I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
9
,
No
.
1
,
Ap
r
il
2
0
2
0
,
p
p
.
5
7
~
6
2
I
SS
N:
2252
-
8
7
7
6
,
DOI
: 1
0
.
1
1
5
9
1
/iji
ct.
v
9
i
1
.
p
p
5
7
-
6
2
57
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Suppo
rt
v
ec
tor m
a
chine bas
ed alzh
eimer’s d
isea
se di
a
g
no
sis
using
sy
nchro
ny
f
ea
tures
Nilesh
K
ulk
a
rni
De
p
a
rt
m
e
n
t
o
f
El
e
c
tro
n
ics
&
Tele
c
o
m
m
u
n
ica
ti
o
n
,
S
h
rima
ti
Ka
sh
ib
a
i
Na
v
a
le Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
In
d
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
0
,
2
0
18
R
ev
is
ed
Dec
3
0
,
2
0
19
Acc
ep
ted
J
an
1
2
,
2
0
20
P
re
v
io
u
s
re
se
a
rc
h
wo
rk
h
a
s
h
ig
h
li
g
h
ted
t
h
a
t
n
e
u
ro
-
si
g
n
a
ls
o
f
A
lzh
e
ime
r’s
d
ise
a
se
p
a
ti
e
n
ts
a
re
lea
st
c
o
m
p
lex
a
n
d
h
a
v
e
lo
w
sy
n
c
h
ro
n
iza
ti
o
n
a
s c
o
m
p
a
re
d
to
t
h
a
t
o
f
h
e
a
lt
h
y
a
n
d
n
o
rm
a
l
su
b
jec
ts.
T
h
e
c
h
a
n
g
e
s
in
E
EG
sig
n
a
ls
o
f
Alz
h
e
ime
r’s
su
b
jec
ts
sta
rt
a
t
e
a
rly
sta
g
e
b
u
t
a
re
n
o
t
c
li
n
ica
ll
y
o
b
s
e
rv
e
d
a
n
d
d
e
tec
ted
.
T
o
d
e
tec
t
t
h
e
se
a
b
n
o
rm
a
li
ti
e
s,
th
re
e
s
y
n
c
h
r
o
n
y
m
e
a
su
re
s
a
n
d
wa
v
e
let
-
b
a
se
d
fe
a
tu
re
s
h
a
v
e
b
e
e
n
c
o
m
p
u
ted
a
n
d
stu
d
ied
o
n
e
x
p
e
rime
n
tal
d
a
tab
a
se
.
Afte
r
c
o
m
p
u
ti
n
g
th
e
se
sy
n
c
h
r
o
n
y
m
e
a
su
re
s
a
n
d
wa
v
e
let
fe
a
tu
re
s,
it
is
o
b
se
rv
e
d
t
h
a
t
P
h
a
se
S
y
n
c
h
r
o
n
y
a
n
d
C
o
h
e
re
n
c
e
b
a
se
d
fe
a
tu
re
s
a
re
a
b
le
to
d
isti
n
g
u
is
h
b
e
twe
e
n
Alz
h
e
ime
r’s
d
ise
a
se
p
a
ti
e
n
ts
a
n
d
h
e
a
lt
h
y
su
b
jec
ts.
S
u
p
p
o
rt
Ve
c
to
r
M
a
c
h
i
n
e
c
las
sifier
is
u
se
d
f
o
r
c
las
sifica
ti
o
n
g
i
v
in
g
9
4
%
a
c
c
u
ra
c
y
o
n
e
x
p
e
rime
n
tal
d
a
tab
a
se
u
se
d
.
C
o
m
b
in
in
g
,
t
h
e
se
sy
n
c
h
r
o
n
y
fe
a
tu
re
s
a
n
d
o
th
e
r
su
c
h
re
lev
a
n
t
fe
a
tu
re
s
c
a
n
y
ield
a
re
li
a
b
le
sy
ste
m
fo
r
d
iag
n
o
sin
g
t
h
e
Alz
h
e
ime
r’s d
ise
a
se
.
K
ey
w
o
r
d
s
:
Alzh
eim
er
’
s
d
is
ea
s
e
Dem
en
tia
E
lectr
o
en
ce
p
h
al
o
g
r
am
Ma
ch
in
e
lear
n
in
g
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
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
:
Nilesh
Ku
lk
ar
n
i
,
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics &
T
elec
o
m
m
u
n
icatio
n
,
Sh
r
im
ati
Kash
ib
ai
Nav
ale
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
,
Gan
g
ad
h
ar
S Va
ls
ep
atil Rd
,
Am
b
eg
ao
n
B
K,
Pu
n
e,
Ma
h
ar
ash
tr
a
4
1
1
0
4
1
,
I
n
d
ia
.
E
m
ail:
n
iles
h
k
u
lk
ar
n
i
9
9
2
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Alzh
eim
er
’
s
d
is
ea
s
e
(
AD)
i
s
o
n
e
o
f
th
e
n
eu
r
o
d
e
g
en
er
ativ
e
d
is
ea
s
es,
ch
ar
ac
ter
ized
b
y
p
r
o
g
r
ess
iv
e
im
p
air
m
en
t
th
at
g
r
a
d
u
ally
d
estro
y
s
b
r
ai
n
ce
lls
an
d
o
th
e
r
co
g
n
itiv
e
f
u
n
ctio
n
s
.
B
asically
,
it
p
r
o
g
r
ess
iv
ely
lea
d
s
to
to
tal
d
ep
e
n
d
en
c
y
.
I
t
is
m
o
s
t
co
m
m
o
n
n
eu
r
o
d
e
g
en
er
ativ
e
d
is
o
r
d
er
p
ar
ticu
lar
ly
i
n
wester
n
co
u
n
tr
ies
s
u
ch
as
Un
ited
State
s
(
US)
,
C
an
ad
a
an
d
m
an
y
m
o
r
e.
Dem
e
n
tia
r
an
k
s
as
th
ir
d
m
o
s
t
ex
p
en
s
iv
e
d
is
ea
s
e
an
d
s
ix
t
h
lead
in
g
ca
u
s
e
o
f
d
ea
th
o
v
e
r
th
e
wo
r
ld
.
Ap
p
r
o
x
im
ately
,
5
0
-
6
0
%
o
f
p
atien
ts
with
d
em
en
tia
an
d
Mild
C
o
g
n
itiv
e
im
p
air
m
en
t
(
MCI)
o
v
e
r
6
5
y
e
ar
s
o
f
ag
e
p
r
o
g
r
ess
es
to
war
d
s
Alzh
eim
er
ev
er
y
y
ea
r
[
1
,
2
]
.
T
h
er
ef
o
r
e
,
d
iag
n
o
s
is
&
ef
f
ec
tiv
e
tr
ea
tm
en
t
o
f
p
ati
en
ts
in
ea
r
ly
s
tag
e
ar
e
cr
itica
l
an
d
im
p
o
r
tan
t
is
s
u
es
in
Alzh
eim
er
’
s
r
esear
ch
.
Alzh
eim
er
’
s
d
is
ea
s
e
is
b
asica
lly
ch
ar
ac
ter
ized
b
y
wid
e
s
p
r
ea
d
n
eu
r
o
n
al
ce
ll
lo
s
s
,
n
eu
r
o
f
ib
r
illar
y
tan
g
les
&
s
en
ile
p
laq
u
es
in
th
e
v
ar
io
u
s
b
r
ain
r
eg
i
o
n
s
s
u
ch
as
h
i
p
p
o
ca
m
p
u
s
,
en
t
o
r
h
in
al
c
o
r
te
x
,
n
eo
co
r
tex
an
d
m
u
c
h
m
o
r
e.
As
n
u
m
b
e
r
o
f
in
d
iv
id
u
als
with
Alzh
eim
er
’
s
d
is
ea
s
e
is
in
cr
ea
s
in
g
an
d
ab
o
u
t
to
in
cr
ea
s
e
in
f
u
tu
r
e,
d
iag
n
o
s
is
an
d
ef
f
ec
tiv
e
tr
ea
tm
en
t
o
f
d
is
ea
s
e
in
ea
r
l
y
s
tag
e
a
r
e
im
p
o
r
tan
t
r
esear
c
h
ch
allen
g
es.
T
o
s
ea
r
ch
f
o
r
a
co
m
p
u
tatio
n
al
te
ch
n
iq
u
e
f
o
r
e
ar
ly
d
iag
n
o
s
is
o
f
p
atien
ts
wh
o
ar
e
p
r
o
g
r
ess
in
g
to
war
d
s
Alzh
eim
er
’
s
,
b
u
t
d
o
n
o
ex
h
ib
it
an
y
clin
ical
s
y
m
p
to
m
o
f
AD
d
u
r
in
g
m
ed
ical
test
s
is
an
im
p
o
r
tan
t
ch
allen
g
e.
Desp
ite
o
f
th
is
,
an
ea
r
ly
d
iag
n
o
s
is
s
cr
ee
n
in
g
m
eth
o
d
m
u
s
t
b
e
in
ex
p
e
n
s
iv
e,
in
o
r
d
er
to
allo
w
s
cr
ee
n
in
g
o
f
el
d
er
ly
p
atien
t.
E
E
G
is
o
n
e
o
f
th
e
m
o
s
t p
r
o
m
is
in
g
t
o
o
ls
in
s
u
ch
a
ca
s
e.
Neu
r
o
im
ag
in
g
tech
n
i
q
u
es
p
la
y
s
ig
n
if
ican
t
r
o
le
in
Alzh
eim
er
’
s
d
iag
n
o
s
is
b
u
t
th
ey
p
o
s
s
es
s
ev
er
al
d
r
awb
ac
k
s
as
d
is
cu
s
s
ed
in
[
3
]
.
I
m
ag
in
g
m
o
d
alities
in
clu
d
in
g
Ma
g
n
et
ic
R
eso
n
an
ce
I
m
ag
in
g
(
MRI)
,
C
o
m
p
u
ted
T
o
m
o
g
r
ap
h
y
(
C
T
)
,
Sin
g
le
Ph
o
to
n
E
m
is
s
io
n
C
o
m
p
u
ted
T
o
m
o
g
r
a
p
h
y
(
SP
E
C
T
)
an
d
m
an
y
m
o
r
e
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
9
,
No
.
1
,
Ap
r
il
20
20
:
5
7
–
6
2
58
s
p
ec
if
ically
u
s
ed
f
o
r
d
iag
n
o
s
is
o
f
v
ar
io
u
s
d
is
ea
s
es.
B
u
t,
t
h
e
u
s
e
o
f
t
h
ese
tech
n
iq
u
es
i
s
also
r
ep
o
r
ted
in
liter
atu
r
e.
Alth
o
u
g
h
t
h
ese
to
o
ls
ar
e
u
s
ed
f
o
r
Alzh
eim
er
’
s
d
ia
g
n
o
s
is
,
E
E
G
tech
n
iq
u
e
is
s
p
ec
if
ically
em
p
h
asized
in
cu
r
r
e
n
t
r
esear
ch
f
o
r
Alzh
eim
er
’
s
d
iag
n
o
s
is
.
I
t
is
m
o
s
t
well
k
n
o
wn
a
n
d
estab
lis
h
ed
tech
n
iq
u
e
f
o
r
m
ea
s
u
r
in
g
elec
tr
ic
ac
tiv
ity
o
f
th
e
b
r
ain
wh
ich
is
g
en
er
ate
d
b
y
b
illi
o
n
s
o
f
n
eu
r
o
n
s
o
f
th
e
ce
r
eb
al
c
o
r
tex
.
T
h
e
b
io
elec
tr
ic
ce
lls
ar
e
n
o
n
-
in
v
asiv
ely
e
x
am
i
n
ed
b
y
s
er
ies
o
f
elec
tr
o
d
es
p
la
ce
d
o
v
e
r
p
atien
ts
h
ea
d
as
p
er
i
n
ter
n
atio
n
al
1
0
/2
0
s
tan
d
ar
d
s
.
E
E
G
s
ig
n
al
is
s
im
p
ly
a
m
u
ltiv
ar
iate
s
ig
n
al
tr
a
n
s
m
itted
o
v
er
d
if
f
er
e
n
t
ch
an
n
e
ls
with
v
a
r
iatio
n
o
f
d
if
f
er
en
t
s
am
p
lin
g
f
r
eq
u
en
cies
d
ep
en
d
in
g
o
n
ea
c
h
ap
p
licatio
n
[
4
,
5
]
.
T
h
is
to
o
l
tak
es
m
o
r
e
t
im
e
as
it
g
en
er
ates
m
o
r
e
d
ata
wh
ich
n
ee
d
s
to
b
e
an
aly
ze
d
.
E
E
G
s
ig
n
als
ar
e
k
e
y
d
iag
n
o
s
tic
to
o
ls
n
o
t
o
n
ly
f
o
r
n
eu
r
o
lo
g
is
ts
,
b
u
t
also
f
o
r
clin
ician
s
an
d
d
o
ct
o
r
s
.
T
o
d
ay
,
E
E
G
r
ec
o
r
d
in
g
s
a
r
e
also
u
s
ed
in
m
an
y
B
r
ain
C
o
m
p
u
ter
I
n
ter
f
ac
e
(
B
C
I
)
ap
p
licatio
n
s
[
4
]
.
Sev
e
r
al
r
esear
ch
f
in
d
in
g
s
h
a
v
e
i
d
en
tifie
d
th
e
p
o
ten
tial
o
f
E
E
G
f
o
r
d
iag
n
o
s
in
g
d
em
en
tia
an
d
Alzh
eim
er
’
s
d
is
ea
s
e
in
r
ec
en
t
y
ea
r
s
.
Sin
ce
,
E
E
G
r
ec
o
r
d
in
g
s
y
s
tem
s
a
r
e
r
elativ
ely
ch
ea
p
,
in
ex
p
en
s
iv
e
as
well
as
p
o
r
tab
le.
I
n
u
p
co
m
i
n
g
y
ea
r
s
,
th
ey
c
an
b
e
m
aj
o
r
ly
u
s
ed
f
o
r
id
en
ti
f
icatio
n
o
f
s
ev
er
al
n
eu
r
o
-
d
eg
e
n
er
ativ
e
d
is
ea
s
es
s
u
ch
as
Alzh
eim
er
’
s
d
is
ea
s
e,
E
p
ilep
s
y
,
Hu
n
tin
g
to
n
d
is
ea
s
e
an
d
m
an
y
m
o
r
e.
Sev
er
al
d
y
n
am
ical
c
h
an
g
es
r
el
ated
to
n
o
r
m
al
ag
ein
g
ca
n
b
e
e
asil
y
o
b
s
er
v
ed
u
s
in
g
E
E
G
s
ig
n
als
[4
].
Pap
er
is
o
r
g
a
n
ized
in
f
o
llo
wi
n
g
m
a
n
n
er
:
Ma
t
er
ials
an
d
M
eth
o
d
s
ar
e
lis
ted
in
s
ec
tio
n
2
.
Deta
iled
m
eth
o
d
o
l
o
g
y
a
n
d
ex
p
er
im
en
ta
tio
n
is
ex
p
lo
r
ed
in
s
ec
tio
n
3
.
C
las
s
if
icatio
n
r
esu
lts
an
d
p
er
f
o
r
m
an
ce
m
etr
ics
ar
e
ex
p
lo
r
ed
in
s
ec
tio
n
4
an
d
C
o
n
clu
s
io
n
is
s
u
m
m
ar
ized
in
s
ec
tio
n
5
.
2.
M
AT
E
R
I
AL
S &
M
E
T
H
O
D
S
2
.
1
.
P
a
rt
icipa
nts
info
rm
a
t
i
o
n
Data
s
et
in
co
r
p
o
r
ated
in
p
r
esen
t
s
tu
d
y
co
n
s
is
ts
o
f
elec
tr
o
en
ce
p
h
alo
g
r
am
(
E
E
G)
r
ec
o
r
d
ed
in
two
g
r
o
u
p
s
wh
ich
wer
e
ag
ed
f
r
o
m
6
5
to
8
0
y
ea
r
s
:
SUB
1
,
5
0
h
ea
lth
y
s
u
b
jects
an
d
SUB
2
,
5
0
Alzh
eim
er
d
is
ea
s
e
p
atien
ts
wh
ich
wer
e
d
iag
n
o
s
e
d
as
p
er
NI
NC
DS
-
ADRDA
cr
iter
ia.
Al
zh
eim
er
’
s
d
is
ea
s
e
p
atien
ts
wer
e
g
r
o
u
p
ed
as
h
av
in
g
m
o
d
e
r
ate
to
s
ev
e
r
e
s
y
m
p
to
m
s
.
Diag
n
o
s
is
o
f
p
atien
ts
was
m
ad
e
b
y
ex
p
e
r
ien
ce
d
n
eu
r
o
lo
g
is
ts
an
d
ex
p
er
t
clin
ician
s
o
n
th
e
b
asis
o
f
MM
SE
an
d
C
D
R
s
co
r
es.
Alzh
eim
er
’
s
p
atien
ts
s
co
r
ed
b
elo
w
2
6
o
n
C
DR
s
ca
le.
Dem
en
tia
an
d
Alzh
eim
er
’
s
d
is
ea
s
e
p
atien
ts
wer
e
al
s
o
test
ed
u
s
in
g
Sin
g
le
p
h
o
to
n
em
is
s
io
n
co
m
p
u
ted
to
m
o
g
r
a
p
h
y
(
SP
E
C
T
)
tech
n
iq
u
e
f
o
r
ab
o
u
t
1
4
to
1
5
m
o
n
th
s
as
f
u
n
ctio
n
al
test
s
s
u
ch
as
MM
SE
an
d
C
DR
ar
e
n
o
t
s
u
f
f
icien
t
to
d
etec
t
Alzh
eim
er
’
s
d
is
ea
s
e.
An
o
th
er
cr
iter
ia
u
s
ed
f
o
r
d
etec
tin
g
Alzh
e
im
er
’
s
d
is
ea
s
e
was
esti
m
atin
g
p
atien
ts
f
u
n
ctio
n
al
an
d
co
g
n
itiv
e
d
ec
lin
e
f
o
r
p
e
r
io
d
o
f
last
1
0
to
1
5
m
o
n
th
s
b
ased
o
n
talk
with
in
f
o
r
m
a
n
ts
an
d
ex
p
e
r
t
n
e
u
r
o
clin
ician
s
.
Ap
p
r
o
v
al
was
tak
en
f
r
o
m
E
th
ical
co
m
m
ittee
o
f
th
e
h
o
s
p
ital
an
d
p
ar
ticip
a
n
ts
r
elativ
es
r
elate
d
t
o
E
E
G
d
ata
an
d
its
an
al
y
s
is
.
All
p
atien
ts
wer
e
also
c
h
ec
k
e
d
f
o
r
v
ar
io
u
s
d
is
ea
s
es
s
u
ch
as su
g
ar
in
tak
e,
k
id
n
e
y
p
r
o
b
lem
s
an
d
m
an
y
m
o
r
e
as th
e
y
ca
n
also
r
esu
lt in
to
d
em
en
tia
.
2
.
2
.
Rec
o
rding
&
a
cquis
it
i
o
n o
f
E
E
G
da
t
a
E
E
G
s
ig
n
als
wer
e
r
ec
o
r
d
ed
an
d
an
aly
ze
d
u
s
in
g
1
2
-
b
it
r
eso
lu
tio
n
,
2
0
0
Hz
s
am
p
lin
g
r
ate
E
E
G
m
ac
h
in
e
o
f
R
MS
m
an
u
f
ac
t
u
r
i
n
g
.
I
m
p
ed
a
n
ce
o
f
m
ac
h
i
n
e
w
as
k
ep
t
b
elo
w
1
0
Mo
h
m
s
an
d
th
e
elec
tr
o
d
es
wer
e
p
lace
d
ac
co
r
d
in
g
to
t
h
e
I
n
ter
n
atio
n
al
1
0
-
2
0
s
y
s
tem
s
,
r
ec
o
m
m
en
d
ed
b
y
Am
er
ican
E
E
G
s
o
ciety
.
B
iau
r
icu
lar
r
ef
er
en
tial
elec
tr
o
d
es
wer
e
als
o
in
clu
d
ed
s
in
ce
th
ey
ar
e
also
im
p
o
r
tan
t
f
o
r
r
ec
o
r
d
in
g
.
E
E
G
d
ata
was
r
ec
o
r
d
ed
f
o
r
1
5
m
i
n
u
tes
p
er
p
atien
t.
Patien
ts
wer
e
in
r
elax
in
g
m
o
d
e
with
ey
es
clo
s
ed
.
E
E
G
s
i
g
n
al
ar
tifa
cts
wer
e
r
em
o
v
ed
b
y
s
k
illed
n
eu
r
o
p
h
y
s
io
lo
g
is
ts
an
d
clin
ician
s
s
u
ch
as
b
lin
k
i
n
g
e
f
f
ec
t,
d
r
o
wsi
n
e
s
s
,
m
u
s
cle
ar
tifa
cts
an
d
ar
tifa
cts
g
en
e
r
ated
b
y
m
a
ch
in
e
d
u
r
in
g
r
ec
o
r
d
in
g
p
r
o
ce
s
s
.
An
ep
o
ch
o
f
2
0
s
ec
o
n
d
s
was
ex
tr
ac
ted
f
r
o
m
ea
ch
E
E
G
s
ig
n
al
f
r
o
m
lef
t f
r
o
n
tal
(
F3
)
,
r
ig
h
t f
r
o
n
tal
(
F4
)
,
ce
n
tr
al
(
C3
-
C
4
)
,
Par
ietal
(
P3
-
P4
)
an
d
tem
p
o
r
al
(
T
3
)
ch
an
n
els f
o
r
f
u
r
t
h
er
an
al
y
s
is
b
y
v
is
u
al
in
s
p
ec
tio
n
.
Fo
r
ep
o
ch
an
al
y
s
is
,
5
1
2
-
p
o
in
t
h
am
m
in
g
FF
T
alg
o
r
ith
m
was
u
s
ed
f
o
r
f
ilter
in
g
o
f
E
E
G
d
ata.
T
h
e
win
d
o
w
u
s
ed
was
o
f
2
.
5
s
ec
d
u
r
atio
n
with
9
0
%
o
v
er
la
p
b
etwe
en
s
u
cc
ess
i
v
e
win
d
o
ws.
I
n
f
in
ite
im
p
u
ls
e
r
esp
o
n
s
e
L
PF
was
u
s
ed
f
o
r
f
ilter
in
g
o
f
E
E
G
d
ata
with
a
5
0
Hz
cu
t
-
o
f
f
f
r
e
q
u
en
c
y
.
T
h
e
p
o
we
r
g
r
id
i
n
ter
f
er
e
n
ce
was r
em
o
v
ed
u
s
in
g
o
f
l
o
w
p
as
s
f
ilter
.
3.
M
E
T
H
O
DO
L
O
G
Y
Du
e
to
n
o
n
-
s
tatio
n
ar
y
ch
ar
ac
t
er
is
t
ic
o
f
E
E
G
s
ig
n
al;
an
aly
zi
n
g
E
E
G
s
ig
n
al
is
n
o
t
o
n
ly
ted
io
u
s
b
u
t
also
tim
e
co
n
s
u
m
in
g
an
d
d
if
f
icu
lt.
Sin
ce
,
b
r
ain
wav
es
ca
n
b
e
r
ep
r
esen
ted
in
tim
e
as
well
as
f
r
eq
u
en
cy
d
o
m
ain
;
E
E
G
s
ig
n
als
ar
e
ex
p
lo
r
ed
a
n
d
an
aly
ze
d
in
tim
e,
f
r
eq
u
e
n
cy
an
d
tim
e
-
f
r
e
q
u
e
n
cy
d
o
m
ain
[
5
,
6
]
.
MA
T
L
AB
(
2
0
1
5
v
e
r
s
io
n
)
p
l
a
tf
o
r
m
is
en
ab
led
f
o
r
e
x
ec
u
ti
n
g
th
e
alg
o
r
ith
m
s
p
r
o
p
o
s
ed
i
n
p
r
esen
t
r
esear
ch
wo
r
k
.
I
n
th
is
s
ec
tio
n
,
we
d
is
cu
s
s
th
e
p
r
ep
r
o
ce
s
s
in
g
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
in
d
etail
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
S
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
b
a
s
ed
a
lz
h
eime
r
’
s
d
is
ea
s
e
d
ia
g
n
o
s
is
u
s
in
g
s
yn
ch
r
o
n
y
fe
a
tu
r
es (
N
il
esh
K
u
lka
r
n
i)
59
3
.
1
.
B
lo
ck
dia
g
ra
n o
f
t
he
pro
po
s
ed
s
y
s
t
em
Alzh
eim
er
’
s
Dis
ea
s
e
d
iag
n
o
s
i
s
s
y
s
tem
wo
r
k
s
in
d
if
f
e
r
en
t
s
tep
s
,
i)
Fil
ter
in
g
an
d
n
o
is
e
r
em
o
v
al
o
f
r
aw
E
E
G
s
ig
n
a
ca
lled
Pre
p
r
o
ce
s
s
in
g
,
ii)
E
x
tr
ac
tio
n
a
n
d
s
elec
tio
n
o
f
p
r
o
m
in
en
t
f
ea
tu
r
es
f
r
o
m
E
E
G
d
ata,
an
d
iii)
C
la
s
s
if
icatio
n
o
f
E
E
G
d
ata
in
to
d
if
f
er
en
t
s
u
b
jects.
A
r
aw
E
E
G
s
ig
n
al
was
f
ilter
ed
u
s
i
n
g
s
u
itab
le
B
an
d
p
ass
f
ilter
to
r
em
o
v
e
u
n
wan
ted
i
n
f
o
r
m
atio
n
co
n
ten
t
f
r
o
m
s
ig
n
al
wh
ich
g
ets
ad
d
ed
d
u
r
in
g
r
ec
o
r
d
in
g
p
r
o
ce
s
s
.
I
n
p
r
esen
t
wo
r
k
,
a
b
an
d
p
ass
f
ilter
o
f
th
ir
d
o
r
d
er
with
a
p
p
r
o
p
r
iate
g
ain
d
esig
n
e
d
in
b
etwe
en
0
.
5
to
3
0
Hz
was
u
s
ed
f
o
r
f
ilter
in
g
.
I
n
f
e
atu
r
e
e
x
tr
ac
tio
n
s
tag
e,
s
y
n
ch
r
o
n
y
b
as
ed
d
if
f
er
en
t
f
ea
t
u
r
es
ar
e
co
m
p
u
ted
an
d
a
tr
ain
in
g
f
ea
tu
r
e
m
atr
ix
was
co
m
p
u
ted
as a
n
in
p
u
t to
class
if
ier
.
B
lo
ck
d
iag
r
am
o
f
th
e
s
y
s
tem
as sh
o
wn
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
o
f
th
e
s
y
s
tem
3
.
2
.
F
e
a
t
ure
ex
t
r
a
ct
io
n us
ing
s
y
nchro
ny
ba
s
ed
f
ea
t
ures
I
n
th
e
p
r
esen
t
r
ese
ar
ch
s
tu
d
y
,
s
y
n
ch
r
o
n
y
b
ased
f
eq
atu
r
es
wer
e
s
tu
d
ies
an
d
an
aly
ze
d
.
B
r
ain
Sy
n
ch
r
o
n
y
r
esem
b
les
s
im
u
ltan
eo
u
s
ap
p
ea
r
an
ce
o
f
r
h
y
th
m
i
c
d
is
tin
ct
p
atter
n
s
o
v
er
d
if
f
er
en
t
r
eg
io
n
s
o
f
h
ea
d
;
b
ilater
all
y
o
r
u
n
ilater
ally
.
I
t
is
o
b
s
er
v
ed
th
a
t
s
tatis
tical
in
d
ep
en
d
en
ce
ap
p
ea
r
s
to
b
e
s
ig
n
i
f
ican
tly
less
in
ca
s
e
o
f
Alzh
eim
er
’
s
p
atien
ts
a
r
o
u
n
d
d
if
f
er
en
t
r
eg
io
n
s
o
f
b
r
ain
[
5
-
7
]
.
T
o
o
b
s
er
v
e
t
h
is
lo
s
s
o
f
s
y
n
ch
r
o
n
y
i
n
b
r
ain
,
s
y
n
ch
r
o
n
y
m
ea
s
u
r
es
s
u
c
h
as
Ma
g
n
itu
d
e
Sq
u
a
r
e
C
o
h
er
en
ce
(
MSC
)
an
d
Ph
ase
Sy
n
ch
r
o
n
y
wh
ich
co
m
p
ar
ativ
ely
p
r
o
v
id
e
b
etter
r
esu
lts
in
ter
m
s
o
f
class
if
icat
i
o
n
ac
cu
r
ac
y
ar
e
an
aly
ze
d
.
L
e
t
u
s
d
is
cu
s
s
th
ese
f
ea
tu
r
es
in
m
o
r
e
d
etail.
Ma
g
n
itu
d
e
Sq
u
a
r
ed
C
o
h
er
en
ce
(
MSC
)
.
C
o
h
er
en
ce
r
ef
er
s
to
m
ea
s
u
r
em
en
t
o
f
s
y
n
ch
r
o
n
y
b
etwe
en
two
in
d
ep
en
d
en
t sig
n
als (
L
et
u
s
s
ay
x
an
d
y
)
a
n
d
it c
an
b
e
m
ath
em
atica
lly
d
ef
in
ed
as,
=
|
(
)
|
2
|
(
)
|
(
)
|
(
1
)
W
h
er
e
,
f
is
f
r
eq
u
e
n
cy
in
h
er
tz
,
P
xy
in
d
icate
s
cr
o
s
s
s
p
ec
tr
al
d
en
s
ity
o
f
s
ig
n
al
x
an
d
s
ig
n
al
y.
P
xx
a
n
d
P
y
y
r
ep
r
esen
ts
th
e
p
o
we
r
s
p
ec
t
r
al
d
en
s
ities
o
f
x
an
d
y
r
esp
ec
tiv
ely
.
Fo
r
ea
c
h
p
air
o
f
ch
an
n
els
n
am
ely
F3
,
F4
,
C
3
,
C
4
an
d
O1
,
O2
;
co
h
e
r
en
ce
f
ea
tu
r
es
we
r
e
c
o
m
p
u
te
d
a
n
d
a
v
er
ag
e
d
o
v
er
th
e
f
iv
e
s
u
b
-
b
an
d
s
.
C
o
h
er
e
n
ce
h
ig
h
lig
h
ts
th
e
s
y
n
ch
r
o
n
icity
o
f
ac
tiv
atio
n
in
v
a
r
i
o
u
s
b
r
ain
r
e
g
io
n
s
.
E
E
G
co
h
er
e
n
ce
h
elp
s
t
o
ac
ce
s
s
f
u
n
ctio
n
al
co
n
n
ec
tiv
ity
b
etwe
en
v
ar
i
o
u
s
ch
an
n
els
o
v
er
o
cc
ip
ital
r
eg
io
n
s
o
f
b
r
ain
.
I
n
to
tal,
we
h
av
e
co
m
p
u
ted
to
tal
(
6
ch
an
n
els
*
4
f
r
e
q
u
en
c
y
b
an
d
s
=
2
4
f
ea
tu
r
es)
f
o
r
5
0
s
u
b
je
cts
co
n
s
is
tin
g
o
f
h
ea
lth
y
as
we
ll
as
Alzh
eim
er
af
f
ec
ted
in
tr
ain
i
n
g
m
o
d
e.
So
,
it c
o
n
s
is
ts
o
f
to
tal
5
0
*
2
4
=
1
2
0
0
f
ea
t
u
r
es.
Ph
ase
Sy
n
ch
r
o
n
y
i
n
d
icate
s
in
ter
d
ep
en
d
e
n
ce
o
f
s
ig
n
als
x
a
n
d
y
am
o
n
g
two
p
h
ases
∅
an
d
∅
.
E
v
en
th
o
u
g
h
th
e
am
p
litu
d
es
o
f
s
ig
n
als
x
a
n
d
y
ar
e
k
ep
t
s
tatis
tically
d
ep
en
d
en
t,
t
h
e
in
s
tan
tan
e
o
u
s
p
h
a
s
es
ca
n
b
e
s
tr
o
n
g
ly
s
y
n
ch
r
o
n
ize
d
.
I
t is g
iv
e
n
b
y
f
o
llo
win
g
f
o
r
m
u
la
[
8
]
:
∅
,
=
∅
(
)
−
∅
(
)
=
(
2
)
W
h
er
e
co
-
ef
f
icien
ts
m
an
d
n
r
ep
r
esen
ts
in
teg
er
s
d
ep
ictin
g
f
r
eq
u
e
n
cy
lo
ck
i
n
g
r
atio
an
d
∅
,
is
its
r
elativ
e
o
r
p
h
ase
d
if
f
er
e
n
ce
.
Fo
r
co
m
p
u
tin
g
s
y
n
ch
r
o
n
izati
o
n
b
etwe
en
two
p
h
ases
,
it
is
im
p
o
r
tan
t
f
o
r
u
s
to
k
n
o
w
th
e
p
h
ase
o
f
two
s
ig
n
als
at
in
s
tan
tan
eo
u
s
v
alu
e.
I
t
ca
n
b
e
an
aly
ze
d
b
y
u
s
in
g
Hilb
er
t
t
r
an
s
f
o
r
m
wh
ich
is
g
iv
en
as:
(
)
=
(
)
+
̃
(
)
(
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
9
,
No
.
1
,
Ap
r
il
20
20
:
5
7
–
6
2
60
I
n
ab
o
v
e
eq
u
atio
n
,
(
)
is
co
m
p
lex
ter
m
with
is
(
)
r
ea
l
ter
m
an
d
̃
(
)
r
ep
r
esen
ts
its
Hilb
er
t
tr
an
s
f
o
r
m
.
Hilb
er
t
T
r
an
s
f
o
r
m
i
s
co
m
p
u
ted
as,
̃
(
)
=
1
∫
(
)
−
∞
−
∞
(
4
)
I
n
ab
o
v
e
eq
u
atio
n
,
PV
r
ep
r
ese
n
ts
C
au
ch
y
Prin
cip
le
v
alu
e
.
I
n
s
tan
tan
eo
u
s
p
h
ase
∅
(
)
an
d
∅
(
)
f
o
r
s
ig
n
als x
an
d
y
a
r
e
ca
lcu
lated
as:
∅
(
)
=
a
r
c
ta
n
(
̃
(
)
(
)
)
(
5
)
I
n
p
r
esen
t
s
tu
d
y
,
s
y
n
ch
r
o
n
y
b
ased
f
ea
tu
r
es
wer
e
co
m
p
u
ted
o
n
ea
ch
p
air
o
f
ch
an
n
el
o
f
tw
o
o
p
p
o
s
ite
r
eg
io
n
s
f
o
r
all
f
r
e
q
u
en
c
y
b
a
n
d
s
an
d
th
en
a
v
er
ag
e
d
.
Fo
r
ex
a
m
p
le,
p
h
ase
s
y
n
c
h
r
o
n
y
f
ea
tu
r
e
wer
e
m
ea
s
u
r
ed
o
n
ty
p
ical
ch
an
n
el
s
o
f
r
ig
h
t
an
d
l
ef
t
tem
p
o
r
al
r
e
g
io
n
s
(
s
ay
(
F3
-
T
3
)
,
(
T
3
-
T
4
)
)
an
d
s
o
o
n
.
I
n
p
r
esen
t
s
tu
d
y
,
p
h
ase
s
y
n
ch
r
o
n
y
f
ea
tu
r
e
was
co
m
p
u
ted
f
o
r
f
r
o
n
tal,
tem
p
o
r
al,
p
ar
ietal
an
d
ce
n
tr
al
elec
tr
o
d
e
o
f
E
E
G
s
ig
n
al.
Acc
o
r
d
in
g
ly
,
1
5
0
s
u
ch
f
ea
t
u
r
e
s
wer
e
co
m
p
u
ted
an
d
o
u
t
o
f
it
1
0
0
f
ea
tu
r
es
wer
e
s
elec
ted
as
p
er
W
ilco
x
o
n
test
s
o
n
o
u
r
d
ataset
[
8
]
.
4.
M
ACH
I
N
E
L
E
AR
NING
AN
D
CL
AS
SI
F
I
CAT
I
O
N
T
E
C
H
NQ
U
ES
Ma
ch
in
e
L
ea
r
n
in
g
is
a
s
u
b
s
e
t
o
f
Ar
tific
ial
I
n
tellig
en
ce
in
wh
ich
th
e
d
ata
o
p
tim
izatio
n
is
ca
r
r
ied
u
s
in
g
th
e
p
ast
ex
p
er
ie
n
ce
to
p
r
ed
ict
f
u
tu
r
e
r
esu
lt
o
r
class
if
y
th
e
tar
g
et
in
p
u
t
[
9
,
1
0
]
.
T
h
i
s
d
ata
o
p
tim
izatio
n
ca
n
b
e
d
o
n
e
u
s
in
g
d
if
f
er
e
n
t
alo
g
r
ith
m
s
as
d
is
cu
s
s
ed
in
liter
atu
r
e.
Fo
r
class
if
y
in
g
th
e
tar
g
et
in
p
u
t
d
ata
in
to
two
o
r
m
o
r
e
class
es,
d
if
f
e
r
en
t
m
a
ch
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
ca
n
b
e
u
s
ed
.
T
h
is
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
ar
e
class
if
ied
in
to
th
r
ee
lear
n
in
g
m
ec
h
an
is
m
n
am
ely
:
s
u
p
e
r
v
is
ed
,
u
n
s
u
p
e
r
v
is
ed
an
d
r
ein
f
o
r
c
em
en
t
lear
n
in
g
.
I
n
p
r
esen
t
r
esear
ch
wo
r
k
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
,
a
s
em
i
-
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
was
u
s
ed
f
o
r
class
if
icatio
n
p
u
r
p
o
s
e.
Fo
r
clas
s
if
icatio
n
p
u
r
p
o
s
e,
7
0
%
d
ata
co
n
s
is
tin
g
o
f
b
o
th
s
u
b
jects
was
in
co
r
p
o
r
ated
f
o
r
t
r
ain
in
g
p
u
r
p
o
s
e
an
d
r
est
o
f
3
0
%
d
ata
w
as
k
ep
t
f
o
r
test
in
g
p
u
r
p
o
s
e.
B
ased
o
n
o
b
s
er
v
ed
r
esu
lts
,
co
n
f
u
s
io
n
m
atr
ix
was
cr
ea
ted
an
d
d
if
f
er
en
t
p
er
f
o
r
m
an
ce
s
m
etr
ic
wer
e
ca
lcu
lated
to
m
ea
s
u
r
e
th
e
ef
f
icien
cy
o
f
th
e
class
if
ier
.
Fig
u
r
e
.
2
r
ep
r
esen
ts
th
e
Sem
i
-
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
f
lo
w.
Fig
u
r
e
2
.
Statis
tical
r
ec
o
g
n
itio
n
f
lo
w
f
o
r
s
u
p
er
v
is
ed
class
if
icatio
n
4
.
1
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chine (
SVM
)
cla
s
s
if
ier
C
las
s
if
ier
s
in
m
ac
h
in
e
lear
n
in
g
ar
e
n
o
r
m
ally
f
o
r
m
u
lated
,
d
e
s
ig
n
ed
an
d
ad
o
p
ted
b
y
u
s
in
g
s
tatis
t
ical
le
ar
n
in
g
.
T
h
ey
ca
n
b
e
u
s
ed
f
o
r
class
if
icatio
n
as
well
as
r
eg
r
ess
io
n
p
u
r
p
o
s
e.
SVM
is
s
em
i
-
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
wh
ich
is
v
er
y
ef
f
ec
tiv
e
in
class
if
y
in
g
d
at
a
o
f
h
ig
h
d
im
en
s
io
n
.
I
t
is
also
r
o
b
u
s
t
an
d
ea
s
y
to
im
p
lem
en
t
u
s
in
g
Py
th
o
n
,
MA
T
L
AB
an
d
an
y
o
th
er
to
o
l.
An
o
p
tical
h
y
p
er
p
lan
e
s
ep
ar
ates
th
e
d
ata
b
elo
n
g
in
g
to
two
class
es
u
s
in
g
ap
p
r
o
p
r
i
ate
k
er
n
el
in
ca
s
e
o
f
n
o
n
-
lin
e
ar
,
m
u
lti
-
d
im
e
n
s
io
n
al
d
ata.
I
n
p
r
esen
t
wo
r
k
,
R
B
F
k
er
n
el
was
u
s
ed
an
d
alg
o
r
ith
m
was
im
p
lem
en
te
d
u
s
in
g
MA
T
L
AB
p
r
o
g
r
am
m
in
g
.
L
ea
v
e
-
On
e
-
Su
b
ject
-
Ou
t
(
L
OSO)
cr
o
s
s
-
v
alid
atio
n
tech
n
iq
u
e
was
u
s
ed
f
o
r
class
if
icatio
n
.
T
h
e
a
d
v
an
tag
e
o
f
u
s
in
g
t
h
is
tech
n
iq
u
e
is
th
at
it
elim
in
ates
th
e
p
r
o
b
lem
o
f
o
v
er
-
f
itti
n
g
d
u
r
i
n
g
d
ata
s
ep
ar
ati
o
n
an
d
also
g
u
r
a
n
tees
th
e
g
e
n
er
ality
o
f
class
if
if
er
to
u
n
s
ee
n
o
r
u
n
la
b
elled
d
ata.
4
.
2
.
P
er
f
o
rma
nce
a
na
ly
s
is
o
f
t
he
E
E
G
da
t
a
Dif
f
er
en
t
s
y
n
c
h
r
o
n
y
-
b
ased
E
E
G
f
ea
tu
r
es
s
u
ch
as
Ma
g
n
it
u
d
e
Sq
u
a
r
ed
C
o
h
e
r
en
ce
(
MSC
)
,
Ph
ase
Sy
n
ch
r
o
n
y
a
n
d
C
r
o
s
s
-
c
o
r
r
el
atio
n
wer
e
co
m
p
u
ted
,
an
al
y
ze
d
an
d
m
ea
s
u
r
ed
in
a
p
p
r
o
p
r
iat
e
m
an
n
er
o
n
E
E
G
d
ata.
Fo
r
s
elec
tin
g
tr
ain
i
n
g
d
ata,
co
m
p
u
ted
f
ea
tu
r
es
wer
e
s
elec
ted
f
r
o
m
a
n
y
o
f
th
e
f
o
u
r
s
elec
ted
E
E
G
elec
tr
o
d
es.
I
n
d
iv
i
d
u
al
f
ea
tu
r
e
s
wer
e
also
co
m
p
u
ted
an
d
test
ed
u
s
in
g
SVM
class
f
ier
b
ased
o
n
d
if
f
er
en
t
p
er
f
o
r
m
an
ce
m
et
r
ics
s
u
ch
as
ac
cu
r
ac
y
.
T
h
e
o
b
ta
in
ed
r
es
u
lts
ar
e
s
h
o
wn
in
T
ab
le.
1
B
ased
o
n
d
atab
ase
av
ailab
le
f
o
r
c
o
m
p
u
tatio
n
,
5
0
%
o
f
th
e
d
ata
was
tr
ain
ed
&
r
em
ain
in
g
5
0
%
d
ata
was
lef
t
o
u
t
f
o
r
test
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
S
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
b
a
s
ed
a
lz
h
eime
r
’
s
d
is
ea
s
e
d
ia
g
n
o
s
is
u
s
in
g
s
yn
ch
r
o
n
y
fe
a
tu
r
es (
N
il
esh
K
u
lka
r
n
i)
61
p
u
r
p
o
s
e.
B
ased
o
n
t
h
e
in
d
iv
i
d
u
al
f
ea
tu
r
es
co
m
p
u
ted
&
S
VM
class
if
ier
u
s
ed
,
d
if
f
er
e
n
t
p
er
f
o
r
m
an
ce
m
etr
i
cs
wer
e
o
b
tain
ed
b
ased
o
n
f
o
llo
w
in
g
ter
m
in
o
l
o
g
ies
[9
,
1
0
]
.
=
+
+
+
+
(
6
)
=
+
(
7
)
=
+
(
8
)
W
h
er
e,
T
P st
an
d
s
f
o
r
T
r
u
e
Po
s
itiv
e
(
Alzh
eim
er
’
s
d
is
ea
s
e
p
a
tie
n
ts
co
r
r
ec
tly
class
if
ied
)
,
T
N
s
tan
d
s
f
o
r
T
r
u
e
Neg
ativ
e
(
h
ea
lth
y
in
d
iv
i
d
u
als
co
r
r
ec
tly
class
if
ied
)
,
F
P
s
tan
d
s
f
o
r
Fals
e
Po
s
itiv
es
(
h
ea
lth
y
in
d
i
v
id
u
als
m
is
class
if
ied
)
,
FN stan
d
s
f
o
r
Fals
e
Neg
ativ
e
(
Alzh
eim
er
’
s
d
is
ea
s
e
p
atien
ts
m
is
cla
s
s
if
ied
)
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
m
ea
s
u
r
e
o
n
ea
ch
in
d
iv
id
u
al
f
ea
tu
r
e
F
e
a
t
u
r
e
s
A
c
c
u
r
a
c
y
(
i
n
%)
M
a
g
n
i
t
u
d
e
S
q
u
a
r
e
d
C
o
h
e
r
e
n
c
e
88
P
h
a
se
S
y
n
c
h
r
o
n
y
90
C
o
m
b
i
n
a
t
i
o
n
o
f
B
o
t
h
f
e
a
t
u
r
e
s
94
5.
CO
NCLU
SI
O
N
& R
E
S
E
AR
CH
CH
AL
L
E
NG
E
S
T
h
is
p
ap
er
p
r
esen
ts
a
m
eth
o
d
to
d
iag
n
o
s
e
Alzh
eim
er
’
s
d
is
ea
s
e
b
y
u
s
in
g
d
if
f
er
en
t
Sy
n
c
h
r
o
n
y
b
ased
f
ea
tu
r
es.
T
h
e
aim
o
f
t
h
e
p
r
e
s
en
t
r
esear
ch
wo
r
k
was
to
im
p
r
o
v
e
t
h
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
f
o
r
Alzh
eim
er
’
s
d
iag
n
o
s
is
.
T
h
e
f
ea
tu
r
es
u
s
ed
f
o
r
d
if
f
er
e
n
tiatin
g
b
etwe
en
h
ea
lth
y
an
d
Alzh
eim
e
r
’
s
d
is
ea
s
e
s
u
b
jects
ar
e
n
o
t
n
o
v
el
b
u
t
s
ig
n
if
ican
t
im
p
r
o
v
em
en
ts
ca
n
b
e
o
b
s
er
v
e
d
o
n
u
s
ed
d
atab
ase.
I
n
p
r
esen
t
s
tu
d
y
,
ea
ch
in
d
iv
i
d
u
al
f
ea
tu
r
e
was
u
s
ed
f
o
r
class
if
icatio
n
an
d
all
s
y
n
ch
r
o
n
y
f
ea
tu
r
e
s
wer
e
also
s
ep
ar
ately
was
cla
s
s
if
icatio
n
p
u
r
p
o
s
e.
SVM
clas
s
if
ier
was
u
s
ed
f
o
r
s
ep
ar
atin
g
b
o
th
s
u
b
jects
y
iel
d
in
g
b
etter
r
esu
lts
.
Sp
ec
tr
al
an
aly
s
is
also
p
r
o
v
id
es
b
etter
r
esu
lts
in
an
aly
zin
g
E
E
G
s
ig
n
als
.
I
n
[
1
1
-
14
]
,
au
th
o
r
s
h
av
e
alr
ea
d
y
c
o
n
clu
d
ed
t
h
at
s
ig
n
if
ican
ce
o
f
p
lag
u
es
an
d
n
e
u
r
o
f
i
b
r
illar
y
t
an
g
les
in
co
r
tex
r
e
g
io
n
s
as
well
as
lo
wer
v
o
lu
m
e
o
f
h
ip
p
o
ca
m
p
u
s
s
lo
ws
th
e
s
ig
n
al
in
ca
s
e
o
f
Alzh
eim
er
’
s
d
is
ea
s
e
p
atien
ts
.
PET
as
well
as
MRI
s
ca
n
s
wa
s
al
s
o
s
tu
d
ied
alo
n
g
with
MM
SE
an
d
C
DR
s
co
r
e
s
in
ce
o
n
ly
th
e
s
e
ar
e
n
o
t
s
u
f
f
icien
t
f
o
r
Alzh
e
im
er
’
s
d
iag
n
o
s
is
.
Pre
v
io
u
s
liter
atu
r
e
s
u
m
m
a
r
izes
th
e
in
v
esti
g
atio
n
o
f
s
y
n
c
h
r
o
n
y
-
b
ased
f
ea
tu
r
es
f
o
r
Alzh
eim
e
r
’
s
d
iag
n
o
s
is
.
I
t
ca
n
b
e
co
n
clu
d
ed
th
at
c
o
h
er
en
ce
-
b
ased
f
ea
tu
r
es
d
e
p
ict
s
ig
n
if
ican
t
ef
f
ec
ts
o
n
s
ig
n
als
o
f
Alzh
eim
er
’
s
d
is
ea
s
e
p
atien
ts
in
r
esti
n
g
co
n
d
itio
n
s
an
d
h
ig
h
f
r
e
q
u
en
c
y
b
a
n
d
r
a
n
g
in
g
f
r
o
m
1
3
to
3
0
Hz.
T
h
e
s
y
n
ch
r
o
n
y
-
b
ased
f
ea
tu
r
es
wer
e
c
o
m
p
u
ted
in
d
i
v
id
u
ally
an
d
class
if
ied
b
y
u
s
e
o
f
s
em
i
-
s
u
p
er
v
is
ed
class
if
ier
;
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
g
iv
in
g
b
etter
class
if
icatio
n
ac
cu
r
ac
y
f
o
r
d
is
tin
g
u
is
h
in
g
th
e
s
u
b
jects b
etwe
en
two
g
r
o
u
p
s
.
Fro
m
th
e
f
ea
tu
r
es
co
m
p
u
ted
as
d
is
cu
s
s
ed
in
s
ec
tio
n
3
,
i
t
is
o
b
s
er
v
ed
th
at
lo
wer
d
y
s
f
u
n
ctio
n
al
co
n
n
ec
tiv
ity
is
o
b
s
er
v
e
d
in
c
en
tr
al,
p
a
r
ietal
an
d
o
cc
ip
ital
b
r
ain
r
eg
io
n
s
.
A
lo
wer
s
y
n
ch
r
o
n
izatio
n
in
t
h
ese
ar
ea
s
f
o
r
alp
h
a
an
d
b
eta
b
an
d
id
en
tifie
s
d
is
tu
r
b
an
ce
o
cc
u
r
r
ed
in
p
er
ce
p
tio
n
an
d
c
o
g
n
iti
v
e
d
is
o
r
d
er
.
T
h
u
s
,
th
e
o
b
s
er
v
atio
n
s
co
m
p
u
ted
in
p
r
esen
t
r
esear
ch
wo
r
k
ar
e
in
ag
r
ee
m
en
t
with
s
ev
er
al
p
r
ev
io
u
s
s
tu
d
ies
wh
ich
r
ep
o
r
ts
o
n
d
ec
r
ea
s
e
o
f
n
e
u
r
o
n
al
s
y
n
ch
r
o
n
y
in
Alzh
eim
er
’
s
d
is
ea
s
e
p
atien
ts
a
s
o
b
s
er
v
ed
o
n
E
E
G
s
ig
n
als.
T
h
is
lo
s
s
o
f
s
y
n
ch
r
o
n
y
ap
p
ea
r
s
d
u
e
to
ad
d
itio
n
o
f
n
o
n
–
c
o
n
s
is
ten
t
b
ac
k
g
r
o
u
n
d
ac
tiv
ity
an
d
p
r
esen
ce
o
f
n
eu
r
o
f
i
b
r
illar
y
tan
g
les
in
h
i
p
p
o
ca
m
p
u
s
ar
ea
.
C
o
m
b
in
atio
n
o
f
all
s
y
n
c
h
r
o
n
y
-
b
ased
f
ea
t
u
r
es
p
r
o
v
id
es
b
etter
ac
cu
r
ac
y
as
co
m
p
ar
e
d
to
in
d
i
v
id
u
al
f
ea
tu
r
e.
Fu
tu
r
e
wo
r
k
o
f
p
r
esen
t
r
esear
ch
wo
r
k
in
v
o
lv
es
an
aly
s
is
o
f
ea
ch
E
E
G
s
ig
n
al
in
tim
e
–
f
r
e
q
u
e
n
cy
d
o
m
ain
an
d
to
co
n
clu
d
e
wh
eth
er
th
ey
ca
r
y
an
y
r
elev
an
t
in
f
o
r
m
atio
n
f
o
r
b
etter
d
etec
tio
n
b
y
u
s
in
g
ad
v
a
n
ce
d
s
ig
n
al
p
r
o
ce
s
s
in
g
alg
o
r
it
h
m
s
.
I
t
is
to
co
n
clu
d
e
th
at
wh
en
we
co
m
b
in
e
all
f
ea
tu
r
es
to
g
eth
er
,
class
if
icatio
n
r
ate
a
s
well
as
d
iag
n
o
s
tic
ac
cu
r
ac
y
o
b
tain
ed
is
m
o
r
e
an
d
it
p
r
o
v
id
es
c
o
m
p
a
r
ativ
ely
b
etter
r
esu
lts
in
ter
m
s
o
f
ac
c
u
r
ac
y
.
Fu
tu
r
e
wo
r
k
in
th
is
s
tu
d
y
in
v
o
lv
es m
ak
in
g
an
aly
s
is
o
f
ea
ch
f
r
eq
u
en
cy
b
an
d
s
in
d
ep
th
to
o
b
s
er
v
e
wh
eth
er
th
ey
ca
r
r
y
an
y
o
th
er
s
ig
n
if
ican
t
in
f
o
r
m
atio
n
f
o
r
b
e
tter
d
iag
n
o
s
is
b
y
m
ea
n
s
o
f
v
ar
io
u
s
s
ig
n
al
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
an
d
f
ea
tu
r
es
ex
tr
ac
tio
n
tech
n
iq
u
es.
T
h
e
p
r
e
s
en
t
r
esear
ch
wo
r
k
ex
p
lo
r
es
a
s
ig
n
if
ican
t
m
eth
o
d
o
lo
g
y
f
o
r
A
lzh
eim
er
’s
d
is
ea
s
e
d
iag
n
o
s
is
an
d
f
u
r
t
h
er
r
esear
ch
u
s
in
g
s
o
m
e
m
o
r
e
o
f
th
ese
f
ea
tu
r
es
ca
n
r
ep
o
r
t
r
em
a
r
k
ab
le
ac
h
iev
em
en
ts
in
th
is
f
ield
.
ACK
NO
WL
E
DG
E
M
E
NT
S
Au
h
to
r
s
wo
u
ld
lik
e
to
th
an
k
en
tire
s
taf
f
o
f
Sm
t.
Kash
ib
ai
Nav
ale
Me
d
ical
C
o
lleg
e
&
Gen
er
al
Ho
s
p
ital
f
o
r
p
r
o
v
id
in
g
n
ec
ess
ar
y
E
E
G
d
atab
ase
f
o
r
ca
r
r
y
in
g
r
es
ea
r
ch
wo
r
k
.
A
u
th
o
r
s
w
o
u
ld
also
lik
e
to
th
an
k
an
n
o
y
m
o
u
s
r
ev
iewe
r
s
f
o
r
im
p
r
o
v
in
g
th
e
q
u
ality
o
f
p
ap
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
9
,
No
.
1
,
Ap
r
il
20
20
:
5
7
–
6
2
62
RE
F
E
R
E
NC
E
S
[1
]
Ma
tts
o
n
M.
,
“Path
way
s
to
war
d
s
an
d
awa
y
f
r
o
m
alzh
eim
er
’
s
d
is
ea
s
e
,
”
N
a
tu
r
e
,
vol
.
4
3
0
,
p
p
.
6
3
1
–
6
3
9
,
2004.
[2
]
Meek
P.D.
,
Mc
Keith
an
K.
,
a
n
d
Sh
u
m
o
ck
G.
T
.
,
“
E
co
n
o
m
i
cs
co
n
s
id
er
atio
n
s
of
alz
h
eim
e
r
’
s
d
is
ea
s
e‖
,”
P
h
a
r
ma
co
th
era
p
y
,
vol
.
1
8
,
p
p
.
68
–
7
3
,
Ma
r
c
h
-
Ap
r
il 1
9
9
8
.
[3
]
J
in
g
W
an
,
Z
h
ilin
Z
h
a
n
g
,
“I
d
e
n
tify
in
g
th
e
n
eu
r
o
an
ato
m
ical
b
asis
o
f
co
g
n
itiv
e
im
p
air
m
en
t
in
alzh
eim
e
r
’
s
d
is
ea
s
e
b
y
co
r
r
elatio
n
&
n
o
n
-
l
in
ea
r
ity
–
awa
r
e
s
p
ar
s
e
b
a
y
esian
lear
n
in
g
,
”
I
E
E
E
Tr
a
n
s
.
o
n
Med
.
I
ma
g
in
g
,
v
o
l.3
3
,
n
o
.
7
,
p
p
.
1
4
7
5
–
1
4
8
7
,
J
u
ly
2
0
1
4
.
[4
]
N.
N.
Ku
lk
ar
n
i,
V.
K.
B
air
ag
i
,
“
E
lectr
o
en
ce
p
h
alo
g
r
am
b
ase
d
d
iag
n
o
s
is
o
f
alzh
eim
er
d
is
ea
s
e,
”
in
P
r
o
c.
I
E
E
E
C
o
n
feren
ce
o
n
I
n
tellig
e
n
t S
ystems
a
n
d
C
o
n
tr
o
l,
p
p
.
1
-
5
,
2
0
1
5
.
[5
]
J
ae
s
eu
n
g
J
eo
n
g
,
“E
E
G
d
y
n
a
m
ics
in
p
atien
ts
wi
th
Alzh
eim
er
’
s
d
is
ea
s
e
,
”
A
r
ti
ficia
l
I
n
tellig
en
ce
in
Med
icin
e
,
vol
.
1
1
5
,
no.
7
,
p
p
.
1490
–
1
5
0
5
,
J
u
ly
2
0
0
4
.
[6
]
J
u
s
tin
Dau
wels,
et
al,
“Slo
win
g
an
d
lo
s
s
o
f
co
m
p
le
x
it
y
in
alzh
eim
er
’
s
E
E
G:
two
s
id
es
o
f
th
e
s
am
e
co
in
?
,
”
Hin
d
awi
Acc
ess
o
f
R
esear
ch
,
I
n
tern
a
tio
n
a
l J
o
u
r
n
a
l
o
f A
lz
h
eime
r
’
s
Dis
ea
s
e
,
vo
l.
2011
.
[7
]
R
ay
m
u
n
d
o
C
ass
an
i,
et
all,
“T
h
e
ef
f
ec
ts
o
f
a
u
to
m
ated
ar
tifa
ct
r
e
m
o
v
al
a
lg
o
r
ith
m
s
o
n
elec
tr
o
en
ce
p
h
al
o
g
r
ap
h
y
-
b
ased
alzh
eim
e
r
’
s
d
is
ea
s
e
d
iag
n
o
s
is
,
”
F
r
o
n
tier
s
in
A
g
in
g
N
eu
r
o
s
c
ien
ce
,
v
o
l.
6
,
no.
5
5
,
p
p
.
1
–
1
3
,
Ma
r
2
0
1
4
.
[8
]
Dh
iy
a
Al
-
J
u
m
eily
,
Sh
am
aila
I
r
am
,
Fra
n
co
is
-
B
en
o
is
Vialatte
,
Pau
l
Fer
g
u
s
,
an
d
Ab
ir
Hu
s
s
ain
,
“A
n
o
v
e
l
m
eth
o
d
o
f
ea
r
l
y
d
iag
n
o
s
is
o
f
alzh
eim
er
’
s
d
is
ea
s
e
b
ased
o
n
E
E
G
s
ig
n
als
,”
T
h
e
Scien
tific
W
o
r
ld
J
o
u
r
n
al,
v
o
l.
2
0
1
5
,
A
r
ticle
I
D
9
3
1
3
8
7
,
1
1
p
ag
es,
2
0
1
5
.
d
o
i:1
0
.
1
1
5
5
/2
0
1
5
/9
3
1
3
8
7
[9
]
An
d
r
ea
R
u
ed
a,
Fab
io
A.
Go
n
z
alez
,
“E
x
tr
ac
tin
g
s
alien
t
b
r
ain
p
atter
n
s
f
o
r
im
ag
in
g
-
b
ased
cla
s
s
if
icatio
n
o
f
n
eu
r
o
d
eg
en
e
r
ativ
e
d
is
ea
s
es
,
”
I
E
E
E
Tr
a
n
s
.
Med
.
I
ma
g
in
g
,
v
o
l.
3
3
,
n
o
.
6
,
p
p
.
1
2
6
2
-
1
2
7
4
,
J
u
n
e
2
0
1
4
.
[1
0
]
Su
r
esh
,
M.
,
R
av
ik
u
m
ar
,
M.
,
“
Dim
en
s
io
n
ality
r
ed
u
ctio
n
an
d
class
if
icatio
n
o
f
co
l
o
r
f
ea
tu
r
es
d
ata
u
s
in
g
SVM
an
d
KNN
,”
I
n
tern
a
tio
n
a
l
Jo
u
r
n
a
l
o
f
I
ma
g
e
P
r
o
ce
s
s
i
n
g
a
n
d
V
is
u
a
l
C
o
mmu
n
ica
tio
n
,
v
o
l.
1
,
n
o
.
4
,
p
p
.
2
3
1
9
–
1
7
2
4
,
Feb
r
u
ar
y
2
0
1
3
.
[1
1
]
Nilesh
Ku
lk
ar
n
i,
“
Use
o
f
co
m
p
lex
ity
b
ased
f
ea
tu
r
es
in
d
iag
n
o
s
is
o
f
m
ild
Alzh
eim
er
d
is
ea
s
e
u
s
in
g
E
E
G
s
ig
n
als
,”
I
n
tern
a
tio
n
a
l J
o
u
r
n
a
l o
f I
n
fo
r
ma
tio
n
Tech
n
o
lo
g
y
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
5
9
-
6
4
,
2
0
1
8
.
[1
2
]
N.
N.
Ku
lk
ar
n
i,
V.
K.
B
air
ag
i
,
“E
x
tr
ac
tin
g
Salien
t
f
ea
tu
r
es
f
o
r
E
E
G
b
ased
Diag
n
o
s
is
o
f
Alzh
eim
er
’
s
d
is
ea
s
e
Us
in
g
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
class
if
ier
,
”
I
E
TE
Jo
u
r
n
a
l
o
f
R
esea
r
ch
,
Ta
ylo
r
a
n
d
F
r
a
n
cis,
vol
.
6
3
,
no
.
1
,
p
p
.
1
1
-
22,
Ma
r
c
h
2
0
1
7
.
[1
3
]
N.
Ho
u
m
an
i
et
al.
,
“Dia
g
n
o
s
is
o
f
Alzh
eim
er
’
s
d
is
ea
s
e
wit
h
E
lectr
o
en
ce
p
h
alo
g
r
a
p
h
y
i
n
a
d
if
f
er
en
tial
f
r
am
ewo
r
k
,
”
P
Lo
S
On
e
,
v
o
l.
1
3
,
n
o
.
3
,
2
0
1
8
.
[1
4
]
J
u
s
tin
Dau
wels,
Fra
n
co
is
-
B
en
o
ıt
Vialatte,
an
d
An
d
r
ze
j
C
ich
o
ck
i,
“On
th
e
ea
r
ly
d
ia
g
n
o
s
is
o
f
alzh
eim
er
’
s
d
is
ea
s
e
f
r
o
m
E
E
G
Sig
n
als:
A
m
in
i
-
r
ev
iew
,
”
A
d
v
a
n
ce
s
in
c
o
g
n
itive
N
eu
r
o
d
yn
a
mics
,
p
p
.
7
0
9
-
7
1
6
,
2
0
1
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Nilesh
Nee
lk
an
th
Ku
lk
ar
n
i
w
as
b
o
r
n
in
Pu
n
e,
I
n
d
ia,
in
1
9
9
2
.
He
r
ec
eiv
ed
B
.
E
.
d
eg
r
ee
in
E
lectr
o
n
ics
en
g
i
n
ee
r
in
g
f
r
o
m
th
e
Un
iv
er
s
ity
o
f
Pu
n
e,
Pu
n
e,
I
n
d
i
a,
in
2
0
1
3
,
an
d
th
e
M.
E
.
d
e
g
r
ee
i
n
E
lectr
o
n
ics
&
T
elec
o
m
m
u
n
icatio
n
en
g
in
ee
r
in
g
f
r
o
m
Sav
itrib
ai
Ph
u
le
Pu
n
e
Un
iv
er
s
ity
(
Fo
r
m
e
r
ly
,
Un
iv
er
s
ity
o
f
Pu
n
e
)
in
2
0
1
5
,
r
esp
ec
tiv
ely
.
I
n
2
0
1
6
,
h
e
jo
in
ed
th
e
Dep
ar
tm
en
t
o
f
E
lectr
o
n
ics
E
n
g
in
ee
r
in
g
;
All
I
n
d
ia
Sh
r
i
Sh
iv
aji
Me
m
o
r
ial
So
ciety
’
s
I
n
s
titu
te
o
f
I
n
f
o
r
m
at
io
n
T
ec
h
n
o
lo
g
y
,
as
a
Vis
itin
g
f
ac
u
lty
an
d
t
h
en
co
n
tin
u
ed
as
Ass
i
s
tan
t
Pro
f
ess
o
r
in
E
lec
tr
o
n
ics
E
n
g
i
n
ee
r
in
g
d
ep
a
r
tm
e
n
t.
Pre
s
en
tly
,
h
e
is
wo
r
k
in
g
as
As
s
is
tan
t
Pro
f
ess
o
r
in
Sm
t.
Kash
ib
ai
Nav
ale
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
,
P
u
n
e.
His
cu
r
r
en
t
r
esear
ch
in
ter
ests
in
clu
d
e
B
io
m
ed
ical
E
n
g
i
n
ee
r
in
g
,
B
io
m
ed
ical
Sig
n
al
&
I
m
ag
e
Pro
ce
s
s
in
g
,
Ma
ch
in
e
L
ea
r
n
i
n
g
an
d
Patter
n
R
ec
o
g
n
itio
n
.
He
is
a
m
em
b
er
o
f
th
e
I
n
s
titu
tio
n
o
f
E
n
g
in
ee
r
s
(
I
n
d
ia
)
;
T
h
e
I
n
s
titu
tio
n
o
f
E
lectr
o
n
i
cs
an
d
T
elec
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
s
(
I
E
T
E
)
.
He
is
a
L
if
e
Me
m
b
er
o
f
I
E
I
(
I
n
d
i
a)
,
I
E
T
E
an
d
B
io
m
ed
ical
E
n
g
in
ee
r
in
g
So
ciety
o
f
I
n
d
ia.
He
h
as
f
iled
o
n
e
p
aten
t
at
n
atio
n
al
lev
el.
He
r
ec
eiv
e
d
“Bes
t I
n
n
o
v
ativ
e
Pro
ject
Awa
r
d
”
f
o
r
h
is
r
esear
ch
p
r
o
ject
p
r
e
s
en
ted
at
W
I
E
C
ON
–
2
0
1
6
s
p
o
n
s
o
r
ed
b
y
I
E
E
E
,
Pu
n
e
S
ec
tio
n
.
He
is
r
ec
ip
ien
t
o
f
Pr
o
f
.
M.
N.
Sah
a
Me
m
o
r
ial
Awa
r
d
,
awa
r
d
e
d
b
y
I
E
T
E
,
I
n
d
ia.
He
h
as
p
u
b
lis
h
ed
1
6
r
esear
ch
p
a
p
er
s
at
I
n
ter
n
atio
n
al
lev
el.
Pre
s
en
tly
,
h
e
is
wo
r
k
i
n
g
o
n
B
io
m
ed
ical
C
ir
cu
its
an
d
S
y
s
tem
ap
p
licatio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.