T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
2
0
2
5
,
p
p
.
371
~
381
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
2
3
i
2
.
26412
371
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
Decisio
n suppo
rt
sy
ste
m
in
m
a
chin
e learning
m
o
dels
f
o
r a face
recog
nition
-
ba
sed
attendanc
e sy
ste
m
J
o
s
eph T
eg
uh
Sa
nto
s
o
1,
2
,
Da
nn
y
M
a
no
ng
g
a
2
,
H
endry
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
A
c
a
d
e
mi
c
S
t
u
d
i
e
s,
U
n
i
v
e
r
si
t
a
s Sai
n
s
d
a
n
T
e
k
n
o
l
o
g
i
K
o
mp
u
t
e
r
,
S
e
maran
g
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
S
a
t
y
a
W
a
c
a
n
a
C
h
r
i
st
i
a
n
U
n
i
v
e
r
si
t
y
,
S
a
l
a
t
i
g
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
18
,
2
0
2
4
R
ev
i
s
ed
Dec
2
,
2
0
2
4
A
cc
ep
ted
Dec
26
,
2
0
2
4
T
h
is
re
se
a
rc
h
a
i
m
s
to
d
e
v
e
lo
p
a
p
re
d
ictiv
e
m
o
d
e
l
u
sin
g
f
a
c
e
re
c
o
g
n
it
io
n
-
b
a
se
d
a
tt
e
n
d
a
n
c
e
d
a
ta
a
n
d
in
teg
ra
ti
n
g
d
e
c
isio
n
su
p
p
o
r
t
sy
ste
m
(D
S
S
)
th
e
o
ry
w
it
h
m
a
c
h
in
e
lea
rn
in
g
(M
L
)
tec
h
n
iq
u
e
s
to
i
d
e
n
ti
f
y
h
ig
h
-
p
e
rf
o
r
m
in
g
tea
c
h
e
r
s
a
t
v
o
c
a
ti
o
n
a
l
h
ig
h
sc
h
o
o
ls
(
S
M
K
s
).
T
h
e
n
o
v
e
lt
y
o
f
th
is
re
se
a
r
c
h
li
e
s
in
in
teg
ra
ti
n
g
th
e
o
ry
w
it
h
th
e
u
se
o
f
fa
c
e
re
c
o
g
n
it
io
n
d
a
ta
a
n
d
M
L
a
lg
o
rit
h
m
s
to
p
re
d
ict
a
n
d
i
d
e
n
ti
f
y
h
ig
h
-
p
e
rf
o
r
m
in
g
tea
c
h
e
rs,
th
e
re
b
y
e
n
h
a
n
c
in
g
d
e
c
isio
n
-
m
a
k
in
g
p
ro
c
e
ss
e
s
a
n
d
t
e
a
c
h
e
r
p
e
rf
o
r
m
a
n
c
e
m
a
n
a
g
e
m
e
n
t
in
S
M
K
sc
h
o
o
ls.
T
h
e
d
a
tas
e
t
c
o
n
sists
o
f
S
M
K
tea
c
h
e
rs'
a
tt
e
n
d
a
n
c
e
d
a
ta
o
b
tai
n
e
d
th
ro
u
g
h
a
f
a
c
e
re
c
o
g
n
it
io
n
a
tt
e
n
d
a
n
c
e
sy
ste
m
,
to
talin
g
9
9
8
e
n
tri
e
s.
T
h
is
re
se
a
rc
h
e
m
p
lo
y
s
s
e
n
siti
v
it
y
a
n
a
ly
sis
c
o
n
c
e
p
ts
f
ro
m
DSS
th
e
o
ry
a
n
d
c
las
si
f
ica
ti
o
n
a
p
p
ro
a
c
h
e
s
f
ro
m
M
L
m
o
d
e
ls
u
ti
li
z
in
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
V
M
)
,
d
e
c
isio
n
tree
s
(DT
),
a
n
d
ra
n
d
o
m
f
o
re
st
(RF
).
T
h
e
m
o
d
e
ls
a
re
train
e
d
a
n
d
tes
ted
o
n
G
o
o
g
le
Co
lab
u
si
n
g
P
y
th
o
n
,
w
it
h
d
a
ta
d
istri
b
u
ti
o
n
g
u
id
e
d
b
y
th
e
P
a
re
to
p
r
in
c
ip
le.
T
h
e
re
se
a
r
c
h
f
in
d
in
g
s
in
d
ica
te
th
a
t
in
teg
ra
ti
n
g
DSS
th
e
o
ry
w
it
h
M
L
c
o
n
tri
b
u
tes
to
in
n
o
v
a
ti
o
n
a
n
d
b
e
n
e
f
it
s
in
im
p
ro
v
in
g
d
e
c
isio
n
-
m
a
k
in
g
a
n
d
tea
c
h
e
r
p
e
rf
o
r
m
a
n
c
e
m
a
n
a
g
e
m
e
n
t
b
y
su
c
c
e
ss
f
u
ll
y
p
re
d
ictin
g
h
ig
h
-
p
e
rf
o
rm
in
g
tea
c
h
e
rs.
Ev
a
lu
a
ti
o
n
re
su
lt
s
sh
o
w
th
e
h
ig
h
e
st
a
c
c
u
ra
c
y
ra
te o
f
9
8
%
w
it
h
th
e
RF
m
o
d
e
l,
m
a
k
in
g
it
th
e
b
e
st p
re
d
ict
iv
e
m
o
d
e
l
c
o
m
p
a
re
d
to
th
e
o
th
e
r
tw
o
m
o
d
e
ls.
K
ey
w
o
r
d
s
:
A
tte
n
d
an
ce
s
y
s
te
m
Dec
is
io
n
m
a
k
in
g
Dec
is
io
n
s
u
p
p
o
r
t s
y
s
te
m
Face
r
ec
o
g
n
itio
n
Ma
ch
i
n
e
lear
n
i
n
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
:
J
o
s
ep
h
T
eg
u
h
San
to
s
o
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Facu
l
t
y
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Sat
y
a
W
ac
an
a
C
h
r
is
tia
n
Un
i
v
er
s
i
t
y
St
.
Dip
o
n
eg
o
r
o
No
.
5
2
-
6
0
,
5
0
7
1
1
Salatig
a,
I
n
d
o
n
esia
E
m
ail:
j
o
s
ep
h
_
teg
u
h
@
s
tek
o
m
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
u
s
e
o
f
tech
n
o
lo
g
y
i
n
o
p
tim
izi
n
g
h
u
m
a
n
r
eso
u
r
ce
m
an
a
g
e
m
e
n
t
p
r
o
ce
s
s
es
h
a
s
b
ec
o
m
e
a
p
r
im
ar
y
f
o
cu
s
i
n
v
ar
io
u
s
f
ield
s
.
E
s
p
ec
i
all
y
i
n
t
h
e
c
u
r
r
en
t
d
i
g
ital
er
a,
w
h
er
e
tec
h
n
o
lo
g
y
-
b
ased
atte
n
d
an
ce
s
y
s
te
m
s
h
a
v
e
b
ee
n
w
id
el
y
ad
o
p
ted
,
s
u
ch
as
f
in
g
er
p
r
in
t,
s
m
ar
t
ca
r
d
s
,
r
ad
i
o
f
r
eq
u
en
c
y
id
en
ti
f
icatio
n
(
R
FID
)
,
QR
c
o
d
e
,
an
d
f
ac
e
r
ec
o
g
n
itio
n
.
R
ec
en
tl
y
,
f
ac
e
r
ec
o
g
n
itio
n
tech
n
o
lo
g
y
h
as
b
ec
o
m
e
a
p
o
p
u
lar
alter
n
at
iv
e
f
o
r
m
o
n
ito
r
in
g
in
d
iv
id
u
al
atten
d
a
n
ce
.
T
h
is
is
ev
id
en
ce
d
b
y
t
h
e
in
cr
ea
s
i
n
g
n
u
m
b
er
o
f
s
tu
d
ie
s
f
o
cu
s
in
g
o
n
th
e
i
m
p
l
e
m
en
tatio
n
o
f
f
ac
e
r
ec
o
g
n
itio
n
ac
r
o
s
s
v
ar
i
o
u
s
f
ield
s
an
d
in
s
tit
u
tio
n
s
.
I
n
th
e
f
i
n
an
c
ial
s
ec
to
r
,
Sriv
astav
a
an
d
B
ag
[
1
]
u
s
ed
f
ac
e
r
ec
o
g
n
itio
n
as
a
m
o
d
er
n
m
ar
k
et
in
g
to
o
l,
J
o
o
et
a
l.
[
2
]
d
ev
elo
p
ed
f
ac
e
r
ec
o
g
n
itio
n
f
o
r
p
ay
m
e
n
t
m
eth
o
d
co
n
f
ir
m
atio
n
,
a
n
d
K
h
ap
ar
d
e
et
a
l.
[
3
]
u
s
ed
f
ac
e
r
ec
o
g
n
iti
o
n
f
o
r
f
r
a
u
d
d
etec
tio
n
.
A
d
d
iti
o
n
all
y
,
b
ib
lio
m
e
tr
ic
an
al
y
s
is
d
ata
u
s
i
n
g
Vo
s
v
ie
wer
r
elate
d
to
th
e
u
s
e
o
f
f
ac
e
r
ec
o
g
n
itio
n
s
h
o
w
s
t
h
at
t
h
i
s
to
p
ic
h
as
g
ai
n
ed
s
ig
n
i
f
ica
n
t
atten
tio
n
in
r
ec
en
t
y
ea
r
s
,
p
ar
ticu
lar
l
y
i
n
th
e
ar
ea
o
f
atten
d
an
ce
s
y
s
te
m
s
.
T
h
is
is
in
d
icate
d
b
y
s
ev
er
al
e
m
er
g
i
n
g
s
t
u
d
ies
s
u
c
h
as
[
4
]
-
[
7
]
w
h
ic
h
u
til
ize
f
ac
e
r
ec
o
g
n
itio
n
tech
n
o
lo
g
y
f
o
r
atten
d
an
ce
in
v
ar
io
u
s
in
s
t
itu
tio
n
s
.
Face
r
ec
o
g
n
itio
n
is
also
s
tar
tin
g
to
b
e
in
teg
r
at
ed
w
ith
n
e
w
tech
n
o
lo
g
ie
s
lik
e
m
ac
h
i
n
e
lear
n
i
n
g
(
ML
)
f
o
r
s
p
ec
if
ic
n
ee
d
s
.
Se
v
er
al
r
ec
en
t
s
tu
d
ie
s
[
6
]
,
[
8
]
-
[
1
3
]
u
s
e
M
L
f
o
r
ac
c
u
r
ac
y
ta
s
k
s
in
f
ac
e
r
ec
o
g
n
it
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
3
7
1
-
381
372
d
etec
tio
n
.
A
d
d
itio
n
al
l
y
,
r
esea
r
ch
b
y
[
1
4
]
-
[
1
7
]
u
s
e
v
ar
io
u
s
m
ac
h
in
e
-
le
ar
n
in
g
m
o
d
els
as
t
o
o
ls
f
o
r
an
al
y
s
i
s
in
f
ac
e
r
ec
o
g
n
i
tio
n
.
A
b
o
u
t
p
r
ed
ictiv
e
m
o
d
el
s
,
ML
h
a
s
b
r
o
u
g
h
t
s
i
g
n
i
f
ica
n
t
b
en
ef
its
i
n
v
ar
io
u
s
co
n
tex
ts
,
in
cl
u
d
in
g
e
m
p
lo
y
ee
p
er
f
o
r
m
a
n
ce
p
r
ed
ictio
n
,
s
ales
p
r
ed
ictio
n
,
r
is
k
a
n
a
l
y
s
i
s
,
an
d
m
o
r
e.
Sev
er
al
r
ec
en
t
s
tu
d
ies
[
1
8
]
-
[
2
0
]
u
tili
ze
d
M
L
a
s
a
p
r
ed
ictiv
e
m
o
d
el
f
o
r
th
e
s
ale
s
an
d
p
u
r
c
h
as
e
o
f
g
o
o
d
s
,
w
h
ile
[
2
1
]
e
m
p
lo
y
ed
ML
as
a
to
o
l
f
o
r
p
r
ed
ictin
g
cu
s
to
m
er
p
u
r
ch
as
i
n
g
h
ab
its
.
A
d
d
i
tio
n
a
ll
y
,
r
esea
r
ch
b
y
[
2
2
]
-
[
2
4
]
u
s
ed
ML
to
p
r
ed
ict
an
d
an
al
y
ze
r
is
k
s
.
F
u
r
t
h
er
m
o
r
e,
s
t
u
d
ies
f
o
cu
s
o
n
d
ev
elo
p
in
g
m
o
r
e
c
o
m
p
le
x
p
r
ed
ictiv
e
m
o
d
el
s
to
p
r
ed
ict
in
d
iv
id
u
al
atten
d
an
ce
b
y
co
n
s
id
er
i
n
g
v
ar
i
o
u
s
f
ac
to
r
s
s
u
c
h
as
w
ea
th
er
co
n
d
itio
n
s
,
e
m
p
lo
y
ee
s
ch
ed
u
les
,
an
d
o
th
er
ex
ter
n
al
f
ac
to
r
s
.
R
e
s
ea
r
ch
b
y
[
2
5
]
,
[
2
6
]
co
m
b
i
n
ed
v
ar
io
u
s
d
ata
w
it
h
w
ea
t
h
er
d
ata
u
s
i
n
g
en
s
e
m
b
le
l
ea
r
n
in
g
tec
h
n
iq
u
es
to
p
r
e
d
ict
atten
d
an
ce
an
d
p
u
r
ch
ase
s
w
it
h
h
i
g
h
er
ac
cu
r
ac
y
.
Ho
w
ev
er
,
th
er
e
h
as
b
ee
n
n
o
r
esear
ch
u
tili
zi
n
g
e
m
p
lo
y
ee
atte
n
d
an
ce
d
ata
f
r
o
m
atte
n
d
an
ce
s
y
s
te
m
s
t
h
e
m
s
e
lv
es,
i
n
d
icati
n
g
th
at
th
e
u
s
e
o
f
atte
n
d
an
ce
d
ata
i
s
s
till
a
n
ar
ea
th
at
n
ee
d
s
to
b
e
ex
p
lo
r
ed
f
u
r
th
er
.
I
n
th
e
co
n
te
x
t
o
f
s
ec
o
n
d
ar
y
ed
u
ca
tio
n
,
h
av
i
n
g
ac
co
m
p
li
s
h
ed
teac
h
er
s
an
d
e
f
f
o
r
ts
to
s
u
p
p
o
r
t
th
eir
d
ev
elo
p
m
en
t
ar
e
v
ital
asp
ec
t
s
in
en
s
u
r
in
g
th
e
q
u
alit
y
o
f
ed
u
ca
tio
n
p
r
o
v
id
ed
.
A
d
d
itio
n
all
y
,
th
e
u
s
e
o
f
atten
d
an
ce
d
ata
in
s
ch
o
o
l
atte
n
d
an
ce
s
y
s
te
m
s
to
p
r
ed
ict
th
e
p
er
f
o
r
m
a
n
ce
o
f
v
o
ca
tio
n
al
h
ig
h
s
c
h
o
o
l
(
SMK)
teac
h
er
s
h
as
n
o
t
b
ee
n
s
t
u
d
ied
.
On
th
e
o
t
h
er
h
a
n
d
,
th
er
e
ar
e
n
o
t
m
a
n
y
s
t
u
d
ies
t
h
at
i
n
teg
r
ate
th
ese
a
n
al
y
tica
l
r
esu
lt
s
in
to
s
y
s
te
m
s
th
a
t
d
ir
ec
tl
y
s
u
p
p
o
r
t
d
ec
is
io
n
-
m
a
k
in
g
.
I
n
th
i
s
r
eg
ar
d
,
th
e
ap
p
r
o
p
r
iate
u
s
e
o
f
t
h
eo
r
y
w
ill
s
u
p
p
o
r
t
th
e
d
ev
elo
p
m
e
n
t
o
f
p
r
ed
ictiv
e
m
o
d
els
to
b
ec
o
m
e
m
o
r
e
h
o
lis
tic
a
n
d
ef
f
icie
n
t
.
Dec
is
io
n
-
m
ak
i
n
g
r
eq
u
ir
es
a
s
et
o
f
co
n
ce
p
ts
,
p
r
in
cip
les,
a
n
d
m
e
th
o
d
s
to
d
esi
g
n
,
d
e
v
elo
p
,
an
d
i
m
p
le
m
en
t
s
y
s
te
m
s
,
o
n
e
o
f
w
h
ic
h
is
th
e
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
te
m
(
DSS)
th
eo
r
y
.
T
h
e
m
ai
n
g
o
al
o
f
th
i
s
th
eo
r
y
i
s
to
p
r
o
v
id
e
ef
f
ec
ti
v
e
s
u
p
p
o
r
t
f
o
r
d
ec
is
io
n
-
m
a
k
er
s
in
d
ea
li
n
g
w
it
h
co
m
p
lex
an
d
u
n
s
tr
u
ctu
r
ed
p
r
o
b
lem
s
.
C
o
n
ce
r
n
in
g
ML
,
t
h
is
th
eo
r
y
ca
n
s
u
p
p
o
r
t
th
e
d
ev
elo
p
m
e
n
t
o
f
p
r
ed
ictiv
e
m
o
d
els
to
b
ec
o
m
e
m
o
r
e
h
o
lis
t
ic
an
d
ef
f
icie
n
t.
D
SS
th
eo
r
y
its
el
f
h
as
b
ee
n
ap
p
lied
in
v
ar
io
u
s
f
ie
ld
s
,
f
o
r
in
s
ta
n
ce
,
in
th
e
f
i
n
an
cia
l
s
ec
to
r
,
DSS
is
u
s
ed
to
in
v
esti
g
ate
co
m
p
o
n
e
n
ts
i
n
th
e
f
in
tech
ec
o
s
y
s
te
m
[
2
7
]
.
I
n
d
ec
is
io
n
-
m
a
k
i
n
g
,
DSS
is
i
m
p
le
m
e
n
ted
o
n
co
m
p
u
ter
s
f
o
r
au
to
m
ated
d
ec
is
io
n
-
m
ak
in
g
[
2
8
]
-
[3
2
]
also
u
tili
ze
d
DSS
to
ass
i
s
t
w
eb
-
b
ased
d
ec
is
io
n
-
m
a
k
i
n
g
.
I
n
n
e
w
er
t
ec
h
n
o
lo
g
y
,
s
e
v
er
al
s
tu
d
ie
s
[
3
3
]
-
[
3
5
]
in
teg
r
ated
DSS
t
h
eo
r
y
w
it
h
ar
ti
f
icial
in
t
ellig
e
n
ce
(
AI
)
as
a
to
o
l
f
o
r
d
is
ea
s
e
d
etec
tio
n
o
r
d
iag
n
o
s
i
s
.
A
lt
h
o
u
g
h
th
e
ap
p
licatio
n
o
f
DSS
th
eo
r
y
is
ev
id
en
t
in
v
ar
io
u
s
f
ield
s
,
n
o
r
esear
ch
h
as
b
ee
n
f
o
u
n
d
th
at
u
s
e
s
t
h
is
th
eo
r
y
i
n
co
n
j
u
n
ctio
n
w
it
h
ML
f
o
r
p
r
ed
ictiv
e
tas
k
s
s
i
m
u
lta
n
eo
u
s
l
y
.
A
d
d
itio
n
all
y
,
t
h
e
u
s
e
o
f
D
SS
i
n
th
e
f
ield
o
f
ed
u
ca
tio
n
h
a
s
n
o
t
b
ee
n
ex
p
lo
r
ed
.
I
n
th
e
co
n
te
x
t
o
f
s
ec
o
n
d
ar
y
ed
u
ca
tio
n
,
th
e
u
s
e
o
f
atte
n
d
an
ce
d
ata
f
o
r
s
tr
ateg
ic
d
ec
is
io
n
-
m
a
k
i
n
g
is
s
till
v
er
y
li
m
ited
.
Ma
n
y
s
ch
o
o
ls
r
ec
o
r
d
teac
h
er
atte
n
d
an
ce
u
s
i
n
g
f
ac
e
r
ec
o
g
n
itio
n
s
y
s
te
m
s
,
b
u
t
th
e
s
to
r
ed
d
ata
is
r
ar
ely
u
tili
ze
d
f
o
r
d
ata
-
d
r
iv
en
d
ec
is
io
n
-
m
a
k
i
n
g
.
T
o
f
ill
th
is
g
ap
,
th
is
s
t
u
d
y
ai
m
s
to
d
ev
elo
p
a
p
r
ed
ictiv
e
m
o
d
el
to
id
en
tify
o
u
ts
ta
n
d
in
g
teac
h
er
s
an
d
th
o
s
e
w
h
o
n
ee
d
f
u
r
th
er
d
ev
elo
p
m
en
t
u
s
i
n
g
ML
tech
n
iq
u
e
s
b
ased
o
n
at
ten
d
a
n
ce
d
ata
o
b
tain
ed
th
r
o
u
g
h
a
f
ac
e
r
ec
o
g
n
iti
on
-
b
a
s
ed
atten
d
an
ce
s
y
s
te
m
,
i
n
te
g
r
atin
g
co
n
ce
p
ts
f
r
o
m
DS
S
t
h
eo
r
y
.
DSS
ca
n
p
r
o
v
id
e
a
s
tr
u
ct
u
r
ed
f
r
a
m
e
w
o
r
k
f
o
r
an
al
y
z
in
g
d
ata
an
d
o
f
f
er
i
n
g
i
n
f
o
r
m
ati
v
e
r
ec
o
m
m
en
d
atio
n
s
f
o
r
s
ch
o
o
l
m
a
n
a
g
e
m
en
t.
T
h
r
o
u
g
h
t
h
e
in
teg
r
atio
n
o
f
th
e
s
elec
ted
t
h
eo
r
y
,
th
e
r
es
u
lti
n
g
p
r
ed
ic
ti
v
e
m
o
d
el
i
s
ex
p
ec
ted
to
o
p
tim
ize
p
er
f
o
r
m
an
c
e
m
an
a
g
e
m
e
n
t
an
d
p
r
ed
ictio
n
ac
cu
r
ac
y
i
n
teac
h
e
r
class
i
f
icatio
n
w
h
ile
p
r
o
v
id
in
g
m
o
r
e
h
o
li
s
tic
a
n
d
ap
p
licab
le
in
s
i
g
h
ts
i
n
t
h
e
co
n
tex
t
o
f
ed
u
ca
tio
n
al
o
r
g
an
iz
atio
n
s
.
T
h
u
s
,
t
h
is
r
e
s
ea
r
ch
ai
m
s
n
o
t
o
n
l
y
to
f
ill
a
g
ap
i
n
t
h
e
a
ca
d
em
ic
liter
at
u
r
e
b
u
t
also
to
m
a
k
e
a
tan
g
ib
le
co
n
tr
ib
u
tio
n
to
i
m
p
r
o
v
in
g
th
e
ef
f
ec
ti
v
en
e
s
s
o
f
teac
h
er
a
n
d
s
taf
f
p
er
f
o
r
m
an
c
e
m
an
a
g
e
m
e
n
t in
t
h
e
ed
u
ca
t
io
n
a
l c
o
n
tex
t
.
2.
M
E
T
H
O
D
2
.
1
.
Appro
a
ch
a
nd
t
ec
h
niq
u
e
T
h
is
r
esear
ch
e
m
p
lo
y
s
a
s
en
s
it
iv
i
t
y
a
n
al
y
s
i
s
ap
p
r
o
ac
h
(
DSS
th
eo
r
y
)
a
n
d
M
L
cl
ass
i
f
icatio
n
tech
n
iq
u
es
f
o
r
p
r
ed
ictiv
e
task
s
.
DSS
t
h
eo
r
y
is
a
co
llectio
n
o
f
co
n
ce
p
ts
,
p
r
in
cip
les,
an
d
m
et
h
o
d
s
u
s
ed
to
d
esig
n
,
d
ev
elo
p
,
an
d
im
p
le
m
e
n
t
s
y
s
te
m
s
th
a
t
aid
in
d
ec
is
io
n
-
m
a
k
i
n
g
.
T
h
e
p
r
im
ar
y
g
o
al
o
f
th
is
th
eo
r
y
i
s
to
p
r
o
v
id
e
ef
f
ec
ti
v
e
s
u
p
p
o
r
t
f
o
r
d
ec
is
io
n
-
m
a
k
er
s
in
ad
d
r
ess
in
g
co
m
p
lex
a
n
d
u
n
s
tr
u
ct
u
r
ed
p
r
o
b
lem
s
.
DS
S
en
co
m
p
as
s
es
s
e
v
er
al
ap
p
r
o
ac
h
es
w
it
h
d
i
f
f
er
e
n
t
p
u
r
p
o
s
es
a
n
d
f
u
n
ct
io
n
s
,
i
n
cl
u
d
in
g
s
e
n
s
i
t
iv
it
y
an
al
y
s
is
,
r
is
k
an
al
y
s
is
,
a
n
d
m
u
lti
-
cr
iter
ia
an
al
y
s
i
s
[
3
6
]
.
I
n
th
i
s
s
t
u
d
y
,
t
h
e
s
en
s
iti
v
it
y
an
a
l
y
s
is
ap
p
r
o
ac
h
f
r
o
m
DSS
t
h
eo
r
y
i
s
ch
o
s
en
f
o
r
th
e
d
ev
elo
p
m
e
n
t
o
f
a
p
r
ed
ictiv
e
m
o
d
el
u
s
i
n
g
ML
.
T
h
is
ap
p
r
o
ac
h
is
ca
p
ab
le
o
f
u
n
d
er
s
ta
n
d
in
g
h
o
w
s
en
s
iti
v
e
th
e
ML
m
o
d
el
is
to
ch
an
g
e
s
in
in
p
u
t
p
ar
a
m
eter
s
,
w
h
ic
h
is
v
er
y
h
elp
f
u
l
i
n
id
en
ti
f
y
in
g
th
e
m
o
s
t
in
f
lu
e
n
tia
l
v
ar
iab
le
s
o
r
f
ea
t
u
r
es
i
n
t
h
e
p
r
ed
ictio
n
r
es
u
lt
s
.
A
d
d
itio
n
al
l
y
,
s
e
n
s
iti
v
it
y
a
n
al
y
s
i
s
i
n
D
SS
t
h
eo
r
y
allo
w
s
f
o
r
ad
j
u
s
t
m
en
t
s
o
r
i
m
p
r
o
v
e
m
en
t
s
to
th
e
m
o
d
el
i
f
t
h
er
e
ar
e
v
ar
iab
les
w
it
h
s
ig
n
i
f
i
ca
n
t
i
m
p
ac
ts
o
n
t
h
e
p
r
ed
ictio
n
o
r
if
w
ea
k
n
es
s
es
ar
e
r
ev
ea
led
d
u
r
in
g
s
en
s
itiv
it
y
a
n
al
y
s
i
s
.
T
h
e
ML
class
if
icatio
n
tech
n
iq
u
e
is
u
s
ed
to
p
r
e
d
ict
o
u
ts
tan
d
in
g
SMK
teac
h
er
s
an
d
th
o
s
e
w
h
o
n
ee
d
f
u
r
th
er
d
ev
elo
p
m
e
n
t
b
ased
o
n
th
e
atten
d
an
ce
s
y
s
te
m
d
ataset
o
b
tain
ed
t
h
r
o
u
g
h
f
ac
e
r
ec
o
g
n
itio
n
.
C
la
s
s
i
f
ic
atio
n
is
a
tas
k
w
h
er
e
th
e
s
y
s
te
m
is
g
i
v
e
n
an
in
p
u
t
an
d
s
u
b
s
eq
u
e
n
tl
y
cla
s
s
i
f
ie
s
th
at
in
p
u
t
in
to
th
e
ap
p
r
o
p
r
iate
c
ateg
o
r
y
o
r
class
[
3
7
]
.
T
h
e
class
if
ica
tio
n
ap
p
r
o
ac
h
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
Dec
is
io
n
s
u
p
p
o
r
t sys
tem
in
ma
ch
in
e
lea
r
n
in
g
m
o
d
els fo
r
a
fa
ce
r
ec
o
g
n
itio
n
-
b
a
s
ed
…
(
Jo
s
ep
h
Teg
u
h
S
a
n
to
s
o
)
373
in
th
e
M
L
m
o
d
el
d
ev
elo
p
ed
i
n
th
i
s
r
esear
ch
u
s
e
s
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
,
d
ec
is
io
n
tr
ee
(
D
T
)
,
an
d
r
an
d
o
m
f
o
r
est
(
R
F)
m
o
d
el
s
.
T
h
ese
th
r
ee
m
o
d
els
ar
e
ch
o
s
en
d
u
e
to
th
eir
p
er
f
o
r
m
an
ce
ac
cu
r
ac
y
,
ab
ilit
y
to
h
an
d
le
v
ar
io
u
s
t
y
p
es o
f
d
ata
(
i
n
clu
d
i
n
g
ca
teg
o
r
ical
an
d
n
u
m
er
ical
d
ata)
,
m
o
d
el
f
le
x
ib
ilit
y
,
an
d
s
ca
lab
ilit
y
.
2
.
2
.
I
nte
g
ra
t
i
o
n
o
f
decisi
o
n
s
up
po
rt
s
y
s
t
e
m
t
heo
ry
in
t
h
e
dev
elo
p
m
ent
o
f
m
a
chine
l
ea
rning
predict
iv
e
m
o
de
ls
I
n
teg
r
ati
n
g
co
n
ce
p
ts
an
d
tech
n
iq
u
es
f
r
o
m
DSS
th
eo
r
y
i
n
to
th
e
d
ev
elo
p
m
e
n
t
o
f
M
L
m
o
d
el
s
ca
n
en
h
a
n
ce
t
h
e
s
y
s
te
m
’
s
ab
il
it
y
t
o
p
r
o
v
id
e
b
etter
d
ec
is
io
n
-
m
a
k
in
g
s
u
p
p
o
r
t.
Fig
u
r
e
1
s
h
o
w
s
t
h
e
in
teg
r
atio
n
s
te
p
s
p
er
f
o
r
m
ed
i
n
th
e
M
L
m
o
d
el
.
I
n
th
e
id
en
ti
f
icat
io
n
p
h
ase,
r
e
s
ea
r
ch
n
ee
d
s
a
n
d
ex
is
ti
n
g
p
r
o
b
le
m
s
ar
e
id
en
ti
f
ied
an
d
u
n
d
er
s
to
o
d
f
o
r
d
ec
is
io
n
-
m
ak
in
g
r
eg
ar
d
i
n
g
w
h
ic
h
M
L
m
o
d
el
to
u
s
e.
O
n
ce
t
h
e
p
r
o
b
lem
is
id
en
ti
f
ied
,
d
ata
ch
ar
ac
ter
is
tic
s
,
p
r
o
b
lem
co
m
p
lex
it
y
,
an
d
an
al
y
s
is
o
b
j
ec
tiv
es
ar
e
co
n
s
id
er
ed
w
h
e
n
s
elec
ti
n
g
t
h
e
M
L
m
o
d
el.
Du
r
in
g
th
e
d
ata
co
llectio
n
s
tep
,
teac
h
er
atten
d
an
ce
d
ata
is
g
ath
er
ed
th
r
o
u
g
h
a
f
ac
e
r
ec
o
g
n
itio
n
-
b
ased
atten
d
an
ce
s
y
s
te
m
i
m
p
le
m
e
n
t
ed
in
SMKs.
Su
b
s
eq
u
e
n
tl
y
,
t
h
e
d
ata
u
n
d
er
g
o
es
s
e
v
er
al
p
r
o
ce
s
s
in
g
s
ta
g
es
to
g
en
er
ate
r
elev
a
n
t
f
ea
t
u
r
es
th
r
o
u
g
h
p
r
ep
ar
atio
n
,
clea
n
in
g
,
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
as
n
ee
d
ed
f
o
r
m
o
d
el
tr
ain
in
g
an
d
test
i
n
g
.
Fo
llo
w
i
n
g
t
h
is
s
t
ag
e,
t
h
e
d
ev
elo
p
m
e
n
t
o
f
t
h
e
ML
m
o
d
el
p
r
o
ce
ed
s
w
i
th
tr
ai
n
in
g
a
n
d
tes
tin
g
,
a
n
d
p
r
ed
ictio
n
s
ar
e
m
ad
e
u
s
i
n
g
th
e
p
r
ep
ar
e
d
d
ata.
Fig
u
r
e
1
.
I
n
teg
r
atio
n
m
o
d
el
o
f
DSS
th
eo
r
y
i
n
to
t
h
e
d
ev
elo
p
ed
ML
m
o
d
el
2
.
3
.
Da
t
a
s
et
T
h
e
d
ataset
co
n
s
is
t
s
o
f
d
ata
ex
tr
ac
ted
in
M
y
SQ
L
d
atab
ase
f
o
r
m
at,
s
to
r
ed
u
s
in
g
E
x
ce
l
f
o
r
m
at,
an
d
s
u
b
s
eq
u
en
t
l
y
p
r
o
ce
s
s
ed
ac
co
r
d
in
g
to
r
esear
ch
n
ee
d
s
b
ef
o
r
e
b
ein
g
s
a
v
ed
in
C
SV
f
o
r
m
at
to
s
u
p
p
o
r
t
d
ata
u
s
ag
e
in
t
h
e
tr
ain
i
n
g
an
d
te
s
ti
n
g
o
f
ML
m
o
d
el
s
.
T
h
e
d
ataset
ex
tr
a
cted
f
r
o
m
t
h
e
s
y
s
te
m
f
o
r
r
esear
ch
p
u
r
p
o
s
es
to
tals
9
9
8
en
tr
ies.
A
d
d
itio
n
al
d
ata
in
clu
d
es
p
er
f
o
r
m
an
ce
d
ata
o
f
SMK
teac
h
er
s
o
b
tain
ed
f
r
o
m
p
er
f
o
r
m
a
n
ce
ev
alu
a
tio
n
s
,
class
r
o
o
m
ac
tiv
it
ies,
an
d
in
ter
v
ie
w
s
co
n
d
u
cted
w
it
h
s
ev
er
al
s
ta
f
f
m
e
m
b
er
s
i
n
clu
d
i
n
g
teac
h
er
s
,
p
r
in
cip
als,
an
d
SMK
s
tu
d
e
n
ts
.
T
h
e
d
ataset
u
s
ed
i
n
t
h
e
r
esear
ch
u
n
d
er
g
o
es
p
r
eli
m
i
n
ar
y
a
n
al
y
s
i
s
a
n
d
p
r
o
ce
s
s
in
g
b
ef
o
r
e
u
s
e.
Data
clea
n
in
g
i
n
v
o
l
v
es
f
illi
n
g
in
m
is
s
in
g
v
al
u
es
to
av
o
id
s
k
e
w
ed
d
ata
d
is
tr
ib
u
tio
n
an
d
p
r
ev
en
t
o
v
er
f
i
tti
n
g
.
S
u
b
s
eq
u
en
tl
y
,
t
h
e
d
ata
i
s
lab
eled
an
d
s
ep
ar
ated
ac
co
r
d
in
g
to
th
e
r
eq
u
ir
ed
f
ea
tu
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
3
7
1
-
381
374
T
h
e
d
ataset
is
th
e
n
d
iv
id
ed
in
to
tr
ain
i
n
g
an
d
te
s
ti
n
g
d
ata
u
s
i
n
g
th
e
P
ar
eto
p
r
in
cip
le
o
r
th
e
8
0
/2
0
r
u
le
[
3
8
]
,
w
h
er
e
8
0
%
o
f
t
h
e
d
ata
i
s
u
s
ed
f
o
r
m
o
d
el
tr
ai
n
i
n
g
a
n
d
2
0
%
f
o
r
m
o
d
el
te
s
ti
n
g
an
d
e
v
al
u
atio
n
o
f
th
e
d
e
v
elo
p
ed
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
.
I
n
th
i
s
m
o
d
el
d
e
v
elo
p
m
e
n
t
s
tep
,
8
0
%
o
f
th
e
d
ataset
i
s
tr
ain
ed
u
s
i
n
g
SVM,
DT
,
an
d
R
F
m
o
d
el
s
to
e
n
ab
le
th
e
m
o
d
els
t
o
lear
n
p
atter
n
s
p
r
esen
t i
n
t
h
e
d
ataset.
Var
io
u
s
m
o
d
el
p
ar
a
m
eter
s
ar
e
ad
j
u
s
ted
to
en
h
a
n
ce
p
er
f
o
r
m
a
n
ce
an
d
p
r
e
v
en
t
o
v
er
f
itti
n
g
.
Nex
t,
m
o
d
el
test
i
n
g
is
co
n
d
u
cted
u
s
i
n
g
t
h
e
r
em
ai
n
i
n
g
2
0
%
o
f
th
e
d
ataset
to
ev
alu
ate
m
o
d
e
l
p
er
f
o
r
m
a
n
ce
,
in
v
o
l
v
i
n
g
m
e
asu
r
e
m
en
t
m
etr
ics
s
u
ch
as
a
cc
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
s
co
r
e.
2
.
4
.
E
v
a
lua
t
i
o
n
me
t
rics
2
.
4
.
1
.
Acc
ura
cy
T
h
is
is
a
m
etr
ic
f
o
r
ev
al
u
ati
n
g
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
cla
s
s
i
f
ic
atio
n
m
o
d
els,
e
s
p
ec
iall
y
w
h
en
th
e
tar
g
et
class
es
ar
e
b
alan
ce
d
.
T
h
is
m
etr
ic
m
ea
s
u
r
es
h
o
w
m
an
y
co
r
r
ec
t
p
r
ed
ictio
n
s
ar
e
m
a
d
e
o
u
t
o
f
th
e
to
tal
p
r
ed
ictio
n
s
m
ad
e
b
y
th
e
m
o
d
els
(
SVM,
DT
,
an
d
R
F),
p
r
o
v
id
in
g
a
n
o
v
er
all
p
ictu
r
e
o
f
h
o
w
w
ell
t
h
e
m
o
d
el
s
p
r
ed
ict.
T
h
e
ac
cu
r
ac
y
m
etr
ic
i
s
ca
lcu
lated
u
s
i
n
g
t
h
e
(
1
)
:
=
+
+
+
+
(
1
)
w
h
er
e
tr
u
e
p
o
s
iti
v
e
(
T
P
)
is
th
e
n
u
m
b
er
o
f
co
r
r
ec
t
p
r
ed
ictio
n
s
f
o
r
th
e
p
o
s
it
iv
e
clas
s
.
T
r
u
e
n
eg
ati
v
e
(
T
N)
is
t
h
e
n
u
m
b
er
o
f
co
r
r
ec
t p
r
ed
ictio
n
s
f
o
r
th
e
n
eg
a
tiv
e
cla
s
s
.
F
alse p
o
s
itiv
e
(
FP
)
is
t
h
e
n
u
m
b
er
o
f
i
n
co
r
r
ec
t p
r
ed
ictio
n
s
f
o
r
th
e
p
o
s
iti
v
e
class
.
Fa
ls
e
n
e
g
ati
v
e
(
FN)
is
t
h
e
n
u
m
b
er
o
f
i
n
co
r
r
ec
t p
r
ed
ictio
n
s
f
o
r
th
e
n
e
g
ati
v
e
class
.
2
.
4
.
2
.
Rec
a
ll
T
h
is
m
e
tr
ic
w
ill
m
ea
s
u
r
e
th
e
m
o
d
el
’
s
ab
ilit
y
to
f
in
d
all
p
o
s
itiv
e
s
a
m
p
les
an
d
s
h
o
w
h
o
w
w
ell
it
ef
f
ec
tiv
e
l
y
id
e
n
ti
f
ies
h
i
g
h
-
p
er
f
o
r
m
i
n
g
teac
h
er
s
.
T
h
e
r
ec
all
m
etr
ic
w
il
l
b
e
ca
lcu
lated
u
s
i
n
g
(
2
)
,
w
h
ich
e
n
s
u
r
es
th
at
t
h
e
m
o
d
el’
s
ca
p
ab
ilit
y
to
id
en
ti
f
y
r
ele
v
an
t
s
a
m
p
le
s
is
q
u
an
t
if
ied
p
r
ec
is
el
y
.
Hi
g
h
r
ec
a
ll
in
d
icate
s
t
h
at
t
h
e
m
o
d
el
is
s
u
cc
es
s
f
u
l
i
n
m
i
n
i
m
i
zin
g
f
alse
n
e
g
ati
v
es,
en
s
u
r
i
n
g
th
at
m
o
s
t
h
ig
h
-
p
er
f
o
r
m
i
n
g
teac
h
er
s
ar
e
co
r
r
ec
tly
id
en
ti
f
ied
.
=
+
(
2
)
2
.
4
.
3
.
P
re
cisi
o
n a
nd
F
1
-
sc
o
re
T
h
e
p
r
ec
is
io
n
m
etr
ic
m
ea
s
u
r
e
s
h
o
w
ac
c
u
r
ate
th
e
m
o
d
el
is
i
n
p
r
ed
ictin
g
t
h
e
p
o
s
itiv
e
clas
s
,
i.e
.
,
h
o
w
m
an
y
o
f
t
h
e
p
o
s
itiv
e
p
r
ed
icti
o
n
s
ar
e
p
o
s
itiv
e.
F1
-
s
co
r
e
is
a
h
ar
m
o
n
ic
m
ea
n
o
f
r
ec
all
an
d
p
r
ec
is
io
n
th
at
w
ill
p
r
o
v
id
e
a
co
m
p
r
eh
e
n
s
i
v
e
o
v
er
v
ie
w
o
f
t
h
e
d
ev
elo
p
ed
m
o
d
el
’
s
p
er
f
o
r
m
a
n
ce
b
y
co
n
s
id
er
in
g
r
ec
all
a
n
d
p
r
ec
is
io
n
s
i
m
u
lta
n
eo
u
s
l
y
.
P
r
ec
is
io
n
m
etr
ic
i
s
ca
lc
u
lated
u
s
i
n
g
(
3
)
,
an
d
f
o
r
th
e
F1
-
s
co
r
e
m
e
tr
ic,
it
is
ca
lc
u
lated
u
s
i
n
g
(
4
)
.
=
+
(
3
)
1
−
=
2
×
×
+
(
4
)
2
.
5
.
T
ra
ini
ng
a
nd
t
esting
env
iro
n
m
e
nt
T
h
e
tr
ain
in
g
a
n
d
test
in
g
o
f
th
e
m
o
d
el
ar
e
co
n
d
u
cted
u
s
i
n
g
th
e
P
y
th
o
n
p
r
o
g
r
am
m
i
n
g
lan
g
u
ag
e
w
it
h
th
e
s
ci
k
it
-
lear
n
lib
r
ar
y
i
n
th
e
Go
o
g
le
C
o
lab
en
v
ir
o
n
m
e
n
t.
P
y
th
o
n
is
a
h
i
g
h
l
y
ca
p
ab
le
p
r
o
g
r
a
m
m
i
n
g
lan
g
u
a
g
e
f
o
r
d
ata
an
al
y
s
i
s
in
A
I
.
Me
an
w
h
ile,
th
e
s
cik
i
t
-
lear
n
li
b
r
ar
y
is
p
o
w
er
f
u
l
an
d
ea
s
y
to
u
s
e
f
o
r
v
ar
io
u
s
m
ac
h
in
e
-
lear
n
in
g
alg
o
r
it
h
m
s
.
T
h
is
lib
r
ar
y
w
i
ll
b
e
u
s
ed
to
im
p
le
m
e
n
t
SVM,
DT
,
an
d
R
F
alg
o
r
ith
m
s
.
L
o
ad
in
g
d
atasets
in
co
m
m
a
s
ep
ar
ated
v
alu
e
(
.
C
SV)
f
o
r
m
at
i
n
Go
o
g
le
C
o
l
ab
is
f
ac
il
itated
u
s
in
g
P
an
d
a
s
,
an
o
p
en
-
s
o
u
r
c
e
s
o
f
t
w
ar
e
lib
r
ar
y
u
s
ed
i
n
th
e
P
y
th
o
n
p
r
o
g
r
a
m
m
in
g
la
n
g
u
a
g
e
f
o
r
d
ata
m
an
ip
u
latio
n
an
d
an
al
y
s
i
s
.
T
h
is
lib
r
ar
y
p
r
o
v
id
es
d
ata
s
tr
u
ct
u
r
es
a
n
d
d
ata
an
al
y
s
is
to
o
ls
t
h
at
ar
e
ea
s
y
to
u
s
e,
e
s
p
ec
iall
y
i
n
t
h
e
f
o
r
m
o
f
Data
Fra
m
es.
P
an
d
as e
n
ab
le
u
s
er
s
to
clea
n
,
m
an
ip
u
lat
e,
a
n
d
an
al
y
ze
d
ata
m
o
r
e
e
f
f
icie
n
tl
y
.
2
.
6
.
T
ra
ini
ng
a
nd
t
esting
da
t
a
s
et
Fig
u
r
e
2
s
h
o
w
s
th
e
tr
ai
n
in
g
a
n
d
test
in
g
d
ataset
u
s
i
n
g
a
M
L
m
o
d
el.
I
n
Go
o
g
le
C
o
lab
,
th
e
r
eq
u
ir
ed
lib
r
ar
ies
ar
e
i
m
p
o
r
ted
f
ir
s
t
(
p
an
d
as,
s
k
lear
n
,
SVM
m
o
d
el,
RF
,
DT
,
an
d
also
th
e
n
ec
es
s
a
r
y
m
etr
ics).
U
s
i
n
g
th
e
C
SV
f
o
r
m
at,
t
h
e
d
ataset
is
u
p
lo
ad
ed
in
to
Go
o
g
le
C
o
lab
u
s
i
n
g
P
y
th
o
n
.
I
n
t
h
is
ca
s
e,
th
e
d
ataset
w
as
p
r
ep
ar
ed
u
s
i
n
g
s
ep
ar
ated
lab
els
an
d
f
ea
tu
r
es
r
ea
d
y
f
o
r
p
an
d
as
u
s
in
g
“
&
(
ce
ll)&
”
i
n
E
x
ce
l
i
n
C
S
V
f
o
r
m
at.
T
h
is
d
ataset
co
n
tain
s
atten
d
a
n
ce
d
ata
o
f
SMK
teac
h
er
s
f
o
r
th
e
la
s
t
3
m
o
n
th
s
o
b
tain
ed
th
r
o
u
g
h
a
f
ac
e
r
ec
o
g
n
itio
n
-
b
ased
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
Dec
is
io
n
s
u
p
p
o
r
t sys
tem
in
ma
ch
in
e
lea
r
n
in
g
m
o
d
els fo
r
a
fa
ce
r
ec
o
g
n
itio
n
-
b
a
s
ed
…
(
Jo
s
ep
h
Teg
u
h
S
a
n
to
s
o
)
375
atten
d
an
ce
s
y
s
te
m
.
B
esid
es
la
b
els,
th
e
d
ataset
also
in
cl
u
d
es
s
ev
er
al
f
ea
tu
r
es
s
u
c
h
as
f
r
eq
u
en
c
y
o
f
atte
n
d
an
ce
,
late
ar
r
iv
al
d
ate,
n
u
m
b
er
o
f
w
o
r
k
i
n
g
d
a
y
s
,
an
d
o
th
er
s
.
Fo
r
s
ep
ar
atin
g
f
ea
t
u
r
es
an
d
lab
els
in
th
e
u
p
lo
ad
ed
d
ataset,
th
e
co
m
m
a
n
d
‘
d
ata
’
b
ec
o
m
e
s
#
Feat
u
r
es
an
d
#
L
ab
el
s
,
X=
d
ata.
d
r
o
p
(
‘
P
er
f
o
r
m
a
n
ce
’
,
ax
is
=1
)
#
Featu
r
es
an
d
y
=d
ata[
‘
P
er
f
o
r
m
a
n
ce
’
]
#
L
ab
els,
w
h
er
e
‘
P
er
f
o
r
m
a
n
ce
’
i
s
th
e
lab
el
in
t
h
e
tab
le
w
it
h
a
v
alu
e
o
f
1
f
o
r
h
ig
h
-
p
er
f
o
r
m
in
g
SMK
teac
h
er
s
a
n
d
0
f
o
r
th
o
s
e
n
ee
d
in
g
s
u
p
p
o
r
t.
R
eg
ar
d
in
g
th
e
d
i
v
is
io
n
o
f
d
ata
f
o
r
tr
ain
i
n
g
a
n
d
test
i
n
g
,
t
h
is
r
esear
c
h
f
o
llo
w
s
t
h
e
P
ar
eto
p
r
in
cip
le
(
8
0
/2
0
r
u
le)
[
3
8
]
.
Fig
u
r
e
2
.
T
r
ain
in
g
,
test
i
n
g
,
an
d
p
r
ed
ictio
n
p
r
o
ce
s
s
o
f
th
e
d
e
v
elo
p
ed
ML
m
o
d
el
in
t
h
e
r
ese
ar
ch
I
n
m
o
d
el
tr
ain
in
g
,
SVM,
DT
,
an
d
R
F
m
o
d
els
ar
e
in
itialized
an
d
th
en
tr
ai
n
ed
u
s
i
n
g
t
h
e
tr
ain
in
g
d
ata.
Du
r
in
g
m
o
d
el
p
r
ed
ictio
n
,
th
e
t
esti
n
g
d
ata
is
u
s
ed
.
I
f
n
o
er
r
o
r
m
e
s
s
a
g
e
ap
p
ea
r
s
,
th
e
m
o
d
el
ev
alu
a
tio
n
s
tep
ca
n
p
r
o
ce
ed
.
Ho
w
e
v
er
,
if
an
er
r
o
r
m
ess
a
g
e
ap
p
ea
r
s
in
th
e
p
r
o
m
p
t,
th
e
s
ize
an
d
co
n
ten
t
o
f
th
e
ar
r
ay
ar
e
ch
ec
k
ed
u
s
i
n
g
th
e
‘
s
h
ap
e
’
attr
ib
u
te.
I
f
th
er
e
is
a
n
i
m
b
alan
ce
in
t
h
e
d
ata
at
th
e
i
n
d
ices
th
at
ap
p
ea
r
,
th
e
s
ize
is
ad
j
u
s
ted
to
b
alan
ce
it.
Fu
r
th
er
in
m
o
d
el
ev
alu
atio
n
,
ea
ch
m
o
d
el
is
ev
alu
a
ted
u
s
i
n
g
p
r
ed
ef
i
n
ed
m
etr
ics
to
d
eter
m
i
n
e
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
an
d
th
e
F1
-
s
co
r
e
v
al
u
e
o
f
ea
ch
m
o
d
el.
I
f
n
o
f
u
r
th
er
is
s
u
e
s
ar
is
e,
th
e
ev
al
u
atio
n
r
esu
lt
s
ar
e
d
is
p
la
y
ed
.
T
h
e
Valu
eE
r
r
o
r
th
at
o
cc
u
r
s
d
u
r
i
n
g
m
o
d
el
p
r
ed
ictio
n
in
d
icate
s
a
m
i
s
m
atc
h
in
t
h
e
n
u
m
b
er
o
f
s
a
m
p
les
in
th
e
in
p
u
t
v
ar
i
ab
les
p
r
o
v
id
ed
to
th
e
“
ac
c
u
r
ac
y
_
s
co
r
e(
)
”
f
u
n
ctio
n
.
W
h
e
n
u
s
in
g
t
h
e
f
u
n
ct
io
n
ac
cu
r
ac
y
_
s
co
r
e(
y
_
test
,
s
v
m
_
p
r
ed
)
,
b
o
th
ar
g
u
m
e
n
ts
y
_
te
s
t
an
d
s
v
m
_
p
r
ed
f
o
r
th
e
SVM
m
o
d
el
b
ein
g
u
s
ed
m
u
s
t
h
av
e
t
h
e
s
a
m
e
n
u
m
b
er
o
f
s
a
m
p
les.
I
n
th
i
s
n
o
r
m
aliza
tio
n
test
,
s
ev
er
al
an
al
y
s
es
ar
e
co
n
d
u
cted
in
cl
u
d
in
g
d
escr
ip
tiv
e
an
a
l
y
s
is
,
o
u
tlier
te
s
ts
,
a
n
d
n
o
n
-
p
ar
a
m
etr
ic
an
a
l
y
s
is
u
n
ti
l
t
h
e
d
ata
is
n
o
r
m
all
y
d
i
s
tr
ib
u
ted
a
n
d
r
ea
d
y
f
o
r
tr
ain
in
g
,
test
in
g
,
a
n
d
p
r
ed
ictin
g
r
esu
lt
s
as
n
ee
d
ed
.
A
d
d
it
io
n
all
y
,
S
h
ap
ir
o
-
W
il
k
an
d
Ko
l
m
o
g
o
r
o
v
-
S
m
ir
n
o
v
test
s
ar
e
co
n
d
u
cted
to
ass
e
s
s
t
h
e
n
o
r
m
a
lit
y
o
f
th
e
d
ata
d
is
tr
i
b
u
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
3
7
1
-
381
376
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
M
a
chine le
a
rning
m
o
de
l
T
ab
le
1
s
h
o
w
s
th
e
r
es
u
lts
o
f
ev
a
lu
ati
n
g
3
M
L
m
o
d
els
in
th
i
s
s
tu
d
y
,
s
h
o
w
i
n
g
an
in
ter
esti
n
g
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
in
p
r
ed
ictin
g
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
SMK
teac
h
er
s
w
h
o
ex
ce
l
a
n
d
th
o
s
e
w
h
o
n
ee
d
d
ev
elo
p
m
en
t.
A
cc
o
r
d
in
g
to
t
h
e
f
i
n
d
i
n
g
s
p
r
esen
ted
i
n
T
ab
le
1
,
th
e
SVM
m
o
d
el
ac
h
iev
ed
h
ig
h
ac
cu
r
ac
y
,
r
ea
ch
in
g
9
7
.
2
%,
an
d
p
er
f
ec
t
p
r
ec
is
io
n
o
f
1
0
0
%.
T
h
is
in
d
i
ca
tes
th
at
t
h
e
m
o
d
el
co
r
r
ec
tly
cla
s
s
i
f
ie
s
teac
h
er
s
ap
p
r
o
x
im
a
tel
y
9
7
.
2
%
o
f
th
e
tim
e
an
d
id
en
ti
f
ies
all
teac
h
er
s
w
h
o
ar
e
ex
ce
llin
g
o
r
in
n
ee
d
o
f
d
ev
elo
p
m
e
n
t.
T
h
e
r
ec
all
s
co
r
e
o
f
th
e
SV
M
m
o
d
el
is
9
5
.
7
%,
s
lig
h
tl
y
b
elo
w
t
h
at
o
f
R
F
a
n
d
DT
.
Me
an
w
h
il
e,
th
e
F1
s
co
r
e
f
o
r
SVM
is
th
e
lo
w
e
s
t
at
9
7
.
8
%.
On
th
e
o
th
er
h
an
d
,
th
e
DT
m
o
d
el
ac
h
iev
ed
th
e
s
a
m
e
ac
cu
r
ac
y
le
v
el
as
th
e
RF
,
at
9
8
.
3
%,
w
it
h
p
r
ec
is
io
n
an
d
r
ec
all
r
ea
ch
in
g
1
0
0
%
an
d
9
6
.
4
%,
r
esp
ec
tiv
el
y
.
A
l
th
o
u
g
h
its
p
r
ec
is
io
n
an
d
r
ec
all
ar
e
s
lig
h
tl
y
lo
w
er
t
h
a
n
RF
,
t
h
e
DT
F1
s
co
r
e
is
9
7
.
7
%,
in
d
icat
in
g
g
o
o
d
o
v
er
all
p
er
f
o
r
m
a
n
ce
.
T
ab
le
1
.
T
h
e
r
esu
lts
o
f
t
h
e
m
e
t
r
ic
m
ea
s
u
r
e
m
e
n
ts
o
n
th
e
t
h
r
ee
m
ac
h
in
e
-
lear
n
in
g
m
o
d
el
s
u
s
ed
ML
m
o
d
e
l
M
e
a
su
r
e
me
n
t
m
e
t
r
i
c
s
A
c
c
u
r
a
c
y
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
V
M
0
.
9
7
2
1
.
0
0
.
9
5
7
0
.
9
7
8
RF
0
.
9
8
3
1
.
0
0
.
9
7
4
0
.
9
8
7
DT
0
.
9
8
3
1
.
0
0
.
9
6
4
0
.
9
7
7
Fig
u
r
e
3
s
h
o
w
s
th
e
h
ea
t
m
ap
d
iag
r
a
m
r
eg
ar
d
in
g
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
o
f
t
h
e
m
o
d
els.
I
n
th
e
R
F
m
o
d
el,
d
esp
ite
h
a
v
i
n
g
eq
u
all
y
h
ig
h
ac
c
u
r
ac
y
a
s
SVM
at
9
8
.
3
%,
th
is
m
o
d
el
s
h
o
w
s
s
lig
h
tl
y
lo
w
er
p
r
ec
is
io
n
an
d
r
ec
all
co
m
p
ar
ed
to
SVM,
w
it
h
p
r
ec
is
io
n
an
d
r
ec
all
r
ea
ch
in
g
1
0
0
%
an
d
9
7
.
4
%
r
esp
ec
tiv
el
y
.
A
d
d
itio
n
all
y
,
th
e
F1
s
co
r
e
f
o
r
th
e
R
F
m
o
d
el
r
ea
ch
es
9
8
.
7
%,
in
d
icatin
g
v
er
y
g
o
o
d
o
v
er
all
p
er
f
o
r
m
a
n
ce
.
T
h
er
ef
o
r
e,
alth
o
u
g
h
all
th
r
ee
m
o
d
els
h
a
v
e
h
ig
h
ac
cu
r
ac
y
,
R
F
s
ta
n
d
s
o
u
t
w
it
h
h
i
g
h
er
p
r
ec
is
io
n
a
n
d
F1
s
co
r
e,
i
n
d
icatin
g
t
h
at
R
F
i
s
th
e
m
o
s
t e
f
f
ec
ti
v
e
m
o
d
el
i
n
id
en
ti
f
y
in
g
h
ig
h
-
p
er
f
o
r
m
i
n
g
e
m
p
lo
y
ee
s
b
ased
o
n
atten
d
an
ce
d
ata
.
Fig
u
r
e
3
.
Hea
t
m
ap
d
iag
r
a
m
r
e
g
ar
d
in
g
th
e
p
er
f
o
r
m
a
n
ce
m
etr
i
cs o
f
th
e
M
L
m
o
d
els
u
s
ed
f
o
r
p
r
ed
ictin
g
h
ig
h
-
p
er
f
o
r
m
in
g
teac
h
er
s
3.
2
.
Sens
it
iv
it
y
a
na
l
y
s
is
o
f
t
he
decisi
o
n
s
up
po
rt
s
y
s
t
e
m
c
o
ncept
Fig
u
r
e
4
s
h
o
w
s
t
h
e
s
en
s
iti
v
it
y
an
al
y
s
i
s
r
esu
lt
s
o
f
th
is
s
t
u
d
y
.
S
en
s
iti
v
it
y
a
n
al
y
s
i
s
o
f
th
e
DSS
th
eo
r
y
w
a
s
co
n
d
u
cted
u
s
i
n
g
k
e
y
p
ar
a
m
eter
s
o
n
t
h
r
ee
ML
m
o
d
els:
SVM,
R
F,
an
d
DT
.
Fig
u
r
e
5
s
h
o
w
s
t
h
e
s
en
s
iti
v
it
y
an
al
y
s
is
f
o
r
ea
ch
m
o
d
el
.
Fo
r
th
e
SVM
m
o
d
el,
v
ar
iatio
n
s
w
e
r
e
p
er
f
o
r
m
ed
o
n
t
h
e
p
ar
a
m
ete
r
C
,
w
h
ic
h
co
n
tr
o
ls
th
e
d
ec
is
io
n
b
o
u
n
d
ar
y
h
ar
d
n
e
s
s
.
T
h
e
r
esu
lts
s
h
o
w
t
h
at
SV
M
ac
cu
r
ac
y
te
n
d
s
to
r
e
m
ain
s
tab
le
an
d
q
u
ite
h
i
g
h
ac
r
o
s
s
m
o
s
t
test
ed
v
al
u
es
o
f
C
,
w
ith
s
l
ig
h
t
d
ec
r
ea
s
es
at
s
m
al
ler
C
v
alu
es.
T
h
is
s
u
g
g
est
s
th
a
t
SVM
m
a
y
n
o
t
b
e
o
v
er
l
y
s
en
s
iti
v
e
to
t
h
e
C
p
ar
am
eter
i
n
t
h
is
ca
s
e.
I
n
co
n
tr
ast
,
f
o
r
RF
,
v
ar
iatio
n
s
w
er
e
d
o
n
e
o
n
t
h
e
n
u
m
b
er
o
f
tr
ee
s
(
n
_
esti
m
ato
r
s
)
.
I
t
w
a
s
f
o
u
n
d
th
a
t
R
F
ac
cu
r
ac
y
ten
d
s
to
in
cr
ea
s
e
w
ith
h
ig
h
er
n
u
m
b
er
s
o
f
tr
ee
s
,
in
d
icatin
g
th
at
a
n
e
n
s
e
m
b
le
o
f
m
a
n
y
tr
ee
s
g
e
n
er
all
y
p
r
o
v
id
es
b
ett
er
p
er
f
o
r
m
a
n
ce
,
m
ak
in
g
R
F
ad
v
an
ta
g
eo
u
s
f
o
r
class
i
f
icatio
n
p
r
o
b
lem
s
.
Me
a
n
w
h
ile,
f
o
r
th
e
DT
,
v
ar
iatio
n
s
w
er
e
co
n
d
u
cted
o
n
th
e
tr
ee
d
ep
th
.
T
h
e
r
esu
lts
in
d
icate
th
at
DT
ac
cu
r
ac
y
ten
d
s
to
in
cr
ea
s
e
w
it
h
d
ee
p
er
tr
e
es
u
p
to
a
ce
r
tain
p
o
in
t,
b
u
t
b
ey
o
n
d
th
at
p
o
in
t,
ac
cu
r
ac
y
s
tar
t
s
to
d
ec
r
ea
s
e,
s
u
g
g
e
s
ti
n
g
o
v
er
f
itt
in
g
.
T
h
er
ef
o
r
e,
th
e
tr
ad
e
-
o
f
f
b
et
w
ee
n
i
n
cr
ea
s
in
g
ac
cu
r
ac
y
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
Dec
is
io
n
s
u
p
p
o
r
t sys
tem
in
ma
ch
in
e
lea
r
n
in
g
m
o
d
els fo
r
a
fa
ce
r
ec
o
g
n
itio
n
-
b
a
s
ed
…
(
Jo
s
ep
h
Teg
u
h
S
a
n
to
s
o
)
377
th
e
r
is
k
o
f
o
v
er
f
itt
in
g
w
h
e
n
d
eter
m
i
n
in
g
tr
ee
d
ep
t
h
n
ee
d
s
t
o
b
e
ca
r
ef
u
ll
y
co
n
s
id
er
ed
.
Ov
er
all,
th
ese
f
in
d
i
n
g
s
h
ig
h
li
g
h
t
th
e
s
e
n
s
it
iv
it
y
o
f
ea
ch
m
o
d
el
to
its
r
esp
ec
tiv
e
p
ar
am
eter
s
an
d
e
m
p
h
a
s
ize
th
e
i
m
p
o
r
tan
ce
o
f
p
ar
am
eter
t
u
n
in
g
f
o
r
o
p
tim
iz
i
n
g
m
o
d
el
p
er
f
o
r
m
an
ce
i
n
p
r
ac
tical
ap
p
licatio
n
s
.
Fig
u
r
e
4
.
T
h
e
r
esu
lt o
f
s
e
n
s
iti
v
it
y
an
a
l
y
s
is
f
o
r
ML
m
o
d
el
u
s
e
d
f
o
r
h
ig
h
-
p
er
f
o
r
m
i
n
g
p
r
ed
icti
o
n
s
u
s
i
n
g
D
SS
th
eo
r
y
Fig
u
r
e
5
.
T
h
e
r
esu
lt o
f
s
e
n
s
iti
v
it
y
an
a
l
y
s
is
f
o
r
ea
ch
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
3
7
1
-
381
378
T
h
e
s
en
s
i
tiv
it
y
a
n
al
y
s
is
f
u
r
th
er
in
d
icate
s
t
h
at
t
h
e
SVM
m
o
d
el
d
em
o
n
s
tr
ates
th
e
m
o
s
t
co
n
s
is
ten
t
p
er
f
o
r
m
a
n
ce
,
e
x
h
ib
itin
g
a
n
in
cr
ea
s
e
i
n
ac
c
u
r
ac
y
w
i
th
a
d
j
u
s
t
m
e
n
ts
to
t
h
e
C
p
ar
a
m
e
ter
.
T
h
is
in
cr
ea
s
e
u
n
d
er
s
co
r
es
t
h
e
m
o
d
el
’
s
r
o
b
u
s
t
n
es
s
,
p
ar
ticu
lar
l
y
in
h
i
g
h
-
s
ta
k
es
p
r
ed
ictio
n
s
w
h
er
e
p
r
ec
is
io
n
i
s
cr
itical
.
C
o
n
v
er
s
el
y
,
t
h
e
DT
m
o
d
el
r
ev
ea
ls
th
a
t
its
ac
cu
r
ac
y
is
o
p
ti
m
al
at
ce
r
tain
d
ep
th
s
,
n
ec
ess
itati
n
g
ca
r
ef
u
l
p
ar
am
eter
tu
n
i
n
g
to
av
o
id
o
v
er
f
it
tin
g
.
T
h
e
R
F
m
o
d
el,
ch
ar
ac
ter
ized
b
y
its
en
s
e
m
b
le
ap
p
r
o
ac
h
,
s
h
o
w
s
i
m
p
r
o
v
ed
ac
cu
r
ac
y
w
i
th
a
n
i
n
cr
ea
s
ed
n
u
m
b
er
o
f
tr
ee
s
,
r
ei
n
f
o
r
ci
n
g
th
e
n
o
tio
n
t
h
at
e
n
s
e
m
b
le
m
et
h
o
d
s
ca
n
en
h
a
n
ce
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
.
T
h
ese
in
s
i
g
h
ts
co
llectiv
e
l
y
em
p
h
asize
th
e
n
ec
e
s
s
it
y
o
f
u
n
d
er
s
tan
d
i
n
g
m
o
d
e
l
s
en
s
iti
v
itie
s
in
th
e
co
n
tex
t
o
f
DSS
th
eo
r
y
,
h
i
g
h
lig
h
ti
n
g
th
e
s
ig
n
i
f
ica
n
ce
o
f
s
tr
ateg
ic
p
ar
am
eter
ad
j
u
s
t
m
e
n
ts
to
o
p
tim
ize
ML
o
u
tco
m
e
s
in
p
r
a
ctica
l a
p
p
licatio
n
s
.
3.
3
.
No
rm
a
lity
t
est
I
n
th
e
p
r
ev
io
u
s
l
y
u
s
ed
d
ataset
co
n
s
is
ti
n
g
o
f
998
d
ata
p
o
in
ts
,
it
w
as
f
o
u
n
d
th
at
th
e
d
ata
w
as
n
o
t
n
o
r
m
all
y
d
i
s
tr
ib
u
ted
,
p
r
o
m
p
ti
n
g
f
u
r
t
h
er
an
al
y
s
i
s
.
I
n
th
is
s
t
u
d
y
,
d
ata
n
o
r
m
aliza
tio
n
w
a
s
co
n
d
u
cted
u
s
i
n
g
an
o
u
tlier
f
u
n
ctio
n
to
r
em
o
v
e
u
n
n
ec
e
s
s
ar
y
d
ata
p
o
in
ts
.
Su
b
s
eq
u
en
tl
y
,
test
s
a
n
d
an
al
y
s
es
w
er
e
p
er
f
o
r
m
ed
to
en
s
u
r
e
th
e
s
u
cc
e
s
s
o
f
n
o
r
m
aliz
atio
n
an
d
to
v
er
i
f
y
i
f
t
h
e
d
ata
m
et
t
h
e
ass
u
m
p
tio
n
s
r
eq
u
ir
ed
f
o
r
f
u
r
t
h
er
an
al
y
s
is
.
I
n
th
i
s
ca
s
e,
t
h
e
d
ataset
i
n
itia
ll
y
co
n
ta
in
i
n
g
998
d
ata
p
o
in
t
s
w
as
r
ed
u
ce
d
to
8
7
6
d
ata
p
o
in
ts
r
ea
d
y
f
o
r
u
s
e
.
Descr
ip
tiv
e
a
n
al
y
s
i
s
w
as
t
h
e
n
ca
r
r
ied
o
u
t
to
u
n
d
er
s
tan
d
t
h
e
ch
ar
ac
ter
is
tic
s
o
f
t
h
e
n
o
r
m
a
lize
d
d
ata
d
is
tr
ib
u
tio
n
p
o
s
t
-
o
u
tlier
r
e
m
o
v
a
l.
T
a
b
le
2
s
h
o
w
s
t
h
e
Sh
ap
ir
o
-
W
il
k
an
d
Ko
l
m
o
g
o
r
o
v
-
S
m
ir
n
o
v
p
-
v
al
u
e
test
s
o
n
th
e
m
o
d
els
u
s
ed
.
T
h
e
n
o
r
m
a
lit
y
o
f
th
e
r
esid
u
al
d
is
tr
ib
u
tio
n
w
as
a
s
s
ess
ed
t
h
r
o
u
g
h
r
e
g
r
ess
io
n
a
n
a
l
y
s
i
s
to
f
u
lf
ill
t
h
e
ass
u
m
p
tio
n
s
r
eq
u
ir
ed
b
y
th
e
m
et
h
o
d
u
s
ed
.
Nex
t,
S
h
ap
ir
o
-
W
ilk
an
d
Ko
l
m
o
g
o
r
o
v
-
S
m
ir
n
o
v
test
s
w
er
e
co
n
d
u
cted
o
n
th
e
ev
al
u
atio
n
d
ata
f
r
o
m
ea
c
h
m
o
d
el.
T
h
e
S
h
ap
ir
o
-
W
ilk
test
r
esu
lts
s
h
o
w
ed
th
at
t
h
e
p
-
v
a
lu
e
s
f
o
r
all
th
r
ee
m
o
d
els
(
SVM,
RF
,
an
d
DT
)
w
er
e
w
ell
ab
o
v
e
th
e
s
ig
n
i
f
ica
n
ce
lev
el
o
f
0
.
0
5
,
in
d
icati
n
g
t
h
at
th
e
ev
alu
a
tio
n
d
ata
f
r
o
m
a
ll th
r
ee
m
o
d
el
s
ten
d
ed
to
f
o
llo
w
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
.
T
ab
le
2
.
Sh
ap
ir
o
-
W
ilk
an
d
Ko
l
m
o
g
o
r
o
v
-
S
m
ir
n
o
v
p
-
v
al
u
e
tes
ts
o
n
th
e
m
o
d
els u
s
ed
f
o
r
p
r
ed
ict
io
n
w
it
h
th
e
in
te
g
r
atio
n
o
f
D
SS
t
h
eo
r
y
No
M
o
d
e
l
S
h
a
p
i
r
o
-
W
i
l
k
p
-
v
a
l
u
e
K
o
l
mo
g
o
r
o
v
-
S
mi
r
n
o
v
p
-
v
a
l
u
e
1
S
V
M
0
.
8
9
0
9
0
3
0
.
0
0
1
6
3
3
2
RF
0
.
8
9
9
3
7
3
0
.
0
0
1
4
7
6
3
DT
0
.
8
9
9
3
7
3
0
.
0
0
1
4
7
6
On
th
e
o
t
h
er
h
an
d
,
th
e
Ko
l
m
o
g
o
r
o
v
-
S
m
ir
n
o
v
test
i
n
d
ica
ted
th
at
th
e
p
-
v
al
u
es
w
er
e
s
i
g
n
i
f
ica
n
tl
y
b
elo
w
t
h
e
0
.
0
5
s
ig
n
i
f
ica
n
ce
lev
el,
s
u
g
g
e
s
ti
n
g
th
at
th
e
ev
alu
a
tio
n
d
ata
f
r
o
m
all
t
h
r
ee
m
o
d
els
d
id
n
o
t
s
ig
n
i
f
ica
n
tl
y
d
i
f
f
er
f
r
o
m
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
.
T
h
er
ef
o
r
e,
it
ca
n
b
e
co
n
clu
d
ed
th
at
th
e
ev
alu
atio
n
r
esu
lt
s
in
d
icate
v
er
y
g
o
o
d
p
er
f
o
r
m
an
ce
f
r
o
m
a
ll t
h
r
ee
clas
s
i
f
icatio
n
m
o
d
els,
w
h
ile
t
h
e
e
v
al
u
atio
n
d
ata
ten
d
s
to
f
o
llo
w
a
n
o
r
m
al
d
i
s
tr
ib
u
tio
n
b
ased
o
n
t
h
e
S
h
ap
ir
o
-
W
ilk
test
,
d
esp
ite
m
i
n
o
r
d
if
f
er
en
ce
s
in
d
icate
d
b
y
th
e
Ko
l
m
o
g
o
r
o
v
-
S
m
ir
n
o
v
test
.
T
h
is
p
r
o
v
id
es
ad
d
itio
n
al
co
n
f
id
e
n
ce
in
i
n
ter
p
r
etin
g
th
e
e
v
alu
at
io
n
r
esu
lt
s
an
d
th
e
r
eliab
ilit
y
o
f
t
h
e
co
n
cl
u
s
io
n
s
d
r
a
w
n
f
r
o
m
t
h
e
m
o
d
el
p
er
f
o
r
m
an
ce
an
al
y
s
is
.
3.
4
.
Rec
o
m
m
e
nd
a
t
io
n
Fro
m
t
h
e
r
esear
c
h
f
i
n
d
in
g
s
,
SVM
s
h
o
w
ed
a
n
ac
c
u
r
ac
y
o
f
9
7
.
2
%,
w
it
h
a
m
a
x
i
m
u
m
p
r
ec
is
io
n
o
f
1
0
0
%,
id
en
tical
to
th
e
o
th
er
t
w
o
m
o
d
els,
a
n
d
a
r
ec
all
v
al
u
e
o
f
9
5
.
7
%.
Ho
w
e
v
er
,
its
F1
s
c
o
r
e
w
a
s
q
u
ite
h
i
g
h
,
r
ea
ch
in
g
9
7
.
8
%.
On
th
e
o
th
er
h
an
d
,
DT
ac
h
iev
ed
an
ac
cu
r
a
c
y
o
f
9
8
.
3
%
w
it
h
a
r
ec
all
s
co
r
e
o
f
9
6
.
4
%
an
d
an
F1
-
s
co
r
e
o
f
9
7
.
7
%.
I
n
t
h
i
s
co
n
tex
t
,
R
F
ex
h
ib
ited
t
h
e
h
i
g
h
e
s
t
ac
cu
r
ac
y
co
m
p
ar
ed
to
t
h
e
o
th
er
t
w
o
m
o
d
el
s
,
at
9
8
.
3
%,
w
ith
a
r
ec
all
o
f
9
7
.
4
%.
T
h
is
i
n
d
icate
s
t
h
at
t
h
e
R
F
m
o
d
el
ca
n
p
r
o
v
id
e
v
er
y
g
o
o
d
p
r
e
d
ictio
n
s
i
n
id
en
ti
f
y
i
n
g
SMK
teac
h
er
s
wh
o
ex
ce
l
an
d
t
h
o
s
e
w
h
o
n
ee
d
ad
d
itio
n
al
g
u
id
an
ce
.
W
h
i
le
SVM
an
d
DT
also
p
er
f
o
r
m
ed
w
e
ll,
R
F
s
tr
i
k
es
a
n
o
p
tim
a
l
b
alan
ce
b
et
w
ee
n
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all.
T
h
er
ef
o
r
e,
it
is
h
i
g
h
l
y
r
ec
o
m
m
e
n
d
ed
to
u
s
e
a
R
F
as
th
e
m
o
s
t
s
u
itab
le
m
o
d
el
f
o
r
th
is
p
r
ed
ictio
n
tas
k
.
Mo
r
eo
v
er
,
t
h
is
m
o
d
el
ca
n
also
b
e
em
p
lo
y
ed
i
n
ca
s
es
w
h
er
e
m
ax
i
m
izin
g
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
is
cr
u
c
ial,
w
h
ile
a
DT
m
a
y
b
e
co
n
s
id
er
ed
if
co
m
p
u
tatio
n
al
s
p
ee
d
is
a
p
r
i
m
ar
y
f
ac
to
r
an
d
th
er
e
i
s
to
ler
an
c
e
f
o
r
s
lig
h
t d
ec
r
ea
s
es i
n
th
e
F1
s
co
r
e.
3.
5
.
Dis
cus
s
io
n
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
i
n
d
icate
th
a
t
th
e
R
F
m
o
d
el
o
u
tp
er
f
o
r
m
s
o
t
h
er
s
i
n
p
r
ed
ictin
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
h
i
g
h
-
p
er
f
o
r
m
i
n
g
v
o
ca
tio
n
al
s
c
h
o
o
l
(
SMK)
teac
h
er
s
an
d
th
o
s
e
w
h
o
r
eq
u
ir
e
f
u
r
t
h
er
d
ev
elo
p
m
en
t.
T
h
e
h
ig
h
e
s
t
ac
c
u
r
ac
y
ac
h
ie
v
ed
b
y
t
h
is
m
o
d
el
w
a
s
9
8
.
3
%,
w
it
h
n
ea
r
-
p
er
f
ec
t
p
r
ec
is
io
n
an
d
r
ec
all
v
alu
e
s
o
f
1
0
0
%
an
d
9
7
.
4
%,
r
esp
ec
tiv
el
y
.
T
h
is
p
o
s
itio
n
s
R
F
as
th
e
m
o
s
t
e
f
f
ec
ti
v
e
p
r
ed
ictiv
e
m
o
d
el
co
m
p
ar
ed
to
th
e
SVM
a
n
d
DT
m
o
d
els.
Sev
er
al
p
r
e
v
io
u
s
s
t
u
d
ies
h
a
v
e
h
i
g
h
lig
h
ted
t
h
e
ad
v
an
ta
g
es
o
f
R
F
i
n
h
an
d
li
n
g
lar
g
e
d
atasets
a
n
d
d
ec
is
io
n
-
m
ak
in
g
ta
s
k
s
.
Fo
r
in
s
tan
ce
,
K
h
i
av
i
[
2
6
]
u
s
ed
R
F
to
p
r
ed
ict
b
ase
f
lo
w
g
en
er
atio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
Dec
is
io
n
s
u
p
p
o
r
t sys
tem
in
ma
ch
in
e
lea
r
n
in
g
m
o
d
els fo
r
a
fa
ce
r
ec
o
g
n
itio
n
-
b
a
s
ed
…
(
Jo
s
ep
h
Teg
u
h
S
a
n
to
s
o
)
379
p
o
ten
tial
in
f
lo
o
d
ed
ar
ea
s
an
d
f
o
u
n
d
th
at
R
F
o
u
tp
er
f
o
r
m
ed
o
th
er
m
et
h
o
d
s
s
u
c
h
as
li
n
ea
r
r
eg
r
ess
io
n
an
d
DT
m
o
d
el
s
i
n
ter
m
s
o
f
ac
c
u
r
ac
y
.
T
h
is
ali
g
n
s
w
it
h
o
u
r
f
i
n
d
i
n
g
s
,
w
h
er
e
R
F
d
e
m
o
n
s
tr
ated
s
u
p
er
io
r
r
eliab
ilit
y
in
h
an
d
li
n
g
co
m
p
lex
d
ata
lik
e
f
ac
e
r
ec
o
g
n
itio
n
-
b
ased
atten
d
a
n
ce
d
ata.
A
d
d
itio
n
all
y
,
a
s
t
u
d
y
b
y
[
1
0
]
,
w
h
ic
h
d
ev
elo
p
ed
a
f
ac
e
r
ec
o
g
n
itio
n
alg
o
r
ith
m
f
o
r
f
r
au
d
d
etec
tio
n
s
y
s
te
m
s
,
r
ev
ea
led
t
h
at
i
n
teg
r
atin
g
M
L
w
it
h
R
F
p
r
o
v
id
ed
m
o
r
e
ac
cu
r
ate
an
d
r
e
liab
le
r
esu
lts
co
m
p
a
r
ed
to
o
th
er
s
tan
d
alo
n
e
m
o
d
els.
T
h
ese
f
in
d
in
g
s
s
u
p
p
o
r
t
o
u
r
r
esu
lt
s
,
w
h
er
e
R
F
ef
f
ec
ti
v
el
y
h
an
d
led
v
ar
iat
io
n
s
i
n
atte
n
d
an
ce
d
ata
an
d
p
r
o
d
u
ce
d
m
o
r
e
s
ta
b
le
p
r
ed
ictio
n
s
.
W
h
ile
t
h
e
SVM
m
o
d
el
s
h
o
wed
clo
s
e
ac
cu
r
ac
y
to
R
F
at
9
7
.
2
%,
it
ap
p
ea
r
ed
less
s
en
s
iti
v
e
to
d
at
a
v
ar
iatio
n
s
,
p
ar
ticu
lar
l
y
w
i
th
a
s
lig
h
tl
y
lo
w
er
r
ec
all
o
f
9
5
.
7
%.
T
h
is
is
co
n
s
is
ten
t
w
i
th
t
h
e
f
i
n
d
in
g
s
o
f
[
8
]
,
w
h
o
f
o
u
n
d
th
a
t
SV
M
w
as
les
s
e
f
f
i
cien
t
i
n
h
a
n
d
lin
g
co
m
p
le
x
o
r
n
o
n
li
n
ea
r
f
ea
t
u
r
es
s
u
c
h
as
att
en
d
an
ce
d
ata.
T
h
eir
s
tu
d
y
h
ig
h
li
g
h
ted
th
at
al
th
o
u
g
h
S
VM
p
er
f
o
r
m
s
w
el
l
i
n
b
i
n
a
r
y
clas
s
i
f
icatio
n
tas
k
s
,
th
e
m
o
d
el
r
eq
u
ir
es
p
r
ec
is
e
p
ar
am
eter
ad
j
u
s
t
m
e
n
ts
to
f
u
n
ct
io
n
o
p
ti
m
al
l
y
,
esp
ec
ial
l
y
w
it
h
h
eter
o
g
e
n
eo
u
s
d
atas
ets.
T
h
e
DT
also
d
em
o
n
s
tr
ated
s
o
lid
p
er
f
o
r
m
a
n
ce
w
it
h
a
n
ac
c
u
r
ac
y
o
f
9
8
.
3
%,
b
u
t
t
h
is
m
o
d
el
is
m
o
r
e
p
r
o
n
e
to
o
v
er
f
itti
n
g
,
p
ar
ticu
lar
l
y
w
i
th
h
i
g
h
-
d
i
m
e
n
s
i
o
n
al
d
ata.
C
h
av
a
n
a
n
d
S
h
er
ek
ar
[
9
]
o
b
s
er
v
ed
s
i
m
ilar
i
s
s
u
es
in
t
h
eir
u
s
e
o
f
DT
f
o
r
f
ac
e
r
ec
o
g
n
itio
n
M
L
ta
s
k
s
,
w
h
er
e
th
e
m
o
d
el
p
er
f
o
r
m
an
c
e
d
eg
r
ad
ed
w
h
e
n
f
ac
ed
w
it
h
h
ig
h
l
y
v
ar
iab
le
d
ata.
I
n
o
u
r
s
tu
d
y
,
t
h
e
D
T
ac
h
iev
ed
th
e
s
a
m
e
p
r
ec
is
io
n
as
th
e
RF
,
b
u
t
w
i
th
a
s
li
g
h
tl
y
lo
wer
r
ec
all
o
f
9
6
.
4
%,
in
d
icati
n
g
t
h
at
t
h
e
m
o
d
el
w
as
less
e
f
f
ec
t
iv
e
at
id
e
n
ti
f
y
i
n
g
all
teac
h
er
s
r
eq
u
ir
in
g
d
ev
elo
p
m
e
n
t.
I
n
teg
r
ati
n
g
DS
S
t
h
eo
r
y
i
n
d
ev
elo
p
in
g
M
L
m
o
d
el
s
h
a
s
s
ig
n
i
f
ican
tl
y
e
n
h
an
ce
d
p
r
ed
ictio
n
ac
cu
r
ac
y
an
d
d
ec
is
io
n
-
m
a
k
in
g
ca
p
ab
ilit
ies.
DS
S h
e
lp
s
id
en
ti
f
y
th
e
m
o
s
t i
n
f
lu
e
n
tial
in
p
u
t p
ar
a
m
e
ter
s
,
allo
w
in
g
d
y
n
a
m
ic
m
o
d
el
ad
j
u
s
t
m
e
n
t
s
b
ased
o
n
i
n
p
u
t d
ata
v
ar
iatio
n
s
.
A
s
t
u
d
y
b
y
[
3
2
]
d
em
o
n
s
tr
ated
t
h
at
i
n
te
g
r
atin
g
DSS
in
w
eb
-
b
ased
s
y
s
te
m
s
i
m
p
r
o
v
ed
d
ec
is
io
n
-
m
a
k
i
n
g
ac
c
u
r
ac
y
b
y
o
f
f
er
i
n
g
b
etter
s
en
s
iti
v
it
y
a
n
al
y
s
i
s
t
o
ch
an
g
i
n
g
in
p
u
ts
.
Ou
r
r
esear
ch
co
r
r
o
b
o
r
ates
th
ese
f
i
n
d
in
g
s
,
s
h
o
w
i
n
g
t
h
at
D
SS
i
m
p
r
o
v
e
s
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
b
y
g
u
id
in
g
m
o
d
el
p
ar
a
m
e
ter
s
elec
tio
n
,
p
a
r
ticu
lar
l
y
f
o
r
cr
itical
v
ar
iab
les
s
u
c
h
as tea
c
h
er
atten
d
a
n
ce
an
d
laten
es
s
.
T
h
e
f
in
d
i
n
g
s
o
f
t
h
i
s
r
esear
ch
h
av
e
s
i
g
n
i
f
ica
n
t
i
m
p
licatio
n
s
f
o
r
s
ch
o
o
l
m
an
a
g
e
m
en
t,
p
ar
ticu
lar
l
y
i
n
i
m
p
r
o
v
i
n
g
teac
h
er
p
er
f
o
r
m
a
n
ce
in
v
o
ca
tio
n
al
s
c
h
o
o
ls
.
T
h
e
in
te
g
r
atio
n
o
f
f
ac
e
r
ec
o
g
n
itio
n
-
b
a
s
ed
atten
d
an
ce
s
y
s
te
m
s
w
i
th
M
L
m
o
d
els
a
n
d
DSS
ca
n
as
s
is
t
s
c
h
o
o
ls
i
n
id
e
n
ti
f
y
in
g
h
i
g
h
-
p
er
f
o
r
m
in
g
teac
h
er
s
a
n
d
p
r
o
v
id
in
g
r
ec
o
m
m
e
n
d
atio
n
s
f
o
r
f
u
r
t
h
er
d
ev
elo
p
m
en
t
f
o
r
th
o
s
e
n
ee
d
in
g
s
u
p
p
o
r
t.
T
h
is
alig
n
s
w
it
h
r
es
ea
r
ch
b
y
[
1
]
,
w
h
ic
h
id
en
ti
f
ied
th
at
u
s
i
n
g
f
ac
e
r
ec
o
g
n
itio
n
tech
n
o
lo
g
y
i
n
ed
u
ca
tio
n
ca
n
en
h
a
n
ce
h
u
m
a
n
r
es
o
u
r
ce
m
a
n
a
g
e
m
e
n
t
ef
f
icien
c
y
,
p
ar
ticu
lar
l
y
in
m
o
n
ito
r
in
g
a
n
d
ev
alu
a
tin
g
s
ta
f
f
p
er
f
o
r
m
an
ce
.
O
u
r
s
tu
d
y
e
m
p
h
asi
ze
s
th
e
i
m
p
o
r
tan
c
e
o
f
u
til
izin
g
e
x
is
t
in
g
atte
n
d
an
c
e
d
ata
f
o
r
m
o
r
e
s
tr
ateg
ic
d
ec
is
io
n
-
m
a
k
i
n
g
,
a
n
ar
ea
th
at
h
as
n
o
t
y
e
t
b
ee
n
w
id
el
y
ad
o
p
ted
in
th
e
I
n
d
o
n
esia
n
ed
u
ca
tio
n
s
y
s
te
m
.
W
h
ile
th
i
s
s
t
u
d
y
p
r
o
v
id
es
v
a
lu
ab
le
in
s
i
g
h
t
s
,
s
e
v
er
al
li
m
it
atio
n
s
s
h
o
u
ld
b
e
n
o
ted
.
T
h
e
d
ataset
is
li
m
ited
to
SMK
teac
h
er
s
’
atte
n
d
an
ce
d
ata
o
v
er
t
h
e
la
s
t
t
h
r
e
e
m
o
n
t
h
s
.
F
u
tu
r
e
r
esear
c
h
s
h
o
u
ld
in
co
r
p
o
r
ate
a
lar
g
er
an
d
m
o
r
e
d
iv
er
s
e
d
atas
et,
co
n
s
id
er
in
g
o
th
er
f
ac
to
r
s
s
u
ch
as
p
er
f
o
r
m
an
ce
e
v
alu
a
tio
n
s
f
r
o
m
s
t
u
d
en
t
s
an
d
p
r
in
cip
als.
A
d
d
itio
n
all
y
,
t
h
is
s
tu
d
y
u
s
ed
th
r
ee
M
L
al
g
o
r
ith
m
s
,
e
x
p
lo
r
in
g
o
th
er
m
o
d
e
ls
s
u
ch
a
s
n
eu
r
al
n
et
w
o
r
k
s
o
r
en
s
e
m
b
le
lear
n
i
n
g
co
u
ld
o
f
f
er
d
ee
p
er
in
s
ig
h
ts
i
n
to
m
o
d
el
r
eliab
ilit
y
i
n
d
i
f
f
er
e
n
t sce
n
ar
io
s
.
4.
CO
NCLU
SI
O
N
I
n
th
i
s
s
t
u
d
y
,
s
e
n
s
i
tiv
it
y
a
n
al
y
s
i
s
o
f
t
h
e
DSS
t
h
eo
r
y
w
a
s
ap
p
lied
to
ML
p
r
ed
ictio
n
m
o
d
els
u
s
in
g
a
clas
s
i
f
icatio
n
ap
p
r
o
ac
h
to
an
al
y
ze
th
e
p
er
f
o
r
m
a
n
ce
an
d
p
r
ed
ict
SMK
teac
h
er
s
w
h
o
ex
ce
l
a
n
d
th
o
s
e
w
h
o
n
ee
d
ad
d
itio
n
al
s
u
p
p
o
r
t.
T
h
e
th
r
ee
ML
m
o
d
el
s
u
s
ed
in
t
h
is
s
t
u
d
y
w
er
e
SVM,
DT
,
an
d
RF
.
T
h
e
r
esu
lt
s
s
h
o
w
ed
t
h
at
all
m
o
d
els
ac
h
ie
v
ed
a
h
i
g
h
p
r
ec
is
io
n
lev
el
o
f
1
0
0
%
,
in
d
icatin
g
th
a
t
th
e
m
o
d
el
s
r
ar
ely
m
a
k
e
m
is
ta
k
es
i
n
class
i
f
y
in
g
teac
h
er
s
w
h
o
ex
ce
l
an
d
th
o
s
e
w
h
o
n
ee
d
ad
d
itio
n
al
s
u
p
p
o
r
t.
Ho
w
ev
er
,
in
ter
m
s
o
f
ac
cu
r
ac
y
,
RF
an
d
DT
p
er
f
o
r
m
ed
b
etter
co
m
p
ar
ed
to
SVM.
T
h
e
ac
cu
r
ac
y
r
ates
f
o
r
R
F
an
d
DT
w
er
e
b
o
th
9
8
.
3
%,
w
h
ile
SV
M
w
as
s
li
g
h
t
l
y
lo
w
er
at
9
7
.
2
%.
T
h
is
s
u
g
g
e
s
ts
t
h
at
b
o
th
R
F
a
n
d
DT
h
av
e
ad
v
a
n
tag
e
s
i
n
p
r
ed
ictin
g
teac
h
e
r
class
i
f
icatio
n
s
.
On
th
e
o
th
er
h
an
d
,
all
th
r
ee
m
o
d
els
als
o
s
h
o
w
ed
b
alan
ce
d
r
esu
lts
b
et
w
ee
n
r
ec
all
an
d
p
r
ec
is
io
n
,
as
in
d
icate
d
b
y
t
h
eir
F1
s
co
r
es.
I
n
th
is
ca
s
e,
th
e
F1
s
co
r
es
f
o
r
all
m
o
d
el
s
w
er
e
ab
o
v
e
9
7
%,
in
d
icati
n
g
t
h
at
all
test
ed
m
o
d
els
w
er
e
ab
le
to
ac
h
iev
e
a
g
o
o
d
b
alan
ce
in
id
en
ti
f
y
i
n
g
teac
h
er
s
w
h
o
n
ee
d
ad
d
itio
n
al
s
u
p
p
o
r
t
(
r
ec
all)
an
d
m
i
n
i
m
izi
n
g
er
r
o
r
s
in
class
if
y
i
n
g
teac
h
er
s
w
h
o
ex
ce
l
(
p
r
ec
is
i
o
n
)
.
T
h
er
e
f
o
r
e,
f
o
r
th
e
p
r
ed
ictio
n
tas
k
in
t
h
i
s
s
t
u
d
y
,
RF
a
n
d
DT
ca
n
b
e
co
n
s
id
er
ed
ex
ce
llen
t c
h
o
ices o
v
er
SV
M
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
ex
te
n
d
s
ap
p
r
ec
iatio
n
to
co
lleag
u
e
s
an
d
ad
v
is
er
s
f
o
r
th
eir
v
al
u
ab
le
in
s
i
g
h
ts
an
d
ex
p
er
tis
e,
w
h
ic
h
w
er
e
cr
u
cial
to
th
e
s
u
cc
ess
o
f
t
h
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
S
r
i
v
a
st
a
v
a
a
n
d
S
.
B
a
g
,
“
M
o
d
e
r
n
-
d
a
y
mark
e
t
i
n
g
c
o
n
c
e
p
t
s
b
a
se
d
o
n
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
a
n
d
n
e
u
r
o
-
mark
e
t
i
n
g
:
a
r
e
v
i
e
w
a
n
d
f
u
t
u
r
e
r
e
se
a
r
c
h
d
i
r
e
c
t
i
o
n
s
,
”
Be
n
c
h
m
a
r
k
i
n
g
,
v
o
l
.
3
1
,
n
o
.
2
,
p
p
.
4
1
0
–
4
3
8
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
8
/
B
I
J
-
09
-
2
0
2
2
-
0
5
8
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
3
7
1
-
381
380
[
2
]
K
.
Jo
o
,
J.
K
i
m,
a
n
d
J.
H
w
a
n
g
,
“
Ef
f
e
c
t
s
o
f
f
o
o
d
se
r
v
i
c
e
c
o
n
s
u
me
r
s
’
p
e
r
c
e
p
t
i
o
n
s
o
f
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
p
a
y
me
n
t
o
n
a
t
t
i
t
u
d
e
,
d
e
si
r
e
,
a
n
d
b
e
h
a
v
i
o
r
a
l
i
n
t
e
n
t
i
o
n
s:
a
c
r
o
ss
-
c
u
l
t
u
r
a
l
st
u
d
y
,
”
J
o
u
r
n
a
l
o
f
T
ra
v
e
l
&
T
o
u
ri
s
m
Ma
r
k
e
t
i
n
g
,
v
o
l
.
4
1
,
n
o
.
3
,
p
p
.
3
5
9
–
3
7
6
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
5
4
8
4
0
8
.
2
0
2
4
.
2
3
1
8
4
2
9
.
[
3
]
R
.
P
.
K
,
A
.
K
h
a
p
a
r
d
e
,
V
.
B
e
n
d
r
e
,
a
n
d
J
.
K
a
t
t
i
,
“
F
r
a
u
d
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
b
y
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
a
n
d
w
i
t
h
o
u
t
mas
k
f
o
r
b
a
n
k
i
n
g
a
p
p
l
i
c
a
t
i
o
n
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
p
p
.
1
–
2
4
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
024
-
1
9
0
2
1
-
1.
[
4
]
M
.
B
a
r
h
a
t
e
e
t
a
l
.
,
“
I
n
n
o
v
a
t
i
v
e
a
t
t
e
n
d
a
n
c
e
t
r
a
c
k
i
n
g
:
f
a
c
i
a
l
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
2
0
2
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Em
e
r
g
i
n
g
S
m
a
rt
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s,
E
S
C
I
2
0
2
4
,
I
EEE,
M
a
r
.
2
0
2
4
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
ESCI
5
9
6
0
7
.
2
0
2
4
.
1
0
4
9
7
3
6
4
.
[
5
]
R
.
M
i
sr
a
a
n
d
S
.
K
.
S
h
a
k
y
a
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
a
t
t
e
n
d
a
n
c
e
sy
st
e
m,
sm
a
r
t
l
e
a
r
n
i
n
g
,
c
o
l
l
e
g
e
e
n
q
u
i
r
y
u
si
n
g
A
I
C
h
a
t
-
B
o
t
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
R
e
c
e
n
t
T
ren
d
s
i
n
E
n
g
i
n
e
e
r
i
n
g
&
T
e
c
h
n
o
l
o
g
y
(
I
C
RTET
-
2
0
2
3
)
,
2
0
2
3
,
p
p
.
1
6
4
–
1
7
0
.
[
6
]
D
.
V
.
N
a
g
a
g
o
p
i
r
a
j
u
,
D
.
M
.
D
e
e
p
a
k
,
M
.
V
.
V
i
n
a
y
,
E.
A
.
K
u
mar
,
a
n
d
K
.
S
u
p
r
i
y
a
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
b
l
o
c
k
c
h
a
i
n
-
b
a
se
d
r
e
a
l
-
t
i
me
f
a
c
i
a
l
r
e
c
o
g
n
i
t
i
o
n
a
t
t
e
n
d
a
n
c
e
sy
s
t
e
m,
”
T
u
rki
s
h
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
M
a
t
h
e
m
a
t
i
c
s
E
d
u
c
a
t
i
o
n
(
T
U
R
C
O
MA
T
)
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
3
3
–
1
3
7
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
6
1
8
4
1
/
t
u
r
c
o
ma
t
.
v
1
5
i
1
.
1
4
5
5
4
.
[
7
]
Y
.
Z
h
a
n
g
,
W
.
X
i
e
,
a
n
d
X
.
Y
u
,
“
D
e
si
g
n
a
n
d
i
m
p
l
e
me
n
t
a
t
i
o
n
o
f
l
i
v
e
n
e
ss
d
e
t
e
c
t
i
o
n
sy
st
e
m
b
a
se
d
o
n
i
m
p
r
o
v
e
d
sh
u
f
f
l
e
n
e
t
V
2
,
”
S
i
g
n
a
l
,
I
m
a
g
e
a
n
d
Vi
d
e
o
Pr
o
c
e
ss
i
n
g
,
v
o
l
.
1
7
,
n
o
.
6
,
p
p
.
3
0
3
5
–
3
0
4
3
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
7
6
0
-
023
-
0
2
5
2
4
-
z.
[
8
]
I
.
B
r
a
n
e
scu
,
R
.
I
.
C
i
o
b
a
n
u
,
C
.
D
o
b
r
e
,
a
n
d
C
.
M
a
v
r
o
mo
u
st
a
k
i
s,
“
D
e
c
e
n
t
r
a
l
i
z
e
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
3
2
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
P
a
r
a
l
l
e
l
a
n
d
D
i
s
t
ri
b
u
t
e
d
C
o
m
p
u
t
i
n
g
,
I
S
PD
C
2
0
2
3
,
I
EEE,
Ju
l
.
2
0
2
3
,
p
p
.
1
–
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
P
D
C
5
9
2
1
2
.
2
0
2
3
.
0
0
0
1
0
.
[
9
]
S
.
R
.
C
h
a
v
a
n
a
n
d
S
.
S
h
e
r
e
k
a
r
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
sy
st
e
m
u
si
n
g
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
&
i
t
s
mo
d
e
l
w
i
t
h
i
t
s
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
H
e
t
e
ro
g
e
n
o
u
s
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
,
B
o
c
a
R
a
t
o
n
:
C
R
C
P
r
e
ss,
2
0
2
3
,
p
p
.
2
0
9
–
2
2
4
.
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
3
6
3
6
0
6
-
14.
[
1
0
]
J.
K
.
Esse
l
,
J
.
A
.
M
e
n
s
a
h
,
E.
O
c
r
a
n
,
a
n
d
L
.
A
si
e
d
u
,
“
O
n
t
h
e
se
a
r
c
h
f
o
r
e
f
f
i
c
i
e
n
t
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
a
l
g
o
r
i
t
h
m
su
b
j
e
c
t
t
o
m
u
l
t
i
p
l
e
e
n
v
i
r
o
n
me
n
t
a
l
c
o
n
s
t
r
a
i
n
t
s
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
7
,
p
p
.
1
–
1
4
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
2
8
5
6
8
.
[
1
1
]
A
.
G
o
e
l
,
A
.
K
.
G
o
e
l
,
a
n
d
A
.
K
u
mar,
“
T
h
e
r
o
l
e
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
u
t
i
l
i
z
i
n
g
s
p
a
t
i
a
l
i
n
f
o
r
ma
t
i
o
n
,
”
S
p
a
t
i
a
l
I
n
f
o
rm
a
t
i
o
n
R
e
se
a
rc
h
,
v
o
l
.
3
1
,
n
o
.
3
,
p
p
.
2
7
5
–
2
8
5
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
3
2
4
-
0
2
2
-
0
0
4
9
4
-
x
.
[
1
2
]
M
.
N
.
N
a
i
k
,
A
.
K
a
u
r
,
N
.
Y
a
t
h
i
r
a
j
u
,
S
.
D
a
s,
a
n
d
K
.
P
a
n
t
,
“
I
mp
r
o
v
e
d
a
n
d
a
c
c
u
r
a
t
e
f
a
c
e
mas
k
d
e
t
e
c
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
t
h
e
c
r
o
w
d
e
d
p
l
a
c
e
s,
”
i
n
2
0
2
3
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
C
o
m
p
u
t
i
n
g
a
n
d
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
i
n
E
n
g
i
n
e
e
r
i
n
g
,
I
C
AC
I
T
E
2
0
2
3
,
I
EEE,
M
a
y
2
0
2
3
,
p
p
.
5
7
2
–
5
7
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
I
T
E5
7
4
1
0
.
2
0
2
3
.
1
0
1
8
2
5
6
7
.
[
1
3
]
S
.
S
a
l
e
e
m,
J.
S
h
i
n
e
y
,
B
.
P
.
S
h
a
n
,
a
n
d
V
.
K
.
M
i
s
h
r
a
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
f
a
c
i
a
l
f
e
a
t
u
r
e
s,
”
Ma
t
e
r
i
a
l
s
T
o
d
a
y
:
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
8
0
,
p
p
.
3
8
5
7
–
3
8
6
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
ma
t
p
r
.
2
0
2
1
.
0
7
.
4
0
2
.
[
1
4
]
A
.
M
u
g
h
a
i
d
e
t
a
l
.
,
“
A
n
o
v
e
l
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
t
e
c
h
n
i
q
u
e
f
o
r
f
a
k
e
a
c
c
o
u
n
t
s
d
e
t
e
c
t
i
o
n
sy
st
e
m
o
n
c
y
b
e
r
so
c
i
a
l
n
e
t
w
o
r
k
s,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
2
,
n
o
.
1
7
,
p
p
.
2
6
3
5
3
–
2
6
3
7
8
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
3
-
1
4
3
4
7
-
8.
[
1
5
]
R
a
n
g
a
y
y
a
,
V
i
r
u
p
a
k
s
h
a
p
p
a
,
a
n
d
N
.
P
a
t
i
l
,
“
I
mp
r
o
v
e
d
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
me
t
h
o
d
u
s
i
n
g
S
V
M
-
M
R
F
w
i
t
h
K
T
B
D
b
a
se
d
K
C
M
se
g
me
n
t
a
t
i
o
n
a
p
p
r
o
a
c
h
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
y
st
e
m
Ass
u
r
a
n
c
e
E
n
g
i
n
e
e
ri
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
–
1
2
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
1
9
8
-
0
2
1
-
0
1
4
8
3
-
3.
[
1
6
]
G
.
S
a
n
i
l
,
K
.
P
r
a
k
a
sh
,
S
.
P
r
a
b
h
u
,
V
.
C
.
N
a
y
a
k
,
a
n
d
S
.
S
e
n
g
u
p
t
a
,
“
2D
-
3
D
f
a
c
i
a
l
i
mag
e
a
n
a
l
y
si
s
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
f
a
c
i
a
l
f
e
a
t
u
r
e
s
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
w
i
t
h
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
o
r
f
o
r
e
n
si
c
s
a
p
p
l
i
c
a
t
i
o
n
s,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
8
2
5
2
1
–
8
2
5
3
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
8
4
4
3
.
[
1
7
]
X
.
Z
h
o
u
a
n
d
T
.
C
.
Z
h
u
,
“
S
u
r
v
e
y
o
f
r
e
s
e
a
r
c
h
o
n
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
me
t
h
o
d
s
b
a
se
d
o
n
d
e
p
t
h
l
e
a
r
n
i
n
g,
”
J
o
u
rn
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
2
7
1
7
,
n
o
.
1
,
p
p
.
1
–
7
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
2
7
1
7
/
1
/
0
1
2
0
2
7
.
[
1
8
]
C
.
D
.
K
o
t
h
a
p
a
l
l
i
,
G
.
N
a
v
y
a
,
U
.
Jal
a
d
h
i
,
S
.
R
.
S
u
l
t
h
a
n
a
,
D
.
L
.
S
.
K
u
mar,
a
n
d
S
.
P
.
P
r
a
v
e
e
n
,
“
P
r
e
d
i
c
t
i
n
g
b
u
y
a
n
d
se
l
l
si
g
n
a
l
s
f
o
r
st
o
c
k
s
u
si
n
g
b
o
l
l
i
n
g
e
r
b
a
n
d
s
a
n
d
M
A
C
D
w
i
t
h
t
h
e
h
e
l
p
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
u
st
a
i
n
a
b
l
e
C
o
m
p
u
t
i
n
g
a
n
d
S
m
a
rt
S
y
s
t
e
m
s
(
I
C
S
C
S
S
)
,
I
EEE,
Ju
n
.
2
0
2
3
,
p
p
.
3
3
3
–
3
4
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
S
S
5
7
6
5
0
.
2
0
2
3
.
1
0
1
6
9
5
0
0
.
[
1
9
]
Z
.
Y
.
C
h
e
n
,
Z
.
P
.
F
a
n
,
a
n
d
M
.
S
u
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
f
o
r
d
a
t
a
-
d
r
i
v
e
n
d
e
m
a
n
d
e
st
i
m
a
t
i
o
n
a
n
d
a
ss
o
r
t
me
n
t
p
l
a
n
n
i
n
g
c
o
n
si
d
e
r
i
n
g
c
r
o
ss
-
se
l
l
i
n
g
a
n
d
s
u
b
s
t
i
t
u
t
i
o
n
s,
”
I
N
FO
RM
S
J
o
u
r
n
a
l
o
n
C
o
m
p
u
t
i
n
g
,
v
o
l
.
3
5
,
n
o
.
1
,
p
p
.
1
5
8
–
1
7
7
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
2
8
7
/
i
j
o
c
.
2
0
2
2
.
1
2
5
1
.
[
2
0
]
S
.
L
a
h
mi
r
i
,
S
.
B
e
k
i
r
o
s,
a
n
d
C
.
A
v
d
o
u
l
a
s,
“
A
c
o
mp
a
r
a
t
i
v
e
a
sse
ssm
e
n
t
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
f
o
r
p
r
e
d
i
c
t
i
n
g
h
o
u
s
i
n
g
p
r
i
c
e
s
u
si
n
g
B
a
y
e
si
a
n
o
p
t
i
m
i
z
a
t
i
o
n
,
”
D
e
c
i
s
i
o
n
A
n
a
l
y
t
i
c
s J
o
u
rn
a
l
,
v
o
l
.
6
,
p
p
.
1
–
8
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
3
.
1
0
0
1
6
6
.
[
2
1
]
G
.
C
h
a
u
b
e
y
,
P
.
R
.
G
a
v
h
a
n
e
,
D
.
B
i
s
e
n
,
a
n
d
S
.
K
.
A
r
j
a
r
i
a
,
“
C
u
st
o
me
r
p
u
r
c
h
a
s
i
n
g
b
e
h
a
v
i
o
r
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
J
o
u
rn
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
z
e
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
4
,
n
o
.
1
2
,
p
p
.
1
6
1
3
3
–
1
6
1
5
7
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
2
6
5
2
-
0
2
2
-
0
3
8
3
7
-
6.
[
2
2
]
H
.
I
sh
i
b
a
sh
i
,
“
F
r
a
mew
o
r
k
f
o
r
r
i
sk
a
sse
ssm
e
n
t
o
f
e
c
o
n
o
mi
c
l
o
ss
f
r
o
m
st
r
u
c
t
u
r
e
s
d
a
mag
e
d
b
y
r
a
i
n
f
a
l
l
-
i
n
d
u
c
e
d
l
a
n
d
sl
i
d
e
s
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
G
e
o
ri
s
k
:
Asse
ssm
e
n
t
a
n
d
M
a
n
a
g
e
m
e
n
t
o
f
Ri
sk
f
o
r
E
n
g
i
n
e
e
re
d
S
y
s
t
e
m
s
a
n
d
G
e
o
h
a
z
a
r
d
s
,
v
o
l
.
1
8
,
n
o
.
1
,
p
p
.
2
2
8
–
2
4
3
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
1
7
4
9
9
5
1
8
.
2
0
2
3
.
2
2
8
8
6
0
6
.
[
2
3
]
I
.
S
h
i
n
o
h
a
r
a
e
t
a
l
.
,
“
Re
-
t
e
a
r
a
f
t
e
r
a
r
t
h
r
o
sco
p
i
c
r
o
t
a
t
o
r
c
u
f
f
t
e
a
r
s
u
r
g
e
r
y
:
r
i
sk
a
n
a
l
y
si
s u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
J
o
u
rn
a
l
o
f
S
h
o
u
l
d
e
r
a
n
d
El
b
o
w
S
u
rg
e
ry
,
v
o
l
.
3
3
,
n
o
.
4
,
p
p
.
8
1
5
–
8
2
2
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
s
e
.
2
0
2
3
.
0
7
.
0
1
7
.
[
2
4
]
B
.
Z
h
a
o
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
o
n
h
e
a
v
y
me
t
a
l
s
a
c
c
u
m
u
l
a
t
i
o
n
r
i
s
k
i
n
r
i
c
e
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
m
a
p
p
i
n
g
p
o
l
l
u
t
i
o
n
r
i
sk
,
”
J
o
u
rn
a
l
o
f
H
a
za
r
d
o
u
s
M
a
t
e
ri
a
l
s
,
v
o
l
.
4
4
8
,
p
.
1
3
0
8
7
9
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
h
a
z
ma
t
.
2
0
2
3
.
1
3
0
8
7
9
.
[
2
5
]
R
.
A
r
b
o
r
e
t
t
i
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
v
e
st
a
d
i
u
m
a
t
t
e
n
d
a
n
c
e
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
n
i
n
g
:
a
c
a
se
st
u
d
y
i
n
i
t
a
l
i
a
n
f
o
o
t
b
a
l
l
,
”
J
o
u
rn
a
l
o
f
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
v
o
l
.
5
,
p
p
.
1
–
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
1
5
9
/
j
mi
d
s.
2
0
2
4
.
0
0
4
.
[
2
6
]
A
.
N
.
K
h
i
a
v
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
i
n
g
o
f
b
a
se
f
l
o
w
g
e
n
e
r
a
t
i
o
n
p
o
t
e
n
t
i
a
l
:
a
c
a
se
s
t
u
d
y
o
f
t
h
e
c
o
m
b
i
n
e
d
a
p
p
l
i
c
a
t
i
o
n
o
f
B
W
M
a
n
d
F
a
l
l
b
a
c
k
b
a
r
g
a
i
n
i
n
g
a
l
g
o
r
i
t
h
m,
”
J
o
u
r
n
a
l
o
f
H
y
d
r
o
l
o
g
y
,
v
o
l
.
6
3
6
,
p
.
1
3
1
2
2
0
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
h
y
d
r
o
l
.
2
0
2
4
.
1
3
1
2
2
0
.
[
2
7
]
R
.
A
i
,
Y
.
Z
h
e
n
g
,
S
.
Y
ü
k
se
l
,
a
n
d
H
.
D
i
n
ç
e
r
,
“
I
n
v
e
st
i
g
a
t
i
n
g
t
h
e
c
o
mp
o
n
e
n
t
s o
f
f
i
n
t
e
c
h
e
c
o
sy
st
e
m f
o
r
d
i
st
r
i
b
u
t
e
d
e
n
e
r
g
y
i
n
v
e
st
me
n
t
s
w
i
t
h
a
n
i
n
t
e
g
r
a
t
e
d
q
u
a
n
t
u
m
s
p
h
e
r
i
c
a
l
d
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
st
e
m,
”
Fi
n
a
n
c
i
a
l
I
n
n
o
v
a
t
i
o
n
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
–
2
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
8
5
4
-
0
2
2
-
0
0
4
4
2
-
6.
[
2
8
]
S
.
K
i
m,
E
.
H
.
K
i
m,
a
n
d
H
.
S
.
K
i
m,
“
P
h
y
si
c
i
a
n
k
n
o
w
l
e
d
g
e
b
a
se
:
c
l
i
n
i
c
a
l
d
e
c
i
si
o
n
su
p
p
o
r
t
sy
st
e
ms,
”
Y
o
n
s
e
i
M
e
d
i
c
a
l
J
o
u
r
n
a
l
,
v
o
l
.
6
3
,
n
o
.
1
,
p
p
.
8
–
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
4
9
/
Y
M
J.
2
0
2
2
.
6
3
.
1
.
8
.
[
2
9
]
T
.
D
o
n
o
v
a
n
,
B
.
A
b
e
l
l
,
M
.
F
e
r
n
a
n
d
o
,
S
.
M
.
M
c
P
h
a
i
l
,
a
n
d
H
.
E.
C
a
r
t
e
r
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
c
o
st
s
o
f
h
o
sp
i
t
a
l
-
b
a
s
e
d
c
o
mp
u
t
e
r
i
se
d
d
e
c
i
si
o
n
su
p
p
o
r
t
sy
st
e
ms:
a
sy
st
e
mat
i
c
r
e
v
i
e
w
,
”
I
m
p
l
e
m
e
n
t
a
t
i
o
n
S
c
i
e
n
c
e
,
v
o
l
.
1
8
,
n
o
.
1
,
p
p
.
1
–
1
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
0
1
2
-
0
2
3
-
0
1
2
6
1
-
8
.
[
3
0
]
X
.
L
i
u
e
t
a
l
.
,
“
D
i
scre
p
a
n
c
y
b
e
t
w
e
e
n
p
e
r
c
e
p
t
i
o
n
s
a
n
d
a
c
c
e
p
t
a
n
c
e
o
f
c
l
i
n
i
c
a
l
d
e
c
i
si
o
n
s
u
p
p
o
r
t
S
y
st
e
ms:
i
mp
l
e
me
n
t
a
t
i
o
n
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
f
o
r
v
a
n
c
o
my
c
i
n
d
o
si
n
g
,
”
B
MC
M
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
a
n
d
D
e
c
i
s
i
o
n
M
a
k
i
n
g
,
v
o
l
.
2
3
,
n
o
.
1
,
p
p
.
1
–
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
1
1
-
0
2
3
-
0
2
2
5
4
-
9.
[
3
1
]
B
.
A
b
e
l
l
e
t
a
l
.
,
“
I
d
e
n
t
i
f
y
i
n
g
b
a
r
r
i
e
r
s
a
n
d
f
a
c
i
l
i
t
a
t
o
r
s
t
o
s
u
c
c
e
ssf
u
l
i
m
p
l
e
me
n
t
a
t
i
o
n
o
f
c
o
m
p
u
t
e
r
i
z
e
d
c
l
i
n
i
c
a
l
d
e
c
i
si
o
n
s
u
p
p
o
r
t
sy
st
e
ms i
n
h
o
sp
i
t
a
l
s:
a
N
A
S
S
S
f
r
a
mew
o
r
k
-
i
n
f
o
r
me
d
sco
p
i
n
g
r
e
v
i
e
w
,
”
I
m
p
l
e
m
e
n
t
a
t
i
o
n
S
c
i
e
n
c
e
,
v
o
l
.
1
8
,
n
o
.
1
,
p
p
.
1
–
2
0
,
2
0
2
3
,
d
o
i
:
Evaluation Warning : The document was created with Spire.PDF for Python.