa
m
il
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
g
u
n
g
m
u
h
a
m
a
d
to
h
a
@g
m
a
il
.
c
o
m
.
Ag
u
n
g
S
u
r
y
a
Wib
o
wo
re
c
e
iv
e
d
h
is
P
h
.
D.
d
e
g
re
e
fro
m
Je
o
n
b
u
k
Na
ti
o
n
a
l
Un
iv
e
rsity
,
S
o
u
t
h
Ko
re
a
.
He
is
c
u
rre
n
tl
y
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
t
Telk
o
m
Un
i
v
e
rsity
,
I
n
d
o
n
e
sia
.
His
a
re
a
s
o
f
e
x
p
e
rti
se
in
c
l
u
d
e
c
o
n
tr
o
l
e
n
g
i
n
e
e
rin
g
,
a
rti
f
icia
l
in
telli
g
e
n
c
e
(m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
in
g
),
a
n
d
b
io
i
n
fo
rm
a
ti
c
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
g
u
n
g
sw
@te
l
k
o
m
u
n
iv
e
rsit
y
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.