I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
36
,
No
.
2
,
N
o
v
em
b
e
r
20
24
,
p
p
.
9
9
4
~1
0
0
1
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
36.
i
2
.
p
p
994
-
1
0
0
1
994
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Perf
o
rma
nce
of d
y
slexia da
tas
et
for ma
chine l
ea
rnin
g
a
lg
o
rithms
J
.
J
incy
1
,2
,
P
.
Su
bh
a
H
ency
J
o
s
e
1
1
D
e
p
a
r
t
me
n
t
o
f
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
B
i
o
me
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
K
a
r
u
n
y
a
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
a
n
d
S
c
i
e
n
c
e
s,
C
o
i
mb
a
t
o
r
e
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
C
S
I
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
K
e
t
t
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
22
,
2
0
2
4
R
ev
is
ed
J
u
n
25
,
2
0
2
4
Acc
ep
ted
J
u
l
14
,
2
0
2
4
Lea
rn
in
g
d
isa
b
il
it
y
is
a
c
o
n
d
it
i
o
n
u
s
u
a
l
a
m
o
n
g
st
m
o
st
p
o
p
u
lac
e
d
u
e
t
o
p
o
o
r
p
h
o
n
o
lo
g
ica
l
c
a
p
a
b
il
it
y
i
n
h
u
m
a
n
s
m
a
k
in
g
t
h
e
m
imp
a
ired
.
On
e
su
c
h
n
e
u
ro
l
o
g
ica
l
d
is
o
rd
e
r
is
d
e
v
e
lo
p
m
e
n
tal
d
y
sle
x
ia,
a
lac
k
o
f
re
a
d
in
g
a
n
d
writi
n
g
s
k
il
ls
lea
d
i
n
g
to
d
iffi
c
u
lt
y
in
sc
h
o
o
l
e
d
u
c
a
ti
o
n
.
Th
e
e
ss
e
n
ti
a
l
c
a
u
se
s
o
f
d
e
v
e
lo
p
m
e
n
tal
d
y
sle
x
ia
a
re
th
e
c
o
n
su
m
p
t
io
n
o
f
m
o
re
d
ru
g
t
re
a
tme
n
ts
d
u
ri
n
g
p
re
g
n
a
n
c
y
,
th
e
o
v
e
r
-
t
h
e
-
c
o
u
n
ter
p
u
rc
h
a
se
o
f
m
e
d
icin
e
s
fo
r
m
i
n
o
r
a
il
m
e
n
ts
with
o
u
t
th
e
re
c
o
m
m
e
n
d
a
ti
o
n
o
f
p
h
y
sic
ian
s,
a
n
d
u
n
c
a
re
d
-
fo
r
h
e
a
d
a
c
c
id
e
n
ts
d
u
rin
g
e
a
rly
li
fe
.
T
h
e
o
c
c
u
rre
n
c
e
o
f
th
is
tr
o
u
b
le
is
a
c
u
t
e
in
In
d
ia.
Attem
p
ts
we
re
m
a
d
e
b
y
m
a
n
y
to
d
e
tec
t
d
y
sle
x
ic
c
h
il
d
re
n
t
o
r
e
d
u
c
e
th
e
in
ten
sit
y
o
f
th
is
h
a
ss
le.
In
th
is
p
r
o
p
o
se
d
e
ffo
rt,
m
a
c
h
in
e
lea
rn
i
n
g
i
s
u
se
d
t
o
lo
c
a
te
sig
n
if
ica
n
t
st
y
les
c
h
a
ra
c
teriz
in
g
p
e
o
p
le
u
si
n
g
EE
G
sa
m
p
les
.
A
d
a
tas
e
t
is
u
se
d
fo
r
e
x
a
m
in
a
ti
o
n
o
f
d
e
v
e
l
o
p
m
e
n
tal
d
y
sle
x
ia,
a
n
d
c
las
sifica
ti
o
n
is d
o
n
e
u
sin
g
K
n
e
a
re
st
n
e
ig
h
b
o
r
(KN
N)
,
d
e
c
isio
n
tree
,
l
in
e
a
r
d
isc
rimin
a
n
t
a
n
a
ly
sis
(LDA)
,
a
n
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
to
e
v
a
l
u
a
te
th
e
p
e
r
fo
rm
a
n
c
e
.
Th
is
p
iec
e
o
f
re
se
a
rc
h
wo
rk
is
d
o
n
e
o
n
M
ATLAB
t
o
p
r
o
v
i
d
e
r
e
su
lt
s
o
n
sim
u
latio
n
wit
h
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
9
0
.
7
6
%
f
o
r
S
VM,
se
n
siti
v
it
y
o
f
8
9
%
fo
r
S
V
M
,
a
n
d
LDA
with
9
1
.
8
9
%
sp
e
c
ifi
c
it
y
fo
r
S
V
M
p
ro
v
id
i
n
g
o
p
ti
m
u
m
y
ield
.
K
ey
w
o
rd
s
:
Dy
s
lex
ia
EEG
K
n
ea
r
est n
eig
h
b
o
r
Ma
ch
in
e
lear
n
in
g
SVM
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
:
P.
Su
b
h
a
Hen
cy
J
o
s
e
Dep
ar
tm
en
t o
f
B
io
m
ed
ical
E
n
g
in
ee
r
in
g
,
Fa
cu
lty
o
f
B
io
m
ed
ical
E
n
g
in
ee
r
in
g
Kar
u
n
y
a
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
an
d
Scien
ce
s
C
o
im
b
ato
r
e,
I
n
d
ia
E
m
ail: h
en
cy
2
0
0
0
2
0
0
0
@
k
ar
u
n
y
a.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
A
n
eu
r
o
lo
g
ical
d
is
o
r
d
e
r
ter
m
e
d
d
y
s
lex
ia
af
f
ec
ts
5
%
to
1
5
%
o
f
I
n
d
ian
k
id
s
,
wh
o
ar
e
lab
el
ed
as
lazy
b
ec
au
s
e
o
f
th
eir
in
ca
p
ab
ilit
y
in
r
ea
d
in
g
,
wr
itin
g
,
m
at
h
em
a
tic
s
k
ill
s
[
1
]
.
T
h
ey
y
ea
r
n
to
b
e
ap
p
r
ec
iated
an
d
ac
ce
p
ted
b
y
s
o
ciety
tu
r
n
in
g
t
h
eir
life
in
to
s
o
cial
tr
au
m
a
.
T
h
e
lear
n
i
n
g
d
is
ab
ilit
ies
lik
e
r
ea
d
in
g
an
d
wr
itin
g
cu
r
b
s
th
e
life
o
f
y
o
u
n
g
ch
ild
r
en
'
s
ed
u
ca
tio
n
an
d
f
u
tu
r
e
e
n
d
ea
v
o
r
.
Gen
etic
r
esear
ch
s
h
o
ws
th
at
d
y
s
lex
ia
is
in
h
er
ited
f
r
o
m
th
e
f
am
ily
.
Ar
o
u
n
d
2
3
-
6
5
%
o
f
ch
ild
r
e
n
h
av
e
tak
en
o
v
er
f
r
o
m
th
e
g
en
es
o
f
th
eir
p
ar
e
n
ts
u
n
n
o
ticea
b
l
y
.
L
ea
r
n
in
g
d
is
ab
i
liti
es
ar
e
o
f
p
r
ed
o
m
in
an
t
ty
p
e
’
s
d
y
s
lex
ia,
d
y
s
ca
lcu
lia
an
d
d
y
s
g
r
ap
h
ia
.
Dy
s
lex
ia
is
a
s
elec
ted
p
r
o
b
lem
r
elate
d
to
in
f
o
r
m
atio
n
s
o
u
n
d
s
an
d
p
h
r
ases
d
u
e
to
a
lack
o
f
p
h
o
n
o
lo
g
ical
p
r
o
ce
s
s
in
g
[
2
]
,
Dy
s
g
r
ap
h
ia
is
r
elate
d
to
d
ef
icien
cy
in
wr
itin
g
wo
r
d
s
an
d
s
cr
ip
t
s
h
ig
h
ly
d
if
f
icu
lt
to
d
ec
o
d
e
[
3
]
,
D
y
s
ca
lcu
lia
is
an
ar
ith
m
etic
d
is
o
r
d
e
r
th
at
ca
u
s
es p
o
o
r
m
ath
em
atica
l
an
d
lo
g
ical
ca
p
ac
ity
[
4
]
.
T
h
er
e
ar
e
m
an
y
s
tan
d
ar
d
ized
test
s
f
o
r
an
aly
s
is
o
f
d
y
s
lex
ia
with
r
eg
ar
d
to
r
ea
d
in
g
,
wr
itin
g
,
s
p
ellin
g
ab
ilit
ies,
m
en
tal
ca
lib
er
,
an
d
wo
r
k
in
g
m
em
o
r
y
.
Glan
cin
g
at
th
e
test
s
th
e
s
ev
er
ity
o
f
th
e
in
f
ir
m
ity
ca
n
b
e
id
en
tifie
d
.
T
h
e
wea
k
lin
g
u
is
t
ic
ab
ilit
ies
ca
n
b
e
ass
ess
ed
u
s
in
g
wo
r
d
test
an
d
q
u
esti
o
n
n
air
e
co
n
n
ec
ted
t
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
P
erfo
r
ma
n
ce
o
f d
yslexia
d
a
ta
s
et
fo
r
ma
ch
in
e
lea
r
n
in
g
a
lg
o
r
i
th
ms
(
J.
Jin
cy
)
995
r
ea
d
in
g
an
d
wr
itin
g
b
ased
o
n
clin
ical
o
b
s
er
v
atio
n
[5
]
.
I
n
ad
d
itio
n
t
o
I
Q
test
s
n
eu
r
o
b
i
o
lo
g
ical
b
eh
a
v
io
r
in
b
r
ain
s
tr
u
ctu
r
e
ca
n
b
e
an
aly
ze
d
b
y
u
s
in
g
im
ag
in
g
to
o
ls
an
d
th
eir
b
e
h
av
io
r
co
u
l
d
b
e
u
n
d
er
s
to
o
d
.
Neu
r
al
co
n
n
ec
tiv
ity
v
ar
ies
f
o
r
d
y
s
lex
ic
an
d
n
o
r
m
al
ch
ild
r
en
alt
er
in
g
th
eir
b
r
ain
p
atter
n
.
F
u
n
ctio
n
al
m
ag
n
etic
r
eso
n
an
ce
im
a
g
in
g
(
F
MRI
)
is
a
tech
n
iq
u
e
u
s
ed
to
an
a
l
y
ze
wo
r
d
r
ec
o
g
n
itio
n
b
ased
o
n
c
h
an
g
es
in
th
e
b
lo
o
d
f
lo
w
in
th
e
f
r
o
n
tal
an
d
o
cc
ip
it
al
r
eg
io
n
s
.
T
h
e
test
s
ar
e
b
ased
o
n
im
ag
es
an
d
w
o
r
d
s
th
at
ar
e
u
s
ed
r
eg
u
lar
l
y
[
6
]
.
FMR
I
h
as
b
ee
n
v
er
y
b
en
ef
ici
al
it
h
as
d
r
asti
c
p
itfa
lls
th
at
m
ak
e
th
e
r
ea
l
n
eu
r
al
p
asti
m
e
id
en
tific
atio
n
h
ar
d
co
n
s
eq
u
en
tly
lea
d
in
g
t
o
a
m
a
x
im
u
m
m
o
d
if
ied
m
o
d
el
th
is
o
p
tim
izatio
n
s
et
o
f
r
u
les
co
m
p
lem
en
ts
th
e
s
ig
n
al
ex
ce
llen
t
with
in
th
e
v
icin
ity
o
f
in
ter
est
in
s
id
e
th
e
m
in
d
[
7
]
.
E
y
e
-
tr
ac
k
in
g
tech
n
o
lo
g
y
h
as
p
r
o
v
e
d
ex
ce
p
tio
n
al
s
tr
ateg
ies
f
o
r
c
h
ar
ac
ter
izi
n
g
d
y
s
lex
ia
am
o
n
g
r
e
g
u
lar
an
d
d
y
s
lex
ic
r
ea
d
er
s
.
E
y
e
m
o
v
em
e
n
t
is
u
s
ed
to
tr
ac
k
an
d
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
ar
e
u
s
ed
to
ass
ess
th
e
f
u
n
ctio
n
s
r
elatin
g
to
f
ix
atio
n
s
an
d
s
ac
ca
d
es.
T
h
e
s
o
lu
tio
n
to
d
y
s
lex
ia
ca
n
b
e
p
r
o
v
id
ed
b
y
ea
r
ly
in
ter
v
e
n
tio
n
with
ce
r
e
b
r
al
m
o
r
p
h
o
lo
g
y
wh
ich
g
ain
s
h
ig
h
ac
cu
r
ac
y
with
ec
o
n
o
m
ic
im
p
ac
t
b
u
t
q
u
iet
jer
k
y
[
8
]
.
B
ein
g
a
g
en
d
er
-
o
r
ien
te
d
d
is
o
r
d
er
f
u
n
ctio
n
al
an
d
s
tr
u
ctu
r
al
d
ev
elo
p
m
en
t
an
d
m
o
r
p
h
o
lo
g
ical
s
tu
d
y
was
d
o
n
e
b
y
E
K
L
am
b
e
[
9
]
s
h
o
wed
a
d
i
f
f
er
en
t
b
r
ain
ac
tiv
ati
o
n
p
atter
n
b
etwe
en
d
y
s
lex
ic
m
ales a
n
d
f
em
ales,
w
h
ich
is
in
f
lu
en
ce
d
o
n
an
aly
s
is
.
C
h
y
l
et
a
l.
[
1
0
]
s
tu
d
ied
n
eu
r
o
im
ag
in
g
in
th
e
lan
g
u
ag
e
ar
ea
s
o
f
b
r
ain
p
r
o
v
id
es
th
e
g
r
ea
test
ch
allen
g
e
an
d
r
ec
o
m
m
en
d
s
f
u
tu
r
e
en
h
a
n
ce
m
en
t
in
th
e
g
r
ay
a
r
ea
s
o
f
r
e
s
ea
r
ch
.
B
is
ca
ld
i
et
a
l.
[
1
1
]
ex
p
lain
ed
s
ac
ca
d
es
in
f
iv
e
n
o
n
-
co
g
n
itiv
e
task
s
.
T
h
e
cr
iter
io
n
o
f
th
e
e
y
e
-
m
o
v
em
en
t
d
ata
was
co
m
p
o
s
ed
o
f
twelv
e
p
er
s
o
n
s
wh
o
ar
e
co
n
s
id
er
ed
to
b
e
d
y
s
lex
ic
a
n
d
wer
e
g
r
o
u
p
e
d
i
n
to
two
g
r
o
u
p
s
(
D1
an
d
D2
)
b
ased
o
n
v
ar
io
u
s
m
etr
ics.
C
o
m
p
ar
in
g
b
o
th
g
r
o
u
p
s
,
m
o
r
e
d
etai
ls
o
n
th
eir
s
ac
ca
d
es
an
d
f
ix
atio
n
s
wer
e
r
ec
eiv
e
d
.
T
h
e
s
tan
d
ar
d
task
s
o
f
th
e
d
y
s
lex
ic
s
u
b
jects
Dy
s
L
ex
ML
is
a
m
ac
h
in
e
lear
n
in
g
to
o
l
u
s
ed
to
class
if
y
d
y
s
lex
ia
b
ased
o
n
ey
e
m
o
v
em
en
t
f
o
r
a
s
m
all
f
ea
tu
r
e
s
et,
wh
ich
wa
s
f
o
u
n
d
to
b
e
v
er
y
ac
cu
r
ate
in
th
e
p
r
esen
ce
o
f
n
o
is
e
u
s
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
[
1
2
]
.
Sm
all
s
am
p
les
an
d
s
m
all
ef
f
ec
ts
also
p
r
o
v
i
d
e
ef
f
icien
t
d
y
s
lex
ia
tr
ea
tm
e
n
t
s
tu
d
ies,
ac
co
r
d
i
n
g
to
r
esear
ch
er
s
f
r
o
m
I
taly
,
allo
win
g
o
n
e
to
r
ea
ch
ad
eq
u
ate
p
o
wer
[
1
3
]
.
E
lectr
o
en
ce
p
h
alo
g
r
am
(
EEG
)
is
a
n
o
n
-
in
v
asiv
e
m
eth
o
d
th
at
p
r
o
v
id
es
p
r
o
m
is
in
g
im
a
g
es
o
f
t
h
e
co
r
t
ical
p
ar
ts
o
f
th
e
b
r
ain
at
l
o
w
co
s
t
in
r
esp
o
n
s
e
to
v
ar
io
u
s
ac
tiv
iti
es
lik
e
r
ea
d
in
g
an
d
wr
itin
g
.
On
in
v
esti
g
atio
n
d
o
n
e
EEG
-
b
ased
class
if
icatio
n
f
r
am
ewo
r
k
p
r
o
v
id
es
a
p
atter
n
th
at
h
as
m
ea
n
in
g
f
u
l
d
ata
t
h
at
ca
n
b
e
ar
r
an
g
e
d
in
a
s
u
itab
le
o
r
d
er
an
d
class
if
ied
u
s
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
[
1
4
]
.
O
n
s
y
s
tem
atic
an
aly
s
is
o
f
th
e
ex
is
tin
g
r
esear
ch
th
e
f
o
llo
win
g
g
ap
s
ar
e
b
ein
g
id
en
tifie
d
as
m
o
s
t
o
f
th
e
d
iag
n
o
s
is
m
eth
o
d
ar
e
b
ased
o
n
co
n
v
e
n
tio
n
al
I
Q
test
an
d
ass
is
tiv
e
te
ch
n
o
lo
g
y
,
th
e
en
tire
ca
u
s
e
o
f
th
e
co
n
d
iti
o
n
is
n
o
t u
n
d
e
r
s
to
o
d
[
1
5
]
.
E
v
e
n
th
o
u
g
h
d
y
s
lex
ia
ca
n
b
e
p
r
e
d
icted
d
if
f
e
r
en
t
way
s
t
h
e
v
ast
s
ep
ar
atio
n
b
etwe
en
th
e
co
n
tr
o
ls
p
r
o
v
id
e
clea
r
em
p
at
h
y
to
war
d
s
th
e
d
is
ea
s
ed
.
Sm
al
ler
s
am
p
les
o
f
th
e
i
n
f
o
r
m
a
t
i
o
n
c
a
n
n
o
t
p
r
o
v
i
d
e
a
g
e
n
e
r
a
l
i
z
a
ti
o
n
b
u
t
r
a
t
h
e
r
l
a
r
g
e
s
a
m
p
l
e
s
et
c
a
n
p
r
o
v
i
d
e
d
e
p
t
h
o
f
t
h
e
u
n
f
o
l
d
i
n
g
[
1
6
]
.
A
n
o
v
el
m
et
h
o
d
o
f
d
y
s
lex
ia
an
aly
s
is
is
p
u
t
f
o
r
war
d
to
b
r
i
n
g
an
en
d
t
o
b
lin
d
b
elief
o
n
d
y
s
lex
ia
with
ea
r
ly
in
ter
v
en
tio
n
,
p
o
s
s
ib
ilit
y
o
f
d
etec
tio
n
u
s
in
g
d
ataset
an
d
s
tu
d
y
t
h
e
d
is
o
r
d
er
in
a
n
eu
r
o
lo
g
ic
al
p
er
s
p
ec
tiv
e
with
m
ac
h
in
e
lear
n
in
g
.
2.
B
ACK
G
RO
UND
S
T
UD
Y
T
h
e
EEG
r
ec
ei
v
ed
f
r
o
m
a
d
y
s
lex
ic
m
an
ag
er
u
n
d
er
g
o
es
s
tatis
tical
an
aly
s
is
b
ef
o
r
e
class
if
y
in
g
th
e
o
u
tp
u
t.
T
h
e
im
p
o
r
tan
t
s
tep
s
tak
en
to
tech
n
iq
u
e
th
e
u
n
co
o
k
ed
s
ig
n
al
ar
e:
i
)
p
r
ep
r
o
ce
s
s
in
g
a
n
d
ar
tifa
ct
r
em
o
v
al
,
ii
)
f
ac
t
an
aly
s
is
u
s
in
g
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
an
d
iii
)
c
lass
if
icatio
n
to
g
et
th
e
p
r
ef
e
r
r
ed
f
in
al
r
es
u
lts
.
2
.
1
.
P
re
pro
ce
s
s
ing
E
E
G
s
tatis
tic
s
co
llected
f
r
o
m
th
e
u
s
e
o
f
6
4
ch
a
n
n
els
in
t
h
e
ey
es
clo
s
ed
n
o
tio
n
f
o
r
2
m
in
u
tes
ar
e
s
am
p
led
at
2
5
0
Hz.
Data
is
i
m
p
o
r
ted
in
to
th
e
m
in
d
-
v
is
io
n
an
aly
ze
r
,
s
p
lin
e
in
ter
p
o
latio
n
is
ca
r
r
ied
o
u
t,
a
n
d
im
m
o
d
er
ate
ar
tifa
cts
ar
e
elim
i
n
ated
.
T
h
e
E
E
G
s
ig
n
al
u
n
d
er
g
o
es
ex
tr
ac
tio
n
o
f
th
e
s
ig
n
al
o
f
in
ter
est
u
s
in
g
th
e
f
ast
f
o
u
r
ier
tr
an
s
f
o
r
m
(
FF
T
)
,
d
ec
o
m
p
o
s
in
g
it
in
t
o
f
o
u
r
f
r
e
q
u
en
cy
b
an
d
s
:
d
elta
(
0
.
5
–
4
Hz
)
;
th
eta
(
4
–
8
Hz)
;
alp
h
a
(8
–
1
3
Hz)
;
b
eta
(
1
3
–
3
0
Hz)
[
1
7
].
T
h
e
B
io
s
em
i
d
ev
ice
r
ec
o
r
d
e
d
E
E
G
in
d
icato
r
s
s
am
p
led
co
n
tin
u
o
u
s
l
y
at
2
0
4
8
Hz,
s
eg
m
en
ted
o
f
f
-
li
n
e
in
to
1
.
7
5
-
s
ec
o
n
d
ep
o
ch
s
.
T
h
e
ev
en
t
-
r
elate
d
p
o
ten
tial
(
E
R
P
)
in
d
icato
r
s
th
at
wer
e
o
b
tain
e
d
wer
e
b
aselin
e
c
o
r
r
ec
ted
with
th
e
ai
d
o
f
av
e
r
a
g
in
g
th
e
s
ig
n
als
th
e
ca
u
s
e
o
f
p
r
e
-
p
r
o
ce
s
s
in
g
is
to
p
u
t
o
f
f
u
n
wan
ted
n
o
is
e
an
d
o
r
g
an
ize
th
e
s
ig
n
als
b
ased
o
n
ap
p
licab
le
f
ea
tu
r
es
[
1
8
]
.
Fo
llo
wed
b
y
p
r
e
-
p
r
o
ce
s
s
in
g
th
e
v
al
u
es a
r
e
ass
ig
n
ed
n
u
m
er
ical
ex
p
r
ess
io
n
s
.
T
h
e
v
ar
iety
o
f
ca
p
ab
ilit
ies v
ar
ies
f
r
o
m
1
2
-
2
5
6
[
19
].
2
.
2
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
T
h
e
m
ath
em
atica
l
to
o
l
f
o
r
a
n
a
ly
zin
g
E
E
G
is
th
e
FF
T
,
wh
er
e
th
e
p
o
wer
s
p
ec
tr
al
d
en
s
ity
is
ca
lcu
lated
f
o
r
all
f
o
u
r
f
r
eq
u
en
cy
b
a
n
d
s
.
T
h
e
p
er
io
d
o
g
r
a
m
is
g
en
er
a
ted
f
r
o
m
th
e
co
r
r
elate
d
s
eq
u
en
ce
.
T
h
e
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
is
a
s
y
s
tem
atic
m
eth
o
d
u
s
ed
f
o
r
f
ea
t
u
r
e
e
x
tr
ac
tio
n
.
Ou
t
o
f
th
e
s
ev
en
Da
u
b
ec
h
ies
(
d
b
)
,
o
n
e
p
r
o
v
es
to
b
e
a
n
ef
f
icien
t
o
n
e
f
o
r
d
y
s
lex
ia
an
aly
s
is
[
2
0
]
.
T
h
e
E
E
G
s
ig
n
al
is
s
p
lit
in
to
d
if
f
er
en
t
f
r
e
q
u
en
cies
u
s
in
g
two
s
ets
o
f
f
u
n
ctio
n
s
.
T
h
e
ap
p
r
o
x
im
ate
co
e
f
f
icien
t
i
s
f
u
r
th
er
d
ec
o
m
p
o
s
ed
i
n
to
5
l
ev
els,
an
d
th
e
th
ir
d
d
e
t
a
i
l
e
d
l
e
v
e
l
o
f
p
o
w
e
r
g
i
v
e
s
1
6
–
3
2
H
z
,
w
h
i
c
h
i
s
t
h
e
b
e
t
a
b
a
n
d
o
f
t
h
e
E
E
G
s
i
g
n
a
l
t
h
a
t
i
n
c
r
e
a
s
e
s
f
o
r
d
y
s
l
e
x
i
c
s
[
2
1
]
.
E
E
G
b
ased
an
aly
s
is
ca
n
b
e
d
o
n
e
in
tim
e
d
o
m
ain
,
f
r
eq
u
en
c
y
an
d
tim
e
f
r
e
q
u
en
c
y
d
o
m
ain
in
n
o
v
ativ
e
f
ea
tu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
2
,
No
v
em
b
er
20
24
:
9
9
4
-
1
001
996
e
x
tr
ac
tio
n
ca
n
p
r
o
v
id
e
ac
cu
r
a
cy
an
d
r
eliab
le
r
esu
lts
Usi
n
g
a
s
s
is
tiv
e
tech
n
o
lo
g
ies
lik
e
B
C
I
p
r
o
v
id
es
en
h
an
ce
d
r
esu
lts
wh
en
ch
an
n
el
s
elec
tio
n
is
d
o
n
e
u
s
in
g
m
u
lti
-
ch
an
n
el
B
C
I
.
2
.
3
.
F
e
a
t
ure
re
du
ct
io
n
Dif
f
er
en
t
d
ata
r
ed
u
ctio
n
m
e
th
o
d
s
co
m
p
r
is
e
in
d
ep
e
n
d
en
t
co
m
p
o
n
e
n
ts
an
aly
s
is
(
I
C
A)
,
p
r
in
cip
al
co
m
p
o
n
en
ts
an
aly
s
is
(
PC
A)
,
an
d
d
is
cr
im
in
an
t
an
al
y
s
is
(
L
DA)
.
Hig
h
d
im
en
s
io
n
al
d
ata
is
g
r
o
u
p
ed
in
to
lo
wer
d
im
en
s
io
n
a
b
y
f
o
r
m
in
g
s
u
b
s
et
s
u
ch
f
o
r
tr
ain
in
g
an
d
test
in
g
,
o
n
wh
ich
a
n
aly
s
is
ca
n
b
e
d
o
n
e
[
2
2
]
.
As
th
e
c
a
t
e
g
o
r
y
o
f
d
a
t
a
i
s
o
f
l
o
w
q
u
a
l
i
t
y
w
i
t
h
r
e
d
u
n
d
a
n
t
f
e
a
t
u
r
e
a
n
d
n
o
i
s
y
f
e
a
t
u
r
e
s
d
a
t
a
i
s
c
o
o
k
e
d
b
e
f
o
r
e
a
n
a
l
y
z
i
n
g
[
2
3
]
.
T
h
e
two
v
ag
u
e
ca
teg
o
r
ies,
n
am
ely
d
y
s
lex
ic
a
n
d
r
eg
u
lar
r
ea
d
er
s
,
ar
e
class
if
ied
u
s
in
g
r
ed
u
ce
d
r
ed
u
n
d
a
n
t
f
ea
tu
r
es a
n
d
less
co
m
p
lex
ity
with
b
ett
er
ac
cu
r
ac
y
.
2
.
4
.
Cla
s
s
if
ica
t
io
n
Ma
ch
in
e
l
ea
r
n
in
g
alg
o
r
ith
m
s
ar
e
p
r
o
v
e
n
class
if
ier
s
u
s
ed
f
o
r
clin
ical
d
iag
n
o
s
tics
.
T
h
e
o
u
tco
m
e
o
f
th
e
class
if
ier
m
ay
b
e
s
k
illed
u
s
in
g
s
u
p
er
v
is
ed
o
r
u
n
s
u
p
e
r
v
is
ed
tr
ain
in
g
an
d
ac
c
u
r
ac
y
,
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
m
ay
b
e
o
b
tain
e
d
.
s
u
p
p
o
r
t
v
e
cto
r
m
ac
h
in
es
(
SVM)
,
n
eu
r
al
n
etwo
r
k
s
,
d
ec
is
io
n
tr
ee
s
,
B
ay
esian
class
if
ier
s
,
K
m
ea
n
s
clu
s
ter
in
g
,
an
d
lo
g
is
tic
r
eg
r
ess
io
n
ar
e
v
ar
ied
class
if
ier
s
th
at
p
r
o
v
id
e
class
if
icati
o
n
o
f
m
etr
ics
[
2
4
]
.
Usma
n
et
a
l.
[
2
5
]
d
id
an
a
n
aly
s
is
o
n
th
e
p
r
im
ar
y
d
ev
ice
m
aster
in
g
b
i
o
m
ar
k
e
r
s
an
d
ch
allen
g
es
p
r
im
ar
ily
b
ased
o
n
th
e
o
u
tp
u
t
o
f
twen
ty
-
two
d
ec
id
ed
o
n
ar
ticles
th
e
u
s
e
o
f
P
R
I
SMA.
T
h
ey
co
n
clu
d
e
d
th
at
SVM
is
p
r
o
v
ed
to
b
e
th
e
f
ir
s
t
-
class
class
if
ier
th
a
t
o
f
f
er
s
n
ice
o
u
tco
m
es
r
eg
ar
d
l
ess
o
f
ex
tr
ao
r
d
in
a
r
y
ass
ets
o
f
r
ec
o
r
d
s
.
I
n
o
r
d
er
to
en
ab
le
th
e
o
p
en
u
n
iv
er
s
ity
f
o
r
d
ev
elo
p
in
g
s
u
itab
le
co
u
r
s
es
f
o
r
tr
ain
in
g
lo
w
-
en
g
a
g
ed
s
tu
d
en
ts
a
s
u
itab
le
m
o
d
el
was
d
ev
elo
p
ed
an
d
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
SVM,
d
ec
is
io
n
tr
ee
,
g
r
ad
ien
t
b
o
o
s
ted
,
Nav
ie
b
ay
es
class
if
ier
s
wer
e
u
s
ed
.
On
an
aly
zin
g
th
e
s
tatis
tical
p
ar
am
eter
s
k
ap
p
a,
r
ec
all,
a
n
d
ac
cu
r
ac
y
was
o
b
tain
ed
.
L
o
g
is
tic
r
eg
r
ess
io
n
is
an
ef
f
ec
tiv
e
tech
n
iq
u
e
t
o
clea
r
u
p
th
e
ca
teg
o
r
y
p
r
o
b
lem
an
d
to
g
et
t
h
e
ex
p
ec
ted
r
esu
lts
.
T
h
u
s
,
f
in
al
r
esu
lts
ar
e
c
o
n
tin
u
ally
b
ased
to
tally
o
n
t
h
e
ch
o
ice
o
f
th
e
p
r
o
p
er
v
er
s
io
n
to
r
eso
lv
e
a
s
p
ec
if
ic
p
r
o
b
lem
[
2
6
]
.
2
.
5
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n
Ma
ch
in
e
lear
n
in
g
alg
o
r
ith
m
s
ar
e
p
r
o
v
e
n
class
if
ier
s
u
s
ed
f
o
r
clin
ical
d
iag
n
o
s
tics
.
T
h
e
o
u
tco
m
e
o
f
th
e
class
if
ier
m
ay
b
e
s
k
illed
u
s
in
g
s
u
p
er
v
i
s
ed
o
r
u
n
s
u
p
er
v
is
ed
tr
ain
in
g
,
an
d
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
an
d
s
p
ec
if
icity
m
ay
b
e
o
b
tain
ed
.
SVM,
n
eu
r
al
n
etwo
r
k
s
,
d
ec
is
io
n
tr
ee
s
,
B
ay
esian
class
if
ier
s
,
K
-
m
ea
n
s
clu
s
ter
in
g
,
a
n
d
lo
g
is
tic
r
eg
r
ess
io
n
ar
e
clas
s
if
i
er
s
th
at
p
r
o
v
id
e
th
e
class
if
ica
tio
n
o
f
f
ac
ts
.
Fig
u
r
e
1
d
em
o
n
s
tr
ates
th
e
v
ar
io
u
s
lev
el
o
f
an
aly
s
is
o
f
E
E
G
s
ig
n
als
with
ar
tifa
cts
an
d
n
o
is
es.
On
th
e
o
th
er
h
an
d
,
th
e
in
p
u
t
d
ataset
f
o
r
th
e
d
y
s
lex
ia
class
if
icatio
n
in
th
i
s
h
y
p
o
th
esis
co
m
p
r
is
es
in
te
r
v
al
v
alu
es
th
at
ar
e
in
itially
tr
an
s
f
o
r
m
ed
in
to
m
id
p
o
in
ts
a
n
d
th
en
in
to
an
in
t
u
itio
n
is
tic
f
u
zz
y
d
o
m
ain
r
ep
r
e
s
en
tatio
n
.
T
h
e
s
elec
ted
in
s
tan
ce
'
s
m
is
s
in
g
v
alu
es
ar
e
ch
o
s
en
,
a
n
d
th
e
r
em
ain
in
g
ch
ar
ac
ter
is
tics
th
at
ar
e
co
m
p
ar
ed
to
t
h
o
s
e
o
f
o
th
er
e
x
am
p
les
in
th
e
f
u
ll
s
et.
Data
is
d
iv
id
ed
in
to
tr
ain
in
g
an
d
test
s
ets
u
s
in
g
an
a
p
p
r
o
p
r
iate
m
ac
h
in
e
lear
n
in
g
t
ec
h
n
iq
u
e,
a
n
d
th
e
class
if
icatio
n
p
ar
am
eter
s
ar
e
c
o
n
f
ir
m
e
d
.
Fig
u
r
e
1
.
Var
io
u
s
s
tag
es
f
o
r
E
E
G
s
ig
n
al
p
r
o
ce
s
s
in
g
3.
P
RO
P
O
SE
D
SYS
T
E
M
T
h
is
f
r
am
ewo
r
k
,
illu
s
tr
ated
i
n
Fig
u
r
e
2
,
p
r
o
v
id
es
a
f
o
u
n
d
atio
n
f
o
r
th
e
i
n
ter
co
n
n
ec
ted
ap
p
r
o
ac
h
,
wh
ich
r
en
d
er
s
it
m
o
r
e
lik
ely
to
d
iag
n
o
s
e
d
y
s
lex
ia
ac
cu
r
atel
y
.
T
h
e
d
ataset
is
im
p
lem
en
tatio
n
u
s
es
MA
T
L
A
B
2
0
1
3
a
s
o
f
twar
e
with
4
GB
R
AM
an
d
2
.
3
0
GHZ
p
r
o
ce
s
s
o
r
.
T
h
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
p
r
o
v
id
e
d
t
h
e
f
in
est
s
o
lu
tio
n
i
n
th
e
d
y
s
lex
i
a
d
etec
tio
n
in
s
id
e
th
e
KE
E
L
d
atasets
an
d
id
en
tify
d
y
s
lex
ia
an
d
n
o
r
m
al
co
n
tr
o
ls
.
T
h
e
d
ataset
e
n
co
m
p
ass
es
attr
i
b
u
tes
co
u
n
t o
f
1
2
an
d
n
o
o
u
tp
u
t
lab
els
is
2
with
m
is
s
in
g
v
al
u
es
(
X/Y)
wh
ich
ar
e
r
ep
lace
d
b
y
d
ete
r
m
in
in
g
KNN
b
etwe
en
th
eir
o
b
tain
ed
m
e
an
v
alu
e
f
r
o
m
th
e
n
ea
r
est
n
ei
g
h
b
o
r
.
T
h
e
ac
q
u
i
r
ed
d
ataset
h
ad
u
n
d
er
g
o
n
e
u
p
s
am
p
lin
g
an
d
d
o
w
n
s
am
p
lin
g
.
T
h
e
em
p
ir
ical
s
tu
d
y
tak
es
p
lace
b
y
s
p
litt
in
g
th
e
d
ata
in
to
t
r
ain
in
g
s
et
an
d
test
s
et
with
1
0
f
o
ld
cr
o
s
s
v
alid
atio
n
to
o
b
tain
t
h
e
d
y
s
lex
ic
an
d
n
o
r
m
al
co
n
tr
o
ls
.
T
h
e
ac
tu
al
class
o
b
tain
ed
is
co
m
p
a
r
ed
with
p
r
e
d
icted
class
an
d
a
cc
u
r
ac
y
,
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
ar
e
o
b
tain
e
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
P
erfo
r
ma
n
ce
o
f d
yslexia
d
a
ta
s
et
fo
r
ma
ch
in
e
lea
r
n
in
g
a
lg
o
r
i
th
ms
(
J.
Jin
cy
)
997
Fig
u
r
e
2
.
Pro
p
o
s
ed
b
lo
ck
d
iag
r
am
Fo
r
m
ed
ical
team
s
to
g
ain
s
o
c
ial
b
en
ef
its
,
th
ese
co
m
b
in
e
d
d
y
s
lex
ia
p
r
ed
ictio
n
m
o
d
el
em
p
l
o
y
in
g
th
e
K
EEL
d
ata
s
et
o
f
f
er
s
an
ev
alu
atio
n
o
f
a
c
o
m
p
ar
a
b
le
ex
p
er
im
en
t
[
2
7
]
.
B
y
co
m
b
in
in
g
n
u
m
er
o
u
s
f
ea
tu
r
e
co
m
p
o
n
en
ts
,
it
ca
n
o
f
f
er
m
ea
n
in
g
f
u
l
i
n
f
o
r
m
atio
n
o
n
th
e
u
n
d
er
p
in
n
i
n
g
tr
en
d
s
an
d
f
ea
t
u
r
e
s
o
f
th
e
d
ata.
Ou
t
o
f
th
e
s
ca
r
city
o
f
d
ata
th
is
ea
r
ly
d
iag
n
o
s
is
m
eth
o
d
p
r
o
v
id
es
a
p
latf
o
r
m
f
o
r
g
iv
in
g
co
n
f
id
en
c
e
in
jo
u
r
n
ey
o
f
o
u
r
s
tu
d
y
with
lim
ited
r
eso
u
r
ce
s
.
4.
M
E
T
H
O
DS
O
ur
s
u
g
g
ested
ap
p
r
o
a
ch
wo
r
k
s
b
y
u
s
in
g
a
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
to
id
en
tif
y
d
y
s
lex
ia
p
r
ed
ictio
n
h
o
ts
p
o
ts
an
d
ad
ap
t
r
esear
ch
o
b
jectiv
es
ac
co
r
d
in
g
ly
.
Usi
n
g
a
tr
ain
ed
alg
o
r
ith
m
,
th
e
u
n
lab
el
ed
test
d
ataset
was
m
ap
p
ed
to
id
en
tif
y
s
im
ilar
class
e
s
[
28
].
B
ase
d
o
n
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
in
v
esti
g
ated
b
y
T
u
r
k
is
h
p
r
o
f
ess
io
n
al
[
2
9
]
u
s
in
g
C
AR
T
an
d
C
h
i
s
q
u
ar
e
m
o
d
el
h
as
lo
w
er
r
o
r
r
ate
an
d
ca
n
b
e
u
s
ed
f
o
r
m
o
r
e
g
en
er
alize
d
d
ata.
KNN
v
ar
ian
ts
s
h
o
wed
th
at
it
ca
n
b
e
u
s
ed
f
o
r
an
y
d
atas
et
o
win
g
to
th
e
f
ac
t
o
f
its
v
er
s
atility
an
d
o
p
en
to
ch
an
g
e.
I
t
h
as
less
b
ias
an
d
h
ig
h
p
o
ten
tial
to
cr
e
ate
ac
cu
r
at
e
class
if
icatio
n
f
o
r
g
r
ea
ter
v
al
u
e
o
f
K
[
3
0
]
.
T
h
e
r
esear
ch
e
r
s
f
r
o
m
Pak
is
tan
p
r
o
p
o
s
ed
SVM
ap
p
r
o
ac
h
f
u
r
n
is
h
es
th
at
h
eter
o
g
en
e
o
u
s
d
ata
ca
n
b
e
class
i
f
ied
with
o
p
tim
al
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
[
3
1
]
.
Hu
et
a
l.
[
3
2
]
p
r
a
ctice
d
L
DA
to
o
b
tain
d
im
en
s
io
n
ality
r
ed
u
cti
on
,
p
r
o
v
id
i
n
g
ef
f
ec
tiv
e
f
o
r
s
am
p
le
d
ata
with
lo
w
co
s
t.
Ou
r
class
if
ier
'
s
o
v
er
all
p
er
f
o
r
m
an
ce
is
c
o
n
s
id
er
ed
b
ased
o
n
th
e
co
n
f
u
s
io
n
m
atr
ix
a
n
d
R
OC
(
r
ec
eiv
er
'
s
wo
r
k
in
g
c
u
r
v
e)
.
I
n
L
DA
is
a
class
if
ier
with
[
3
3
]
,
m
u
lt
i
class
es
(
d
ep
en
d
e
n
t
v
ar
iab
les)
ar
e
d
escr
ib
ed
b
ase
d
o
n
tar
g
et
(
in
d
ep
en
d
en
t
v
a
r
iab
les)
.
T
h
e
d
if
f
er
en
t
1
2
attr
ib
u
tes
o
f
d
y
s
lex
ia
ar
e
class
if
ied
b
as
ed
o
n
th
e
o
n
t
h
e
tar
g
et
class
es
.
T
h
e
g
r
ad
ien
t
b
ased
L
DA
with
lo
ca
l
m
in
im
a
is
u
s
ed
to
r
ed
u
ce
th
e
co
s
t
f
u
n
ctio
n
c
au
s
ed
b
y
th
e
ac
tu
al
an
d
p
r
ed
icted
o
u
tp
u
t
iter
ativ
e
ly
.
T
h
e
lear
n
in
g
r
ate
is
ch
o
s
en
s
u
ch
t
h
at
co
n
v
er
g
en
ce
is
o
b
tain
ed
with
least
o
s
c
i
ll
a
t
i
o
n
s
.
I
t
c
a
n
b
e
s
c
a
l
a
b
l
e
f
o
r
o
t
h
e
r
l
a
r
g
e
r
d
a
t
a
s
et
a
n
d
f
l
e
x
ib
l
e
.
A
l
g
o
r
i
t
h
m
f
o
r
L
D
A
s
h
o
w
n
i
n
A
l
g
o
r
i
t
h
m
1
.
Alg
o
r
ith
m
1.
L
DA
1:Pick A Random Starting Point X=Random(X)
2:Assign The Valuethreshold=0.000001
While
Condition Is True;
Gradient = Compute_Gradient(X)
Next_X=Ste
p(X, Gradient, Alpha=
-
0,001)
If Distance (Next_X, X)<Threshold ;
3: Assign Gradient Negative Step
4:When C
onverging Attained Process Stop
Break;
5:
Continue If We Are Not
Return X X=Next_X
SVM
ap
p
r
o
ac
h
o
u
t
p
er
f
o
r
m
s
L
DA
b
ased
o
n
d
ec
is
io
n
b
o
u
n
d
ar
y
an
d
e
r
r
o
r
r
ate
th
u
s
s
tan
d
s
s
u
p
er
io
r
[
3
4
]
.
T
h
u
s
,
im
p
o
r
te
d
d
ataset
u
n
d
er
g
o
es
tr
ain
-
test
s
p
lit
an
d
1
0
f
o
ld
c
r
o
s
s
v
alid
atio
n
an
d
u
s
in
g
R
ad
ial
b
ias
f
u
n
ctio
n
th
e
attr
ib
u
tes
ar
e
tr
ain
ed
,
class
if
icatio
n
is
d
o
n
e
to
o
b
tain
o
p
tim
al
ac
cu
r
ac
y
.
A
l
g
o
r
i
t
h
m
f
o
r
SV
M
s
h
o
w
n
i
n
A
l
g
o
r
it
h
m
2
.
Alg
o
r
ith
m
2.
SVM
1: Start the partitioning
2: Check For j=1:k
3: determine the training set= k
-
1subsets;
4: Assume Testing set=remaining subsets;
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
2
,
No
v
em
b
er
20
24
:
9
9
4
-
1
001
998
5: Obtain Parameter_ optimization (k);
6:
Again test on testing set & End the for statement;
7: Return accuracy of entir
e dataset
Decision Tree works as follows:
As
we
d
ea
l
with
lo
w
q
u
ality
d
ata
d
ec
is
io
n
tr
ee
class
if
ier
s
ar
e
ef
f
icie
n
t
in
class
if
y
in
g
m
i
s
s
in
g
d
ata
s
im
p
lify
in
g
in
to
s
im
p
ler
m
o
d
els
with
r
o
b
u
s
t
ex
ce
p
tio
n
s
[
3
5
]
f
r
o
m
th
e
d
ataset
s
u
b
s
et
ar
e
f
o
r
m
e
d
as
k
ey
1
lis
t
an
d
k
e
y
2
lis
t
b
ased
o
n
s
p
ec
if
ic
attr
ib
u
te.
Fu
r
t
h
er
s
p
litt
in
g
is
d
o
n
e
b
y
m
ea
s
u
r
in
g
en
tr
o
p
y
v
alu
e
b
ased
o
n
p
o
s
itiv
e
an
d
n
eg
ativ
e
class
es
m
ax
im
u
m
li
k
elih
o
o
d
tr
ain
i
n
g
is
to
r
e
d
u
ce
t
h
e
co
m
p
le
x
ity
.
A
l
g
o
r
i
t
h
m
f
o
r
d
e
c
i
s
i
o
n
t
r
ee
s
h
o
w
n
i
n
A
l
g
o
r
i
th
m
3
.
Alg
o
r
ith
m
3
.
Dec
is
io
n
tr
ee
1: Start keeping first attributes and the class attribute.
2:
Co
mp
ar
e
th
e
at
tr
ib
ut
e
na
me
fr
om
th
e
ke
y1
li
st
an
d
ke
y2
li
st
,
wh
er
e
ke
y1
is
th
e
li
st
to
st
or
e
at
tr
ib
ut
es
na
me
s
ba
se
d
on
th
e
as
ce
nd
in
g
or
d
er
of
th
e
en
tr
op
y
va
lu
e,
an
d
ke
y2
is
th
e
li
st to store attributes names in original order.
3:
Bo
th
ar
e
sa
me
th
en
re
m
ov
e
th
e
at
tr
ib
ut
es
fr
om
t
he
da
ta
se
t
an
d
al
so
re
mo
v
e
th
e
at
tr
ib
ut
e
from the key2 list and evaluate.
4: Do step until last attributes in the dataset.
K
m
ea
n
s
clu
s
ter
in
g
is
u
n
s
u
p
er
v
is
ed
clu
s
ter
in
g
alg
o
r
i
th
m
in
wh
ich
o
p
tim
al
eu
clid
ea
n
d
is
tan
ce
is
ca
lcu
lated
in
d
ataset.
I
t
p
r
o
v
id
es
a
p
r
ee
m
in
en
t
r
ec
all
r
ate
f
o
r
m
ed
ical
d
ataset
[
3
6
]
.
R
an
d
o
m
K
was
in
itialized
an
d
m
ea
n
was
ca
lcu
lated
.
T
h
e
m
ea
n
co
o
r
d
in
ated
is
u
p
d
ate
d
an
d
a
v
er
ag
e
is
ca
lcu
lated
.
R
ep
ea
ted
ly
iter
atin
g
we
g
et
th
e
clu
s
ter
o
f
d
y
s
lex
ic
an
d
n
o
r
m
al
r
ea
d
er
s
.
A
l
g
o
r
i
t
h
m
f
o
r
K
m
ea
n
s
clu
s
ter
in
g
s
h
o
w
n
i
n
A
l
g
o
r
i
t
h
m
4
.
Alg
o
r
ith
m
4
.
K
-
m
ea
n
s
clu
s
ter
i
n
g
1:
Ca
lc
ul
at
e
“d
(x
,
xi
)”
i
=1
,
2…
n;
wh
er
e
d
de
n
ot
es
th
e
Eu
cl
id
ea
n
di
st
a
nc
e
be
tw
ee
n
th
e
points.
2: Arrange the calculated n Euclidean distances in non
-
decreasing order.
3: Let k be a positive integer, take the first k distances from this sorted list.
4: Find those k
-
points corresponding to these k
-
distances.
5: Let ki denotes the number of point
s belonging to the ith class among k points i.e. k ≥ 0
6: If ki >kj
∀
i ≠ j then put x in class i.
Su
m
m
ar
izin
g
KNN
p
r
o
v
i
d
es
h
ig
h
er
er
r
o
r
p
r
ed
ictio
n
r
ate
an
d
with
f
ast
r
esp
o
n
s
e
.
Dy
s
lex
ia
d
ata
s
et
is
lar
g
e;
SVM
wi
th
h
ig
h
er
d
im
en
s
io
n
al
s
p
ac
e
an
d
non
lin
ea
r
m
o
d
els
ca
n
p
r
o
v
i
d
e
ef
f
icien
t
m
eth
o
d
s
o
f
co
m
p
ar
is
o
n
.
As
m
ac
h
in
e
is
tr
y
in
g
to
r
ep
lace
h
u
m
an
s
in
m
ed
i
ca
l
f
ie
ld
less
in
ter
v
e
n
ed
s
etu
p
to
war
d
s
p
r
e
d
ictio
n
o
f
d
y
s
lex
ia
ca
n
u
p
h
o
ld
th
e
s
o
ciety
wh
ich
in
n
ee
d
o
f
p
r
o
p
er
h
an
d
lin
g
.
Dep
lo
y
i
n
g
th
e
ab
o
v
e
m
o
d
els
ca
n
p
r
o
v
id
e
a
p
latf
o
r
m
o
n
wh
ich
a
n
aly
s
is
ca
n
b
e
b
u
ilt f
o
r
a
s
m
ar
t
er
s
o
ciety
.
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Ou
r
wo
r
k
u
tili
ze
s
Kee
l
r
esp
o
s
ito
r
y
d
ata
s
et
f
o
r
d
y
s
lex
ia
a
n
a
ly
s
is
u
s
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
an
d
2
×
2
co
n
f
u
s
io
n
m
at
r
ix
is
g
ain
ed
u
s
in
g
MA
T
L
AB
to
o
l
.
T
h
e
d
ataset
is
lo
w
q
u
ality
wit
h
6
5
in
s
tan
ce
s
with
1
2
attr
ib
u
tes
cr
is
p
an
d
v
ag
u
e
v
alu
es.
T
h
e
p
er
f
o
r
m
an
ce
m
e
a
s
u
r
em
en
ts
p
r
o
d
u
ce
d
f
o
r
ev
er
y
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
th
at
is
ev
alu
ated
ar
e
p
r
esen
ted
in
co
n
tin
g
en
c
y
tab
l
es.
I
n
th
e
m
atr
ix
,
ea
ch
r
o
w
r
ep
r
esen
ts
an
ac
t
u
al
class
o
cc
u
r
r
en
ce
,
an
d
ea
ch
c
o
lu
m
n
r
e
p
r
esen
ts
in
s
tan
ce
s
o
f
a
f
o
r
ec
ast
class
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
'
s
r
o
w
i
an
d
co
lu
m
n
j
ele
m
en
ts
in
d
icate
th
e
n
u
m
b
e
r
o
f
in
s
tan
ce
s
in
wh
ic
h
th
e
p
r
ed
icted
class
is
j
an
d
th
e
ac
tu
al
class
is
i.
T
ab
le
1
s
h
o
ws
th
e
r
esu
lts
o
f
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
L
DA
alg
o
r
ith
m
in
class
if
y
in
g
d
y
s
lex
ia
u
s
in
g
th
e
two
lab
els
tar
g
ets
o
r
o
u
tco
m
e
.
Ou
r
m
o
d
el
r
ec
o
g
n
iz
ed
,
2
5
d
y
s
lex
i
c
in
d
iv
id
u
als
an
d
g
r
o
u
p
e
d
as
d
y
s
lex
ic
(
T
p
)
wh
ile
3
2
s
k
illed
r
ea
d
er
s
ar
e
i
d
en
tifie
d
as sk
illed
r
ea
d
er
(T
n
)
.
Nev
er
th
eless
5
d
y
s
lex
ic
in
d
iv
id
u
als
ar
e
m
is
class
if
ied
a
s
s
k
illed
r
ea
d
er
s
(
F
n
)
an
d
3
s
k
i
ll
ed
r
ea
d
er
s
ar
e
m
is
class
if
ied
as
d
y
s
lex
ic
(F
p
)
w
ith
a
wid
e
m
a
r
g
in
o
f
s
ep
a
r
atio
n
.
I
n
p
ar
with
it
T
ab
le
2
d
ep
icts
th
e
r
esu
lts
o
f
th
e
SVM
alg
o
r
ith
m
in
class
if
y
in
g
d
y
s
lex
ia
with
o
p
tim
al
lin
e
.
Ou
r
m
o
d
el
r
ec
o
g
n
iz
ed
,
2
4
d
y
s
lex
ic
in
d
iv
id
u
als
an
d
g
r
o
u
p
ed
as
d
y
s
lex
ic
(
T
p
)
wh
ile
3
1
s
k
illed
r
ea
d
er
s
ar
e
id
en
tifie
d
as
s
k
illed
r
ea
d
e
r
(T
n
)
.
Nev
er
th
e
less
6
d
y
s
lex
ic
in
d
iv
id
u
als
ar
e
m
is
class
if
ied
as
s
k
illed
r
ea
d
er
s
(
F
n
)
an
d
3
s
k
i
lled
r
ea
d
er
s
ar
e
m
is
cl
ass
if
ied
as d
y
s
lex
ic
(F
p
)
.
T
ab
le
1
.
C
o
n
tin
g
en
cy
m
atr
ix
f
o
r
lin
ea
r
d
is
cr
im
in
ate
an
aly
s
is
A
c
t
u
a
l
v
s
p
r
e
d
i
c
t
e
d
D
y
sl
e
x
i
c
S
k
i
l
l
e
d
r
e
a
d
e
r
s
D
y
sl
e
x
i
c
2
5
(T
p
)
5
(
F
n
)
S
k
i
l
l
e
d
R
e
a
d
e
r
s
3
(
F
p
)
3
2
(
T
n
)
T
ab
le
2
.
C
o
n
tin
g
en
cy
m
atr
ix
f
o
r
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
in
e
A
c
t
u
a
l
v
s
p
r
e
d
i
c
t
e
d
D
y
sl
e
x
i
c
S
k
i
l
l
e
d
r
e
a
d
e
r
s
D
y
sl
e
x
i
c
25
(T
p
)
6
(
F
n
)
S
k
i
l
l
e
d
r
e
a
d
e
r
s
3
(
F
p
)
3
1
(
T
n
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
P
erfo
r
ma
n
ce
o
f d
yslexia
d
a
ta
s
et
fo
r
ma
ch
in
e
lea
r
n
in
g
a
lg
o
r
i
th
ms
(
J.
Jin
cy
)
999
A
Dec
i
s
io
n
tr
ee
class
if
ier
p
r
esen
ted
in
T
a
b
le
3
is
u
s
ed
f
o
r
h
an
d
li
n
g
n
o
n
lin
ea
r
r
elati
o
n
s
h
ip
f
o
r
class
if
y
in
g
d
y
s
lex
ia
.
Ou
r
m
o
d
el
r
ec
o
g
n
ize
d
,
2
5
d
y
s
lex
ic
in
d
iv
id
u
als
an
d
g
r
o
u
p
e
d
as
d
y
s
lex
ic
(
T
p
)
wh
ile
3
1
s
k
illed
r
ea
d
er
s
a
r
e
id
e
n
tifie
d
as
s
k
illed
r
ea
d
er
(T
n
)
.
Nev
e
r
t
h
eless
6
d
y
s
lex
ic
in
d
iv
i
d
u
als
ar
e
m
is
class
if
ied
as
s
k
illed
r
ea
d
er
s
(
F
n
)
a
n
d
3
s
k
i
l
led
r
ea
d
er
s
a
r
e
m
is
class
if
ied
as
d
y
s
lex
ic
(F
p
)
with
a
g
o
o
d
i
n
ter
p
r
etab
ilit
y
th
a
n
SVM
to
o
v
er
f
it
tr
ain
in
g
d
ata
.
T
ab
le
4
r
ep
r
esen
t
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
KNN
with
,
3
1
s
k
illed
r
ea
d
er
s
ar
e
id
en
tifie
d
as
s
k
illed
r
ea
d
er
(
T
n
)
.
Ne
v
er
th
eless
6
d
y
s
lex
ic
i
n
d
iv
id
u
als
ar
e
m
is
class
if
ied
as
s
k
illed
r
ea
d
er
s
(
Fn
)
an
d
3
s
k
illed
r
ea
d
er
s
ar
e
m
is
cl
ass
if
ied
as d
y
s
lex
ic
(
Fp
)
.
T
ab
le
3
.
C
o
n
tin
g
en
cy
m
atr
ix
f
o
r
d
ec
is
io
n
tr
ee
class
if
ier
A
c
t
u
a
l
v
s
p
r
e
d
i
c
t
e
d
D
y
sl
e
x
i
c
S
k
i
l
l
e
d
r
e
a
d
e
r
s
D
y
sl
e
x
i
c
2
5
(
T
p
)
6
(
F
n
)
S
k
i
l
l
e
d
r
e
a
d
e
r
s
3
(
F
p
)
3
1
(
T
n
)
T
ab
le
4
.
C
o
n
tin
g
en
cy
m
atr
ix
f
o
r
KNN
class
if
ier
A
c
t
u
a
l
v
s
p
r
e
d
i
c
t
e
d
D
y
sl
e
x
i
c
S
k
i
l
l
e
d
r
e
a
d
e
r
s
D
y
sl
e
x
i
c
24
(T
p
)
6
(
F
n
)
S
k
i
l
l
e
d
r
e
a
d
e
r
s
3
(F
p
)
3
1
(
T
n
)
T
h
is
k
in
d
o
f
d
ata
v
is
u
aliza
tio
n
d
is
p
lay
s
th
e
d
if
f
er
e
n
t
class
if
ier
s
'
p
er
f
o
r
m
a
n
ce
s
.
T
h
e
p
e
r
f
o
r
m
a
n
ce
m
etr
ics f
r
o
m
th
e
c
o
n
f
u
s
io
n
m
a
tr
ix
is
b
e
co
m
b
i
n
ed
to
g
et
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
an
d
s
p
ec
if
icit
y
:
To
ta
l A
cc
u
r
a
cy
=
∑
(
,
)
/
=
1
(
1
)
=
/
(
+
)
(
2)
=
/
(
+
)
(
3
)
T
p
=d
y
s
lex
ic
class
if
ied
as d
y
s
lex
ic
F
p
=
s
k
illed
r
ea
d
er
s
m
is
class
if
ie
d
as d
y
s
lex
ic
T
n
=
s
k
illed
r
ea
d
er
class
if
ied
as sk
illed
r
ea
d
er
s
F
n
=
d
y
s
lex
ic
m
is
class
if
ied
as s
k
illed
r
ea
d
er
s
C
o
m
p
ar
in
g
d
if
f
er
en
t
p
e
r
f
o
r
m
a
n
ce
s
m
etr
ics
d
er
iv
in
g
f
r
o
m
T
a
b
le
5
,
SVM
o
u
tp
er
f
o
r
m
s
o
th
er
a
lg
o
r
ith
m
with
an
ac
cu
r
ac
y
r
ate
o
f
9
0
.
7
6
%,
an
d
s
p
ec
if
ici
ty
o
f
9
1
.
8
9
%.
On
d
iv
i
n
g
f
u
r
th
e
r
th
e
s
en
s
itiv
ity
o
f
L
DA
is
8
9
.
2
8
%
n
ea
r
to
SVM
d
em
o
n
s
tr
atin
g
a
s
p
ec
i
f
ic
p
r
o
b
lem
id
en
tific
atio
n
.
T
ab
le
5
.
Alg
o
r
ith
m
m
o
d
els co
m
p
r
ess
io
n
r
esu
lt
A
l
g
o
r
i
t
h
m
S
e
n
s
i
t
i
v
i
t
y
(
%)
S
p
e
c
i
f
i
c
i
t
y
(
%)
A
c
c
u
r
a
c
y
(
%)
K
N
N
8
5
.
7
8
6
.
4
8
8
6
.
1
5
D
e
c
i
s
i
o
n
t
r
e
e
7
8
.
5
7
8
3
.
7
8
8
1
.
5
3
LD
A
8
9
.
2
8
8
6
.
4
8
8
7
.
6
9
S
V
M
8
9
.
2
8
9
1
.
8
9
9
0
.
7
6
T
h
e
g
r
ap
h
ical
r
ep
r
esen
tatio
n
c
h
ar
t
in
Fig
u
r
e
3
p
r
o
v
es
th
at
d
e
s
p
ite
o
f
th
e
lo
w
-
q
u
ality
d
ataset
,
b
o
o
s
ted
d
ec
is
io
n
tr
ee
class
if
ier
i
s
d
ea
l
in
g
with
m
is
s
in
g
v
alu
es
p
r
o
v
id
in
g
h
ig
h
e
r
s
en
s
itiv
ity
[
3
7
]
.
SVM
p
r
o
v
id
es
wid
e
s
ep
ar
atio
n
b
etwe
en
th
e
class
es
o
f
th
e
in
p
u
t
p
av
in
g
way
f
o
r
h
ig
h
er
ac
cu
r
ac
y
[
3
8
]
.
B
ein
g
an
in
tr
o
d
u
cto
r
y
class
if
ier
KNN
it
h
as
ad
d
r
ess
ed
th
e
p
atter
n
r
ec
o
g
n
itio
n
p
r
o
b
lem
b
y
co
n
s
id
er
in
g
th
e
d
ata
i
n
th
e
n
eig
h
b
o
r
d
ata
p
o
in
ts
f
o
r
s
m
aller
s
am
p
le
with
s
ig
n
if
ican
t sp
ec
if
icity
.
As
am
p
le
o
f
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
h
as
b
ee
n
r
ev
iewe
d
o
u
r
s
tu
d
y
u
s
es
f
ew
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
th
at
p
r
o
v
id
es
s
ig
n
i
f
ican
t
s
p
ec
if
icity
an
d
s
en
s
itiv
ity
.
W
h
ile
ea
r
lier
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
t
h
e
im
p
ac
t
o
f
d
y
s
lex
ia
in
ch
ild
r
en
in
th
e
d
if
f
er
en
t
ag
e
g
r
o
u
p
s
a
n
d
g
en
d
er
,
th
ey
h
a
v
e
n
o
t
e
x
p
licitly
ad
d
r
ess
ed
its
in
f
lu
en
ce
o
n
ea
r
ly
ch
ild
h
o
o
d
b
etwe
en
5
-
1
0
y
ea
r
s
.
Mo
r
eo
v
e
r
,
th
e
p
u
b
licly
av
ailab
le
d
ataset
is
h
a
v
in
g
s
m
all
s
am
p
les
co
m
p
r
im
is
in
g
o
f
ey
e
tr
ac
k
in
g
,
s
tan
d
ar
d
ize
d
test
,
F
MRI
an
d
q
u
esti
o
n
n
air
e.
T
h
is
s
tu
d
y
i
s
ten
d
ed
t
o
h
a
v
e
a
g
r
ea
ter
in
f
l
u
en
ce
o
n
u
tili
za
tio
n
o
f
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
to
g
iv
e
ac
c
u
r
ate
p
r
ed
ictio
n
with
o
u
t
b
ias.
W
e
f
o
u
n
d
th
at
th
e
p
er
f
o
r
m
an
ce
m
et
r
ics
o
f
v
ar
io
u
s
class
if
ier
s
ar
e
co
r
r
elate
d
a
n
d
s
u
cc
ess
iv
e
tr
ain
in
g
an
d
te
s
tin
g
ex
h
ib
it
th
eir
u
n
iq
u
en
ess
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
m
ay
b
en
ef
it
th
e
ec
o
n
o
m
ic
d
ev
elo
p
m
en
t
o
f
o
u
r
co
u
n
tr
y
with
o
u
t
ad
v
er
s
ely
im
p
ac
tin
g
illi
ter
ac
y
r
ate.
Ho
wev
er
,
h
y
b
r
id
izatio
n
ca
n
b
e
p
r
o
v
id
e
d
to
en
h
a
n
ce
th
e
p
er
f
o
r
m
an
ce
o
f
d
etec
tio
n
tech
n
iq
u
e
with
ef
f
icien
t f
ea
tu
r
e
r
e
d
u
ctio
n
tech
n
iq
u
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
2
,
No
v
em
b
er
20
24
:
9
9
4
-
1
001
1000
Fig
u
r
e
3
.
Gr
a
p
h
ical
r
ep
r
esen
tatio
n
o
f
v
ar
io
u
s
alg
o
r
ith
m
s
5.
CO
NCLU
SI
O
N
E
v
e
n
t
h
o
u
g
h
a
m
p
l
e
o
f
t
e
s
t
i
n
g
m
e
t
h
o
d
s
o
f
d
y
s
l
e
x
i
a
is
a
v
a
i
l
a
b
le
o
u
r
s
c
o
p
e
d
e
a
l
s
w
i
t
h
d
y
s
l
e
x
ia
d
i
a
g
n
o
s
is
u
s
i
n
g
E
E
G
i
n
a
p
i
n
c
h
,
t
h
e
r
e
s
e
a
r
c
h
e
r
s
a
n
d
m
e
d
i
c
al
p
r
a
ct
i
t
i
o
n
e
r
s
,
c
a
n
c
r
a
c
k
u
p
o
n
t
h
e
t
r
a
d
it
i
o
n
a
l
m
et
h
o
d
s
.
O
u
r
s
t
u
d
y
i
n
s
is
t
o
n
l
e
a
r
n
i
n
g
d
i
s
o
r
d
e
r
b
e
i
n
g
a
n
e
u
r
o
l
o
g
i
c
a
l
c
o
n
d
i
t
i
o
n
c
a
n
b
e
s
t
u
d
i
e
d
u
s
i
n
g
l
a
te
s
t
t
e
c
h
n
o
l
o
g
y
w
i
t
h
a
c
c
u
r
a
t
e
,
s
p
e
c
i
f
ic
r
e
s
u
l
t
wi
t
h
h
ig
h
d
e
g
r
e
e
s
e
n
s
i
t
i
v
it
y
.
T
h
is
v
a
r
io
u
s
m
a
c
h
i
n
e
le
a
r
n
i
n
g
a
p
p
r
o
a
c
h
i
s
a
n
e
y
e
o
p
e
n
e
r
to
t
h
e
S
p
e
c
i
a
l
e
d
u
c
a
ti
o
n
t
e
a
c
h
e
r
s
,
d
o
c
t
o
r
s
,
a
n
d
c
h
i
l
d
r
e
n
.
I
n
f
u
t
u
r
e
t
h
i
s
c
o
n
d
i
t
i
o
n
i
s
l
o
o
k
e
d
u
p
o
n
a
s
a
d
e
f
i
c
i
e
n
c
y
t
h
a
t
i
s
c
u
r
a
b
l
e
r
at
h
e
r
t
h
a
n
c
a
u
s
i
n
g
s
e
t
b
a
c
k
i
n
s
c
h
o
o
l
e
d
u
c
at
i
o
n
m
ak
i
n
g
o
u
r
c
o
u
n
t
r
y
d
o
o
m
e
d
t
o
d
a
r
k
n
e
s
s
.
ACK
NO
WL
E
G
M
E
N
T
Au
th
o
r
s
th
an
k
th
eir
co
lleg
e
m
an
a
g
em
en
t
f
o
r
p
r
o
v
id
i
n
g
th
eir
s
u
p
p
o
r
t
a
n
d
in
f
r
astru
ctu
r
e
to
war
d
s
th
e
co
m
p
letio
n
o
f
th
e
r
esear
ch
w
o
r
k
.
W
e
also
ex
p
r
ess
o
u
r
s
in
ce
r
e
g
r
atitu
d
e,
t
o
s
in
ce
r
e
h
ea
r
ts
wh
o
s
h
ed
th
eir
gu
id
in
g
lig
h
t to
ac
c
o
m
p
lis
h
th
i
s
s
tu
d
y
with
d
ed
icatio
n
a
n
d
h
a
r
d
wo
r
k
.
RE
F
E
R
E
NC
E
S
[
1
]
T.
N
.
I
.
E
x
p
r
e
ss,
“
D
y
s
l
e
x
i
a
n
o
t
j
u
st
a
men
t
a
l
h
e
a
l
t
h
p
r
o
b
l
e
m,
i
t
’
s a
so
c
i
a
l
p
r
o
b
l
e
m
,
sa
y
s
e
x
p
e
r
t
,
”
2
0
2
0
.
[
2
]
J
.
J
i
n
c
y
a
n
d
P
.
S
.
H
.
J
o
s
e
,
“
S
u
r
v
e
y
o
n
i
n
t
e
r
v
e
n
t
i
o
n
a
n
d
d
i
a
g
n
o
s
i
s
o
f
d
y
s
l
e
x
i
a
,
”
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
A
d
v
a
n
c
e
s
i
n
E
l
e
c
t
r
i
c
a
l
,
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
S
u
s
t
a
i
n
a
b
l
e
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
A
E
C
T
)
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
E
C
T
4
9
1
3
0
.
2
0
2
1
.
9
3
9
2
6
0
6
.
[
3
]
P
.
D
r
o
t
á
r
a
n
d
M
.
D
o
b
e
š,
“
D
y
s
g
r
a
p
h
i
a
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
0
,
n
o
.
1
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
0
-
7
8
6
1
1
-
9.
[
4
]
S
.
H
a
b
e
r
st
r
o
h
a
n
d
G
.
S
c
h
u
l
t
e
-
K
ö
r
n
e
,
“
D
i
a
g
n
o
st
i
k
u
n
d
B
e
h
a
n
d
l
u
n
g
d
e
r
r
e
c
h
e
n
s
t
ö
r
u
n
g
,
”
D
e
u
t
sc
h
e
s
Arzt
e
b
l
a
t
t
I
n
t
e
rn
a
t
i
o
n
a
l
,
v
o
l
.
1
1
6
,
n
o
.
7
,
p
p
.
1
0
7
–
1
1
4
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
3
2
3
8
/
a
r
z
t
e
b
l
.
2
0
1
9
.
0
1
0
7
.
[
5
]
M
.
P
o
u
l
s
e
n
,
H
.
J
u
u
l
,
a
n
d
C
.
El
b
r
o
,
“
A
n
a
t
i
o
n
a
l
t
e
s
t
o
f
d
y
sl
e
x
i
a
,
”
An
n
a
l
s
o
f
D
y
s
l
e
x
i
a
,
v
o
l
.
7
3
,
n
o
.
3
,
p
p
.
3
3
7
–
3
5
5
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
8
8
1
-
0
2
3
-
0
0
2
8
5
-
5.
[
6
]
G.
H
.
G
l
o
v
e
r
,
“
O
v
e
r
v
i
e
w
o
f
f
u
n
c
t
i
o
n
a
l
ma
g
n
e
t
i
c
r
e
s
o
n
a
n
c
e
i
ma
g
i
n
g
,
”
N
e
u
ro
su
r
g
e
ry
C
l
i
n
i
c
s
o
f
N
o
rt
h
Am
e
ri
c
a
,
v
o
l
.
2
2
,
n
o
.
2
,
p
p
.
1
3
3
–
1
3
9
,
A
p
r
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
c
.
2
0
1
0
.
1
1
.
0
0
1
.
[
7
]
S
.
M
o
h
a
ma
d
,
W
.
M
a
n
so
r
,
a
n
d
K
.
Y
.
Le
e
,
“
R
e
v
i
e
w
o
f
n
e
u
r
o
l
o
g
i
c
a
l
t
e
c
h
n
i
q
u
e
s o
f
d
i
a
g
n
o
s
i
n
g
d
y
sl
e
x
i
a
i
n
c
h
i
l
d
r
e
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
1
3
I
EE
E
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
S
y
st
e
m
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
I
C
S
ET
2
0
1
3
,
A
u
g
.
2
0
1
3
,
p
p
.
3
8
9
–
3
9
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
En
g
T.
2
0
1
3
.
6
6
5
0
2
0
6
.
[
8
]
A
.
J
o
t
h
i
P
r
a
b
h
a
a
n
d
R
.
B
h
a
r
g
a
v
i
,
“
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
f
o
r
d
y
s
l
e
x
i
a
f
r
o
m
f
i
x
a
t
i
o
n
s
a
n
d
sa
c
c
a
d
i
c
e
y
e
m
o
v
e
me
n
t
e
v
e
n
t
s,”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
ra
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
9
5
,
p
.
1
0
5
5
3
8
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
2
0
.
1
0
5
5
3
8
.
[
9
]
E.
K
.
L
a
mb
e
,
“
D
y
sl
e
x
i
a
,
g
e
n
d
e
r
,
a
n
d
b
r
a
i
n
i
ma
g
i
n
g
,
”
N
e
u
r
o
p
sy
c
h
o
l
o
g
i
a
,
v
o
l
.
3
7
,
n
o
.
5
,
p
p
.
5
2
1
–
5
3
6
,
F
e
b
.
1
9
9
9
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
0
2
8
-
3
9
3
2
(
9
8
)
0
0
1
4
6
-
8.
[
1
0
]
K
.
C
h
y
l
,
G
.
F
r
a
g
a
-
G
o
n
z
á
l
e
z
,
S
.
B
r
e
m,
a
n
d
K
.
J
e
d
n
o
r
ó
g
,
“
B
r
a
i
n
d
y
n
a
mi
c
s
o
f
(
a
)
t
y
p
i
c
a
l
r
e
a
d
i
n
g
d
e
v
e
l
o
p
men
t
—
a
r
e
v
i
e
w
o
f
l
o
n
g
i
t
u
d
i
n
a
l
s
t
u
d
i
e
s,
”
n
p
j
S
c
i
e
n
c
e
o
f
L
e
a
r
n
i
n
g
,
v
o
l
.
6
,
n
o
.
1
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
3
9
-
0
2
0
-
0
0
0
8
1
-
5.
[
1
1
]
M
.
B
i
sca
l
d
i
,
S
.
G
e
z
e
c
k
,
a
n
d
V
.
S
t
u
h
r
,
“
P
o
o
r
sac
c
a
d
i
c
c
o
n
t
r
o
l
c
o
r
r
e
l
a
t
e
s
w
i
t
h
d
y
s
l
e
x
i
a
,
”
N
e
u
ro
p
sy
c
h
o
l
o
g
i
a
,
v
o
l
.
3
6
,
n
o
.
1
1
,
p
p
.
1
1
8
9
–
1
2
0
2
,
N
o
v
.
1
9
9
8
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
0
2
8
-
3
9
3
2
(
9
7
)
0
0
1
7
0
-
X.
[
1
2
]
T.
A
s
v
e
st
o
p
o
u
l
o
u
e
t
a
l
.
,
“
D
y
sl
e
x
m
l
:
S
c
r
e
e
n
i
n
g
t
o
o
l
f
o
r
d
y
s
l
e
x
i
a
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
a
r
Xi
v
p
r
e
p
ri
n
t
a
r
Xi
v
:
1
9
0
3
.
0
6
2
7
4
,
2
0
1
9
.
[
1
3
]
E.
To
f
f
a
l
i
n
i
,
D
.
G
i
o
f
r
è
,
M
.
P
a
s
t
o
r
e
,
B
.
C
a
r
r
e
t
t
i
,
F
.
F
r
a
c
c
a
d
o
r
i
,
a
n
d
D
.
S
z
ű
c
s
,
“
D
y
sl
e
x
i
a
t
r
e
a
t
me
n
t
s
t
u
d
i
e
s:
a
s
y
st
e
mat
i
c
r
e
v
i
e
w
a
n
d
su
g
g
e
st
i
o
n
s
o
n
t
e
st
i
n
g
t
r
e
a
t
me
n
t
e
f
f
i
c
a
c
y
w
i
t
h
sma
l
l
e
f
f
e
c
t
s
a
n
d
sm
a
l
l
sam
p
l
e
s,”
Be
h
a
v
i
o
r
Re
se
a
rc
h
M
e
t
h
o
d
s
,
v
o
l
.
5
3
,
n
o
.
5
,
p
p
.
1
9
5
4
–
1
9
7
2
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
7
5
8
/
s1
3
4
2
8
-
0
2
1
-
0
1
5
4
9
-
x.
[
1
4
]
H
.
P
e
r
e
r
a
,
M
.
F
.
S
h
i
r
a
t
u
d
d
i
n
,
a
n
d
K
.
W
.
W
o
n
g
,
“
R
e
v
i
e
w
o
f
EEG
-
b
a
se
d
p
a
t
t
e
r
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
a
m
e
w
o
r
k
s
f
o
r
d
y
s
l
e
x
i
a
,
”
Bra
i
n
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
5
,
n
o
.
2
,
J
u
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
7
0
8
-
0
1
8
-
0
0
7
9
-
9.
[
1
5
]
M
.
J.
S
n
o
w
l
i
n
g
,
C
.
H
u
l
me
,
a
n
d
K
.
N
a
t
i
o
n
,
“
D
e
f
i
n
i
n
g
a
n
d
u
n
d
e
r
st
a
n
d
i
n
g
d
y
sl
e
x
i
a
:
p
a
s
t
,
p
r
e
s
e
n
t
a
n
d
f
u
t
u
r
e
,
”
O
x
f
o
r
d
Re
v
i
e
w
o
f
Ed
u
c
a
t
i
o
n
,
v
o
l
.
4
6
,
n
o
.
4
,
p
p
.
5
0
1
–
5
1
3
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
3
0
5
4
9
8
5
.
2
0
2
0
.
1
7
6
5
7
5
6
.
[
1
6
]
K
.
V
a
si
l
e
i
o
u
,
J.
B
a
r
n
e
t
t
,
S
.
T
h
o
r
p
e
,
a
n
d
T
.
Y
o
u
n
g
,
“
C
h
a
r
a
c
t
e
r
i
s
i
n
g
a
n
d
j
u
st
i
f
y
i
n
g
s
a
m
p
l
e
s
i
z
e
s
u
f
f
i
c
i
e
n
c
y
i
n
i
n
t
e
r
v
i
e
w
-
b
a
s
e
d
st
u
d
i
e
s:
S
y
st
e
ma
t
i
c
a
n
a
l
y
s
i
s
o
f
q
u
a
l
i
t
a
t
i
v
e
h
e
a
l
t
h
r
e
s
e
a
r
c
h
o
v
e
r
a
1
5
-
y
e
a
r
p
e
r
i
o
d
,
”
BM
C
M
e
d
i
c
a
l
R
e
se
a
rc
h
M
e
t
h
o
d
o
l
o
g
y
,
v
o
l
.
1
8
,
n
o
.
1
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
8
7
4
-
0
1
8
-
0
5
9
4
-
7.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
P
erfo
r
ma
n
ce
o
f d
yslexia
d
a
ta
s
et
fo
r
ma
ch
in
e
lea
r
n
in
g
a
lg
o
r
i
th
ms
(
J.
Jin
cy
)
1001
[
1
7
]
R
.
K
a
t
m
a
h
,
F
.
A
l
-
S
h
a
r
g
i
e
,
U
.
T
a
r
i
q
,
F
.
B
a
b
i
l
o
n
i
,
F
.
A
l
-
M
u
g
h
a
i
r
b
i
,
a
n
d
H
.
A
l
-
N
a
s
h
a
s
h
,
“
A
r
e
v
i
e
w
o
n
me
n
t
a
l
s
t
r
e
ss
a
ssess
me
n
t
met
h
o
d
s
u
s
i
n
g
e
e
g
s
i
g
n
a
l
s,
”
S
e
n
so
rs
,
v
o
l
.
2
1
,
n
o
.
1
5
,
p
.
5
0
4
3
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
1
1
5
5
0
4
3
.
[
1
8
]
A
.
F
r
i
d
a
n
d
L
a
r
r
y
M
.
M
a
n
e
v
i
t
z
,
“
F
e
a
t
u
r
e
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
c
o
r
r
e
l
a
t
i
n
g
a
n
d
c
l
a
ss
i
f
y
i
n
g
b
e
t
w
e
e
n
b
r
a
i
n
a
r
e
a
s a
n
d
d
y
sl
e
x
i
a
,
”
a
rXi
v
p
re
p
r
i
n
t
a
rXi
v
:
1
8
1
2
.
1
0
6
2
2
,
2
0
1
8
.
[
1
9
]
A
.
L.
G
o
l
a
n
d
e
a
n
d
T.
P
a
v
a
n
k
u
m
a
r
,
“
Ea
r
l
y
p
r
e
d
i
c
t
i
o
n
o
f
h
e
a
r
t
a
b
n
o
r
ma
l
i
t
i
e
s
u
si
n
g
r
o
b
u
st
p
r
e
-
p
r
o
c
e
ssi
n
g
a
n
d
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
i
o
n
a
l
g
o
r
i
t
h
m,
”
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
R
e
sea
r
c
h
i
n
D
y
n
a
m
i
c
a
l
a
n
d
C
o
n
t
ro
l
S
y
st
e
m
s
,
v
o
l
.
1
2
,
n
o
.
7
,
p
p
.
3
8
0
–
3
9
4
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
5
3
7
3
/
JA
R
D
C
S
/
V
1
2
I
7
/
2
0
2
0
2
0
1
9
.
[
2
0
]
S
.
P
a
r
m
a
r
a
n
d
C
.
P
a
u
n
w
a
l
a
,
“
A
n
o
v
e
l
a
n
d
e
f
f
i
c
i
e
n
t
w
a
v
e
l
e
t
s
c
a
t
t
e
r
i
n
g
t
r
a
n
sf
o
r
m
a
p
p
r
o
a
c
h
f
o
r
p
r
i
m
i
t
i
v
e
-
st
a
g
e
d
y
sl
e
x
i
a
-
d
e
t
e
c
t
i
o
n
u
si
n
g
e
l
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
m
si
g
n
a
l
s
,
”
H
e
a
l
t
h
c
a
re
An
a
l
y
t
i
c
s
,
v
o
l
.
3
,
p
.
1
0
0
1
9
4
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
a
l
t
h
.
2
0
2
3
.
1
0
0
1
9
4
.
[
2
1
]
A
.
C
h
a
d
d
a
d
,
Y
.
W
u
,
R
.
K
a
t
e
b
,
a
n
d
A
.
B
o
u
r
i
d
a
n
e
,
“
El
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
p
h
y
si
g
n
a
l
p
r
o
c
e
ssi
n
g
:
a
c
o
mp
r
e
h
e
n
si
v
e
r
e
v
i
e
w
a
n
d
a
n
a
l
y
si
s
o
f
m
e
t
h
o
d
s
a
n
d
t
e
c
h
n
i
q
u
e
s,”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
1
4
,
p
.
6
4
3
4
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
1
4
6
4
3
4
.
[
2
2
]
W
.
C
h
e
n
,
Y
.
C
a
i
,
A
.
L
i
,
Y
.
S
u
,
a
n
d
K
.
J
i
a
n
g
,
“
EEG
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
me
t
h
o
d
b
a
se
d
o
n
ma
x
i
m
u
m
i
n
f
o
r
ma
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
a
n
d
q
u
a
n
t
u
m
p
a
r
t
i
c
l
e
sw
a
r
m,”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
rt
s
,
v
o
l
.
1
3
,
n
o
.
1
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
3
-
4
1
6
8
2
-
5.
[
2
3
]
R
.
N
i
s
b
e
t
,
G
.
M
i
n
e
r
,
a
n
d
K
.
Y
a
l
e
,
“
A
d
a
t
a
p
r
e
p
a
r
a
t
i
o
n
c
o
o
k
b
o
o
k
,
”
i
n
H
a
n
d
b
o
o
k
o
f
S
t
a
t
i
s
t
i
c
a
l
A
n
a
l
y
si
s
a
n
d
D
a
t
a
Mi
n
i
n
g
Ap
p
l
i
c
a
t
i
o
n
s
,
El
s
e
v
i
e
r
,
2
0
1
7
,
p
p
.
7
2
7
–
7
4
0
.
[
2
4
]
A
.
S
u
b
a
si
a
n
d
M
.
I
.
G
u
r
so
y
,
“
EEG
si
g
n
a
l
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
P
C
A
,
I
C
A
,
L
D
A
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s,
”
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
.
3
7
,
n
o
.
1
2
,
p
p
.
8
6
5
9
–
8
6
6
6
,
D
e
c
.
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
0
.
0
6
.
0
6
5
.
[
2
5
]
O
.
L
.
U
s
m
a
n
,
R
.
C
.
M
u
n
i
y
a
n
d
i
,
K
.
O
m
a
r
,
a
n
d
M
.
M
o
h
a
m
a
d
,
“
A
d
v
a
n
c
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
f
o
r
d
y
s
l
e
x
i
a
b
i
o
m
a
r
k
e
r
d
e
t
e
c
t
i
o
n
:
a
r
e
v
i
e
w
o
f
i
m
p
l
e
m
e
n
t
a
t
i
o
n
d
e
t
a
i
l
s
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
9
,
p
p
.
3
6
8
7
9
–
3
6
8
9
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
1
.
3
0
6
2
7
0
9
.
[
2
6
]
S
.
S
p
e
r
a
n
d
e
i
,
“
U
n
d
e
r
st
a
n
d
i
n
g
l
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
a
n
a
l
y
si
s
,
”
Bi
o
c
h
e
m
i
a
Me
d
i
c
a
,
v
o
l
.
2
4
,
n
o
.
1
,
p
p
.
1
2
–
1
8
,
2
0
1
4
,
d
o
i
:
1
0
.
1
1
6
1
3
/
B
M
.
2
0
1
4
.
0
0
3
.
[
2
7
]
N
.
D
.
A
l
q
a
h
t
a
n
i
,
B
.
A
l
z
a
h
r
a
n
i
,
a
n
d
M
.
S
.
R
a
mz
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
f
o
r
d
y
sl
e
x
i
a
p
r
e
d
i
c
t
i
o
n
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
5
,
p
.
2
8
0
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
5
2
8
0
4
.
[
2
8
]
R
.
A
l
a
n
a
z
i
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
o
f
c
h
r
o
n
i
c
d
i
sea
ses
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
J
o
u
r
n
a
l
o
f
H
e
a
l
t
h
c
a
re
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
9
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
2
8
2
6
1
2
7
.
[
2
9
]
M
.
O
z
c
a
n
a
n
d
S
.
P
e
k
e
r
,
“
A
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
r
e
g
r
e
ss
i
o
n
t
r
e
e
a
l
g
o
r
i
t
h
m
f
o
r
h
e
a
r
t
d
i
s
e
a
se
mo
d
e
l
i
n
g
a
n
d
p
r
e
d
i
c
t
i
o
n
,
”
H
e
a
l
t
h
c
a
re
An
a
l
y
t
i
c
s
,
v
o
l
.
3
,
p
.
1
0
0
1
3
0
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
a
l
t
h
.
2
0
2
2
.
1
0
0
1
3
0
.
[
3
0
]
S
.
U
d
d
i
n
,
I
.
H
a
q
u
e
,
H
.
L
u
,
M
.
A
.
M
o
n
i
,
a
n
d
E
.
G
i
d
e
,
“
C
o
m
p
a
r
a
t
i
v
e
p
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
s
i
s
o
f
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
u
r
(
K
N
N
)
a
l
g
o
r
i
t
h
m
a
n
d
i
t
s
d
i
f
f
e
r
e
n
t
v
a
r
i
a
n
t
s
f
o
r
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
022
-
1
0
3
5
8
-
x.
[
3
1
]
S
.
M
.
S
.
S
h
a
h
,
F
.
A
.
S
h
a
h
,
S
.
A
.
H
u
ssai
n
,
a
n
d
S
.
B
a
t
o
o
l
,
“
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s
-
b
a
se
d
h
e
a
r
t
d
i
se
a
se
d
i
a
g
n
o
si
s
u
si
n
g
f
e
a
t
u
r
e
su
b
s
e
t
,
w
r
a
p
p
i
n
g
se
l
e
c
t
i
o
n
a
n
d
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
8
4
,
p
.
1
0
6
6
2
8
,
Ju
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
0
.
1
0
6
6
2
8
.
[
3
2
]
L.
H
u
,
J
.
X
u
,
L.
T
i
a
n
,
a
n
d
W
.
Z
h
a
n
g
,
“
S
e
l
f
-
c
e
n
t
r
a
l
i
z
e
d
j
o
i
n
t
l
y
s
p
a
r
se
max
i
mu
m
mar
g
i
n
c
r
i
t
e
r
i
o
n
f
o
r
r
o
b
u
st
d
i
me
n
si
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
,
”
K
n
o
w
l
e
d
g
e
-
B
a
s
e
d
S
y
st
e
m
s
,
v
o
l
.
2
0
6
,
p
.
1
0
6
3
4
3
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
2
0
.
1
0
6
3
4
3
.
[
3
3
]
A
.
S
h
a
r
ma
a
n
d
K
.
K
.
P
a
l
i
w
a
l
,
“
C
a
n
c
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
y
g
r
a
d
i
e
n
t
LD
A
t
e
c
h
n
i
q
u
e
u
si
n
g
m
i
c
r
o
a
r
r
a
y
g
e
n
e
e
x
p
r
e
s
si
o
n
d
a
t
a
,
”
D
a
t
a
a
n
d
K
n
o
w
l
e
d
g
e
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
6
6
,
n
o
.
2
,
p
p
.
3
3
8
–
3
4
7
,
A
u
g
.
2
0
0
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
t
a
k
.
2
0
0
8
.
0
4
.
0
0
4
.
[
3
4
]
R
.
M
a
d
h
a
n
a
g
o
p
a
l
,
R
.
C
.
A
v
i
n
a
a
s
h
,
a
n
d
K
.
K
a
r
t
h
i
c
k
,
“
C
o
mp
a
r
i
s
o
n
o
f
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s
a
n
d
l
i
n
e
a
r
d
i
s
c
r
i
m
i
n
a
n
t
a
n
a
l
y
si
s
f
o
r
i
n
d
i
a
n
i
n
d
u
s
t
r
i
e
s
,
”
S
t
a
t
i
s
t
i
k
a
M
a
t
h
e
m
a
t
i
k
a
,
v
o
l
.
4
,
n
o
.
3
,
p
p
.
7
4
–
8
0
,
2
0
1
2
.
[
3
5
]
Y
.
Y
.
S
o
n
g
a
n
d
L.
U
.
Y
i
n
g
,
“
D
e
c
i
si
o
n
t
r
e
e
me
t
h
o
d
s:
a
p
p
l
i
c
a
t
i
o
n
s
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
,
”
S
h
a
n
g
h
a
i
Ar
c
h
i
v
e
s
o
f
Psy
c
h
i
a
t
r
y
,
v
o
l
.
2
7
,
n
o
.
2
,
p
.
1
3
0
,
2
0
1
5
.
[
3
6
]
V
.
S
h
e
t
h
,
U
.
Tr
i
p
a
t
h
i
,
a
n
d
A
.
S
h
a
r
ma,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
p
u
r
p
o
s
e
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
1
5
,
p
p
.
4
2
2
–
4
3
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
2
.
1
2
.
0
4
4
.
[
3
7
]
J.
L
o
v
e
l
i
n
e
Ze
e
ma
a
n
d
D
.
F
r
a
n
c
i
s
X
a
v
i
e
r
C
h
r
i
st
o
p
h
e
r
,
“
E
v
o
l
v
i
n
g
o
p
t
i
mi
z
e
d
n
e
u
t
r
o
s
o
p
h
i
c
C
m
e
a
n
s
c
l
u
s
t
e
r
i
n
g
u
si
n
g
b
e
h
a
v
i
o
r
a
l
i
n
s
p
i
r
a
t
i
o
n
o
f
a
r
t
i
f
i
c
i
a
l
b
a
c
t
e
r
i
a
l
f
o
r
a
g
i
n
g
(
O
N
C
M
C
-
A
B
F
)
i
n
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
d
y
s
l
e
x
i
a
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
4
,
n
o
.
5
,
p
p
.
1
7
4
8
–
1
7
5
4
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
1
9
.
0
9
.
0
0
8
.
[
3
8
]
P
.
J.
R
o
s
e
,
“
U
n
c
e
r
t
a
i
n
t
y
b
a
s
e
d
c
h
a
o
t
i
c
p
i
g
e
o
n
i
n
s
p
i
r
e
d
o
p
t
i
mi
z
e
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
f
o
r
e
f
f
e
c
t
i
v
e
D
y
sl
e
x
i
a
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
d
e
n
s
i
t
y
p
e
a
k
c
l
u
s
t
e
r
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
a
n
d
D
i
g
i
t
a
l
S
y
st
e
m
s
,
v
o
l
.
1
4
,
n
o
.
1
,
2
0
2
3
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
J.
J
in
c
y
re
c
e
iv
e
d
h
e
r
U
G
in
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
In
str
u
m
e
n
tatio
n
En
g
i
n
e
e
rin
g
a
t
K
a
ru
n
y
a
Un
iv
e
rs
it
y
,
In
d
ia
.
S
h
e
d
i
d
h
e
r
P
G
in
E
m
b
e
d
d
e
d
sy
ste
m
i
n
th
e
sa
m
e
in
stit
u
te
i
n
t
h
e
y
e
a
r
2
0
0
8
.
Be
i
n
g
a
n
a
c
ti
v
e
Ac
a
d
e
m
icia
n
w
o
rk
i
n
g
i
n
CS
I
c
o
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
Ke
tt
i,
In
d
ia
fo
r
1
4
y
e
a
rs
is
w
o
r
k
in
g
fo
r
EE
G
b
a
se
d
d
y
sle
x
ia
a
n
a
ly
sis
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s.
He
r
a
re
a
s
o
f
i
n
tere
st
a
re
b
io
m
e
d
ica
l
si
g
n
a
l
p
ro
c
e
ss
in
g
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
p
u
b
li
sh
e
d
p
a
p
e
r
in
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
with
th
e
ti
tl
e
su
rv
e
y
o
n
in
terv
e
n
ti
o
n
a
n
d
d
iag
n
o
sis
o
f
d
y
sle
x
ia,
e
x
p
lo
ra
ti
o
n
o
f
lea
rn
in
g
d
iso
rd
e
r
u
si
n
g
m
a
c
h
i
n
e
lea
rn
in
g
a
n
d
p
re
li
m
i
n
a
ry
st
u
d
y
o
f
d
y
sle
x
ia
u
sin
g
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
j
in
c
y
d
h
a
s2
2
@g
m
a
il
.
c
o
m
.
P.
S
u
b
h
a
H
e
n
c
y
J
o
se
is
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
Ka
ru
n
y
a
In
sti
tu
t
e
o
f
Tec
h
n
o
l
o
g
y
a
n
d
S
c
ien
c
e
,
Ka
ru
n
y
a
Un
iv
e
rsity
,
In
d
ia.
S
h
e
h
o
l
d
s
P
h
.
D
.
d
e
g
re
e
in
p
r
o
c
e
ss
c
o
n
tro
l
e
n
g
i
n
e
e
rin
g
with
sp
e
c
ializa
ti
o
n
i
n
b
i
o
m
e
d
ica
l
i
n
stru
m
e
n
ts
a
n
d
a
rti
ficia
l
i
n
telli
g
e
n
c
e
in
h
e
a
lt
h
c
a
re
.
Be
i
n
g
a
n
e
m
in
e
n
t
r
e
se
a
rc
h
e
r
h
a
s
p
u
b
li
sh
e
d
p
a
p
e
r
in
4
3
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls,
3
8
in
ter
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s,
with
2
8
S
c
o
p
u
s
c
it
a
ti
o
n
s.
He
r
re
se
a
rc
h
p
ro
jec
t
in
c
lu
d
e
fe
tal
ECG
m
o
n
it
o
r
in
g
in
ru
ra
l
a
re
a
s,
h
e
a
lt
h
m
o
n
it
o
r
in
g
fo
r
p
re
g
n
a
n
t
wo
m
e
n
in
ru
ra
l
a
re
a
s
with
e
m
e
rg
e
n
c
y
tri
g
g
e
r
fo
r
v
isu
a
ll
y
imp
a
ired
a
n
d
so
o
n
.
As
a
su
c
c
e
ss
fu
l
m
e
n
to
r
s
h
e
h
a
s
c
o
m
p
lete
d
g
u
i
d
in
g
3
8
M
Tec
h
sc
h
o
lars
a
n
d
6
re
se
a
rc
h
s
c
h
o
l
a
r
o
n
f
o
r
p
u
r
s
u
i
n
g
t
h
e
s
i
s
w
o
r
k
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
h
e
n
c
y
2
0
0
0
2
0
0
0
@
k
a
r
u
n
y
a
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.