I
nte
rna
t
io
na
l J
o
urna
l o
f
Rec
o
nfig
ura
ble a
nd
E
m
be
dd
e
d Sy
s
t
e
m
s
(
I
J
R
E
S)
Vo
l.
15
,
No
.
2
,
J
u
ly
20
26
,
p
p
.
259
~
2
6
8
I
SS
N:
2089
-
4864
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
r
es
.
v
1
5
.
i
2
.
pp
2
5
9
-
268
259
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
es.ia
esco
r
e.
co
m
Predic
ting stud
en
t
a
ca
de
m
ic out
co
m
es
fro
m
e
-
lea
rni
ng
interaction
da
ta u
sing
hybrid
m
a
ch
ine learning
m
o
de
ls
Sa
j
it
hu
nis
a
H
us
s
a
in
,
J
a
y
a
cha
nd
ra
n J
ey
a
chidra
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
P
e
r
i
y
a
r
M
a
n
i
a
mm
a
i
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
&
Te
c
h
n
o
l
o
g
y
,
T
h
a
n
j
a
v
u
r
,
I
n
d
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
2
1
,
2
0
2
4
R
ev
i
s
ed
Ma
r
3
,
2
0
2
6
A
cc
ep
ted
Ma
y
3
0
,
2
0
2
6
T
h
e
ra
p
id
g
ro
w
th
o
f
d
ig
it
a
l
lea
rn
i
n
g
p
latf
o
rm
s
h
a
s
g
e
n
e
ra
ted
larg
e
v
o
lu
m
e
s
o
f
stu
d
e
n
t
in
tera
c
ti
o
n
d
a
ta,
p
r
o
v
id
in
g
o
p
p
o
rtu
n
it
ies
f
o
r
i
n
telli
g
e
n
t
p
re
d
ictio
n
o
f
a
c
a
d
e
m
ic
o
u
tco
m
e
s.
Be
y
o
n
d
e
d
u
c
a
ti
o
n
a
l
a
n
a
ly
ti
c
s,
su
c
h
p
re
d
icti
o
n
tas
k
s
a
re
re
lev
a
n
t
f
o
r
re
c
o
n
f
i
g
u
r
a
b
le
s
y
ste
m
s,
e
m
b
e
d
d
e
d
p
latf
o
rm
s,
v
e
r
y
l
a
rg
e
s
c
a
le
i
n
teg
ra
ti
o
n
(
V
L
S
I
)
a
c
c
e
lera
to
rs,
a
n
d
in
ter
n
e
t
o
f
t
h
in
g
s
(
Io
T
)
-
e
n
a
b
led
e
d
g
e
d
e
v
ice
s
in
sm
a
rt
lea
rn
in
g
e
n
v
iro
n
m
e
n
ts.
T
h
is
stu
d
y
p
ro
p
o
se
s
a
h
y
b
rid
m
a
c
h
in
e
lea
rn
in
g
f
ra
m
e
w
o
rk
f
o
r
p
re
d
ictin
g
stu
d
e
n
t
p
e
rf
o
rm
a
n
c
e
u
sin
g
th
e
e
-
lea
rn
in
g
stu
d
e
n
t
re
a
c
ti
o
n
s
d
a
tas
e
t
,
w
h
ich
c
a
p
tu
re
s
e
n
g
a
g
e
m
e
n
t
p
a
tt
e
rn
s,
b
e
h
a
v
io
ra
l
re
sp
o
n
se
s,
a
n
d
in
tera
c
ti
o
n
d
y
n
a
m
ic
s.
Ei
g
h
t
c
las
sif
iers
—
e
X
trem
e
g
ra
d
ien
t
b
o
o
st
in
g
(
X
G
Bo
o
st)
,
K
-
n
e
a
re
st
n
e
ig
h
b
o
r
s
(
KNN
)
,
d
e
c
isio
n
t
re
e
(DT
)
,
r
a
n
d
o
m
f
o
re
st
(RF
)
,
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
V
M
)
,
m
u
lt
i
l
a
y
e
r
p
e
rc
e
p
tro
n
(
M
L
P
)
,
r
a
d
ial
b
a
sis
f
u
n
c
ti
o
n
(
RBF
)
,
a
n
d
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
(
DNN
)
—
a
re
e
v
a
lu
a
ted
u
sin
g
b
o
t
h
a
n
8
0
–
2
0
train
–
tes
t
sp
li
t
a
n
d
K
-
f
o
ld
c
ro
ss
-
v
a
li
d
a
ti
o
n
to
a
ss
e
ss
a
c
c
u
ra
c
y
a
n
d
g
e
n
e
ra
li
z
a
ti
o
n
.
Re
su
lt
s
sh
o
w
t
h
e
RBF
m
o
d
e
l
a
c
h
iev
e
s
th
e
h
ig
h
e
st
a
c
c
u
ra
c
y
o
f
1
.
0
0
,
d
e
m
o
n
stra
ti
n
g
it
s
a
b
il
it
y
to
c
a
p
t
u
re
c
o
m
p
lex
,
n
o
n
li
n
e
a
r
b
e
h
a
v
io
r.
F
r
o
m
a
sy
s
tem
s
p
e
rsp
e
c
ti
v
e
,
th
e
f
ra
m
e
w
o
rk
c
a
n
b
e
m
a
p
p
e
d
o
n
to
f
ield
p
r
o
g
ra
m
m
a
b
le
g
a
te
a
rra
y
s
(F
P
G
A
s
)
o
r
e
m
b
e
d
d
e
d
d
e
v
ice
s,
lev
e
ra
g
in
g
p
a
ra
ll
e
l
c
o
m
p
u
tatio
n
f
o
r
lo
w
-
late
n
c
y
in
f
e
re
n
c
e
,
a
n
d
in
teg
ra
ted
w
it
h
Io
T
-
e
n
a
b
led
sm
a
rt
c
las
sro
o
m
s
f
o
r
re
a
l
-
ti
m
e
e
d
g
e
a
n
a
l
y
ti
c
s.
T
h
e
se
f
in
d
in
g
s
c
o
n
f
irm
th
a
t
h
y
b
rid
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
n
o
t
o
n
ly
im
p
ro
v
e
stu
d
e
n
t
p
e
rf
o
r
m
a
n
c
e
p
re
d
ictio
n
b
u
t
a
lso
se
rv
e
a
s
p
ra
c
ti
c
a
l
w
o
rk
lo
a
d
s
f
o
r
re
c
o
n
f
ig
u
ra
b
le,
e
m
b
e
d
d
e
d
,
a
n
d
V
L
S
I
-
b
a
se
d
in
telli
g
e
n
t
sy
ste
m
s
in
d
ig
it
a
l
e
d
u
c
a
ti
o
n
.
K
ey
w
o
r
d
s
:
Ma
ch
i
n
e
lear
n
i
n
g
Mo
d
el
Mu
lti
-
la
y
er
p
er
ce
p
tr
o
n
P
ip
elin
e
R
an
d
o
m
f
o
r
est
Stack
ed
c
las
s
i
f
ier
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
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
ay
ac
h
an
d
r
an
J
e
y
ac
h
id
r
a
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
A
p
p
licatio
n
s
,
P
er
i
y
ar
Ma
n
ia
m
m
ai
I
n
s
tit
u
te
o
f
Scien
ce
&
T
ec
h
n
o
l
o
g
y
Valla
m
-
613403
,
T
h
an
j
av
u
r
,
T
a
m
il Na
d
u
,
I
n
d
ia
E
m
ail:
c
h
it
h
u
_
ra
j@p
m
u
.
e
d
u
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
ap
id
d
ig
ital
tr
an
s
f
o
r
m
ati
o
n
o
f
ed
u
ca
tio
n
h
a
s
f
u
n
d
a
m
e
n
tall
y
c
h
a
n
g
ed
h
o
w
s
tu
d
e
n
ts
in
ter
ac
t
w
it
h
lear
n
in
g
co
n
te
n
t,
i
n
s
tr
u
cto
r
s
,
an
d
p
ee
r
s
,
lead
in
g
to
t
h
e
w
id
esp
r
ea
d
ad
o
p
tio
n
o
f
e
-
lear
n
in
g
p
latf
o
r
m
s
ac
r
o
s
s
s
ch
o
o
ls
,
u
n
i
v
er
s
it
ies,
an
d
p
r
o
f
es
s
io
n
al
tr
ai
n
i
n
g
e
n
v
ir
o
n
m
en
ts
.
Un
li
k
e
tr
ad
itio
n
a
l
class
r
o
o
m
s
ett
in
g
s
,
d
i
g
ital
lear
n
in
g
s
y
s
te
m
s
co
n
ti
n
u
o
u
s
l
y
r
ec
o
r
d
d
etailed
tr
ac
es o
f
lear
n
er
b
eh
av
io
r
,
in
cl
u
d
in
g
ti
m
e
s
p
en
t o
n
i
n
s
tr
u
ctio
n
a
l
m
ater
ials
,
r
esp
o
n
s
e
s
to
q
u
izze
s
,
p
ar
ticip
atio
n
in
d
is
cu
s
s
io
n
s
,
f
r
eq
u
en
c
y
o
f
lo
g
i
n
s
,
an
d
p
atter
n
s
o
f
en
g
ag
e
m
e
n
t
w
it
h
m
u
lti
m
ed
ia
r
eso
u
r
ce
s
[
1
]
–
[
3
]
.
T
h
ese
lar
g
e
v
o
l
u
m
e
s
o
f
i
n
ter
ac
tio
n
d
ata
h
a
v
e
cr
ea
ted
n
e
w
o
p
p
o
r
tu
n
itie
s
f
o
r
u
n
d
er
s
ta
n
d
in
g
h
o
w
s
tu
d
e
n
ts
le
ar
n
,
h
o
w
t
h
e
y
s
tr
u
g
g
le,
an
d
wh
at
f
ac
to
r
s
co
n
tr
ib
u
te
to
th
eir
ac
ad
em
ic
s
u
cc
e
s
s
o
r
f
ail
u
r
e.
A
t
t
h
e
s
a
m
e
ti
m
e,
th
e
in
cr
ea
s
i
n
g
d
i
v
er
s
it
y
o
f
lear
n
er
s
in
o
n
li
n
e
en
v
ir
o
n
m
e
n
ts
,
co
u
p
led
w
ith
v
ar
iatio
n
s
in
m
o
ti
v
atio
n
,
p
r
io
r
k
n
o
w
led
g
e,
an
d
lear
n
i
n
g
s
t
y
les,
h
as
m
ad
e
it
m
o
r
e
d
if
f
ic
u
lt
f
o
r
in
s
tr
u
cto
r
s
to
m
o
n
ito
r
in
d
iv
id
u
al
p
r
o
g
r
es
s
an
d
p
r
o
v
id
e
ti
m
e
l
y
in
te
r
v
en
tio
n
s
[
4
]
–
[
6
]
.
As
a
r
es
u
lt,
th
er
e
i
s
a
g
r
o
w
in
g
n
ee
d
f
o
r
i
n
telli
g
e
n
t,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
259
-
2
6
8
260
d
ata
-
d
r
iv
en
ap
p
r
o
ac
h
es
th
at
ca
n
au
to
m
atica
ll
y
a
n
al
y
ze
le
ar
n
er
b
eh
av
io
r
an
d
ac
cu
r
ately
p
r
ed
ict
s
tu
d
e
n
t
o
u
tco
m
es
b
ef
o
r
e
f
i
n
al
a
s
s
e
s
s
m
en
ts
ar
e
co
m
p
le
ted
.
I
n
t
h
is
co
n
tex
t,
ed
u
ca
tio
n
a
l
d
ata
m
in
i
n
g
a
n
d
lear
n
in
g
an
al
y
tics
h
av
e
e
m
er
g
ed
as
i
m
p
o
r
tan
t
r
esear
ch
ar
ea
s
th
a
t
s
ee
k
to
tr
an
s
f
o
r
m
r
a
w
e
-
lear
n
in
g
d
ata
in
to
ac
tio
n
ab
le
in
s
i
g
h
ts
th
a
t
ca
n
s
u
p
p
o
r
t
p
er
s
o
n
alize
d
i
n
s
tr
u
ctio
n
,
ad
ap
ti
v
e
c
o
n
ten
t
d
eliv
er
y
,
an
d
ea
r
l
y
w
ar
n
in
g
s
y
s
te
m
s
f
o
r
at
-
r
is
k
s
t
u
d
en
ts
.
P
r
ed
ictin
g
s
t
u
d
en
t p
er
f
o
r
m
a
n
ce
is
o
n
e
o
f
th
e
m
o
s
t c
r
it
ical
ta
s
k
s
w
it
h
i
n
t
h
i
s
d
o
m
ai
n
,
a
s
it e
n
ab
les
ed
u
ca
to
r
s
to
id
en
t
if
y
lear
n
er
s
w
h
o
m
a
y
n
ee
d
ad
d
itio
n
al
s
u
p
p
o
r
t,
r
ec
o
m
m
e
n
d
tar
g
eted
lear
n
in
g
r
e
s
o
u
r
ce
s
,
a
n
d
d
esig
n
in
ter
v
en
tio
n
s
th
at
i
m
p
r
o
v
e
r
eten
tio
n
a
n
d
o
v
er
all
ac
h
i
ev
e
m
e
n
t
[
7
]
–
[
1
0
]
.
T
r
a
d
itio
n
al
s
tati
s
tical
m
et
h
o
d
s
h
a
v
e
b
ee
n
u
s
ed
f
o
r
p
er
f
o
r
m
an
ce
p
r
ed
ictio
n
,
b
u
t
th
e
y
o
f
te
n
r
el
y
o
n
s
tr
o
n
g
as
s
u
m
p
tio
n
s
ab
o
u
t
d
ata
d
is
tr
ib
u
tio
n
an
d
lin
ea
r
r
elatio
n
s
h
ip
s
,
w
h
ic
h
r
ar
el
y
h
o
ld
in
r
e
al
-
w
o
r
ld
e
-
lear
n
i
n
g
en
v
ir
o
n
m
e
n
t
s
w
h
er
e
lear
n
er
b
eh
av
io
r
is
co
m
p
lex
,
n
o
n
li
n
e
ar
,
an
d
in
f
lu
e
n
ce
d
b
y
m
a
n
y
in
ter
ac
ti
n
g
f
ac
to
r
s
.
Ma
ch
i
n
e
lear
n
i
n
g
tech
n
iq
u
e
s
o
f
f
er
a
m
o
r
e
f
lex
ib
le
a
n
d
p
o
w
er
f
u
l
alter
n
ati
v
e
b
ec
au
s
e
th
e
y
ca
n
lear
n
p
atter
n
s
d
ir
ec
tl
y
f
r
o
m
d
ata,
ca
p
t
u
r
e
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
,
an
d
ad
ap
t
to
h
eter
o
g
en
eo
u
s
lear
n
er
p
o
p
u
latio
n
s
w
it
h
o
u
t
r
eq
u
ir
in
g
e
x
p
licit
p
r
io
r
m
o
d
els
[
1
1
]
–
[
1
4
]
.
Ov
er
th
e
p
ast
d
ec
a
d
e,
a
w
id
e
r
an
g
e
o
f
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
it
h
m
s
,
in
cl
u
d
in
g
d
ec
is
io
n
t
r
ee
s
(
DT
)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
(
SVM)
,
K
-
n
ea
r
est
n
ei
g
h
b
o
r
s
(
KNN)
,
en
s
e
m
b
le
m
o
d
els,
an
d
n
eu
r
al
n
et
w
o
r
k
s
,
h
av
e
b
ee
n
ap
p
lied
to
ed
u
ca
tio
n
al
d
at
asets
w
it
h
p
r
o
m
is
in
g
r
esu
lt
s
,
d
em
o
n
s
tr
ati
n
g
th
a
t
s
tu
d
e
n
t
i
n
ter
ac
tio
n
s
w
it
h
o
n
li
n
e
p
latf
o
r
m
s
ca
n
b
e
s
tr
o
n
g
p
r
ed
icto
r
s
o
f
ac
ad
em
ic
o
u
tco
m
es.
Ho
w
e
v
er
,
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
e
m
o
d
els
v
ar
ies
w
id
el
y
d
ep
en
d
i
n
g
o
n
th
e
n
atu
r
e
o
f
th
e
d
ataset,
th
e
q
u
alit
y
o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
a
n
d
th
e
ev
a
lu
atio
n
s
tr
ateg
y
u
s
ed
to
v
alid
ate
t
h
e
m
o
d
els.
I
n
p
ar
ticu
lar
,
e
-
lear
n
in
g
d
ata
ar
e
o
f
ten
n
o
i
s
y
,
in
co
m
p
lete,
a
n
d
h
i
g
h
l
y
i
m
b
al
an
ce
d
,
w
h
ic
h
ca
n
lead
to
o
v
er
f
itti
n
g
a
n
d
m
is
lead
i
n
g
p
er
f
o
r
m
an
ce
e
s
ti
m
ate
s
i
f
m
o
d
el
s
ar
e
ev
a
lu
ated
u
s
i
n
g
a
s
in
g
le
tr
ai
n
–
test
s
p
lit
[
1
5
]
–
[
1
8
]
.
T
h
er
ef
o
r
e,
it
is
es
s
e
n
tial
t
o
co
m
p
ar
e
m
u
l
tip
le
lear
n
in
g
al
g
o
r
ith
m
s
u
n
d
er
r
o
b
u
s
t v
alid
atio
n
s
ch
e
m
e
s
to
d
eter
m
in
e
w
h
ic
h
ap
p
r
o
ac
h
es
ar
e
m
o
s
t
r
eliab
le
f
o
r
r
ea
l
-
w
o
r
ld
d
ep
lo
y
m
e
n
t.
T
h
e
e
-
lear
n
i
n
g
s
t
u
d
en
t
r
ea
cti
o
n
s
d
ataset
u
s
ed
in
th
i
s
s
tu
d
y
p
r
o
v
id
es
a
r
ic
h
r
ep
r
esen
tat
i
o
n
o
f
h
o
w
s
tu
d
e
n
ts
in
ter
ac
t
w
it
h
o
n
lin
e
l
ea
r
n
in
g
m
ater
ial
s
,
ca
p
tu
r
i
n
g
b
o
th
co
g
n
iti
v
e
a
n
d
b
eh
a
v
io
r
al
asp
ec
ts
o
f
lear
n
i
n
g
th
r
o
u
g
h
t
h
eir
r
ea
ctio
n
s
,
ac
tiv
i
t
y
p
atter
n
s
,
an
d
en
g
a
g
e
m
e
n
t
in
d
icato
r
s
.
Su
c
h
d
atasets
g
o
b
ey
o
n
d
s
i
m
p
le
tes
t
s
co
r
es
b
y
r
ef
lec
tin
g
h
o
w
s
t
u
d
e
n
ts
ac
t
u
all
y
p
ar
ticip
ate
i
n
t
h
e
le
ar
n
in
g
p
r
o
ce
s
s
,
m
ak
in
g
t
h
e
m
p
ar
ticu
lar
l
y
v
al
u
ab
le
f
o
r
p
r
ed
ictiv
e
m
o
d
elin
g
.
B
y
a
n
al
y
z
in
g
t
h
ese
i
n
ter
ac
tio
n
f
ea
t
u
r
es,
it
b
ec
o
m
es
p
o
s
s
ib
le
to
m
o
v
e
f
r
o
m
r
ea
cti
v
e
ev
alu
a
tio
n
,
w
h
er
e
p
er
f
o
r
m
a
n
c
e
is
m
ea
s
u
r
ed
o
n
l
y
a
f
ter
f
i
n
al
ex
a
m
s
,
to
p
r
o
ac
tiv
e
p
r
ed
ictio
n
,
w
h
er
e
p
o
ten
tial
lear
n
in
g
d
if
f
ic
u
ltie
s
ca
n
b
e
d
etec
ted
ea
r
ly
.
T
h
is
s
h
if
t
is
esp
ec
iall
y
i
m
p
o
r
ta
n
t
in
o
n
li
n
e
ed
u
ca
tio
n
,
w
h
er
e
in
s
tr
u
cto
r
s
m
a
y
h
a
v
e
l
i
m
ited
d
ir
ec
t
co
n
tact
w
it
h
s
tu
d
e
n
ts
a
n
d
m
u
s
t
r
el
y
o
n
d
i
g
ital
tr
ac
es
to
u
n
d
er
s
tan
d
t
h
eir
p
r
o
g
r
ess
[
1
0
]
,
[
1
2
]
,
[
1
9
]
,
[
2
0
]
.
Desp
ite
th
e
av
ailab
il
it
y
o
f
ad
v
an
ce
d
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
e
s
,
th
er
e
i
s
s
ti
ll
n
o
co
n
s
en
s
u
s
o
n
w
h
ic
h
m
o
d
el
s
p
r
o
v
id
e
th
e
b
est
b
alan
ce
b
et
w
ee
n
ac
cu
r
ac
y
,
s
tab
ili
t
y
,
an
d
in
ter
p
r
etab
ilit
y
f
o
r
s
tu
d
e
n
t
p
er
f
o
r
m
a
n
ce
p
r
ed
ictio
n
.
So
m
e
m
o
d
els,
s
u
ch
a
s
d
ee
p
n
eu
r
al
n
et
w
o
r
k
s
(
DNN
)
an
d
r
ad
ial
b
asis
f
u
n
c
tio
n
(
R
B
F
)
n
et
w
o
r
k
s
,
ar
e
h
ig
h
l
y
e
x
p
r
ess
iv
e
an
d
ca
p
ab
le
o
f
ca
p
tu
r
in
g
co
m
p
le
x
p
atter
n
s
,
b
u
t t
h
e
y
m
a
y
also
b
e
p
r
o
n
e
to
o
v
er
f
itti
n
g
an
d
r
eq
u
ir
e
ca
r
e
f
u
l
v
ali
d
atio
n
[
3
]
,
[
2
1
]
–
[
2
3
]
.
Oth
er
s
,
s
u
ch
as
r
an
d
o
m
f
o
r
est
s
(
R
F)
an
d
KNN
,
ar
e
m
o
r
e
r
o
b
u
s
t
to
n
o
is
e
a
n
d
ca
n
o
f
f
er
s
tr
o
n
g
g
e
n
er
aliza
tio
n
,
b
u
t
th
eir
p
er
f
o
r
m
a
n
ce
d
ep
en
d
s
o
n
p
ar
a
m
eter
t
u
n
i
n
g
an
d
th
e
s
tr
u
ct
u
r
e
o
f
th
e
d
ata
[
2
4
]
,
[
2
5
]
.
Fu
r
t
h
er
m
o
r
e,
w
h
en
i
n
teg
r
ated
in
to
I
o
T
-
en
ab
led
ed
u
ca
tio
n
al
ec
o
s
y
s
te
m
s
—
s
u
c
h
as
s
m
ar
t
cl
ass
r
o
o
m
s
,
w
ea
r
ab
le
lear
n
i
n
g
s
en
s
o
r
s
,
an
d
in
ter
ac
tiv
e
ed
u
ca
tio
n
al
d
ev
i
ce
s
—
t
h
e
p
r
o
p
o
s
ed
p
r
e
d
ictiv
e
f
r
a
m
e
w
o
r
k
en
ab
les
r
ea
l
-
ti
m
e
ed
g
e
an
al
y
tics
f
o
r
ea
r
l
y
w
ar
n
in
g
s
y
s
te
m
s
,
ad
ap
tiv
e
co
n
ten
t
d
eliv
er
y
,
an
d
p
er
s
o
n
alize
d
f
ee
d
b
ac
k
.
B
y
r
ed
u
cin
g
r
elia
n
ce
o
n
c
lo
u
d
-
b
ased
p
r
o
ce
s
s
i
n
g
,
s
u
c
h
ar
ch
itect
u
r
es
i
m
p
r
o
v
e
s
ca
lab
il
it
y
,
p
r
iv
ac
y
,
a
n
d
r
esp
o
n
s
iv
e
n
e
s
s
i
n
lar
g
e
-
s
ca
le
l
ea
r
n
in
g
en
v
ir
o
n
m
e
n
ts
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
e
g
r
o
w
i
n
g
av
a
ilab
ilit
y
o
f
d
ig
ital
lear
n
i
n
g
p
latf
o
r
m
s
h
as
le
d
to
an
i
n
cr
ea
s
i
n
g
in
ter
est
i
n
u
s
in
g
d
ata
-
d
r
iv
en
m
eth
o
d
s
to
u
n
d
er
s
ta
n
d
an
d
p
r
ed
ict
s
tu
d
en
t
ac
ad
e
m
ic
p
er
f
o
r
m
a
n
ce
.
A
s
e
-
lear
n
in
g
s
y
s
te
m
s
co
n
ti
n
u
o
u
s
l
y
co
llect
d
etailed
r
ec
o
r
d
s
o
f
s
tu
d
en
t
i
n
te
r
ac
tio
n
s
,
as
s
ess
m
e
n
ts
,
a
n
d
b
eh
av
io
r
al
r
esp
o
n
s
e
s
,
th
ese
d
ata
h
av
e
b
ec
o
m
e
v
al
u
ab
le
r
eso
u
r
ce
s
f
o
r
d
ev
elo
p
in
g
p
r
ed
ictiv
e
m
o
d
els
th
at
s
u
p
p
o
r
t
ac
ad
em
ic
p
lan
n
i
n
g
an
d
ea
r
l
y
in
ter
v
e
n
tio
n
[
1
3
]
–
[
1
5
]
.
R
ec
en
t
s
tu
d
ies
d
e
m
o
n
s
tr
ate
th
at
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
s
ar
e
p
ar
ticu
lar
l
y
e
f
f
ec
t
iv
e
f
o
r
ca
p
tu
r
in
g
co
m
p
le
x
,
n
o
n
l
in
ea
r
r
elatio
n
s
h
ip
s
b
et
w
ee
n
lear
n
er
b
eh
av
io
r
an
d
ac
ad
e
m
ic
o
u
t
co
m
e
s
[
1
6
]
.
B
h
i
m
a
v
ar
ap
u
et
a
l
.
[
4
]
co
n
d
u
cted
a
co
m
p
r
eh
e
n
s
i
v
e
co
m
p
ar
is
o
n
o
f
s
ev
er
al
cla
s
s
i
f
icatio
n
alg
o
r
ith
m
s
f
o
r
p
r
ed
ictin
g
s
t
u
d
en
t a
ca
d
e
m
i
c
p
er
f
o
r
m
an
ce
.
T
h
eir
w
o
r
k
e
v
alu
ated
m
o
d
el
s
s
u
ch
as
K
NN
,
DT
,
SVM
,
RF
,
an
d
n
eu
r
al
n
et
w
o
r
k
s
o
n
ed
u
ca
ti
o
n
al
d
atasets
.
T
h
e
a
u
th
o
r
s
s
h
o
w
ed
t
h
at
n
o
s
in
g
le
al
g
o
r
ith
m
co
n
s
is
te
n
tl
y
o
u
tp
er
f
o
r
m
ed
o
th
er
s
ac
r
o
s
s
all
s
ce
n
ar
io
s
,
b
u
t
en
s
e
m
b
le
m
et
h
o
d
s
an
d
n
eu
r
al
n
et
w
o
r
k
–
b
ased
m
o
d
els
g
en
er
all
y
ex
h
ib
ited
h
i
g
h
er
p
r
ed
ictiv
e
ac
cu
r
ac
y
an
d
b
etter
r
o
b
u
s
tn
ess
.
T
h
eir
f
in
d
in
g
s
e
m
p
h
asized
th
e
im
p
o
r
tan
ce
o
f
u
s
i
n
g
m
u
ltip
le
clas
s
i
f
ier
s
a
n
d
p
r
o
p
e
r
v
alid
atio
n
s
tr
ateg
ies
to
e
n
s
u
r
e
r
eliab
le
p
er
f
o
r
m
a
n
ce
es
ti
m
atio
n
i
n
ac
ad
e
m
ic
p
r
ed
ictio
n
tas
k
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
P
r
ed
ictin
g
s
tu
d
en
t a
ca
d
emic
o
u
tco
mes fro
m
e
-
lea
r
n
in
g
in
tera
ctio
n
d
a
ta
u
s
in
g
…
(
S
a
jith
u
n
i
s
a
Hu
s
s
a
in
)
261
T
h
e
in
teg
r
atio
n
o
f
i
n
ter
n
et
o
f
t
h
in
g
s
(
I
o
T
)
tech
n
o
lo
g
ie
s
in
to
ed
u
ca
tio
n
h
as
f
u
r
t
h
er
en
r
ic
h
ed
th
e
t
y
p
e
s
o
f
d
ata
av
ailab
le
f
o
r
s
tu
d
en
t
an
al
y
tics
.
Hu
s
s
ai
n
an
d
Di
m
ilil
e
r
[
7
]
ex
p
lo
r
e
d
s
tu
d
en
t
g
r
ad
e
p
r
ed
ictio
n
in
an
I
o
T
-
en
ab
led
lear
n
i
n
g
en
v
ir
o
n
m
e
n
t,
w
h
er
e
d
ata
w
er
e
co
llected
f
r
o
m
s
m
ar
t
clas
s
r
o
o
m
s
a
n
d
lear
n
i
n
g
p
latf
o
r
m
s
.
T
h
eir
s
tu
d
y
d
e
m
o
n
s
tr
ated
th
at
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
s
u
c
h
as
DT
,
l
o
g
is
tic
r
eg
r
es
s
io
n
,
a
n
d
SV
M
co
u
ld
ef
f
ec
tiv
e
l
y
u
tili
ze
b
eh
a
v
io
r
al
an
d
in
ter
ac
tio
n
f
ea
tu
r
e
s
to
p
r
e
d
ict
s
tu
d
en
t
g
r
ad
es.
T
h
e
au
th
o
r
s
h
ig
h
li
g
h
ted
th
at
I
o
T
-
b
ased
lear
n
in
g
s
y
s
te
m
s
a
llo
w
m
o
r
e
g
r
an
u
lar
tr
ac
k
i
n
g
o
f
s
t
u
d
en
t
a
ctiv
it
y
,
w
h
ich
s
ig
n
i
f
ica
n
tl
y
i
m
p
r
o
v
es
th
e
ac
cu
r
ac
y
o
f
p
r
ed
ictiv
e
m
o
d
els.
A
r
ec
en
t
la
r
g
e
-
s
ca
le
s
tu
d
y
b
y
Ah
m
ed
et
a
l
.
[
1
]
in
tr
o
d
u
ce
d
ex
p
lain
ab
le
m
ac
h
i
n
e
lear
n
i
n
g
f
o
r
ac
ad
em
i
c
p
er
f
o
r
m
a
n
ce
p
r
ed
ictio
n
.
B
y
c
o
m
b
i
n
i
n
g
tr
ad
itio
n
a
l
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els
w
it
h
ex
p
lai
n
ab
ilit
y
tec
h
n
iq
u
e
s
,
th
eir
f
r
a
m
e
w
o
r
k
allo
w
ed
in
s
titu
tio
n
s
n
o
t
o
n
l
y
to
p
r
ed
ict
o
u
tco
m
e
s
b
u
t
also
to
u
n
d
er
s
tan
d
w
h
y
s
p
ec
if
ic
p
r
ed
ictio
n
s
w
er
e
m
ad
e.
T
h
eir
r
esu
lt
s
s
h
o
w
ed
t
h
at
en
s
e
m
b
le
m
o
d
el
s
s
u
c
h
as
R
F
an
d
g
r
ad
ie
n
t
b
o
o
s
tin
g
ac
h
ie
v
ed
h
ig
h
p
r
ed
ictiv
e
ac
c
u
r
ac
y
,
w
h
i
le
ex
p
lain
ab
ili
t
y
to
o
ls
p
r
o
v
id
ed
in
s
i
g
h
t
s
in
to
k
e
y
f
ac
to
r
s
s
u
ch
a
s
atten
d
a
n
ce
,
ass
i
g
n
m
e
n
t
s
u
b
m
i
s
s
io
n
p
atter
n
s
,
an
d
en
g
a
g
e
m
en
t
le
v
els.
T
h
is
w
o
r
k
r
ein
f
o
r
ce
d
th
e
n
e
ed
f
o
r
tr
an
s
p
ar
en
t
p
r
ed
ictiv
e
s
y
s
te
m
s
i
n
ed
u
ca
tio
n
al
d
ec
is
io
n
-
m
a
k
in
g
.
eXtr
e
m
e
g
r
ad
ien
t
b
o
o
s
ti
n
g
(
XGB
o
o
s
t)
h
as
e
m
er
g
ed
as
a
p
ar
ticu
lar
l
y
s
tr
o
n
g
al
g
o
r
ith
m
f
o
r
s
t
u
d
en
t
p
er
f
o
r
m
a
n
ce
p
r
ed
ictio
n
.
Ass
el
m
a
n
et
a
l
.
[
2
]
d
em
o
n
s
tr
ate
d
th
at
XGB
o
o
s
t
o
u
tp
er
f
o
r
m
e
d
s
ev
er
al
b
aselin
e
class
i
f
ier
s
in
p
r
ed
icti
n
g
s
t
u
d
en
t
r
es
u
lt
s
b
y
e
f
f
icie
n
tl
y
h
an
d
lin
g
n
o
n
li
n
ea
r
r
elatio
n
s
h
ip
s
an
d
m
is
s
in
g
d
ata
.
Si
m
i
lar
l
y
,
C
h
en
g
et
a
l
.
[
5
]
p
r
o
p
o
s
ed
a
h
y
b
r
id
f
r
am
e
w
o
r
k
th
at
co
m
b
i
n
ed
XGB
o
o
s
t
w
ith
a
n
ad
ap
tiv
e
ev
o
lu
tio
n
ar
y
o
p
tim
izatio
n
s
tr
ate
g
y
,
ac
h
ie
v
i
n
g
i
m
p
r
o
v
ed
p
r
ed
ictio
n
ac
c
u
r
ac
y
i
n
ac
ad
e
m
ic
p
er
f
o
r
m
a
n
ce
ev
al
u
atio
n
.
T
h
ese
s
tu
d
ie
s
in
d
icate
t
h
at
b
o
o
s
ti
ng
-
b
a
s
ed
m
o
d
els
ar
e
w
e
ll
s
u
ited
f
o
r
ed
u
ca
tio
n
al
d
ataset
s
,
w
h
ich
ar
e
o
f
te
n
h
eter
o
g
e
n
eo
u
s
a
n
d
h
i
g
h
d
i
m
e
n
s
io
n
al.
E
ar
ly
p
r
ed
ictio
n
o
f
s
t
u
d
en
t
o
u
tco
m
e
s
h
as
a
ls
o
b
ee
n
a
f
o
c
u
s
in
s
p
ec
ialized
ed
u
ca
t
io
n
al
d
o
m
a
in
s
.
Ma
s
to
u
r
et
a
l
.
[
9
]
a
p
p
lied
m
ac
h
in
e
lear
n
i
n
g
m
et
h
o
d
s
to
p
r
ed
ict
m
ed
ic
al
s
t
u
d
en
t
s
’
p
er
f
o
r
m
an
ce
in
h
ig
h
-
s
ta
k
es
ex
a
m
in
at
io
n
s
.
T
h
eir
r
esu
lt
s
s
h
o
w
ed
th
at
m
o
d
el
s
s
u
c
h
as
RF
,
SVM
,
an
d
n
eu
r
al
n
et
w
o
r
k
s
c
o
u
ld
id
en
tify
at
-
r
is
k
s
tu
d
e
n
ts
w
ell
b
e
f
o
r
e
f
i
n
al
a
s
s
ess
m
e
n
ts
,
allo
w
in
g
ti
m
el
y
a
ca
d
em
ic
s
u
p
p
o
r
t.
T
h
is
h
i
g
h
li
g
h
t
s
t
h
e
p
r
ac
tical
i
m
p
o
r
tan
ce
o
f
p
r
ed
ictiv
e
a
n
al
y
tics
in
r
ed
u
ci
n
g
f
a
ilu
r
e
r
ates a
n
d
i
m
p
r
o
v
i
n
g
lear
n
i
n
g
s
u
cc
e
s
s
.
B
ey
o
n
d
s
tr
u
ct
u
r
ed
ac
ad
em
ic
r
ec
o
r
d
s
,
s
ev
er
al
s
tu
d
ies
h
a
v
e
ex
p
lo
r
ed
alter
n
ativ
e
d
ata
s
o
u
r
ce
s
f
o
r
u
n
d
er
s
ta
n
d
in
g
s
tu
d
e
n
t
b
eh
av
io
r
.
Z
h
ao
et
a
l
.
[
1
2
]
d
ev
elo
p
ed
Stu
d
en
tl
y
ze
r
,
a
s
y
s
te
m
f
o
r
an
al
y
z
in
g
a
n
d
v
i
s
u
al
izin
g
e
-
lear
n
i
n
g
d
ata,
en
ab
lin
g
ed
u
ca
to
r
s
to
o
b
s
er
v
e
tr
en
d
s
i
n
s
t
u
d
en
t
e
n
g
a
g
e
m
en
t
an
d
ac
tiv
i
t
y
.
W
an
g
et
a
l
.
[
1
0
]
in
tr
o
d
u
ce
d
th
e
Stu
d
en
t
L
if
e
d
ata
s
et,
w
h
ich
u
s
es
s
m
ar
tp
h
o
n
e
s
e
n
s
o
r
d
ata
to
ass
es
s
m
en
tal
h
ea
lt
h
an
d
ac
ad
em
ic
p
er
f
o
r
m
an
ce
,
r
ev
ea
li
n
g
t
h
at
li
f
est
y
le
p
atter
n
s
s
tr
o
n
g
l
y
in
f
l
u
en
ce
lear
n
in
g
o
u
tc
o
m
e
s
.
E
ar
lier
w
o
r
k
b
y
Fire
et
a
l
.
[
2
0
]
s
h
o
w
ed
t
h
a
t
s
o
cial
n
et
w
o
r
k
d
ata
co
u
ld
b
e
u
s
ed
to
p
r
ed
ict
ex
a
m
s
co
r
es,
d
em
o
n
s
tr
ati
n
g
t
h
at
p
ee
r
in
ter
ac
tio
n
s
a
n
d
o
n
lin
e
ac
tiv
it
y
ca
n
p
r
o
v
id
e
m
ea
n
i
n
g
f
u
l
in
d
icato
r
s
o
f
ac
ad
e
m
ic
p
er
f
o
r
m
an
ce
.
Neu
r
al
n
e
t
w
o
r
k
–
b
ased
ap
p
r
o
ac
h
es
h
a
v
e
al
s
o
b
ee
n
ex
ten
s
i
v
el
y
s
tu
d
ied
i
n
o
n
li
n
e
lear
n
in
g
en
v
ir
o
n
m
e
n
t
s
.
Ay
d
o
ğ
d
u
[
3
]
ap
p
lied
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
s
to
p
r
ed
ict
s
tu
d
en
t
f
i
n
al
p
er
f
o
r
m
an
ce
i
n
e
-
lear
n
i
n
g
p
latf
o
r
m
s
an
d
s
h
o
w
ed
th
a
t
n
eu
r
al
m
o
d
els
co
u
ld
ca
p
tu
r
e
c
o
m
p
le
x
lear
n
i
n
g
b
eh
a
v
io
r
s
m
o
r
e
ef
f
ec
tiv
el
y
th
a
n
tr
ad
iti
o
n
al
s
tatis
t
ical
m
et
h
o
d
s
.
T
h
ese
f
in
d
i
n
g
s
s
u
p
p
o
r
t
th
e
u
s
e
o
f
d
ee
p
lear
n
in
g
ar
ch
itect
u
r
es
f
o
r
m
o
d
elin
g
th
e
n
o
n
li
n
ea
r
d
y
n
a
m
ics o
f
s
tu
d
e
n
t
en
g
a
g
e
m
en
t.
3.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
c
o
m
p
lete
m
eth
o
d
o
lo
g
ical
f
r
a
m
e
w
o
r
k
ad
o
p
ted
f
o
r
p
r
e
d
ictin
g
s
t
u
d
en
t
ac
ad
em
ic
p
er
f
o
r
m
an
ce
u
s
in
g
t
h
e
e
-
lear
n
i
n
g
s
tu
d
e
n
t
r
ea
ctio
n
s
d
ataset
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
is
d
esi
g
n
ed
to
en
s
u
r
e
r
o
b
u
s
tn
e
s
s
,
f
air
n
ess
,
an
d
g
en
er
aliza
b
ilit
y
b
y
co
m
b
i
n
i
n
g
s
y
s
te
m
a
tic
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
co
m
p
r
e
h
en
s
iv
e
f
ea
t
u
r
e
en
g
i
n
ee
r
in
g
,
m
u
lt
ip
le
m
ac
h
in
e
lea
r
n
in
g
an
d
d
ee
p
lear
n
in
g
m
o
d
els,
an
d
r
ig
o
r
o
u
s
v
alid
atio
n
s
tr
ateg
ie
s
.
3
.
1
.
Da
t
a
s
et
d
escript
io
n
T
h
e
e
-
lear
n
in
g
s
t
u
d
en
t
r
ea
ctio
n
s
d
ataset
co
n
tai
n
s
i
n
ter
ac
tio
n
-
le
v
el
r
ec
o
r
d
s
co
llected
f
r
o
m
an
o
n
li
n
e
lear
n
in
g
p
lat
f
o
r
m
.
E
ac
h
i
n
s
ta
n
ce
r
ep
r
esen
ts
a
lear
n
er
’
s
ac
ti
v
i
t
y
an
d
i
n
clu
d
e
s
f
ea
t
u
r
es s
u
c
h
a
s
:
−
T
im
e
s
p
en
t o
n
lear
n
i
n
g
m
ater
i
als
−
Fre
q
u
en
c
y
o
f
lo
g
i
n
s
−
Qu
iz
an
d
a
s
s
i
g
n
m
e
n
t r
esp
o
n
s
e
p
atter
n
s
−
Stu
d
e
n
t r
ea
ctio
n
s
to
co
n
te
n
t
−
E
n
g
a
g
e
m
en
t in
d
icato
r
s
T
h
e
tar
g
et
v
ar
iab
le
r
ep
r
esen
t
s
t
h
e
s
t
u
d
en
t’
s
ac
ad
e
m
ic
r
esu
lt,
w
h
ic
h
is
co
n
v
er
ted
in
to
ca
te
g
o
r
ical
lab
els
f
o
r
class
i
f
icatio
n
(
e.
g
.
,
p
ass
/
f
ai
l o
r
p
er
f
o
r
m
an
ce
g
r
ad
e
).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
259
-
2
6
8
262
L
et
t
h
e
d
at
aset b
e
d
en
o
ted
as:
=
{
(
,
)
}
=
1
w
h
er
e
=
[
1
,
2
,
.
.
.
,
]
r
ep
r
esen
ts
th
e
f
ea
t
u
r
e
v
ec
to
r
o
f
s
t
u
d
en
t
I
,
r
ep
r
esen
t
s
th
e
ac
ad
e
m
ic
o
u
tco
m
e
lab
el
,
N
is
th
e
to
tal
n
u
m
b
er
o
f
s
tu
d
e
n
t
in
s
tan
ce
s
(
4
,
8
5
0
u
n
i
q
u
e
s
tu
d
en
ts
)
,
an
d
D
is
th
e
n
u
m
b
er
o
f
ex
tr
ac
ted
f
ea
t
u
r
es.
3
.
2
.
Da
t
a
p
re
pro
ce
s
s
ing
R
a
w
e
-
lear
n
in
g
d
atase
ts
o
f
te
n
co
n
tain
m
is
s
in
g
v
al
u
es,
n
o
is
e,
an
d
f
ea
t
u
r
es
w
i
th
h
eter
o
g
e
n
e
o
u
s
s
ca
les,
w
h
ic
h
ca
n
n
eg
a
tiv
e
l
y
a
f
f
ec
t
t
h
e
lear
n
i
n
g
p
er
f
o
r
m
a
n
ce
o
f
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els.
T
h
er
ef
o
r
e,
ap
p
r
o
p
r
iate
p
r
ep
r
o
ce
s
s
in
g
is
ess
e
n
tial
to
en
s
u
r
e
d
ata
q
u
alit
y
,
m
o
d
el
co
n
v
er
g
e
n
ce
,
an
d
r
eliab
le
p
r
e
d
ictio
n
s
.
T
h
e
f
o
llo
w
i
n
g
s
tep
s
ar
e
a
p
p
lied
,
alo
n
g
w
i
th
t
h
eir
r
atio
n
ale
,
an
d
ex
p
ec
ted
i
m
p
ac
t o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
3
.
2
.
1
.
M
is
s
ing
v
a
lue i
m
pu
t
a
t
io
n
Miss
i
n
g
v
al
u
es a
r
e
r
ep
lace
d
u
s
in
g
m
ea
n
o
r
KNN
i
m
p
u
tatio
n
:
=
{
1
∑
,
∈
(
)
,
ℎ
w
h
er
e
(
)
th
e
s
et
o
f
k
n
ea
r
est
n
ei
g
h
b
o
r
s
f
o
r
f
ea
tu
r
e
.
R
atio
n
ale
:
−
Me
an
i
m
p
u
tatio
n
p
r
o
v
id
es
a
s
i
m
p
le
esti
m
ate
th
at
r
ed
u
ce
s
th
e
im
p
ac
t
o
f
m
i
s
s
i
n
g
v
al
u
es
o
n
g
lo
b
al
f
ea
tu
r
e
d
is
tr
ib
u
tio
n
s
.
−
KNN
i
m
p
u
tatio
n
p
r
eser
v
e
s
lo
ca
l p
atter
n
s
b
y
r
ep
lacin
g
m
is
s
i
n
g
v
al
u
es
w
it
h
av
er
a
g
es
f
r
o
m
s
i
m
ilar
s
t
u
d
en
t
s
,
m
ai
n
tai
n
in
g
b
eh
a
v
io
r
al
co
r
r
elatio
n
s
i
n
en
g
a
g
e
m
e
n
t d
ata.
I
m
p
ac
t o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
:
−
I
m
p
u
tatio
n
p
r
ev
en
t
s
lo
s
s
o
f
d
ata
d
u
e
to
m
is
s
in
g
v
alu
e
s
,
i
m
p
r
o
v
in
g
s
tat
is
tical
p
o
w
er
.
−
KNN
-
b
ased
i
m
p
u
tatio
n
allo
w
s
m
o
d
els
to
ca
p
t
u
r
e
co
n
te
x
tu
a
l
p
atter
n
s
i
n
s
tu
d
e
n
t
b
eh
a
v
io
r
,
w
h
ic
h
e
n
h
a
n
ce
s
p
r
ed
ictio
n
ac
cu
r
ac
y
,
p
ar
ticu
lar
l
y
f
o
r
lear
n
er
s
w
i
th
p
ar
tiall
y
o
b
s
er
v
ed
in
ter
ac
tio
n
h
is
to
r
ies.
3
.
2
.
2
.
F
ea
t
ure
n
o
rm
a
liza
t
io
n
T
o
av
o
id
b
ias f
r
o
m
d
i
f
f
er
en
t
n
u
m
er
ic
s
ca
les,
m
i
n
–
m
a
x
n
o
r
m
aliza
ti
o
n
is
ap
p
lied
:
′
=
−
−
T
h
is
en
s
u
r
es a
ll
f
ea
tu
r
e
s
lie
b
et
w
ee
n
0
an
d
1
.
R
atio
n
ale
:
−
E
n
s
u
r
es
th
at
all
f
ea
tu
r
e
s
co
n
tr
i
b
u
te
eq
u
all
y
to
d
is
tan
ce
-
b
ased
m
o
d
el
s
(
lik
e
KNN)
an
d
g
r
ad
ie
n
t
-
b
ased
m
o
d
els
(
lik
e
DNN
o
r
m
u
lti
la
y
er
p
er
ce
p
t
r
o
n
(
ML
P
)
.
−
P
r
ev
en
ts
f
ea
t
u
r
es
w
it
h
lar
g
e
n
u
m
er
ical
r
an
g
es
f
r
o
m
d
o
m
i
n
ati
n
g
lear
n
in
g
d
y
n
a
m
ics,
wh
ich
ca
n
lead
to
s
u
b
o
p
ti
m
al
d
ec
is
io
n
b
o
u
n
d
ar
ie
s
.
I
m
p
ac
t o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
:
−
I
m
p
r
o
v
es c
o
n
v
er
g
e
n
ce
s
p
ee
d
in
g
r
ad
ien
t
-
b
ased
o
p
ti
m
izer
s
.
−
E
n
h
a
n
ce
s
p
r
ed
ictio
n
s
tab
ilit
y
a
n
d
g
e
n
er
aliza
tio
n
,
e
s
p
ec
iall
y
w
h
e
n
m
o
d
els
i
n
te
g
r
ate
m
u
lt
ip
le
h
eter
o
g
e
n
eo
u
s
f
ea
t
u
r
es (
e.
g
.
,
ti
m
e
s
p
en
t,
n
u
m
b
er
o
f
click
s
,
an
d
q
u
iz
s
co
r
es).
3
.
3
.
F
e
a
t
ure
v
ec
t
o
r
co
ns
t
ruct
io
n
T
h
e
clea
n
ed
d
ataset
is
co
n
v
er
t
ed
in
to
a
n
u
m
er
ical
f
ea
tu
r
e
m
a
tr
ix
:
=
[
11
12
…
…
.
.
1
21
22
…
…
.
.
2
.
.
…
…
.
.
…
.
.
.
…
…
.
.
.
1
2
…
…
.
.
]
an
d
o
u
tp
u
t
v
ec
to
r
:
=
[
1
,
2
,
.
.
.
,
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
P
r
ed
ictin
g
s
tu
d
en
t a
ca
d
emic
o
u
tco
mes fro
m
e
-
lea
r
n
in
g
in
tera
ctio
n
d
a
ta
u
s
in
g
…
(
S
a
jith
u
n
i
s
a
Hu
s
s
a
in
)
263
R
atio
n
ale
:
−
Stru
ct
u
r
in
g
th
e
d
ataset
in
to
X
an
d
Y
allo
w
s
m
ac
h
i
n
e
l
ea
r
n
in
g
m
o
d
els
to
ef
f
icie
n
tl
y
lear
n
p
atter
n
s
b
et
w
ee
n
s
tu
d
e
n
t b
eh
a
v
io
r
s
an
d
o
u
tco
m
es.
−
Facilitate
s
s
ca
lab
le
tr
ain
i
n
g
ac
r
o
s
s
d
if
f
er
e
n
t a
l
g
o
r
ith
m
s
(
KN
N,
DT
,
SVM,
an
d
DNN)
.
I
m
p
ac
t o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
:
−
P
r
o
p
er
f
ea
tu
r
e
co
n
s
tr
u
ctio
n
en
s
u
r
es
t
h
at
b
eh
av
io
r
al
n
u
a
n
ce
s
(
e.
g
.
,
co
n
s
is
te
n
c
y
i
n
lo
g
i
n
,
q
u
i
z
p
er
f
o
r
m
a
n
ce
,
an
d
co
n
ten
t e
n
g
ag
e
m
e
n
t)
ar
e
ca
p
tu
r
ed
in
th
e
m
o
d
el
in
p
u
t.
−
I
m
p
r
o
v
es
p
r
ed
ictiv
e
ac
cu
r
ac
y
a
n
d
in
ter
p
r
etab
ilit
y
,
as
m
o
d
els
ca
n
d
ir
ec
tl
y
m
ap
s
tr
u
ctu
r
ed
in
p
u
t
s
to
p
er
f
o
r
m
a
n
ce
o
u
tco
m
es.
3.
4
.
Cla
s
s
if
ica
t
io
n
m
o
de
ls
T
h
e
class
i
f
icatio
n
la
y
er
i
s
th
e
co
r
e
an
al
y
tical
co
m
p
o
n
e
n
t
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
e
n
t
p
er
f
o
r
m
an
c
e
p
r
ed
ictio
n
f
r
a
m
e
w
o
r
k
,
as it tr
an
s
f
o
r
m
s
m
u
ltid
i
m
en
s
io
n
al
e
-
le
ar
n
in
g
in
ter
ac
tio
n
d
ata
in
to
m
ea
n
in
g
f
u
l a
ca
d
e
m
ic
o
u
tco
m
e
p
r
ed
ictio
n
s
.
T
h
e
ei
g
h
t
clas
s
i
f
ier
s
e
m
p
lo
y
ed
i
n
t
h
is
s
tu
d
y
r
ep
r
esen
t
f
u
n
d
a
m
e
n
tall
y
d
if
f
er
e
n
t
lear
n
i
n
g
p
h
ilo
s
o
p
h
ies,
allo
w
i
n
g
th
e
s
y
s
te
m
to
ca
p
tu
r
e
b
o
th
s
i
m
p
le
b
eh
av
io
r
al
s
i
m
i
lar
ities
a
n
d
h
i
g
h
l
y
co
m
p
lex
n
o
n
l
in
ea
r
p
atter
n
s
in
s
tu
d
e
n
t
en
g
a
g
e
m
e
n
t.
E
ac
h
m
o
d
el
lear
n
s
a
m
ap
p
i
n
g
f
r
o
m
t
h
e
i
n
p
u
t
f
ea
tu
r
e
s
p
ac
e
∈
to
a
d
is
cr
ete
o
u
tco
m
e
lab
el
∈
{
1
,
2
,
…
,
}
,
w
h
er
e
ea
ch
f
ea
tu
r
e
co
r
r
esp
o
n
d
s
to
a
m
ea
s
u
r
ab
le
asp
ec
t
o
f
lear
n
er
b
eh
av
io
r
,
s
u
c
h
as a
cti
v
it
y
f
r
eq
u
e
n
c
y
,
r
ea
ctio
n
p
atter
n
s
,
o
r
ass
es
s
m
en
t p
er
f
o
r
m
an
ce
.
KNN
p
er
f
o
r
m
s
clas
s
i
f
icatio
n
b
y
m
ea
s
u
r
in
g
s
i
m
ilar
it
y
b
etw
ee
n
lear
n
er
s
i
n
th
e
f
ea
tu
r
e
s
p
ac
e.
T
h
e
E
u
clid
ea
n
d
is
ta
n
ce
q
u
an
ti
f
ie
s
h
o
w
s
i
m
i
lar
t
w
o
s
tu
d
e
n
ts
an
d
ar
e
b
ased
o
n
th
eir
in
ter
ac
tio
n
p
r
o
f
iles
.
T
h
e
p
r
ed
icted
class
o
f
a
n
e
w
s
t
u
d
en
t is o
b
tain
ed
b
y
a
m
aj
o
r
ity
v
o
te
a
m
o
n
g
its
k
clo
s
es
t n
ei
g
h
b
o
r
s
:
(
,
)
=
√
∑
(
,
)
2
=
1
̂
=
(
1
,
2
,
…
,
T
h
is
f
o
r
m
u
lat
io
n
allo
w
s
KN
N
to
id
en
ti
f
y
g
r
o
u
p
s
o
f
lear
n
er
s
w
i
th
s
i
m
ilar
e
n
g
ag
e
m
e
n
t
p
atter
n
s
,
ass
u
m
in
g
t
h
at
s
tu
d
e
n
ts
w
h
o
i
n
ter
ac
t
w
i
th
lear
n
i
n
g
m
a
ter
ials
in
co
m
p
ar
ab
le
w
a
y
s
ar
e
li
k
el
y
to
ac
h
ie
v
e
s
i
m
ilar
o
u
tco
m
es.
KNN
i
s
p
ar
tic
u
lar
l
y
e
f
f
ec
tiv
e
in
e
-
lear
n
i
n
g
en
v
i
r
o
n
m
e
n
ts
w
h
er
e
s
t
u
d
en
t
b
eh
a
v
io
r
n
atu
r
all
y
f
o
r
m
s
clu
s
ter
s
,
s
u
c
h
as
co
n
s
i
s
ten
t
lear
n
er
s
,
ir
r
eg
u
lar
p
ar
ticip
an
ts
,
a
n
d
h
ig
h
l
y
ac
tiv
e
s
t
u
d
en
ts
.
DT
class
i
f
y
s
tu
d
e
n
ts
b
y
r
ec
u
r
s
iv
e
l
y
p
ar
titi
o
n
in
g
t
h
e
f
e
atu
r
e
s
p
ac
e
u
s
in
g
attr
ib
u
te
s
t
h
at
m
ax
i
m
ize
in
f
o
r
m
at
io
n
g
a
in
.
(
,
)
=
(
)
−
∑
|
|
|
|
(
)
∈
W
h
er
e
(
)
is
th
e
e
n
tr
o
p
y
o
f
t
h
e
cu
r
r
en
t
d
ataset
(
to
tal
u
n
ce
r
tai
n
t
y
)
a
n
d
is
th
e
s
u
b
s
et
o
f
S
w
h
er
e
f
ea
tu
r
e
A
h
as
v
alu
e
.
W
h
er
e
en
tr
o
p
y
m
ea
s
u
r
es t
h
e
u
n
ce
r
tain
t
y
i
n
s
t
u
d
en
t o
u
tco
m
e
lab
els.
is
th
e
p
r
o
b
ab
ilit
y
o
f
class
iii i
n
th
e
d
ataset
.
(
)
=
−
∑
l
og
2
(
)
)
I
n
ed
u
ca
tio
n
al
d
ata,
th
i
s
m
ea
n
s
th
at
attr
ib
u
tes
s
u
ch
as
q
u
iz
s
co
r
es,
co
n
ten
t
v
ie
w
in
g
ti
m
e,
o
r
r
ea
ctio
n
m
etr
ics
ar
e
s
e
lecte
d
to
b
est
s
ep
ar
ate
h
ig
h
-
an
d
lo
w
-
p
er
f
o
r
m
i
n
g
s
t
u
d
en
t
s
.
DT
c
r
ea
te
in
ter
p
r
etab
le
r
u
les,
s
u
ch
as
“
i
f
en
g
ag
e
m
e
n
t
ti
m
e
is
h
i
g
h
a
n
d
q
u
iz
ac
cu
r
ac
y
ex
ce
ed
s
a
th
r
esh
o
ld
,
th
en
p
er
f
o
r
m
a
n
ce
is
li
k
el
y
g
o
o
d
,
”
m
ak
in
g
th
e
m
u
s
e
f
u
l
f
o
r
ac
ad
e
m
ic
s
ta
k
eh
o
ld
er
s
.
Ho
w
e
v
er
,
s
i
n
g
le
tr
ee
s
m
a
y
o
v
er
f
it,
e
s
p
ec
iall
y
w
h
e
n
b
eh
av
io
r
al
d
ata
ar
e
n
o
is
y
.
SVM
ad
d
r
ess
th
is
b
y
f
in
d
i
n
g
th
e
o
p
tim
a
l
d
ec
is
io
n
b
o
u
n
d
a
r
y
t
h
at
m
a
x
i
m
ize
s
th
e
m
ar
g
i
n
b
et
w
ee
n
s
tu
d
e
n
t c
las
s
es.
T
h
is
is
ac
h
ie
v
ed
b
y
m
in
i
m
iz
in
g
:
1
2
|
|
|
|
2
+
∑
s
u
b
j
ec
t to
:
(
⋅
+
)
≥
1
−
∥
∥
2
/
2
r
ep
r
esen
ts
th
e
m
ar
g
in
w
id
t
h
(
s
m
al
ler
∥
w
∥
→
lar
g
er
m
ar
g
i
n
)
.
ar
e
s
lack
v
ar
iab
les allo
w
i
n
g
s
o
m
e
m
i
s
clas
s
i
f
icatio
n
s
to
h
a
n
d
le
o
v
er
lap
p
in
g
b
eh
a
v
io
r
p
atter
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
259
-
2
6
8
264
3.
5
.
A
s
i
m
ple
d
ee
p
n
eura
l
n
e
t
w
o
rk
T
h
e
DNN
u
s
ed
in
th
is
s
t
u
d
y
is
d
elib
er
ately
d
esi
g
n
ed
as
a
co
m
p
ac
t
y
et
ex
p
r
ess
iv
e
ar
ch
itec
tu
r
e
to
m
o
d
el
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
s
t
u
d
en
t
i
n
ter
ac
tio
n
b
e
h
av
io
r
an
d
ac
ad
em
ic
p
er
f
o
r
m
a
n
ce
.
T
h
e
n
et
w
o
r
k
f
o
llo
w
s
a
s
eq
u
en
tial
s
tr
u
ct
u
r
e
co
m
p
o
s
e
d
o
f
t
h
r
ee
f
u
ll
y
co
n
n
ec
ted
l
a
y
er
s
w
i
th
o
u
tp
u
t
d
i
m
en
s
io
n
s
o
f
1
8
,
9
,
an
d
1
,
r
esp
ec
tiv
el
y
.
T
h
is
p
r
o
g
r
es
s
i
v
e
r
ed
u
ctio
n
in
la
y
er
s
ize
e
n
ab
les
th
e
n
et
w
o
r
k
to
lear
n
h
ier
ar
ch
ical
ab
s
tr
ac
tio
n
s
,
w
h
er
e
lo
w
-
lev
el
b
e
h
av
io
r
al
s
i
g
n
al
s
ar
e
g
r
ad
u
a
ll
y
tr
an
s
f
o
r
m
ed
in
to
h
i
g
h
-
le
v
el
r
ep
r
esen
tati
o
n
s
t
h
at
ar
e
d
ir
ec
tl
y
lin
k
ed
to
s
tu
d
en
t o
u
tco
m
e
s
.
T
h
e
f
ir
s
t
d
en
s
e
la
y
er
,
w
h
ic
h
co
n
tain
s
1
8
n
eu
r
o
n
s
a
n
d
1
8
0
p
ar
a
m
eter
s
,
s
er
v
e
s
as
th
e
p
r
i
m
a
r
y
f
ea
t
u
r
e
tr
an
s
f
o
r
m
atio
n
s
tag
e.
I
t
r
ec
ei
v
es
n
o
r
m
alize
d
i
n
p
u
t
f
ea
t
u
r
es
r
ep
r
esen
tin
g
s
t
u
d
en
t
s
’
en
g
a
g
e
m
en
t,
r
ea
ctio
n
s
,
an
d
in
ter
a
ctio
n
p
atter
n
s
w
it
h
in
t
h
e
e
-
lear
n
i
n
g
s
y
s
te
m
.
T
h
r
o
u
g
h
weig
h
ted
lin
ea
r
co
m
b
in
at
io
n
s
f
o
llo
w
ed
b
y
n
o
n
lin
ea
r
ac
tiv
atio
n
,
th
is
la
y
er
ca
p
tu
r
es
f
u
n
d
a
m
en
tal
lear
n
i
n
g
b
eh
a
v
io
r
s
s
u
c
h
as
co
n
s
i
s
te
n
c
y
o
f
p
ar
tic
ip
atio
n
,
in
te
n
s
it
y
o
f
co
n
ten
t
i
n
ter
ac
tio
n
,
an
d
r
esp
o
n
s
iv
e
n
es
s
to
ass
ess
m
e
n
t
s
.
B
y
ex
p
an
d
in
g
t
h
e
f
ea
t
u
r
e
s
p
ac
e
in
to
an
1
8
-
d
i
m
e
n
s
io
n
al
laten
t r
ep
r
esen
tat
io
n
,
th
e
n
et
wo
r
k
g
ain
s
t
h
e
f
le
x
ib
ilit
y
n
ee
d
ed
to
m
o
d
el
s
u
b
tle
v
ar
iatio
n
s
i
n
s
tu
d
en
t b
eh
av
io
r
.
T
h
e
s
ec
o
n
d
d
en
s
e
la
y
er
r
ed
u
ce
s
t
h
is
r
ep
r
ese
n
tatio
n
to
9
n
eu
r
o
n
s
u
s
in
g
1
7
1
p
ar
a
m
eter
s
.
T
h
i
s
l
a
y
er
p
la
y
s
a
cr
itical
r
o
le
in
co
n
s
o
lid
atin
g
an
d
r
e
f
in
i
n
g
t
h
e
ex
tr
ac
ted
p
atter
n
s
.
I
t
lear
n
s
i
n
ter
ac
tio
n
s
b
et
w
ee
n
b
eh
a
v
io
r
al
f
ac
to
r
s
,
s
u
c
h
as
h
o
w
s
u
s
tai
n
e
d
en
g
ag
e
m
e
n
t
co
m
b
in
ed
w
it
h
ass
es
s
m
en
t
ac
c
u
r
ac
y
in
f
l
u
e
n
c
es
lear
n
in
g
s
u
cc
ess
.
T
h
is
d
im
e
n
s
io
n
alit
y
r
ed
u
ctio
n
also
s
u
p
p
r
ess
es
n
o
is
e
a
n
d
r
ed
u
n
d
an
t
i
n
f
o
r
m
atio
n
,
i
m
p
r
o
v
i
n
g
t
h
e
s
tab
ilit
y
an
d
g
en
er
aliza
tio
n
o
f
t
h
e
m
o
d
el.
T
h
e
f
in
al
d
en
s
e
la
y
er
co
n
s
is
t
s
o
f
a
s
in
g
le
n
e
u
r
o
n
w
i
th
1
0
p
ar
am
eter
s
,
w
h
ic
h
p
r
o
d
u
ce
s
th
e
o
u
tp
u
t
p
r
ed
ictio
n
.
I
n
class
if
icatio
n
m
o
d
e,
th
is
n
eu
r
o
n
o
u
tp
u
t
s
a
p
r
o
b
ab
ilit
y
s
co
r
e
in
d
icatin
g
th
e
li
k
eli
h
o
o
d
o
f
a
s
tu
d
en
t
b
elo
n
g
i
n
g
to
a
p
ar
ticu
lar
p
er
f
o
r
m
an
ce
ca
te
g
o
r
y
.
T
h
e
u
s
e
o
f
a
s
ig
m
o
id
o
r
So
f
tMa
x
ac
ti
v
atio
n
f
u
n
ctio
n
en
s
u
r
e
s
th
at
t
h
e
o
u
tp
u
t c
a
n
b
e
in
ter
p
r
et
ed
in
p
r
o
b
ab
ilis
tic
ter
m
s
,
f
ac
il
i
tatin
g
d
ec
is
io
n
-
m
a
k
in
g
i
n
ed
u
ca
tio
n
al
co
n
te
x
ts
.
3.
5
.
1
.
M
o
del t
r
a
ini
ng
,
t
esting
,
a
nd
K
-
f
o
ld cr
o
s
s
-
v
a
lid
a
t
io
n
T
h
e
tr
ain
in
g
p
h
ase
in
v
o
l
v
es
le
ar
n
in
g
th
e
m
ap
p
in
g
f
u
n
ctio
n
f
:
X→Y
f
r
o
m
t
h
e
in
p
u
t
f
ea
tu
r
e
s
p
ac
e
X
to
th
e
o
u
tp
u
t
lab
el
s
p
ac
e
Y
u
s
i
n
g
a
s
u
b
s
et
o
f
th
e
d
a
taset.
Du
r
i
n
g
th
i
s
p
h
ase,
th
e
m
o
d
el
p
ar
am
eter
s
—
w
ei
g
h
t
s
an
d
b
iases
i
n
n
e
u
r
al
n
et
w
o
r
k
s
o
r
s
p
lit
cr
iter
ia
in
tr
ee
-
b
ased
m
o
d
els
—
ar
e
o
p
ti
m
ized
to
m
i
n
i
m
i
ze
a
p
r
ed
ef
in
ed
lo
s
s
f
u
n
ctio
n
(
)
,
s
u
ch
as c
r
o
s
s
-
e
n
tr
o
p
y
f
o
r
clas
s
if
icatio
n
:
(
)
=
−
∑
(
̂
)
=
1
w
h
er
e
is
t
h
e
n
u
m
b
er
o
f
tr
ai
n
i
n
g
s
a
m
p
le
s
,
is
th
e
tr
u
e
lab
el,
an
d
̂
is
th
e
p
r
ed
icted
p
r
o
b
ab
ilit
y
.
On
ce
t
h
e
m
o
d
el
i
s
tr
ai
n
ed
,
its
p
er
f
o
r
m
a
n
ce
is
e
v
al
u
ated
o
n
t
h
e
te
s
ti
n
g
s
et,
w
h
ic
h
w
a
s
n
o
t
u
s
ed
d
u
r
i
n
g
tr
ain
i
n
g
.
T
h
is
s
tep
p
r
o
v
id
es a
n
u
n
b
iased
est
i
m
a
te
o
f
m
o
d
el
g
en
er
aliza
tio
n
.
T
h
e
test
ac
c
u
r
ac
y
is
ca
lc
u
lated
as:
=
I
n
th
i
s
s
tu
d
y
,
an
8
0
–
2
0
h
o
ld
-
o
u
t
s
p
lit
is
u
s
ed
,
w
h
er
e
8
0
%
o
f
t
h
e
d
ata
is
al
lo
ca
ted
to
tr
ain
i
n
g
an
d
2
0
%
to
test
i
n
g
.
T
h
is
d
iv
is
io
n
en
s
u
r
es
th
at
m
o
d
els
lear
n
s
u
f
f
icien
t
p
atter
n
s
w
h
ile
leav
in
g
en
o
u
g
h
s
a
m
p
le
s
f
o
r
an
in
d
ep
en
d
en
t
ev
alu
a
tio
n
.
3.
5
.
2
.
T
a
rg
et
v
a
ria
ble (
o
utp
ut
la
bels
)
T
h
e
ac
ad
em
ic
o
u
tco
m
e
i
s
r
ep
r
esen
ted
as
a
ca
teg
o
r
ical
lab
el,
tr
an
s
f
o
r
m
ed
f
r
o
m
r
a
w
f
i
n
al
co
u
r
s
e
p
er
f
o
r
m
a
n
ce
.
T
w
o
v
ar
ia
n
ts
o
f
th
e
tar
g
et
ar
e
u
s
ed
d
ep
en
d
in
g
o
n
th
e
m
o
d
eli
n
g
tas
k
:
−
B
in
ar
y
lab
el:
∈
{
,
}
w
h
er
e
a
s
t
u
d
en
t is lab
eled
P
a
s
s
if
t
h
e
f
in
al
g
r
ad
e
≥
th
r
esh
o
ld
(
e.
g
.
,
5
0
%),
else
F
a
il
.
−
Mu
lti
-
cla
s
s
g
r
ad
es:
_
∈
{
,
,
,
,
}
M
ap
p
ed
f
r
o
m
s
co
r
e
r
an
g
es
u
s
i
n
g
i
n
s
tit
u
tio
n
al
g
r
ad
in
g
cr
iter
i
a
.
T
h
e
d
ataset
u
s
ed
f
o
r
clas
s
if
i
ca
tio
n
ex
p
er
i
m
en
t
s
in
th
is
m
an
u
s
cr
ip
t e
m
p
lo
y
s
t
h
e
b
in
ar
y
p
ass
/
f
ail
lab
el
u
n
le
s
s
o
th
er
w
is
e
s
tated
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
P
r
ed
ictin
g
s
tu
d
en
t a
ca
d
emic
o
u
tco
mes fro
m
e
-
lea
r
n
in
g
in
tera
ctio
n
d
a
ta
u
s
in
g
…
(
S
a
jith
u
n
i
s
a
Hu
s
s
a
in
)
265
4.
RE
SU
L
T
S
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
p
r
o
p
o
s
ed
s
i
m
p
le
D
NN
w
as
e
v
al
u
ate
d
o
v
er
1
0
0
tr
ain
in
g
ep
o
ch
s
u
s
i
n
g
s
ep
ar
ate
tr
ain
i
n
g
an
d
test
in
g
d
atasets
.
T
h
e
m
o
d
el
’
s
co
n
v
er
g
e
n
ce
b
eh
av
io
r
an
d
p
r
ed
ictiv
e
ca
p
ab
ilit
y
w
er
e
ass
e
s
s
ed
th
r
o
u
g
h
lo
s
s
,
r
ec
all,
an
d
ac
cu
r
ac
y
,
w
h
ic
h
ar
e
s
tan
d
ar
d
in
d
icato
r
s
o
f
class
if
icatio
n
r
eliab
ilit
y
an
d
g
en
er
aliza
tio
n
ab
ilit
y
.
Fi
g
u
r
e
s
1
–
4
illu
s
tr
ate
t
h
e
lear
n
i
n
g
d
y
n
a
m
ic
s
o
f
t
h
e
D
NN
d
u
r
in
g
tr
ain
in
g
an
d
tes
tin
g
.
T
h
e
ev
o
lu
tio
n
o
f
tr
ai
n
i
n
g
a
n
d
test
in
g
lo
s
s
ac
r
o
s
s
ep
o
ch
s
is
ill
u
s
tr
ated
in
Fig
u
r
e
1
.
B
o
th
cu
r
v
es e
x
h
ib
it
a
m
o
n
o
to
n
icall
y
d
ec
r
ea
s
in
g
tr
en
d
,
in
d
icatin
g
s
tab
le
lear
n
i
n
g
an
d
co
n
v
er
g
e
n
ce
o
f
th
e
DNN.
At
th
e
in
itia
l
ep
o
ch
s
,
th
e
tr
ai
n
i
n
g
lo
s
s
is
ap
p
r
o
x
i
m
at
el
y
0
.
8
5
,
w
h
ile
th
e
tes
tin
g
lo
s
s
is
s
li
g
h
t
l
y
h
i
g
h
er
at
ar
o
u
n
d
0
.
9
5
,
w
h
ich
is
t
y
p
ical
d
u
e
to
th
e
m
o
d
el
’
s
ea
r
l
y
-
s
tag
e
u
n
d
er
f
i
tti
n
g
.
R
ec
all
m
ea
s
u
r
es
t
h
e
m
o
d
el’
s
ab
ilit
y
to
co
r
r
ec
tly
id
en
tify
p
o
s
itiv
e
in
s
tan
ce
s
,
w
h
ic
h
is
p
ar
ticu
lar
l
y
i
m
p
o
r
tan
t
i
n
ap
p
licatio
n
s
w
h
e
r
e
f
alse
n
eg
at
iv
e
s
ar
e
co
s
tl
y
.
T
h
e
r
ec
all
tr
en
d
s
f
o
r
b
o
th
tr
ain
in
g
a
n
d
test
i
n
g
s
et
s
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
2
.
T
h
e
tr
ai
n
in
g
r
ec
all
s
tar
ts
at
ap
p
r
o
x
i
m
a
tel
y
0
.
5
5
an
d
in
cr
ea
s
es
s
h
ar
p
l
y
d
u
r
in
g
t
h
e
f
ir
s
t
2
0
ep
o
ch
s
,
r
ea
ch
in
g
ab
o
u
t 0
.
8
0
,
r
ef
lecti
n
g
r
ap
id
lear
n
in
g
o
f
d
is
c
r
i
m
i
n
ati
v
e
f
ea
t
u
r
es.
Fig
u
r
e
1
.
T
r
ain
in
g
an
d
test
in
g
lo
s
s
cu
r
v
es o
f
t
h
e
DNN
m
o
d
el
o
v
er
1
0
0
ep
o
ch
s
Fig
u
r
e
2
.
T
r
ain
in
g
an
d
test
in
g
r
ec
all
cu
r
v
es o
f
th
e
DNN
m
o
d
el
o
v
er
1
0
0
ep
o
ch
s
T
h
e
class
if
ica
tio
n
ac
c
u
r
ac
y
o
f
th
e
D
NN
d
u
r
in
g
tr
ai
n
in
g
a
n
d
test
in
g
is
ill
u
s
tr
ated
in
Fi
g
u
r
e
3
.
T
h
e
tr
ain
i
n
g
ac
c
u
r
ac
y
i
n
cr
ea
s
es
f
r
o
m
ap
p
r
o
x
i
m
atel
y
0
.
5
0
at
th
e
f
ir
s
t
ep
o
ch
to
n
ea
r
l
y
0
.
8
5
b
y
th
e
2
0
th
ep
o
ch
,
s
h
o
w
i
n
g
r
ap
id
co
n
v
er
g
en
ce
.
A
f
ter
5
0
e
p
o
ch
s
,
ac
cu
r
ac
y
s
tab
ilize
s
,
u
lt
i
m
atel
y
r
ea
ch
i
n
g
ar
o
u
n
d
0
.
9
2
at
th
e
1
0
0
th
ep
o
ch
.
T
h
e
p
r
ec
is
io
n
r
esu
lts
o
f
th
e
D
NN
m
o
d
el
ar
e
p
r
esen
ted
in
Fi
g
u
r
e
4
.
Fig
u
r
e
3
.
T
r
ain
in
g
an
d
test
in
g
ac
cu
r
ac
y
c
u
r
v
es o
f
th
e
DNN
m
o
d
el
o
v
er
1
0
0
ep
o
ch
s
Fig
u
r
e
4
.
T
r
ain
in
g
an
d
test
in
g
p
r
ec
is
io
n
o
f
th
e
D
NN
m
o
d
el
o
v
er
1
0
0
ep
o
ch
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
259
-
2
6
8
266
Fig
u
r
e
5
p
r
esen
ts
a
co
m
p
ar
ati
v
e
ev
al
u
atio
n
o
f
m
u
ltip
le
m
a
ch
in
e
lear
n
in
g
clas
s
i
f
ier
s
b
ase
d
o
n
th
eir
ac
cu
r
ac
y
s
co
r
es
u
s
i
n
g
an
8
0
–
2
0
tr
ain
–
test
s
p
lit.
T
h
e
r
esu
lts
il
lu
s
tr
ate
n
o
tab
le
p
er
f
o
r
m
an
ce
v
ar
iatio
n
s
ac
r
o
s
s
th
e
m
o
d
el
s
.
Fi
g
u
r
e
6
co
m
p
ar
es
t
h
e
p
er
f
o
r
m
an
ce
o
f
s
e
v
er
al
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els u
s
i
n
g
K
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
to
p
r
o
v
id
e
a
m
o
r
e
r
o
b
u
s
t e
s
ti
m
ate
o
f
g
e
n
er
aliza
tio
n
ca
p
ab
ilit
y
.
Fig
u
r
e
5
.
A
cc
u
r
ac
y
co
m
p
ar
is
o
n
o
f
d
if
f
er
en
t
class
i
f
icatio
n
m
o
d
els
u
s
i
n
g
an
8
0
–
2
0
tr
ain
–
test
s
p
lit
Fig
u
r
e
6
.
A
cc
u
r
ac
y
co
m
p
ar
is
o
n
o
f
m
ac
h
i
n
e
lear
n
in
g
m
o
d
el
s
ev
al
u
ated
u
s
i
n
g
K
-
f
o
l
d
cr
o
s
s
-
v
al
id
atio
n
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
in
v
es
tig
ated
t
h
e
e
f
f
ec
tiv
e
n
e
s
s
o
f
ei
g
h
t
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els
i
n
p
r
ed
ictin
g
s
t
u
d
en
t
ac
ad
em
ic
o
u
tco
m
es
u
s
in
g
e
-
le
ar
n
in
g
i
n
ter
ac
tio
n
d
ata.
U
n
d
er
8
0
–
2
0
s
p
lit
v
alid
atio
n
,
t
h
e
R
B
F
m
o
d
el
ac
h
iev
ed
th
e
h
i
g
h
e
s
t
ac
cu
r
ac
y
o
f
1
.
0
0
,
h
ig
h
lig
h
ti
n
g
its
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
lex
p
atter
n
s
in
lear
n
er
b
eh
av
io
r
.
Ho
w
e
v
er
,
K
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
r
es
u
l
ts
d
e
m
o
n
s
tr
ated
t
h
at
R
F
an
d
DNN
p
r
o
v
id
ed
th
e
m
o
s
t
s
tab
le
an
d
r
eliab
le
p
er
f
o
r
m
a
n
ce
,
b
o
th
attain
i
n
g
an
ac
cu
r
ac
y
o
f
0
.
8
9
,
f
o
llo
w
ed
clo
s
el
y
b
y
SVM
an
d
R
B
F.
T
h
ese
f
i
n
d
in
g
s
i
n
d
i
ca
te
th
at
w
h
ile
ce
r
tain
m
o
d
els
m
a
y
ex
ce
l
u
n
d
er
a
s
i
m
p
le
tr
ain
–
te
s
t
s
p
lit,
en
s
e
m
b
le
an
d
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
ar
e
b
etter
s
u
ited
f
o
r
g
e
n
er
aliza
tio
n
ac
r
o
s
s
d
if
f
er
en
t
s
u
b
s
ets
o
f
d
ata.
Ov
er
all,
th
e
r
es
u
lts
co
n
f
ir
m
th
a
t
co
m
b
in
i
n
g
ad
v
an
ce
d
m
ac
h
in
e
lear
n
i
n
g
tec
h
n
iq
u
es
w
it
h
r
o
b
u
s
t
v
alid
atio
n
s
tr
ateg
ie
s
ca
n
en
h
an
ce
p
r
ed
ictiv
e
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
,
e
n
ab
lin
g
ed
u
ca
to
r
s
to
id
en
tify
at
-
r
is
k
s
tu
d
e
n
ts
e
ar
l
y
an
d
i
m
p
le
m
en
t
p
er
s
o
n
ali
ze
d
in
ter
v
e
n
tio
n
s
i
n
d
ig
ital
lear
n
i
n
g
e
n
v
ir
o
n
m
en
ts
.
Fu
t
u
r
e
r
esear
ch
w
ill
in
v
est
ig
at
e
h
y
b
r
id
s
tack
i
n
g
w
it
h
d
ee
p
le
ar
n
in
g
co
m
p
o
n
en
t
s
,
d
y
n
a
m
ic
f
ea
tu
r
e
e
n
g
in
ee
r
i
n
g
,
an
d
th
e
i
n
co
r
p
o
r
atio
n
o
f
ex
p
la
in
ab
le
ar
tific
ial
i
n
telli
g
e
n
ce
te
ch
n
iq
u
es
to
e
n
h
a
n
ce
m
o
d
el
tr
a
n
s
p
ar
en
c
y
an
d
ad
ap
tab
ilit
y
i
n
d
iv
er
s
e
o
n
l
in
e
lear
n
i
n
g
e
n
v
ir
o
n
m
en
t
s
.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
Au
t
h
o
r
s
s
tate
n
o
f
u
n
d
i
n
g
i
n
v
o
l
v
ed
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
j
o
u
r
n
al
u
s
e
s
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Saj
ith
u
n
is
a
H
u
s
s
ai
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
J
ay
ac
h
an
d
r
an
J
e
y
ac
h
id
r
a
✓
✓
✓
✓
✓
✓
✓
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
si
s
I
:
I
n
v
e
st
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
si
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
P
r
ed
ictin
g
s
tu
d
en
t a
ca
d
emic
o
u
tco
mes fro
m
e
-
lea
r
n
in
g
in
tera
ctio
n
d
a
ta
u
s
in
g
…
(
S
a
jith
u
n
i
s
a
Hu
s
s
a
in
)
267
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
is
n
o
t a
p
p
licab
le
to
th
is
p
ap
er
as n
o
n
e
w
d
at
a
w
er
e
cr
ea
ted
o
r
an
al
y
ze
d
in
t
h
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
W
.
A
h
me
d
,
M
.
A
.
W
a
n
i
,
P
.
P
l
a
w
i
a
k
,
S
.
M
e
sh
o
u
l
,
A
.
M
a
h
mo
u
d
,
a
n
d
M
.
H
a
mm
a
d
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
a
c
a
d
e
mi
c
p
e
r
f
o
r
man
c
e
p
r
e
d
i
c
t
i
o
n
w
i
t
h
e
x
p
l
a
i
n
a
b
i
l
i
t
y
f
o
r
e
n
h
a
n
c
e
d
d
e
c
i
si
o
n
-
ma
k
i
n
g
i
n
e
d
u
c
a
t
i
o
n
a
l
i
n
st
i
t
u
t
i
o
n
s,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
2
6
8
7
9
,
Ju
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
025
-
1
2
3
5
3
-
4.
[
2
]
A
.
A
ssel
man
,
M
.
K
h
a
l
d
i
,
a
n
d
S
.
A
a
mm
o
u
,
“
En
h
a
n
c
i
n
g
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
st
u
d
e
n
t
p
e
r
f
o
r
man
c
e
b
a
se
d
o
n
t
h
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
X
G
B
o
o
st
a
l
g
o
r
i
t
h
m,”
I
n
t
e
ra
c
t
i
v
e
L
e
a
r
n
i
n
g
E
n
v
i
r
o
n
m
e
n
t
s
,
v
o
l
.
3
1
,
n
o
.
6
,
p
p
.
3
3
6
0
–
3
3
7
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
4
9
4
8
2
0
.
2
0
2
1
.
1
9
2
8
2
3
5
.
[
3
]
Ş
.
A
y
d
o
ğ
d
u
,
“
P
r
e
d
i
c
t
i
n
g
st
u
d
e
n
t
f
i
n
a
l
p
e
r
f
o
r
man
c
e
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
i
n
o
n
l
i
n
e
l
e
a
r
n
i
n
g
e
n
v
i
r
o
n
me
n
t
s,”
Ed
u
c
a
t
i
o
n
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
2
5
,
n
o
.
3
,
p
p
.
1
9
1
3
–
1
9
2
7
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
6
3
9
-
0
1
9
-
1
0
0
5
3
-
x.
[
4
]
N
.
B
h
i
mav
a
r
a
p
u
,
B
.
V
.
P
r
a
sa
n
t
h
i
,
C
.
H
.
L
.
V
e
e
n
a
d
h
a
r
i
,
M
.
D
.
S
a
t
i
sh
,
V
.
D
.
R
.
M
a
t
t
a
,
a
n
d
I
.
K
.
P
r
a
d
e
e
p
,
“
P
r
e
d
i
c
t
i
n
g
S
t
u
d
e
n
t
A
c
a
d
e
mi
c
P
e
r
f
o
r
man
c
e
U
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
:
A
C
o
m
p
a
r
i
so
n
o
f
C
l
a
ssi
f
i
c
a
t
i
o
n
A
l
g
o
r
i
t
h
ms,
”
i
n
S
p
ri
n
g
e
r
Pr
o
c
e
e
d
i
n
g
s
i
n
Ma
t
h
e
m
a
t
i
c
s
a
n
d
S
t
a
t
i
s
t
i
c
s
,
v
o
l
.
4
4
1
,
p
p
.
7
0
3
–
716
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
5
1
3
3
8
-
1
_
5
6
.
[
5
]
B
.
C
h
e
n
g
,
Y
.
L
i
u
,
a
n
d
Y
.
Ji
a
,
“
Ev
a
l
u
a
t
i
o
n
o
f
st
u
d
e
n
t
s’
p
e
r
f
o
r
man
c
e
d
u
r
i
n
g
t
h
e
a
c
a
d
e
mi
c
p
e
r
i
o
d
u
s
i
n
g
t
h
e
X
G
-
B
o
o
st
C
l
a
ssi
f
i
e
r
-
En
h
a
n
c
e
d
A
EO
h
y
b
r
i
d
mo
d
e
l
,
”
Ex
p
e
r
t
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
2
1
3
6
.
[
6
]
Z
.
C
h
e
n
,
G
.
C
e
n
,
Y
.
W
e
i
,
a
n
d
Z
.
L
i
,
“
S
t
u
d
e
n
t
P
e
r
f
o
r
man
c
e
P
r
e
d
i
c
t
i
o
n
A
p
p
r
o
a
c
h
B
a
se
d
o
n
E
d
u
c
a
t
i
o
n
a
l
D
a
t
a
M
i
n
i
n
g
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
3
1
2
6
0
–
1
3
1
2
7
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
3
5
9
8
5
.
[
7
]
A
.
A
.
H
u
ssai
n
a
n
d
K
.
D
i
mi
l
i
l
e
r
,
“
S
t
u
d
e
n
t
G
r
a
d
e
P
r
e
d
i
c
t
i
o
n
U
s
i
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
i
n
I
o
T
Er
a
,
”
L
e
c
t
u
re
N
o
t
e
s
o
f
t
h
e
I
n
s
t
i
t
u
t
e
f
o
r
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s,
S
o
c
i
a
l
-
I
n
f
o
rm
a
t
i
c
s
a
n
d
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
En
g
i
n
e
e
ri
n
g
,
L
N
I
C
S
T
,
v
o
l
.
3
5
3
,
p
p
.
6
5
–
8
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
6
9
4
3
1
-
9
_
6
.
[
8
]
O
.
H
.
T
.
L
u
,
A
.
Y
.
Q
.
H
u
a
n
g
,
J.
C
.
H
.
H
u
a
n
g
,
A
.
J.
Q
.
L
i
n
,
H
.
O
g
a
t
a
,
a
n
d
S
.
J.
H
.
Y
a
n
g
,
“
A
p
p
l
y
i
n
g
l
e
a
r
n
i
n
g
a
n
a
l
y
t
i
c
s
f
o
r
t
h
e
e
a
r
l
y
p
r
e
d
i
c
t
i
o
n
o
f
st
u
d
e
n
t
s’
a
c
a
d
e
mi
c
p
e
r
f
o
r
man
c
e
i
n
b
l
e
n
d
e
d
l
e
a
r
n
i
n
g
,
”
Ed
u
c
a
t
i
o
n
a
l
T
e
c
h
n
o
l
o
g
y
a
n
d
S
o
c
i
e
t
y
,
v
o
l
.
2
1
,
n
o
.
2
,
p
p
.
2
2
0
–
2
3
2
,
2
0
1
8
.
[
9
]
H
.
M
a
s
t
o
u
r
,
T
.
D
e
h
g
h
a
n
i
,
E
.
M
o
r
a
d
i
,
a
n
d
S
.
Esl
a
m
i
,
“
Ea
r
l
y
p
r
e
d
i
c
t
i
o
n
o
f
me
d
i
c
a
l
st
u
d
e
n
t
s’
p
e
r
f
o
r
man
c
e
i
n
h
i
g
h
-
st
a
k
e
s
e
x
a
mi
n
a
t
i
o
n
s
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,”
H
e
l
i
y
o
n
,
v
o
l
.
9
,
n
o
.
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
3
.
e
1
8
2
4
8
.
[
1
0
]
R
.
W
a
n
g
e
t
a
l
.
,
“
S
t
u
d
e
n
t
L
i
f
e
:
U
si
n
g
s
martp
h
o
n
e
s
t
o
a
sse
ss
me
n
t
a
l
h
e
a
l
t
h
a
n
d
a
c
a
d
e
mi
c
p
e
r
f
o
r
man
c
e
o
f
c
o
l
l
e
g
e
st
u
d
e
n
t
s,
”
i
n
Mo
b
i
l
e
H
e
a
l
t
h
:
S
e
n
s
o
rs,
A
n
a
l
y
t
i
c
M
e
t
h
o
d
s,
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
C
h
a
m:
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
1
7
,
p
p
.
7
–
33
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
5
1
3
9
4
-
2
_
2
.
[
1
1
]
M
.
H
.
Z
a
k
a
r
i
a
,
“
E
-
L
e
a
r
n
i
n
g
2
.
0
Ex
p
e
r
i
e
n
c
e
s
W
i
t
h
i
n
H
i
g
h
e
r
Ed
u
c
a
t
i
o
n
:
Th
e
o
r
i
si
n
g
S
t
u
d
e
n
t
s
’
a
n
d
T
e
a
c
h
e
r
s
’
Ex
p
e
r
i
e
n
c
e
s
i
n
W
e
b
2
.
0
l
e
a
r
n
i
n
g
,
”
Q
u
e
e
n
sl
a
n
d
U
n
i
v
e
r
si
t
y
o
f
Te
c
h
n
o
l
o
g
y
,
2
0
1
3
.
[
1
2
]
Z
.
Z
h
a
o
,
Y
.
L
e
i
,
Y
.
D
o
u
,
Y
.
H
.
H
o
,
H
.
C
.
B
.
C
h
a
n
,
a
n
d
C
.
C
.
H
.
C
h
a
n
,
“
S
t
u
d
e
n
t
l
y
z
e
r
f
o
r
A
n
a
l
y
z
i
n
g
a
n
d
V
i
s
u
a
l
i
z
i
n
g
E
-
l
e
a
r
n
i
n
g
D
a
t
a
,
”
L
e
c
t
u
r
e
N
o
t
e
s
i
n
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
2
3
9
,
p
p
.
1
4
7
–
1
5
2
,
2
0
1
9
.
[
1
3
]
V
.
A
r
k
o
r
f
u
l
a
n
d
N
.
A
b
a
i
d
o
o
,
“
T
h
e
r
o
l
e
o
f
e
-
l
e
a
r
n
i
n
g
,
t
h
e
a
d
v
a
n
t
a
g
e
s
a
n
d
d
i
sa
d
v
a
n
t
a
g
e
s
o
f
i
t
s
a
d
o
p
t
i
o
n
i
n
h
i
g
h
e
r
e
d
u
c
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
d
u
c
a
t
i
o
n
a
n
d
R
e
se
a
rc
h
,
v
o
l
.
2
,
n
o
.
1
2
,
p
p
.
3
9
7
–
4
1
0
,
2
0
1
4
.
[
1
4
]
S
.
R
.
R
a
t
k
a
l
l
e
,
“
R
o
l
e
o
f
I
C
T
i
n
E
-
L
e
a
r
n
i
n
g
,”
J
o
u
r
n
a
l
o
f
Em
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
I
n
n
o
v
a
t
i
v
e
R
e
se
a
rc
h
,
v
o
l
.
7
,
n
o
.
7
,
p
p
.
1
3
2
0
–
1
3
2
4
,
2
0
2
0
.
[
1
5
]
M
.
F
e
r
r
a
r
i
,
“
E
-
l
e
a
r
n
i
n
g
S
t
u
d
e
n
t
R
e
a
c
t
i
o
n
s,”
K
a
g
g
l
e
,
2
0
2
3
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m/
d
a
t
a
se
t
s/
mar
l
o
n
f
e
r
r
a
r
i
/
e
l
e
a
r
n
i
n
g
-
st
u
d
e
n
t
-
r
e
a
c
t
i
o
n
s
.
[
1
6
]
P
.
F
a
b
i
a
n
e
t
a
l
.
,
“
S
c
i
k
i
t
-
l
e
a
r
n
:
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
i
n
P
y
t
h
o
n
,
”
J
o
u
r
n
a
l
o
f
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
se
a
rc
h
,
v
o
l
.
1
2
,
p
p
.
2
8
2
5
–
2
8
3
0
,
2
0
1
1
.
[
1
7
]
K
.
A
.
H
.
A
ssi
r
y
a
n
d
A
.
M
u
n
i
a
samy
,
“
P
r
e
d
i
c
t
i
n
g
L
e
a
r
n
i
n
g
S
t
y
l
e
s
U
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
C
l
a
ssi
f
i
e
r
s,”
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
E
l
e
c
t
r
i
c
a
l
,
C
o
m
p
u
t
e
r,
a
n
d
E
n
e
r
g
y
T
e
c
h
n
o
l
o
g
i
e
s
,
I
C
E
C
ET
2
0
2
2
,
Ju
l
.
2
0
2
2
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
EC
ET
5
5
5
2
7
.
2
0
2
2
.
9
8
7
2
9
7
1
.
[
1
8
]
Y
.
M
.
I
.
H
a
ssan
,
A
.
El
k
o
r
a
n
y
,
a
n
d
K
.
W
a
ssi
f
,
“
U
t
i
l
i
z
i
n
g
S
o
c
i
a
l
C
l
u
s
t
e
r
i
n
g
-
B
a
se
d
R
e
g
r
e
ssi
o
n
M
o
d
e
l
f
o
r
P
r
e
d
i
c
t
i
n
g
S
t
u
d
e
n
t
’
s
G
P
A
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
4
8
9
4
8
–
4
8
9
6
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
7
2
4
3
8
.
[
1
9
]
J.
Z
i
mm
e
r
man
n
,
K
.
H
.
B
r
o
d
e
r
se
n
,
H
.
R
.
H
e
i
n
i
m
a
n
n
,
a
n
d
J
.
M
.
B
u
h
ma
n
n
,
“
A
mo
d
e
l
-
b
a
se
d
a
p
p
r
o
a
c
h
t
o
p
r
e
d
i
c
t
i
n
g
g
r
a
d
u
a
t
e
-
l
e
v
e
l
p
e
r
f
o
r
man
c
e
u
si
n
g
i
n
d
i
c
a
t
o
r
s o
f
u
n
d
e
r
g
r
a
d
u
a
t
e
-
l
e
v
e
l
p
e
r
f
o
r
man
c
e
,
”
J
ED
M
-
J
o
u
rn
a
l
o
f
E
d
u
c
a
t
i
o
n
a
l
D
a
t
a
Mi
n
i
n
g
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
1
5
1
–
1
7
6
,
2
0
1
5
.
[
2
0
]
M
.
F
i
r
e
,
G
.
K
a
t
z
,
Y
.
El
o
v
i
c
i
,
B
.
S
h
a
p
i
r
a
,
a
n
d
L
.
R
o
k
a
c
h
,
“
P
r
e
d
i
c
t
i
n
g
S
t
u
d
e
n
t
Ex
a
m’
s
S
c
o
r
e
s
b
y
A
n
a
l
y
z
i
n
g
S
o
c
i
a
l
N
e
t
w
o
r
k
D
a
t
a
,
”
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
Ac
t
i
v
e
M
e
d
i
a
T
e
c
h
n
o
l
o
g
y
,
S
p
r
i
n
g
e
r
,
B
e
r
l
i
n
,
H
e
i
d
e
l
b
e
r
g
,
2
0
1
2
,
p
p
.
5
8
4
–
5
9
5
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
3
5
2
3
6
-
2
_
5
9
.
[
2
1
]
M
.
Z
a
k
a
r
i
a
,
“
T
h
e
A
d
o
p
t
i
o
n
o
f
e
-
L
e
a
r
n
i
n
g
2
.
0
i
n
H
i
g
h
e
r
E
d
u
c
a
t
i
o
n
b
y
Te
a
c
h
e
r
s
a
n
d
S
t
u
d
e
n
t
s:
A
n
I
n
v
e
st
i
g
a
t
i
o
n
U
si
n
g
M
i
x
e
d
M
e
t
h
o
d
s 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
e
-
E
d
u
c
a
t
i
o
n
,
e
-
Bu
s
i
n
e
ss,
e
-
M
a
n
a
g
e
m
e
n
t
a
n
d
e
-
L
e
a
rn
i
n
g
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
1
0
8
–
1
1
2
,
2
0
1
2
,
d
o
i
:
1
0
.
7
7
6
3
/
i
j
e
e
e
e
.
2
0
1
2
.
v
2
.
9
0
.
[
2
2
]
J.
B
r
o
w
n
l
e
e
,
D
e
v
e
l
o
p
D
e
e
p
L
e
a
r
n
i
n
g
Mo
d
e
l
s O
n
T
h
e
a
n
o
A
n
d
T
e
n
s
o
rF
l
o
w
U
si
n
g
K
e
r
a
s
,
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
M
a
s
t
e
r
y
,
2
0
1
6
.
[
2
3
]
J
.
B
r
o
w
n
l
e
e
,
En
semb
l
e
L
e
a
r
n
i
n
g
A
l
g
o
ri
t
h
m
s W
i
t
h
Py
t
h
o
n
,
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
M
a
s
t
e
r
y
,
2
0
2
1
.
[
2
4
]
S
.
H
u
ss
a
i
n
a
n
d
J
.
Je
y
a
c
h
i
d
r
a
,
"
A
st
a
c
k
e
d
c
l
a
ssi
f
i
e
r
mo
d
e
l
f
o
r
e
n
h
a
n
c
e
d
s
t
u
d
e
n
t
p
e
r
f
o
r
man
c
e
p
r
e
d
i
c
t
i
o
n
i
n
e
-
l
e
a
r
n
i
n
g
e
n
v
i
r
o
n
me
n
t
s,"
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
E
l
e
c
t
r
o
n
i
c
s
E
n
g
i
n
e
e
r
i
n
g
I
n
d
o
n
e
si
a
(
I
J
E
EI
)
,
v
o
l
.
1
4
,
n
o
.
1
,
2
0
2
6
,
d
o
i
:
1
0
.
5
2
5
4
9
/
I
JEE
I
.
V
1
4
I
1
.
7
4
1
4
0
2
2
8
3
[
2
5
]
K
.
U
.
P
.
K
u
mar,
O
.
G
a
n
d
h
i
,
M
.
V
.
R
e
d
d
y
,
a
n
d
S
.
V
.
N
.
S
r
i
n
i
v
a
s
u
,
“
U
sag
e
o
f
K
N
N
,
D
e
c
i
si
o
n
T
r
e
e
a
n
d
R
a
n
d
o
m Fo
r
e
st
A
l
g
o
r
i
t
h
ms
i
n
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
P
e
r
f
o
r
man
c
e
A
n
a
l
y
si
s
w
i
t
h
a
C
o
m
p
a
r
a
t
i
v
e
M
e
a
su
r
e
,
”
i
n
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
Ad
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
S
p
r
i
n
g
e
r
,
S
i
n
g
a
p
o
r
e
,
2
0
2
1
,
v
o
l
.
1
2
8
0
,
p
p
.
4
0
5
–
4
1
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
15
-
9
5
1
6
-
5
_
3
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
259
-
2
6
8
268
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
a
jith
u
n
is
a
H
u
ss
a
in
is
a
Re
se
a
rc
h
S
c
h
o
lar
in
th
e
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s
in
P
e
riy
a
r
M
a
n
iam
m
a
i
In
stit
u
te
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
,
T
h
a
n
jav
u
r
-
6
1
3
4
0
3
,
In
d
ia.
S
h
e
re
c
e
iv
e
d
h
e
r
M
.
S
c
.
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
in
T
h
iru
v
a
ll
u
v
a
r
Un
iv
e
rsit
y
,
V
e
ll
o
re
.
S
h
e
is
in
tere
ste
d
u
n
d
e
r
t
h
e
d
o
m
a
in
o
f
m
a
c
h
in
e
lea
rn
in
g
,
e
-
l
e
a
rn
in
g
,
a
n
d
d
a
ta
m
in
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
ji
th
u
n
isa
5
0
1
7
@
p
m
u
.
e
d
u
.
Dr
.
J
a
y
a
c
h
a
n
d
r
a
n
J
e
y
a
c
h
id
r
a
is
a
P
ro
f
e
ss
o
r
in
th
e
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s,
P
e
r
iy
a
r
M
a
n
ia
m
m
a
i
In
stit
u
te
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
,
T
h
a
n
jav
u
r
-
6
1
3
4
0
3
,
In
d
ia.
S
h
e
re
c
e
iv
e
d
h
e
r
M
CA
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
A
p
p
li
c
a
ti
o
n
s
f
ro
m
Bh
a
ra
th
id
a
sa
n
Un
iv
e
rsit
y
,
T
rich
y
.
S
h
e
c
o
m
p
lete
d
h
e
r
P
h
.
D.
in
Da
ta
M
in
i
n
g
.
He
r
c
u
rre
n
t
r
e
se
a
rc
h
in
tere
st
is
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
a
ta
m
in
in
g
.
S
h
e
is
a
n
a
c
ti
v
e
L
i
f
e
M
e
m
b
e
r
o
f
th
e
I
n
d
ian
S
o
c
iety
f
o
r
T
e
c
h
n
ica
l
Ed
u
c
a
ti
o
n
(IS
T
E)
a
n
d
th
e
Co
m
p
u
ter
S
o
c
iety
o
f
In
d
ia
(CS
I).
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
h
it
h
u
_
ra
j@p
m
u
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.