I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
24
,
p
p
.
6
9
9
2
~
7
0
0
0
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
6
9
9
2
-
7
0
0
0
6992
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Bra
ille
co
de clas
si
ficatio
ns too
l bas
e
d on co
mput
er vis
io
n f
o
r
v
isua
l impa
ired
H
a
ny
M
.
Sa
da
k
1
,
Ash
ra
f
A.
M
.
K
ha
la
f
1
,
Aziz
a
I
.
H
us
s
ein
2
,
G
er
g
es Ma
ns
o
ur
Sa
la
m
a
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
M
i
n
i
a
U
n
i
v
e
r
si
t
y
,
M
i
n
i
a
,
Eg
y
p
t
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
Ef
f
a
t
U
n
i
v
e
r
si
t
y
,
J
e
d
d
a
h
,
K
i
n
g
d
o
m o
f
S
a
u
d
i
A
r
a
b
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
5
,
2
0
2
4
R
ev
is
ed
Au
g
8
,
2
0
2
4
Acc
ep
ted
Au
g
1
4
,
2
0
2
4
Bli
n
d
a
n
d
v
is
u
a
ll
y
im
p
a
ired
p
e
o
p
le
(VIP)
fa
c
e
m
a
n
y
c
h
a
ll
e
n
g
e
s
in
writi
n
g
a
s
th
e
y
u
s
u
a
ll
y
u
se
trad
i
ti
o
n
a
l
to
o
l
s
su
c
h
a
s
S
late
a
n
d
S
ty
l
u
s
o
r
e
x
p
e
n
siv
e
ty
p
e
writers
a
s
P
e
rk
i
n
s
Bra
il
ler,
o
ften
c
a
u
sin
g
a
c
c
e
ss
ib
il
it
y
a
n
d
a
ff
o
rd
a
b
i
li
ty
issu
e
s.
Th
is
a
rti
c
le
in
tr
o
d
u
c
e
s
a
n
o
v
e
l
p
o
rtab
le,
c
o
st
-
e
ffe
c
ti
v
e
d
e
v
ice
th
a
t
h
e
l
p
s
VIP
h
o
w
to
write
b
y
u
ti
l
izin
g
a
d
e
e
p
-
lea
rn
in
g
m
o
d
e
l
to
d
e
tec
t
a
Br
a
il
le
c
e
ll
.
Us
in
g
d
e
e
p
lea
rn
i
n
g
i
n
ste
a
d
o
f
e
l
e
c
tri
c
a
l
c
ircu
it
s
c
a
n
re
d
u
c
e
c
o
sts
a
n
d
e
n
a
b
le
a
m
o
b
il
e
a
p
p
to
a
c
t
a
s a
v
irt
u
a
l
tea
c
h
e
r
fo
r
b
li
n
d
u
se
rs.
T
h
e
a
p
p
c
o
u
ld
su
g
g
e
s
t
se
n
ten
c
e
s
fo
r
th
e
u
se
r
to
write
a
n
d
c
h
e
c
k
th
e
ir
wo
r
k
,
p
ro
v
id
in
g
a
n
i
n
d
e
p
e
n
d
e
n
t
lea
rn
in
g
p
latfo
rm
.
T
h
is
fe
a
tu
re
is
d
iffi
c
u
lt
t
o
imp
lem
e
n
t
wh
e
n
u
sin
g
e
lec
tro
n
ic
c
ircu
it
s.
A
p
o
rtab
le
d
e
v
ice
g
e
n
e
ra
tes
Bra
il
le
c
h
a
ra
c
ter
c
e
ll
s
u
sin
g
li
g
h
t
-
e
m
it
ti
n
g
d
i
o
d
e
(
LED
)
a
rra
y
s
in
st
e
a
d
o
f
Bra
il
le
h
o
les
.
A
sm
a
rtp
h
o
n
e
c
a
m
e
ra
c
a
p
tu
re
s
th
e
ima
g
e
,
wh
ich
is
th
e
n
p
ro
c
e
ss
e
d
b
y
a
d
e
e
p
lea
rn
in
g
m
o
d
e
l
to
d
e
tec
t
th
e
Bra
il
le
a
n
d
c
o
n
v
e
rt
it
t
o
E
n
g
l
i
sh
tex
t.
Th
is
a
rti
c
le
p
r
o
v
i
d
e
s
a
n
e
w
d
a
tas
e
t
fo
r
c
u
st
o
m
-
Bra
il
le
c
h
a
ra
c
ter
c
e
ll
s.
M
o
re
o
v
e
r,
a
p
p
ly
i
n
g
a
tra
n
sfe
r
lea
rn
in
g
tec
h
n
iq
u
e
o
n
th
e
m
o
b
il
e
n
e
two
r
k
v
e
rsio
n
2
(M
o
b
il
e
Ne
tv
2
)
m
o
d
e
l
o
ffe
rs
a
b
a
sis
fo
r
th
e
d
e
v
e
l
o
p
m
e
n
t
o
f
a
c
o
m
p
re
h
e
n
si
v
e
m
o
b
il
e
a
p
p
li
c
a
ti
o
n
.
T
h
e
a
c
c
u
ra
c
y
b
a
se
d
o
n
th
e
m
o
d
e
l
re
a
c
h
e
d
9
7
%.
K
ey
w
o
r
d
s
:
Ass
i
s
tiv
e
tech
n
o
lo
g
y
B
r
aille
d
ataset
B
r
aille
ty
p
ewr
iter
s
C
o
m
p
u
ter
v
is
io
n
Ma
ch
in
e
lear
n
in
g
Mo
b
ileNetV2
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
:
Han
y
M.
Sad
ak
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
Min
ia
Un
iv
er
s
ity
Min
ia,
E
g
y
p
t
E
m
ail:
h
an
y
.
m
ela
d
@
m
u
.
ed
u
.
e
g
1.
I
NT
RO
D
UCT
I
O
N
Acc
o
r
d
in
g
to
th
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
,
ab
o
u
t
2
.
2
b
illi
o
n
p
eo
p
le
wo
r
ld
wid
e
ar
e
b
lin
d
o
r
v
is
u
ally
im
p
air
ed
[
1
]
.
Vis
u
all
y
im
p
air
e
d
p
eo
p
le
(
VI
P)
a
n
d
b
lin
d
p
eo
p
le
f
ac
e
m
an
y
s
d
if
f
icu
lties
in
lear
n
in
g
to
wr
ite
an
d
r
ea
d
d
u
e
to
a
lack
o
f
teac
h
e
r
s
[
2
]
o
r
th
e
h
ig
h
p
r
ice
o
f
t
h
e
lear
n
in
g
to
o
ls
.
Al
m
o
s
t
all
r
esear
ch
er
s
in
tr
o
d
u
ce
to
o
ls
f
o
r
lear
n
in
g
r
ea
d
in
g
.
Kad
er
et
a
l.
[
3
]
in
tr
o
d
u
ce
s
a
d
ev
ice
f
o
r
p
r
o
n
o
u
n
ci
n
g
th
e
ch
ar
ac
ter
a
n
d
m
ak
in
g
th
e
b
lin
d
s
en
s
e
th
e
p
o
s
itio
n
o
f
th
e
B
r
aille
co
d
e
u
s
in
g
s
ix
s
o
len
o
id
ac
tu
ato
r
,
o
r
r
ea
d
b
r
aille
tex
t
p
a
p
er
an
d
p
r
o
n
o
u
n
ce
it
p
r
o
v
id
i
n
g
s
elf
-
lear
n
in
g
m
eth
o
d
f
o
r
r
ea
d
in
g
,
also
Ar
d
ian
s
ah
an
d
Ok
az
a
k
i
[
4
]
p
r
o
v
id
es
a
m
o
b
il
e
ap
p
to
tr
an
s
late
th
e
wr
itten
B
r
aille
b
o
o
k
in
to
s
p
ee
c
h
f
o
r
lea
r
n
i
n
g
h
o
w
to
r
ea
d
.
R
ef
r
esh
ab
le
B
r
aille
d
is
p
lay
p
lay
s
an
im
p
o
r
tan
t
r
o
le
in
r
ea
d
in
g
.
T
h
e
co
n
tr
ib
u
tio
n
o
f
th
is
p
ap
er
is
in
th
e
ar
ea
o
f
lear
n
in
g
wr
i
tin
g
.
T
h
e
av
ailab
le
wr
itin
g
to
o
ls
ar
e
b
r
ief
ly
d
escr
ib
ed
as
f
o
llo
ws:
s
late
an
d
s
ty
lu
s
is
th
e
o
ld
est
B
r
aille
wr
it
in
g
m
eth
o
d
[
5
]
is
p
o
r
tab
le
b
u
t
s
lo
w
f
o
r
n
o
te
-
ta
k
in
g
,
r
eq
u
i
r
es
p
ap
er
,
an
d
p
r
o
v
id
es
n
o
f
ee
d
b
ac
k
.
Per
k
in
s
B
r
allier
is
a
m
e
ch
an
ical
d
e
v
ice
th
at
h
as
b
ee
n
wid
ely
u
s
ed
m
ec
h
an
ical
B
r
aille
wr
iter
,
s
in
ce
its
in
v
en
tio
n
in
1
9
5
1
.
Per
k
i
n
s
h
as
a
k
ey
co
r
r
esp
o
n
d
i
n
g
to
ea
ch
o
f
th
e
s
ix
d
o
ts
o
f
th
e
B
r
aille
ce
ll,
a
s
p
ac
e
k
e
y
,
an
d
a
b
ac
k
s
p
ac
e
k
ey
.
T
h
is
d
e
v
ice
co
m
es
in
a
n
ew
v
er
s
io
n
ca
lled
s
m
ar
t
B
r
allier
,
wh
ich
was
in
v
en
ted
in
2
0
1
1
.
I
t
h
as
tex
t
-
to
-
s
p
ee
ch
au
d
io
f
ee
d
b
ac
k
an
d
a
d
ig
ital
d
is
p
lay
f
o
r
u
s
e
b
y
b
o
th
s
ig
h
te
d
an
d
b
li
n
d
in
d
i
v
id
u
als
[
6
]
.
T
h
e
p
r
ice
o
f
th
e
Per
k
in
s
B
r
allier
is
h
ig
h
(
ab
o
u
t 1
,
6
0
0
$
)
,
an
d
it
is
a
h
ea
v
y
-
weig
h
t
d
ev
ice,
s
o
it
is
n
o
t
af
f
o
r
d
ab
le
f
o
r
all
s
tu
d
en
ts
.
I
n
ad
d
itio
n
,
it
is
n
o
t
a
p
o
r
ta
b
le
d
ev
ice.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
B
r
a
ille c
o
d
e
cla
s
s
ifica
tio
n
s
to
o
l b
a
s
ed
o
n
co
mp
u
ter visi
o
n
fo
r
visu
a
l imp
a
ir
ed
(
Ha
n
y
M.
S
a
d
a
k
)
6993
Mo
u
n
tb
atten
B
r
aille
was
in
v
en
ted
in
1
9
8
3
[
7
]
,
with
ad
d
itio
n
al
f
ea
tu
r
es
lik
e
au
d
i
o
f
ee
d
b
ac
k
a
n
d
ty
p
e
c
o
r
r
ec
tio
n
s
m
em
o
r
y
s
to
r
ag
e.
I
t
ca
n
co
n
n
e
ct
to
a
co
m
p
u
ter
.
Ho
wev
e
r
,
it
is
an
ex
p
en
s
iv
e
p
r
o
d
u
ct
(
8
,
0
0
0
$
)
,
a
n
d
,
th
er
e
f
o
r
e,
n
o
t
af
f
o
r
d
ab
le
b
y
m
an
y
p
eo
p
l
e
an
d
s
ch
o
o
ls
.
Sm
ar
t
B
r
aille
was
in
v
en
ted
in
2
0
1
1
;
it
is
an
im
p
r
o
v
e
d
v
er
s
io
n
o
f
Per
k
in
s
B
r
allier
[
6
]
b
ec
au
s
e
it
h
as
a
tex
t
-
to
-
s
p
ee
ch
f
ea
tu
r
e.
H
o
wev
er
,
it
is
ex
p
en
s
iv
e.
B
r
aille
n
o
te
-
tak
in
g
d
ev
ices
h
av
e
a
r
ef
r
esh
ab
le
B
r
aille
d
is
p
lay
an
d
MP3
m
ed
ia
p
lay
e
r
.
B
r
ailleNo
te
is
a
p
o
r
tab
le
co
m
p
u
ter
[
8
]
.
B
r
aille
k
ey
b
o
a
r
d
s
[
9
]
h
elp
VI
P
to
u
s
e
s
m
ar
tp
h
o
n
es
o
r
a
co
m
p
u
ter
;
h
o
wev
er
,
it
n
ee
d
s
m
o
r
e
p
r
ac
tice.
t
o
u
ch
s
cr
ee
n
d
ev
ices
h
elp
VI
P
to
im
p
r
o
v
e
th
eir
liv
i
n
g
co
n
d
itio
n
.
Sh
o
k
at
et
a
l.
[
1
0
]
d
ev
el
o
p
in
g
a
m
ac
h
in
e
lear
n
in
g
E
n
g
lis
h
B
r
aille
p
atter
n
id
en
tific
atio
n
b
y
c
o
llectin
g
a
B
r
aille
d
ataset
f
r
o
m
to
u
ch
s
cr
ee
n
d
ev
ices
.
T
h
e
ex
is
tin
g
B
r
aille
wr
itin
g
to
o
ls
f
ac
e
s
ev
er
al
ch
allen
g
es.
Ad
v
an
ce
d
to
o
ls
ar
e
o
f
ten
ex
p
en
s
iv
e
an
d
in
ac
ce
s
s
ib
le,
wh
ile
b
asic
to
o
l
s
r
eq
u
ir
e
co
n
s
tan
t
teac
h
er
g
u
i
d
an
ce
,
lim
itin
g
in
d
e
p
en
d
e
n
t
lear
n
in
g
.
T
o
ad
d
r
ess
th
ese
is
s
u
es,
a
p
r
o
p
o
s
ed
s
o
lu
ti
o
n
is
t
o
d
e
v
elo
p
an
af
f
o
r
d
a
b
le
d
ev
ice
f
o
r
lear
n
in
g
B
r
aille
le
tter
p
lace
m
en
t
an
d
f
o
r
m
atio
n
(
wr
itin
g
tech
n
i
q
u
es).
T
h
is
s
o
lu
tio
n
is
d
i
v
id
ed
in
t
o
two
p
ar
ts
a
p
o
r
tab
le
d
ev
ice
f
o
r
f
o
r
m
attin
g
th
e
B
r
aille
co
d
e
b
y
u
s
in
g
lig
h
t
-
e
m
itti
n
g
d
io
d
e
(
L
E
D
s
)
,
an
d
a
d
ee
p
lear
n
in
g
m
o
d
el
t
o
an
al
y
ze
th
e
B
r
aille
co
d
e
to
d
etec
t
th
e
co
r
r
esp
o
n
d
in
g
E
n
g
l
is
h
ch
ar
ac
ter
.
T
h
e
d
ee
p
lear
n
i
n
g
m
o
d
el
was
tr
ain
ed
o
n
a
d
at
aset.
T
h
e
tar
g
et
f
o
r
th
is
s
tag
e
o
f
t
h
e
r
esear
ch
is
t
o
d
ev
el
o
p
f
ir
m
war
e
an
d
v
alid
ate
th
e
id
ea
o
f
u
s
in
g
d
ee
p
lea
r
n
in
g
to
d
etec
t
th
e
wr
itten
B
r
aille
co
d
e
.
I
n
th
e
f
u
tu
r
e,
we
p
lan
o
n
d
e
p
lo
y
in
g
th
e
d
ee
p
lear
n
in
g
m
o
d
el
o
n
a
m
o
b
ile
ap
p
to
an
aly
ze
wr
itten
letter
s
an
d
p
r
o
n
o
u
n
ce
letter
s
.
I
t
co
u
ld
also
s
u
g
g
est
f
u
tu
r
e
letter
s
f
o
r
m
o
r
e
p
r
ac
tic
e
an
d
s
to
r
e
wr
itten
co
n
ten
t
to
b
e
p
r
in
te
d
later
.
B
y
em
p
o
wer
i
n
g
i
n
d
ep
e
n
d
en
t
B
r
aille
lear
n
in
g
,
th
is
s
o
lu
tio
n
wo
u
ld
r
e
d
u
ce
r
elian
ce
o
n
teac
h
er
ass
is
tan
ce
an
d
in
cr
ea
s
e
ac
ce
s
s
ib
ilit
y
an
d
af
f
o
r
d
ab
ilit
y
.
T
h
is
m
o
b
ile
ap
p
is
th
e
r
e
aso
n
f
o
r
u
s
in
g
d
ee
p
lear
n
in
g
in
s
tead
o
f
u
s
in
g
elec
t
r
ical
cir
cu
it,
s
o
th
is
tec
h
n
iq
u
e
will
h
av
e
m
o
r
e
an
d
m
o
r
e
f
ea
tu
r
es.
Ou
r
r
esear
ch
co
n
tr
ib
u
tio
n
s
in
clu
d
e:
̶
Desig
n
in
g
a
d
ev
ice
Fig
u
r
e
1
T
h
e
d
e
v
ice
f
o
r
m
s
a
B
r
aille
ce
l
l
u
s
in
g
L
E
Ds
in
s
tead
o
f
m
ec
h
an
ical
d
ev
ices
b
y
p
r
ess
in
g
th
e
b
u
tto
n
s
to
m
ak
e
a
co
r
r
esp
o
n
d
in
g
L
E
D
tu
r
n
o
n
to
f
o
r
m
t
h
e
s
am
e
s
h
ap
e
as
th
e
B
r
aille
ch
ar
ac
ter
.
T
h
e
d
esig
n
is
s
im
ilar
to
ex
is
tin
g
ty
p
e
wr
itin
g
d
e
v
ices
as
th
ey
h
av
e
th
e
s
am
e
b
u
tto
n
p
o
s
itio
n
s
.
T
h
e
d
ataset
was
cr
ea
ted
b
y
u
s
in
g
th
is
d
ev
ice,
to
v
alid
ate
th
e
id
ea
o
f
class
if
y
in
g
th
e
B
r
aille
co
d
e
in
t
o
co
r
r
esp
o
n
d
in
g
E
n
g
lis
h
ch
ar
a
cter
s
.
̶
C
r
ea
tin
g
a
d
ataset
f
ir
m
war
e
A
cu
s
to
m
d
ataset
f
o
r
th
e
B
r
aille
alp
h
ab
et
is
c
r
ea
ted
to
u
s
e
it
a
s
a
s
tan
d
ar
d
f
o
r
th
e
co
m
p
u
ter
v
is
io
n
task
s
to
tr
ain
th
e
m
o
d
el
to
r
ec
o
g
n
ize
th
e
B
r
aille
ce
ll a
n
d
co
n
v
er
t it
to
its
co
r
r
esp
o
n
d
i
n
g
E
n
g
lis
h
c
h
ar
ac
ter
.
̶
Dev
elo
p
a
m
o
d
el
b
ased
o
n
d
ee
p
lear
n
in
g
R
ec
en
tly
,
d
ee
p
lear
n
i
n
g
-
b
ased
m
o
d
els
h
av
e
m
a
d
e
g
r
ea
t
ad
v
a
n
ce
s
in
m
an
y
ar
ea
s
,
f
o
r
e
x
am
p
le
,
in
o
b
ject
d
etec
tio
n
an
d
n
atu
r
al
im
a
g
e
cl
ass
if
icatio
n
[
1
1
]
,
[
1
2
]
.
Ap
p
lic
atio
n
s
[
1
3
]
also
in
cl
u
d
e
s
p
ee
c
h
r
ec
o
g
n
itio
n
[
1
4
]
.
Dee
p
lear
n
in
g
is
also
cu
r
r
en
tl
y
u
s
ed
f
o
r
B
r
aille
ch
ar
ac
ter
r
ec
o
g
n
itio
n
[
1
5
]
.
M
o
r
eo
v
er
,
it
is
u
s
ed
in
a
p
p
ly
in
g
T
r
an
s
f
er
lear
n
i
n
g
tech
n
iq
u
es
[
1
6
]
o
n
th
e
Mo
b
ileNetV2
m
o
d
el
[
1
7
]
.
C
u
r
r
en
tly
,
M
o
b
ileNetV2
is
u
s
ed
in
m
an
y
im
ag
e
class
if
icatio
n
r
esear
c
h
to
p
ics,
s
u
ch
as
f
r
u
it
im
ag
e
class
if
icatio
n
[
1
8
]
,
lu
n
g
d
is
ea
s
e
m
u
lticlas
s
class
if
icatio
n
[
1
9
]
,
waste
class
if
icatio
n
[
2
0
]
.
Usi
n
g
d
ee
p
lear
n
in
g
in
s
tead
o
f
elec
tr
ical
cir
cu
its
will
lead
to
n
ew
im
p
r
o
v
em
e
n
ts
an
d
ex
tr
a
f
ea
tu
r
es
in
th
e
f
u
tu
r
e
lik
e,
s
elf
-
lear
n
in
g
m
o
b
ile
ap
p
,
a
n
d
ex
a
m
p
r
o
v
id
er
p
latf
o
r
m
s
f
o
r
VI
P.
T
h
is
m
o
d
el
h
as
9
7
%
ac
c
u
r
ac
y
an
d
v
alid
ates
th
e
id
ea
o
f
co
n
v
er
tin
g
a
ca
p
tu
r
e
d
im
a
g
e
f
o
r
cu
s
to
m
B
r
aille
ch
ar
ac
ter
s
in
to
co
r
r
esp
o
n
d
in
g
E
n
g
lis
h
tex
t b
ased
o
n
a
d
ee
p
-
l
ea
r
n
in
g
a
p
p
r
o
ac
h
.
Fig
u
r
e
1
.
T
h
e
Desig
n
ed
d
ev
ic
e
f
o
r
s
im
u
latin
g
B
r
aille
ce
ll
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
is
d
iv
id
ed
in
t
o
t
h
r
ee
p
ar
ts
:
d
esig
n
in
g
th
e
d
ev
i
ce
,
cr
ea
tin
g
th
e
d
ataset,
an
d
t
r
ain
in
g
th
e
d
ee
p
lear
n
in
g
m
o
d
el.
T
h
e
d
esig
n
ed
d
e
v
ice
is
s
im
ilar
to
ex
is
t
i
n
g
B
r
aille
k
ey
b
o
ar
d
s
.
T
h
e
d
ata
s
et
is
co
n
s
id
er
ed
as
f
ir
m
war
e
f
o
r
tr
ain
in
g
th
e
m
o
d
el.
T
h
e
m
o
d
el
was d
ev
elo
p
e
d
b
ased
o
n
Mo
b
ileNetv
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
9
9
2
-
7
0
0
0
6994
2
.
1
.
Desig
nin
g
t
he
dev
ice
T
h
e
p
r
o
ce
s
s
o
f
d
esig
n
in
g
th
e
e
lectr
o
n
ic
d
ev
ice
in
v
o
lv
ed
t
h
e
f
o
llo
win
g
s
tep
s
.
Firstl
y
,
th
e
p
r
in
ted
cir
cu
it
b
o
ar
d
(
PC
B
)
was
d
esig
n
ed
u
s
in
g
Pro
teu
s
s
o
f
twar
e,
en
s
u
r
in
g
th
e
p
r
o
p
er
lay
o
u
t
o
f
elec
tr
o
n
ic
co
m
p
o
n
en
ts
.
Nex
t,
a
3
D
m
o
d
el
f
o
r
th
e
b
o
x
a
n
d
c
o
v
er
was
cr
ea
te
d
u
tili
zin
g
o
n
s
h
ap
e
s
o
f
twar
e,
allo
win
g
f
o
r
p
r
e
cise
d
im
en
s
io
n
s
an
d
d
esig
n
cu
s
to
m
izatio
n
.
T
h
e
PC
B
was
th
en
p
r
i
n
ted
u
s
in
g
a
co
m
p
u
ter
n
u
m
e
r
ical
co
n
tr
o
l
(
C
N
C
)
m
ac
h
in
e,
wh
ile
th
e
b
o
x
a
n
d
co
v
e
r
wer
e
3
D
p
r
i
n
ted
,
d
ev
ice
is
s
h
o
wn
i
n
Fig
u
r
e
1
.
Fig
u
r
e
2
s
h
o
ws
ex
p
er
im
en
tal
s
etu
p
,
wh
e
r
e
th
e
d
ev
ice
is
p
u
t
u
n
d
er
ca
m
e
r
a
p
h
o
n
e.
T
h
is
d
ev
ice
c
o
n
s
is
ts
o
f
b
u
tto
n
s
an
d
8
L
E
Ds
ar
r
an
g
e
d
i
n
two
co
l
u
m
n
s
,
ea
c
h
co
n
tain
in
g
f
o
u
r
L
E
Ds.
E
ac
h
b
u
tto
n
co
n
n
ec
ts
with
th
e
co
r
r
esp
o
n
d
in
g
L
E
D
as
s
h
o
wn
in
Fig
u
r
e
3
.
T
h
e
ar
r
an
g
em
e
n
t
o
f
th
e
b
u
tto
n
s
an
d
th
e
L
E
Ds
is
s
im
ilar
to
Per
k
in
s
B
r
allier
,
wh
er
e
L
E
Ds
1
to
6
r
e
p
r
esen
t
th
e
s
tan
d
ar
d
B
r
aille
s
ix
-
d
o
t
ce
ll.
T
h
e
s
tan
d
e
r
s
ix
d
o
ts
ar
e
o
r
g
an
ized
in
to
a
3
×
2
ar
r
ay
,
wh
ich
o
f
f
er
s
6
4
co
m
b
in
atio
n
s
o
f
u
n
iq
u
e
p
atter
n
s
.
Fo
r
ex
a
m
p
le,
in
th
e
x
class
s
h
o
wn
in
Fig
u
r
e
4
,
b
u
tto
n
s
1
,
3
,
4
,
a
n
d
6
ar
e
p
r
ess
ed
,
c
o
r
r
esp
o
n
d
in
g
t
o
th
e
Per
k
in
s
B
r
ailler
k
ey
s
,
a
n
d
t
h
e
co
r
r
esp
o
n
d
in
g
L
E
Ds
ar
e
tu
r
n
e
d
o
n
.
as
s
h
o
w
n
in
Fig
u
r
e
4
.
W
e
h
av
e
d
ev
el
o
p
ed
a
cu
s
to
m
B
r
aille
ce
ll
with
eig
h
t
d
ig
its
,
6
L
E
Ds
as
s
tan
d
ar
d
,
a
n
d
L
E
D
7
r
e
p
r
esen
ts
th
e
s
p
ac
e
k
ey
,
an
d
L
E
D
8
r
ep
r
esen
ts
th
e
n
ew
lin
e
k
ey
.
T
h
e
ex
tr
a
two
L
E
Ds
(
7
,
8
)
en
ab
le
th
e
m
o
d
el
to
n
o
t
o
n
l
y
d
etec
t
alp
h
ab
etica
l le
tter
s
b
u
t
also
d
etec
t
s
p
ac
es
b
etwe
en
wo
r
d
s
an
d
n
ew
lin
e
ac
tio
n
r
e
q
u
ir
ed
t
o
s
tar
t
a
n
ew
li
n
e
o
f
te
x
t.
T
h
er
e
is
an
o
th
er
v
er
s
io
n
o
f
th
e
B
r
aille
ce
ll
co
n
s
is
tin
g
o
f
eig
h
t
d
o
ts
[
2
1
]
ar
r
an
g
ed
in
a
4
×
2
ar
r
ay
,
wh
ich
o
f
f
er
s
2
5
6
u
n
i
q
u
e
co
m
b
in
atio
n
s
to
r
ep
r
esen
t
o
n
e
alp
h
ab
et
o
r
a
co
n
t
r
ac
tio
n
o
f
a
wo
r
d
.
Fig
u
r
e
2
.
E
x
p
er
im
e
n
tal
s
etu
p
f
o
r
ca
p
tu
r
in
g
im
a
g
e
o
f
b
r
aille
c
ell
Fig
u
r
e
3
.
th
e
d
ev
ice
lay
o
u
t
Fig
u
r
e
4
.
T
h
e
g
e
n
er
ated
x
class
with
o
u
r
d
ev
ice
v
s
th
e
s
tan
d
e
r
x
class
in
B
r
aille
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
B
r
a
ille c
o
d
e
cla
s
s
ifica
tio
n
s
to
o
l b
a
s
ed
o
n
co
mp
u
ter visi
o
n
fo
r
visu
a
l imp
a
ir
ed
(
Ha
n
y
M.
S
a
d
a
k
)
6995
2
.
2
.
Cre
a
t
ing
t
he
da
t
a
s
et
T
h
e
d
ataset
co
n
s
is
ts
o
f
ap
p
r
o
x
im
ately
2
,
2
0
0
p
ictu
r
es
d
iv
i
d
ed
in
to
1
,
9
3
1
p
ictu
r
es
f
o
r
tr
ai
n
in
g
an
d
2
5
9
p
ictu
r
es
f
o
r
test
in
g
.
All
th
ese
p
ictu
r
es
wer
e
tak
en
f
r
o
m
v
ar
i
o
u
s
an
g
les
an
d
with
d
if
f
er
en
t
b
r
i
g
h
tn
ess
co
n
d
itio
n
s
.
T
h
e
d
ataset
co
n
s
is
ted
o
f
3
7
c
h
ar
ac
ter
s
in
T
ab
le
1
,
co
n
s
is
tin
g
o
f
B
r
aille
g
r
ad
e
1
s
y
m
b
o
ls
.
L
e
g
g
e
et
a
l.
[
2
2
]
s
h
o
ws
th
e
d
if
f
er
e
n
ce
b
etwe
en
B
r
aille
g
r
ad
es.
T
h
e
class
es
co
n
tain
ed
all
th
e
alp
h
ab
etica
l
letter
s
an
d
p
u
n
ctu
atio
n
,
b
ased
o
n
th
e
B
r
aille
g
r
a
d
e
1
s
tan
d
ar
d
s
y
m
b
o
ls
.
Sam
p
les
o
f
o
u
r
d
at
aset
ar
e
s
h
o
wn
in
Fig
u
r
e
5
.
T
o
p
r
ep
a
r
e
th
e
d
ataset
f
o
r
tr
ai
n
in
g
,
s
ev
er
al
s
tep
s
wer
e
f
o
llo
wed
.
First,
m
u
ltip
le
p
ict
u
r
es
o
f
th
e
s
am
e
c
h
ar
ac
ter
s
w
er
e
ca
p
tu
r
e
d
.
T
h
ese
p
ictu
r
es
wer
e
th
en
o
r
g
a
n
ized
i
n
to
3
7
f
o
ld
e
r
s
,
ea
ch
r
e
p
r
esen
ti
n
g
a
s
p
ec
if
ic
B
r
aille
class
.
A
r
an
d
o
m
s
elec
tio
n
o
f
p
ictu
r
es
f
r
o
m
ea
ch
class
was
u
s
ed
to
cr
ea
te
th
e
test
in
g
d
a
ta
,
en
s
u
r
in
g
an
eq
u
al
n
u
m
b
er
o
f
class
e
s
.
A
Py
th
o
n
s
cr
ip
t
was
ex
ec
u
ted
to
r
ea
d
ea
ch
p
ictu
r
e
an
d
g
en
er
ate
a
co
m
m
a
-
s
ep
ar
ated
v
alu
e
(
C
SV
)
f
ile
with
two
c
o
lu
m
n
s
:
th
e
p
ictu
r
e
n
am
e
a
n
d
th
e
c
o
r
r
es
p
o
n
d
in
g
class
.
Ad
d
itio
n
ally
,
a
o
n
e
-
h
o
t
en
co
d
e
d
C
SV
f
ile
was
cr
ea
ted
to
f
ac
ilit
ate
m
u
lti
-
class
clas
s
if
icatio
n
.
T
h
e
p
ictu
r
es
wer
e
cr
o
p
p
e
d
to
f
o
c
u
s
o
n
ly
o
n
th
e
L
E
Ds
an
d
wer
e
m
er
g
ed
in
to
a
s
in
g
le
f
o
ld
er
.
T
h
e
s
am
e
s
tep
s
wer
e
a
p
p
lied
to
th
e
test
in
g
d
ata
to
e
n
s
u
r
e
co
n
s
is
ten
cy
.
T
ab
le
1
.
T
r
ai
n
in
g
d
ataset
class
es with
n
u
m
b
er
o
f
p
ictu
r
es with
ea
ch
class
C
l
a
s
s
n
a
me
P
i
c
t
u
r
e
n
u
m
b
e
r
s
C
l
a
s
s
n
a
me
P
i
c
t
u
r
e
n
u
m
b
e
r
s
C
l
a
s
s
n
a
me
P
i
c
t
u
r
e
n
u
m
b
e
r
s
_
!
57
_
45
_
39
_
−
56
_
53
_
43
_
52
_
42
_
52
_
56
_
′
49
_
43
_
62
_
0
48
_
44
_
62
_
48
_
95
_
51
_
40
_
56
_
#
62
_
41
_
53
_
.
50
_
ℎ
51
_
46
_
53
_
38
_
47
_
67
_
52
_
64
_
79
_
57
_
44
_
34
Fig
u
r
e
5
.
C
u
s
to
m
d
ataset
s
am
p
les
2
.
3
.
Dev
elo
pin
g
a
deep
lea
rning
m
o
del
B
y
ap
p
ly
in
g
tr
an
s
f
er
lear
n
in
g
u
s
in
g
Mo
b
ileNetv
2
as
f
ea
tu
r
e
ex
tr
ac
to
r
s
,
wh
er
e
Mo
b
ileNetv
2
is
a
p
r
e
-
tr
ain
ed
im
ag
e
class
if
icatio
n
m
o
d
el.
T
r
an
s
f
er
lear
n
in
g
tr
a
n
s
f
er
s
th
e
k
n
o
wled
g
e
f
r
o
m
o
n
e
d
o
m
ain
to
an
o
th
er
a
n
d
also
tak
es
less
tim
e
to
tr
ain
n
e
w
m
o
d
els
with
h
ig
h
ac
cu
r
ac
y
s
u
itab
le
with
lim
ited
r
eso
u
r
ce
s
o
f
ce
n
tr
al
p
r
o
ce
s
s
in
g
u
n
it
(
C
PU
)
an
d
g
r
ap
h
ics
p
r
o
c
ess
in
g
u
n
it
(
GPU
)
av
ailab
ilit
y
.
W
e
u
s
ed
Mo
b
ileNetV2
ar
c
h
itectu
r
e
with
o
u
t
a
n
y
cu
s
to
m
izatio
n
o
f
th
e
b
ase
m
o
d
el.
Mo
b
ileNetV2
ar
c
h
itectu
r
e
[
1
6
]
,
is
p
r
ef
e
r
r
ed
o
v
er
o
th
er
s
d
u
e
to
its
s
im
p
le
ar
ch
itectu
r
e
an
d
m
e
m
o
r
y
-
ef
f
ic
ien
t
ch
ar
ac
ter
is
tics
.
T
h
e
ar
c
h
itectu
r
e
co
n
tai
n
s
th
e
in
itial
f
u
lly
co
n
v
o
lu
tio
n
lay
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
9
9
2
-
7
0
0
0
6996
with
3
2
f
ilter
s
,
f
o
llo
wed
b
y
1
9
r
esid
u
al
b
o
ttlen
ec
k
lay
e
r
s
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
co
n
s
is
ts
o
f
3
s
tag
es,
as
s
h
o
wn
in
Fig
u
r
e
6
.
First
s
tag
e:
lab
eled
"b
lo
ck
1
"
is
f
o
r
r
esizin
g
th
e
in
p
u
t im
ag
e
to
(
2
2
4
,
224,
3
)
to
f
it with
Mo
b
ileNetV2
ar
ch
itectu
r
e
in
p
u
t.
Seco
n
d
s
tag
e:
lab
eled
"M
o
b
ileNetV2
"
is
th
e
m
ain
p
ar
t
o
f
th
e
p
r
o
p
o
s
e
d
m
o
d
el
u
s
ed
as
a
class
if
ier
,
as
it
is
m
o
r
e
ef
f
icie
n
t
an
d
s
im
p
ler
in
ca
lcu
latio
n
s
.
I
n
a
d
d
itio
n
,
it
h
as
a
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
ar
ch
itec
tu
r
e
th
at
s
ee
k
s
to
p
er
f
o
r
m
well
o
n
m
o
b
ile
d
ev
ices
f
r
o
m
Go
o
g
le
as
it
is
f
aster
th
a
n
m
an
y
m
o
d
els
an
d
u
s
es
les
s
m
em
o
r
y
,
r
esu
ltin
g
in
b
etter
ac
cu
r
ac
y
.
T
h
ir
d
s
tag
e:
I
t
is
lab
eled
"c
u
s
t
o
m
h
ea
d
"
wh
ich
co
n
s
is
ts
o
f
g
lo
b
al
av
er
ag
e
Po
o
lin
g
2
D,
f
o
llo
wed
b
y
a
Den
s
e
lay
er
with
3
7
o
u
t
p
u
t
class
es
u
s
in
g
th
e
"So
f
t
m
ax
im
u
m
.
"
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
e
So
f
t
Ma
x
ac
tiv
atio
n
f
u
n
ctio
n
is
co
m
m
o
n
ly
u
s
ed
f
o
r
m
u
lticlas
s
class
if
icatio
n
in
d
ee
p
lear
n
in
g
.
I
t
is
u
s
ed
to
c
o
m
p
u
te
p
r
o
b
a
b
ilit
y
d
is
tr
ib
u
tio
n
f
r
o
m
a
v
ec
to
r
o
f
r
ea
l
n
u
m
b
er
s
.
T
h
e
So
f
tMa
x
f
u
n
ctio
n
[
2
3
]
p
r
o
d
u
ce
s
an
o
u
tp
u
t
b
etwe
en
0
a
n
d
with
t
h
e
s
u
m
o
f
th
e
p
r
o
b
ab
ilit
ies
b
ein
g
e
q
u
al
to
1
.
T
h
e
So
f
tMa
x
f
o
r
m
u
la
[
2
4
]
a
p
p
ea
r
s
in
(
1
)
.
(
)
=
ex
p
(
)
∑
ex
p
(
j
)
j
(
1
)
Mo
d
el
tr
ain
in
g
is
ca
r
r
ied
o
u
t
in
th
r
ee
s
tep
s
.
I
m
ag
e
p
r
ep
r
o
ce
s
s
in
g
u
s
in
g
th
e
Ker
as
im
ag
e
d
at
a
g
en
er
ato
r
class
[
2
5
]
.
T
h
is
class
o
f
f
er
s
v
ar
io
u
s
tech
n
iq
u
es
f
o
r
im
a
g
e
p
r
ep
r
o
ce
s
s
in
g
wh
ich
is
u
tili
ze
d
to
r
escale
b
o
th
tr
ain
in
g
an
d
test
im
ag
es
to
a
r
an
g
e
o
f
1
/2
5
5
.
Af
ter
p
r
ep
r
o
ce
s
s
in
g
,
th
e
d
ata
n
ee
d
s
to
b
e
f
o
r
m
atted
as
a
th
r
ee
-
d
im
e
n
s
io
n
al
m
atr
ix
s
u
ch
as 2
2
4
×2
2
4
×3
in
a
way
th
at
th
e
n
e
u
r
al
n
etwo
r
k
ca
n
u
n
d
er
s
tan
d
.
Featu
r
e
ex
tr
ac
tio
n
b
y
ap
p
l
y
in
g
tr
an
s
f
er
lear
n
in
g
o
n
Mo
b
ileN
etV2
ar
ch
itectu
r
e
w
h
ich
was
p
r
e
-
tr
ain
ed
o
n
a
lar
g
e
d
ataset
lik
e
I
m
ag
eNe
t
[
2
6
]
,
wh
er
e
th
e
b
ase
lay
er
s
ar
e
f
r
o
ze
n
,
an
d
o
n
ly
th
e
cu
s
to
m
h
id
d
en
lay
er
s
ar
e
tr
ain
ed
with
r
o
o
t
m
ea
n
s
q
u
a
r
ed
p
r
o
p
ag
atio
n
(
R
MSp
r
o
p
)
o
p
tim
izer
s
[
2
7
]
u
s
in
g
a
lear
n
in
g
r
ate
o
f
0
.
0
0
1
.
Ad
d
itio
n
ally
,
th
e
d
ataset
is
s
p
lit,
allo
ca
tin
g
2
0
%
o
f
th
e
tr
ain
in
g
d
ata
f
o
r
th
e
v
alid
atio
n
p
r
o
ce
s
s
.
T
h
e
class
if
icatio
n
s
tep
in
v
o
lv
es
em
p
lo
y
in
g
t
h
e
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
.
I
t
allo
ws
f
o
r
th
e
d
et
ec
tio
n
o
f
th
e
co
r
r
ec
t
class
o
f
th
e
in
p
u
t im
ag
e
.
T
ab
le
2
d
is
p
lay
s
th
e
s
ettin
g
s
th
at
we
r
e
u
s
ed
.
F
i
gu
r
e
6.
M
o
bi
l
e
N
et
V
2
b
ui
l
di
n
g
bl
o
c
k
T
ab
le
2
.
Settin
g
s
f
o
r
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
Le
a
r
n
i
n
g
r
a
t
e
Ep
o
c
h
s
B
a
t
c
h
si
z
e
O
p
t
i
mi
z
e
r
Lo
ss f
u
n
c
t
i
o
n
0
.
0
0
1
1
0
0
30
R
M
S
p
r
o
p
c
a
t
e
g
o
r
i
c
a
l
c
r
o
ss
e
n
t
r
o
p
y
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
h
e
ac
cu
r
ac
y
o
f
d
etec
tin
g
th
e
E
n
g
lis
h
ch
ar
ac
ter
c
o
r
r
esp
o
n
d
i
n
g
to
B
r
aille
co
d
e.
r
ea
ch
es
alm
o
s
t
9
7
%
as
s
h
o
wn
in
Fig
u
r
e
7
.
T
h
e
v
alid
atio
n
lo
s
s
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
r
ea
ch
es
a
v
er
y
l
o
w
v
alu
e
o
f
0
.
1
9
as
s
h
o
w
n
in
Fig
u
r
e
8
.
T
h
e
p
er
f
o
r
m
a
n
ce
a
n
d
ev
alu
atio
n
o
f
t
h
e
m
o
d
el
a
r
e
m
ea
s
u
r
ed
u
s
in
g
a
co
n
f
u
s
io
n
m
atr
ix
[
2
8
]
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
s
h
o
w
n
in
Fig
u
r
e
9
.
T
h
e
ev
alu
atio
n
o
f
th
e
m
o
d
el
is
b
ased
o
n
s
ev
er
al
f
ac
to
r
s
,
wh
ich
ar
e:
ac
cu
r
a
cy
,
p
r
ec
is
io
n
,
s
en
s
itiv
ity
,
an
d
F1
-
S
co
r
e.
T
h
e
ca
lcu
latio
n
s
an
d
m
ea
s
u
r
em
en
ts
ar
e
g
iv
e
n
by
(
2
)
to
(
6
)
[
2
9
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
B
r
a
ille c
o
d
e
cla
s
s
ifica
tio
n
s
to
o
l b
a
s
ed
o
n
co
mp
u
ter visi
o
n
fo
r
visu
a
l imp
a
ir
ed
(
Ha
n
y
M.
S
a
d
a
k
)
6997
Fig
u
r
e
7
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
g
r
ap
h
Fig
u
r
e
8
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
lo
s
s
g
r
ap
h
=
+
+
+
+
(
2
)
=
+
(
3
)
=
+
(
4
)
1
−
=
2
∗
∗
+
=
2
∗
2
∗
+
+
(
5
)
=
=
+
(
6
)
w
h
er
e
TP
: tr
u
e
p
o
s
itiv
e,
co
r
r
e
ct
p
r
ed
ictio
n
.
TN
: tr
u
e
n
e
g
ativ
e,
co
r
r
ec
t
p
r
ed
ictio
n
.
FP
: f
alse
p
o
s
itiv
e,
f
alse o
r
b
ad
p
r
e
d
ictio
n
.
FN
: f
alse n
eg
a
tiv
e,
th
e
wo
r
s
t p
r
e
d
ictio
n
r
esu
l
t
.
Fig
u
r
e
1
0
s
h
o
ws
th
e
p
r
ed
icte
d
lab
els
v
s
tr
u
e
lab
els
f
o
r
th
e
f
in
al
m
o
d
el
o
u
tp
u
t
r
esu
lt
af
t
er
tr
ain
in
g
.
T
ab
le
3
s
h
o
ws
a
co
m
p
ar
is
o
n
b
etwe
en
ex
is
tin
g
s
o
lu
tio
n
s
f
o
r
B
r
aille
d
ev
ices
an
d
m
eth
o
d
s
.
Yo
u
ca
n
n
o
tice
th
at
o
u
r
p
r
o
p
o
s
ed
d
ev
ice
is
tech
n
o
lo
g
y
-
b
ased
,
p
o
r
ta
b
le,
an
d
c
h
e
ap
er
with
r
ea
s
o
n
ab
le
ac
cu
r
ac
y
co
m
p
ar
ed
t
o
o
th
er
ex
is
tin
g
s
o
lu
tio
n
s
.
T
h
is
h
ig
h
ac
cu
r
ac
y
o
f
th
e
m
o
d
el
is
a
v
alid
atio
n
o
f
u
s
in
g
co
m
p
u
ter
v
is
io
n
in
B
r
aille
lear
n
in
g
wr
itin
g
tech
n
iq
u
es with
o
u
t
u
s
i
n
g
a
n
y
e
x
p
e
n
s
i
v
e
t
o
o
l
s
o
r
h
e
a
v
y
a
n
d
n
o
n
p
o
r
t
a
b
l
e
t
y
p
e
w
r
i
t
e
r
.
W
i
t
h
t
h
e
h
e
l
p
o
f
t
h
is
m
o
d
e
l
,
m
a
n
y
p
r
o
d
u
c
t
s
wi
l
l
b
e
d
e
v
e
l
o
p
e
d
b
a
s
e
d
o
n
i
t
.
T
h
is
m
et
h
o
d
i
s
c
o
n
s
i
d
e
r
e
d
a
n
ew
d
i
r
e
ct
i
o
n
o
f
l
e
a
r
n
i
n
g
B
r
a
i
ll
e
w
r
i
t
i
n
g
c
o
m
p
a
r
e
d
wi
t
h
t
r
a
d
i
t
i
o
n
a
l
t
o
o
l
s
w
h
i
c
h
u
s
e
e
l
ec
t
r
i
ca
l
ci
r
c
u
i
t
s
.
O
n
e
o
f
t
h
e
f
u
t
u
r
e
p
r
o
d
u
c
t
s
is
a
m
o
b
il
e
a
p
p
b
a
s
e
d
o
n
t
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l
.
T
h
i
s
a
p
p
w
i
l
l
s
e
r
v
e
as
a
s
e
l
f
-
l
ea
r
n
i
n
g
p
l
a
t
f
o
r
m
,
a
c
t
i
n
g
a
s
a
v
i
r
t
u
a
l
t
e
a
c
h
e
r
t
o
d
e
t
e
c
t
a
n
d
p
r
o
n
o
u
n
c
e
B
r
a
i
l
l
e
c
o
d
e
.
Ad
d
i
t
i
o
n
a
l
l
y
,
i
t
c
a
n
s
u
g
g
e
s
t
w
o
r
d
s
t
o
b
e
w
r
i
t
t
e
n
a
n
d
p
r
o
v
i
d
e
c
o
r
r
e
c
t
i
o
n
s
.
A
n
o
t
h
e
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
9
9
2
-
7
0
0
0
6998
f
e
a
t
u
r
e
c
a
n
b
e
t
h
e
a
b
i
li
t
y
t
o
p
r
e
p
a
r
e
,
a
d
m
i
n
i
s
t
e
r
,
a
n
d
c
o
r
r
e
c
t
e
x
a
m
p
a
p
e
r
s
,
h
e
l
p
i
n
g
s
c
h
o
o
ls
s
i
g
n
i
f
i
c
a
n
t
l
y
.
E
a
c
h
s
t
u
d
e
n
t
c
a
n
i
n
s
t
a
ll
t
h
e
a
p
p
l
i
c
at
io
n
o
n
t
h
e
i
r
o
w
n
d
e
v
i
c
e
,
o
f
f
e
r
i
n
g
s
c
h
o
o
l
s
a
m
u
c
h
c
h
e
a
p
e
r
s
o
l
u
ti
o
n
.
M
o
r
e
o
v
e
r
,
t
h
i
s
a
p
p
c
a
n
b
e
u
s
e
d
a
s
a
n
o
t
e
t
a
k
i
n
g
,
s
t
o
r
i
n
g
wr
itten
wo
r
d
s
to
b
e
p
r
in
ted
u
s
in
g
B
r
ailler
p
r
in
ter
s
.
Fig
u
r
e
9
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
Fig
u
r
e
1
0
.
Pre
d
icted
lab
els v
s
tr
u
e
lab
el
T
ab
le
3
.
C
o
m
p
a
r
is
o
n
b
etwe
en
ex
is
tin
g
s
o
lu
tio
n
s
f
o
r
B
r
aille
D
e
v
i
c
e
n
a
me
P
r
i
c
e
P
r
o
b
l
e
m w
i
t
h
t
h
e
t
e
c
h
n
i
c
s
P
o
r
t
a
b
l
e
Te
c
h
n
o
l
o
g
y
-
b
a
s
e
d
A
c
c
u
r
a
c
y
P
e
r
k
i
n
s
1
6
0
0
$
O
l
d
m
e
c
h
a
n
i
c
a
l
d
e
s
i
g
n
a
n
d
h
e
a
v
y
No
No
1
0
0
%
S
l
a
t
e
a
n
d
S
t
y
l
u
s
8
0
$
V
e
r
y
s
l
o
w
a
n
d
t
o
o
o
l
d
a
n
d
w
i
t
h
o
u
t
a
n
y
f
e
e
d
b
a
c
k
Y
e
s
No
1
0
0
%
S
mart
B
r
a
l
l
i
e
r
8
0
0
0
$
V
e
r
y
e
x
p
e
n
si
v
e
,
m
a
i
n
t
e
n
a
n
c
e
n
o
t
a
l
w
a
y
s
a
v
a
i
l
a
b
l
e
No
Y
e
s
1
0
0
%
O
u
r
me
t
h
o
d
1
0
$
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Y
e
s
Y
e
s
9
7
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
B
r
a
ille c
o
d
e
cla
s
s
ifica
tio
n
s
to
o
l b
a
s
ed
o
n
co
mp
u
ter visi
o
n
fo
r
visu
a
l imp
a
ir
ed
(
Ha
n
y
M.
S
a
d
a
k
)
6999
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
in
t
r
o
d
u
ce
s
an
in
n
o
v
ativ
e
s
o
lu
tio
n
f
o
r
b
lin
d
a
n
d
v
is
u
ally
im
p
air
ed
in
d
iv
id
u
als,
s
er
v
in
g
as a
wr
itin
g
aid
to
o
l.
B
y
u
s
in
g
a
s
im
p
le
d
esig
n
ed
p
o
r
tab
le
d
ev
ice,
a
cu
s
to
m
d
ataset
was
cr
ea
ted
co
n
s
is
tin
g
o
f
ap
p
r
o
x
im
ately
2
,
2
0
0
p
ictu
r
es
o
f
cu
s
to
m
B
r
aille
c
h
ar
ac
ter
s
d
i
v
id
ed
in
t
o
tr
ain
i
n
g
a
n
d
test
in
g
s
ets.
B
y
em
p
lo
y
in
g
tr
an
s
f
er
lear
n
i
n
g
tec
h
n
iq
u
es
w
ith
Mo
b
ileNetV2
,
a
d
ee
p
lear
n
in
g
m
o
d
el
was
d
e
v
elo
p
ed
an
d
test
ed
.
T
h
e
tr
ain
i
n
g
p
r
o
ce
s
s
was
ex
p
ed
ited
an
d
s
im
p
lifie
d
.
T
h
e
m
o
d
el
was
th
en
ev
alu
ated
o
n
th
e
test
in
g
d
at
aset,
d
em
o
n
s
tr
atin
g
its
ab
ilit
y
to
ac
c
u
r
ately
p
r
e
d
ict
E
n
g
lis
h
C
h
ar
ac
ter
s
co
r
r
esp
o
n
d
i
n
g
to
B
r
aille
ch
ar
ac
te
r
s
with
a
9
7
%
ac
c
u
r
ac
y
r
ate.
T
h
e
d
e
v
ice
with
t
h
e
m
o
d
el
is
an
in
n
o
v
ativ
e
d
ir
ec
tio
n
f
o
r
p
r
o
d
u
cin
g
ty
p
ewr
iter
to
o
ls
b
ased
o
n
c
o
m
p
u
ter
v
is
io
n
in
s
tead
o
f
e
x
p
e
n
s
iv
e
elec
tr
ical
to
o
ls
,
lead
in
g
to
th
e
d
ev
elo
p
m
en
t
o
f
ch
ea
p
er
to
o
ls
f
o
r
b
lin
d
p
eo
p
le.
Fo
r
ex
am
p
le,
th
is
m
o
d
el
p
r
o
v
id
es
th
e
f
o
u
n
d
atio
n
f
o
r
th
e
d
ev
elo
p
m
en
t
o
f
a
co
m
p
r
eh
e
n
s
iv
e
m
o
b
ile
a
p
p
h
e
lp
s
in
s
elf
-
lear
n
in
g
b
r
aille
wr
itin
g
tech
n
iq
u
es
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
S
h
o
k
a
t
,
R
.
R
i
a
z
,
S
.
S
.
R
i
z
v
i
,
K
.
K
h
a
n
,
F
.
R
i
a
z
,
a
n
d
S
.
J.
K
w
o
n
,
“
A
n
a
l
y
s
i
s a
n
d
e
v
a
l
u
a
t
i
o
n
o
f
b
r
a
i
l
l
e
t
o
t
e
x
t
c
o
n
v
e
r
si
o
n
me
t
h
o
d
s,
”
Mo
b
i
l
e
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
2
0
2
0
,
p
p
.
1
–
1
4
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
3
4
6
1
6
5
1
.
[
2
]
E.
R
.
H
o
sk
i
n
,
M
.
K
.
C
o
y
n
e
,
M
.
J
.
W
h
i
t
e
,
S
.
C
.
D
.
D
o
b
r
i
,
T.
C
.
D
a
v
i
e
s
,
a
n
d
S
.
D
.
P
i
n
d
e
r
,
“
Ef
f
e
c
t
i
v
e
n
e
ss
o
f
t
e
c
h
n
o
l
o
g
y
f
o
r
b
r
a
i
l
l
e
l
i
t
e
r
a
c
y
e
d
u
c
a
t
i
o
n
f
o
r
c
h
i
l
d
r
e
n
:
A
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
D
i
sa
b
i
l
i
t
y
a
n
d
R
e
h
a
b
i
l
i
t
a
t
i
o
n
:
Assi
s
t
i
v
e
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
1
2
0
–
1
3
0
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
1
7
4
8
3
1
0
7
.
2
0
2
2
.
2
0
7
0
6
7
6
.
[
3
]
M
.
A
b
d
u
l
K
a
d
e
r
,
R
.
A
h
m
e
d
,
M
.
I
.
R
a
h
m
a
n
N
o
m
a
n
,
A
.
B
i
l
l
a
h
,
a
n
d
M
.
U
d
d
i
n
A
p
p
l
e
,
“
D
e
v
e
l
o
p
i
n
g
a
se
l
f
-
l
e
a
r
n
i
n
g
b
r
a
i
l
l
e
k
i
t
f
o
r
v
i
s
u
a
l
l
y
i
m
p
a
i
r
e
d
p
e
o
p
l
e
,
”
i
n
2
0
1
8
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
n
o
v
a
t
i
o
n
s
i
n
S
c
i
e
n
c
e
,
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
I
C
I
S
ET)
,
O
c
t
.
2
0
1
8
,
p
p
.
4
7
–
51
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
S
ET.
2
0
1
8
.
8
7
4
5
5
9
5
.
[
4
]
J.
Tr
i
A
r
d
i
a
n
s
a
h
a
n
d
Y
.
O
k
a
z
a
k
i
,
“
Th
e
d
e
si
g
n
a
n
d
p
r
o
t
o
t
y
p
i
n
g
o
f
b
r
a
i
l
l
e
t
o
sp
e
e
c
h
a
p
p
l
i
c
a
t
i
o
n
a
s
a
sel
f
-
l
e
a
r
n
i
n
g
s
u
p
p
o
r
t
m
e
d
i
a
f
o
r
v
i
s
u
a
l
l
y
i
m
p
a
i
r
e
d
p
e
r
so
n
,
”
i
n
2
0
2
0
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
V
o
c
a
t
i
o
n
a
l
E
d
u
c
a
t
i
o
n
a
n
d
T
r
a
i
n
i
n
g
(
I
C
O
VET)
,
S
e
p
.
2
0
2
0
,
p
p
.
2
2
4
–
228
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
V
ET5
0
2
5
8
.
2
0
2
0
.
9
2
3
0
0
6
0
.
[
5
]
E.
H
.
K
w
a
y
,
N
.
M
.
S
a
l
l
e
h
,
a
n
d
R
.
A
.
M
a
j
i
d
,
“
S
l
a
t
e
a
n
d
s
t
y
l
u
s:
A
n
a
l
t
e
r
n
a
t
i
v
e
t
o
o
l
f
o
r
b
r
a
i
l
l
e
w
r
i
t
i
n
g
,
”
Pr
o
c
e
d
i
a
-
S
o
c
i
a
l
a
n
d
Be
h
a
v
i
o
ra
l
S
c
i
e
n
c
e
s
,
v
o
l
.
7
,
p
p
.
3
2
6
–
3
3
5
,
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
b
s
p
r
o
.
2
0
1
0
.
1
0
.
0
4
5
.
[
6
]
K
.
J
.
M
i
c
h
a
e
l
so
n
,
L.
M
a
t
z
,
a
n
d
D
.
M
o
r
g
a
n
,
“
U
si
n
g
a
n
e
w
e
l
e
c
t
r
o
n
i
c
b
r
a
i
l
l
e
r
t
o
i
m
p
r
o
v
e
b
r
a
i
l
l
e
l
e
a
r
n
i
n
g
a
t
t
h
e
F
l
o
r
i
d
a
s
c
h
o
o
l
f
o
r
t
h
e
d
e
a
f
a
n
d
b
l
i
n
d
,
”
J
o
u
r
n
a
l
o
f
V
i
su
a
l
I
m
p
a
i
rm
e
n
t
&
Bl
i
n
d
n
e
ss
,
v
o
l
.
1
0
9
,
n
o
.
3
,
p
p
.
2
2
6
–
2
3
1
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
7
7
/
0
1
4
5
4
8
2
X
1
5
1
0
9
0
0
3
0
8
.
[
7
]
C
.
M
o
o
r
e
a
n
d
I
.
M
u
r
r
a
y
,
“
A
n
e
l
e
c
t
r
o
n
i
c
d
e
s
i
g
n
o
f
a
l
o
w
c
o
st
b
r
a
i
l
l
e
t
y
p
e
w
r
i
t
e
r
,
”
i
n
T
h
e
S
e
v
e
n
t
h
A
u
st
r
a
l
i
a
n
a
n
d
N
e
w
Z
e
a
l
a
n
d
I
n
t
e
l
l
i
g
e
n
t
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
C
o
n
f
e
ren
c
e
,
2
0
0
1
,
2
0
0
1
,
p
p
.
1
5
3
–
1
5
7
,
d
o
i
:
1
0
.
1
1
0
9
/
A
N
ZI
I
S
.
2
0
0
1
.
9
7
4
0
6
7
.
[
8
]
C
.
K
a
me
i
-
H
a
n
n
a
n
a
n
d
H
.
L
a
w
so
n
,
“
I
mp
a
c
t
o
f
a
b
r
a
i
l
l
e
-
n
o
t
e
o
n
w
r
i
t
i
n
g
:
Ev
a
l
u
a
t
i
n
g
t
h
e
p
r
o
c
e
ss,
q
u
a
l
i
t
y
,
a
n
d
a
t
t
i
t
u
d
e
s
o
f
t
h
r
e
e
st
u
d
e
n
t
s
w
h
o
a
r
e
v
i
s
u
a
l
l
y
i
m
p
a
i
r
e
d
,
”
J
o
u
r
n
a
l
o
f
S
p
e
c
i
a
l
Ed
u
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
7
,
n
o
.
3
,
p
p
.
1
–
1
4
,
S
e
p
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
7
7
/
0
1
6
2
6
4
3
4
1
2
0
2
7
0
0
3
0
1
.
[
9
]
S
.
B
e
g
ma
t
o
v
,
M
.
A
r
a
b
b
o
e
v
,
K
.
N
o
si
r
o
v
,
K
.
G
a
z
i
e
v
,
J
.
C
.
C
h
e
d
j
o
u
,
a
n
d
K
.
K
y
a
ma
k
y
a
,
“
D
e
v
e
l
o
p
m
e
n
t
o
f
a
p
r
o
t
o
t
y
p
e
o
f
a
b
r
a
i
l
l
e
k
e
y
b
o
a
r
d
f
o
r
sm
a
r
t
p
h
o
n
e
s,
”
i
n
2
0
2
2
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
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
I
S
C
T
)
,
S
e
p
.
2
0
2
2
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
S
C
T5
5
6
0
0
.
2
0
2
2
.
1
0
1
4
6
9
8
9
.
[
1
0
]
S
.
S
h
o
k
a
t
,
R
.
R
i
a
z
,
S
.
S
.
R
i
z
v
i
,
I
.
K
h
a
n
,
a
n
d
A
.
P
a
u
l
,
“
C
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
o
f
E
n
g
l
i
s
h
b
r
a
i
l
l
e
p
a
t
t
e
r
n
s
u
si
n
g
a
u
t
o
ma
t
e
d
t
o
o
l
s a
n
d
R
I
C
A
b
a
s
e
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s,”
S
e
n
so
rs
,
v
o
l
.
2
2
,
n
o
.
5
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
0
5
1
8
3
6
.
[
1
1
]
Y
.
Y
u
a
n
,
C
.
W
a
n
g
,
a
n
d
Z
.
J
i
a
n
g
,
“
P
r
o
x
y
-
b
a
s
e
d
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
s
p
e
c
t
r
a
l
–
s
p
a
t
i
a
l
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
:
E
f
f
i
c
i
e
n
t
a
n
d
r
o
b
u
s
t
,
”
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
G
e
o
s
c
i
e
n
c
e
a
n
d
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
6
0
,
p
p
.
1
–
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
G
R
S
.
2
0
2
1
.
3
0
5
4
0
0
8
.
[
1
2
]
M
.
A
l
a
a
,
G
.
S
a
l
a
ma
,
A
.
G
a
l
a
l
,
a
n
d
H
.
H
a
med
,
“
A
r
o
b
u
st
l
a
n
e
d
e
t
e
c
t
i
o
n
me
t
h
o
d
f
o
r
u
r
b
a
n
r
o
a
d
s
,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
En
g
i
n
e
e
r
i
n
g
T
ren
d
s
,
v
o
l
.
4
1
,
n
o
.
1
,
p
p
.
1
3
–
2
6
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
2
1
6
0
8
/
j
a
e
t
.
2
0
2
0
.
3
7
1
7
2
.
1
0
2
5
.
[
1
3
]
H
.
F
.
K
h
a
l
i
l
,
E
.
M
.
M
a
h
m
o
u
d
,
A
.
M
a
h
r
o
u
s
,
H
.
F
.
A
.
H
a
me
d
,
a
n
d
H
.
s
a
y
e
d
A
h
me
d
,
“
C
N
N
-
M
R
t
u
m
o
r
c
l
a
ss
i
f
i
e
r
:
B
r
a
i
n
t
u
m
o
r
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
s
y
s
t
e
m
b
a
s
e
d
o
n
C
N
N
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
m
o
d
e
l
s
c
o
mb
i
n
e
d
w
i
t
h
d
i
s
t
r
i
b
u
t
e
d
c
o
m
p
u
t
i
n
g
p
r
o
c
e
ss,
”
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
En
g
i
n
e
e
ri
n
g
T
re
n
d
s
,
v
o
l
.
4
3
,
n
o
.
2
,
p
p
.
3
9
9
–
4
2
3
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
2
1
6
0
8
/
j
a
e
t
.
2
0
2
4
.
2
3
7
5
6
7
.
1
2
5
9
.
[
1
4
]
Z.
S
o
n
g
,
“
E
n
g
l
i
sh
s
p
e
e
c
h
r
e
c
o
g
n
i
t
i
o
n
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
w
i
t
h
m
u
l
t
i
p
l
e
f
e
a
t
u
r
e
s
,
”
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
0
2
,
n
o
.
3
,
p
p
.
6
6
3
–
6
8
2
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
6
0
7
-
0
1
9
-
0
0
7
5
3
-
0.
[
1
5
]
I
.
G
.
O
v
o
d
o
v
,
“
S
e
ma
n
t
i
c
-
b
a
se
d
a
n
n
o
t
a
t
i
o
n
e
n
h
a
n
c
e
m
e
n
t
a
l
g
o
r
i
t
h
m
f
o
r
s
e
m
i
-
su
p
e
r
v
i
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
e
f
f
i
c
i
e
n
c
y
i
m
p
r
o
v
e
me
n
t
a
p
p
l
i
e
d
t
o
o
p
t
i
c
a
l
b
r
a
i
l
l
e
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
2
0
2
1
I
EEE
C
o
n
f
e
r
e
n
c
e
o
f
R
u
s
si
a
n
Y
o
u
n
g
R
e
se
a
rc
h
e
rs
i
n
El
e
c
t
ri
c
a
l
a
n
d
E
l
e
c
t
r
o
n
i
c
En
g
i
n
e
e
ri
n
g
(
El
C
o
n
R
u
s)
,
Ja
n
.
2
0
2
1
,
p
p
.
2
1
9
0
–
2
1
9
4
,
d
o
i
:
1
0
.
1
1
0
9
/
El
C
o
n
R
u
s5
1
9
3
8
.
2
0
2
1
.
9
3
9
6
5
3
4
.
[
1
6
]
A
.
R
.
Za
mi
r
,
A
.
S
a
x
,
W
.
S
h
e
n
,
L.
G
u
i
b
a
s,
J
.
M
a
l
i
k
,
a
n
d
S
.
S
a
v
a
r
e
s
e
,
“
Ta
sk
o
n
o
my
:
D
i
s
e
n
t
a
n
g
l
i
n
g
t
a
sk
t
r
a
n
s
f
e
r
l
e
a
r
n
i
n
g
,
”
i
n
2
0
1
8
I
E
EE
/
C
VF
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
si
o
n
a
n
d
Pa
t
t
e
rn
R
e
c
o
g
n
i
t
i
o
n
,
Ju
n
.
2
0
1
8
,
p
p
.
3
7
1
2
–
3
7
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
8
.
0
0
3
9
1
.
[
1
7
]
M
.
S
a
n
d
l
e
r
,
A
.
H
o
w
a
r
d
,
M
.
Z
h
u
,
A
.
Z
h
m
o
g
i
n
o
v
,
a
n
d
L
.
-
C
.
C
h
e
n
,
“
M
o
b
i
l
e
N
e
t
V
2
:
I
n
v
e
r
t
e
d
r
e
s
i
d
u
a
l
s
a
n
d
l
i
n
e
a
r
b
o
t
t
l
e
n
e
c
k
s
,
”
i
n
2
0
1
8
I
E
E
E
/
C
V
F
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
s
i
o
n
a
n
d
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
,
J
u
n
.
2
0
1
8
,
p
p
.
4
5
1
0
–
4
5
2
0
,
doi
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
8
.
0
0
4
7
4
.
[
1
8
]
Y
.
G
u
l
z
a
r
,
“
F
r
u
i
t
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
mo
d
e
l
b
a
se
d
o
n
M
o
b
i
l
e
N
e
t
V
2
w
i
t
h
d
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
5
,
n
o
.
3
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
5
0
3
1
9
0
6
.
[
1
9
]
F
.
J.
M
.
S
h
a
mr
a
t
,
S
.
A
z
a
m,
A
.
K
a
r
i
m,
K
.
A
h
m
e
d
,
F
.
M
.
B
u
i
,
a
n
d
F
.
D
e
B
o
e
r
,
“
H
i
g
h
-
p
r
e
c
i
si
o
n
m
u
l
t
i
c
l
a
ss
c
l
a
s
si
f
i
c
a
t
i
o
n
o
f
l
u
n
g
d
i
s
e
a
se
t
h
r
o
u
g
h
c
u
st
o
mi
z
e
d
M
o
b
i
l
e
N
e
t
V
2
f
r
o
m
c
h
e
st
X
-
r
a
y
i
ma
g
e
s
,
”
C
o
m
p
u
t
e
rs
i
n
B
i
o
l
o
g
y
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
1
5
5
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
b
i
o
me
d
.
2
0
2
3
.
1
0
6
6
4
6
.
[
2
0
]
L.
Y
o
n
g
,
L.
M
a
,
D
.
S
u
n
,
a
n
d
L
.
D
u
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
M
o
b
i
l
e
N
e
t
V
2
t
o
w
a
st
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
PLO
S
O
N
E
,
v
o
l
.
1
8
,
n
o
.
3
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
2
3
3
6
.
[
2
1
]
M
.
N
a
d
e
e
m
,
N
.
A
z
i
z
,
U
.
S
a
j
j
a
d
,
F
.
A
z
i
z
,
a
n
d
H
.
S
h
a
i
k
h
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
B
r
a
i
l
l
e
g
e
n
e
r
a
t
i
o
n
t
e
c
h
n
o
l
o
g
i
e
s
,
”
i
n
2
0
1
6
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
d
R
o
b
o
t
i
c
s
a
n
d
M
e
c
h
a
t
r
o
n
i
c
s
(
I
C
A
R
M
)
,
2
0
1
6
,
p
p
.
2
9
4
–
2
9
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
R
M
.
2
0
1
6
.
7
6
0
6
9
3
5
.
[
2
2
]
G
.
E
.
Le
g
g
e
,
C
.
M
.
M
a
d
i
s
o
n
,
a
n
d
J
.
S
.
M
a
n
sf
i
e
l
d
,
“
M
e
a
su
r
i
n
g
b
r
a
i
l
l
e
r
e
a
d
i
n
g
s
p
e
e
d
w
i
t
h
t
h
e
M
N
R
EA
D
t
e
s
t
,
”
V
i
su
a
l
I
m
p
a
i
rm
e
n
t
Re
se
a
rc
h
,
v
o
l
.
1
,
n
o
.
3
,
p
p
.
1
3
1
–
1
4
5
,
Jan
.
1
9
9
9
,
d
o
i
:
1
0
.
1
0
7
6
/
v
i
mr
.
1
.
3
.
1
3
1
.
4
4
3
8
.
[
2
3
]
C
.
N
w
a
n
k
p
a
,
W
.
I
j
o
ma
h
,
A
.
G
a
c
h
a
g
a
n
,
a
n
d
S
.
M
a
r
sh
a
l
l
,
“
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s
:
C
o
mp
a
r
i
s
o
n
o
f
t
r
e
n
d
s
i
n
p
r
a
c
t
i
c
e
a
n
d
r
e
se
a
r
c
h
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Pr
e
p
r
i
n
t
,
a
rXi
v
.
1
8
1
1
.
0
3
3
7
8
,
N
o
v
.
2
0
1
8
.
[
2
4
]
S
.
M
e
h
r
a
,
G
.
R
a
u
t
,
R
.
D
a
s
P
u
r
k
a
y
a
st
h
a
,
S
.
K
.
V
i
s
h
v
a
k
a
r
ma
,
a
n
d
A
.
B
i
a
si
z
z
o
,
“
A
n
e
mp
i
r
i
c
a
l
e
v
a
l
u
a
t
i
o
n
o
f
e
n
h
a
n
c
e
d
p
e
r
f
o
r
m
a
n
c
e
so
f
t
m
a
x
f
u
n
c
t
i
o
n
i
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
3
4
9
1
2
–
3
4
9
2
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
6
5
3
2
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
9
9
2
-
7
0
0
0
7000
[
2
5
]
C
.
S
h
o
r
t
e
n
a
n
d
T.
M
.
K
h
o
s
h
g
o
f
t
a
a
r
,
“
A
su
r
v
e
y
o
n
i
ma
g
e
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
6
,
n
o
.
1
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
1
9
-
0
1
9
7
-
0.
[
2
6
]
J.
D
e
n
g
,
W
.
D
o
n
g
,
R
.
S
o
c
h
e
r
,
L
.
-
J.
L
i
,
K
a
i
Li
,
a
n
d
L
i
F
e
i
-
F
e
i
,
“
I
mag
e
N
e
t
:
A
l
a
r
g
e
-
sca
l
e
h
i
e
r
a
r
c
h
i
c
a
l
i
ma
g
e
d
a
t
a
b
a
s
e
,
”
i
n
2
0
0
9
I
EE
E
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
Pa
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
J
u
n
.
2
0
0
9
,
p
p
.
2
4
8
–
2
5
5
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
0
9
.
5
2
0
6
8
4
8
.
[
2
7
]
R
.
Za
h
e
e
r
a
n
d
H
.
S
h
a
z
i
y
a
,
“
A
st
u
d
y
o
f
t
h
e
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
i
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
2
0
1
9
T
h
i
rd
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
v
e
n
t
i
v
e
S
y
s
t
e
m
s
a
n
d
C
o
n
t
r
o
l
(
I
C
I
S
C
)
,
Ja
n
.
2
0
1
9
,
p
p
.
5
3
6
–
5
3
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
S
C
4
4
3
5
5
.
2
0
1
9
.
9
0
3
6
4
4
2
.
[
2
8
]
N
.
D
.
M
a
r
o
m
,
L.
R
o
k
a
c
h
,
a
n
d
A
.
S
h
mi
l
o
v
i
c
i
,
“
U
s
i
n
g
t
h
e
c
o
n
f
u
s
i
o
n
ma
t
r
i
x
f
o
r
i
m
p
r
o
v
i
n
g
e
n
sem
b
l
e
c
l
a
ssi
f
i
e
r
s,
”
i
n
2
0
1
0
I
E
EE
2
6
-
t
h
C
o
n
v
e
n
t
i
o
n
o
f
El
e
c
t
ri
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s
E
n
g
i
n
e
e
rs
i
n
I
sra
e
l
,
N
o
v
.
2
0
1
0
,
p
p
.
0
0
0
5
5
5
–
0
0
0
5
5
9
,
d
o
i
:
1
0
.
1
1
0
9
/
EE
EI
.
2
0
1
0
.
5
6
6
2
1
5
9
.
[
2
9
]
A
.
R
.
K
h
a
n
,
“
F
a
c
i
a
l
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
c
o
n
v
e
n
t
i
o
n
a
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
:
C
u
r
r
e
n
t
a
c
h
i
e
v
e
me
n
t
s,
a
n
a
l
y
si
s
a
n
d
r
e
ma
i
n
i
n
g
c
h
a
l
l
e
n
g
e
s
,
”
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
3
,
n
o
.
6
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
i
n
f
o
1
3
0
6
0
2
6
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
a
n
y
M.
S
a
d
a
k
re
c
e
iv
e
d
t
h
e
B.
S
c
.
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
fro
m
M
i
n
ia
Un
iv
e
rsity
,
Eg
y
p
t
in
2
0
1
8
.
He
wo
rk
e
d
a
s
e
m
b
e
d
d
e
d
sy
ste
m
e
n
g
i
n
e
e
r
fro
m
2
0
1
8
ti
ll
2
0
2
0
a
t
Va
leo
Eg
y
p
t
(a
m
u
lt
in
a
ti
o
n
a
l
c
o
m
p
a
n
y
i
n
th
e
a
u
t
o
m
o
ti
v
e
field
).
Cu
rre
n
tl
y
,
h
e
is
tea
c
h
in
g
a
ss
istan
t
a
t
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
M
i
n
ia
Un
i
v
e
rsity
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
e
m
b
e
d
d
e
d
s
y
ste
m
,
a
n
d
a
ss
isti
v
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
n
y
.
m
e
lad
@m
u
.
e
d
u
.
e
g
.
As
h
r
a
f
A.
M.
K
h
a
la
f
re
c
e
iv
e
d
h
is
B.
S
c
.
a
n
d
M
.
S
c
.
d
e
g
re
e
s
in
e
le
c
tri
c
a
l
e
n
g
in
e
e
rin
g
fro
m
M
i
n
ia
Un
i
v
e
rsity
,
E
g
y
p
t,
in
1
9
8
9
a
n
d
1
9
9
4
,
re
sp
e
c
ti
v
e
ly
.
He
r
e
c
e
iv
e
d
th
e
d
e
g
re
e
"
D
o
c
to
r
o
f
e
n
g
in
e
e
rin
g
i
n
sy
s
tem
sc
i
e
n
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
"
fr
o
m
Ka
n
a
z
a
wa
Un
iv
e
rsity
,
Ja
p
a
n
,
o
n
M
a
rc
h
2
2
,
2
0
0
0
-
P
h
.
D.
d
e
g
re
e
in
E
g
y
p
t.
His
re
se
a
rc
h
i
n
tere
sts
in
c
l
u
d
e
Ad
a
p
ti
v
e
sig
n
a
l,
a
u
d
i
o
,
a
n
d
ima
g
e
p
ro
c
e
ss
in
g
,
AI,
NN
s,
M
L,
DL
tec
h
n
i
q
u
e
s
,
d
a
ta
se
c
u
rit
y
,
a
n
d
o
p
t
ica
l
c
o
m
m
u
n
ica
ti
o
n
.
H
e
is
c
u
rre
n
tl
y
a
h
e
a
d
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t
,
M
i
n
ia
Un
iv
e
rsity
,
E
g
y
p
t.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
sh
ra
f.
k
h
a
laf@m
u
.
e
d
u
.
e
g
.
Az
iza
I.
H
u
ss
e
in
re
c
e
iv
e
d
h
e
r
P
h
.
D.
d
e
g
re
e
in
e
lec
tri
c
a
l
a
n
d
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
fro
m
Ka
n
sa
s
S
tate
Un
i
v
e
rsity
,
USA
in
2
0
0
1
a
n
d
t
h
e
M
.
S
c
.
a
n
d
B.
S
c
.
d
e
g
re
e
s
fro
m
As
siu
t
Un
iv
e
rsity
,
E
g
y
p
t
i
n
1
9
8
9
a
n
d
1
9
8
3
,
re
sp
e
c
ti
v
e
ly
.
S
h
e
jo
i
n
e
d
Eff
a
t
Un
iv
e
rsit
y
i
n
S
a
u
d
i
Ara
b
i
a
in
2
0
0
4
a
n
d
e
sta
b
li
sh
e
d
t
h
e
first
e
lec
tri
c
a
l
a
n
d
c
o
m
p
u
ter en
g
i
n
e
e
rin
g
p
ro
g
ra
m
fo
r
w
o
m
e
n
i
n
th
e
c
o
u
n
tr
y
a
n
d
tau
g
h
t
re
late
d
c
o
u
rse
s.
S
h
e
wa
s
th
e
h
e
a
d
o
f
th
e
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t
a
t
Eff
a
t
Un
i
v
e
rsity
fr
o
m
2
0
0
7
-
2
0
1
0
.
S
h
e
wa
s
t
h
e
h
e
a
d
o
f
Co
m
p
u
ter
a
n
d
S
y
ste
m
s
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t,
F
a
c
u
l
ty
o
f
E
n
g
in
e
e
rin
g
,
M
i
n
ia
U
n
iv
e
rsit
y
,
Eg
y
p
t
fro
m
2
0
1
1
-
2
0
1
6
.
S
h
e
wa
s
a
p
ro
fe
ss
o
r
a
n
d
c
h
a
ir
o
f
t
h
e
E
lec
tri
c
a
l
a
n
d
Co
m
p
u
ter
E
n
g
in
e
e
ri
n
g
De
p
a
rtme
n
t
a
n
d
d
irec
to
r
o
f
t
h
e
m
a
ste
r
o
f
e
n
e
r
g
y
p
r
o
g
ra
m
a
t
Eff
a
t
U
n
iv
e
rsit
y
S
a
u
d
i
Ara
b
ia
fro
m
2
0
1
6
-
2
0
2
1
.
Cu
rre
n
tl
y
sh
e
is
a
p
ro
fe
ss
o
r
a
n
d
re
se
a
rc
h
e
r
a
t
th
e
sa
m
e
d
e
p
a
rtme
n
t.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
icro
e
lec
tro
n
ics
,
a
n
a
lo
g
/
d
ig
i
tal
VLS
I
sy
ste
m
d
e
sig
n
,
R
F
c
ircu
it
d
e
sig
n
,
h
ig
h
-
sp
e
e
d
a
n
a
lo
g
-
to
-
d
ig
it
a
l
c
o
n
v
e
rters
d
e
sig
n
,
a
n
d
wir
e
les
s
c
o
m
m
u
n
ica
ti
o
n
s
sy
ste
m
s
d
e
sig
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
z
ib
ra
h
im@
e
ffa
tu
n
iv
e
rsity
.
e
d
u
.
sa
.
G
e
r
g
e
s M
a
n
so
u
r
S
a
l
a
m
a
re
c
e
iv
e
d
a
B
.
S
c
.
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
i
n
e
e
rin
g
a
n
d
a
n
M
.
S
c
.
d
e
g
re
e
i
n
e
lec
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
s
e
n
g
in
e
e
rin
g
fro
m
E
l
-
M
i
n
ia
Un
iv
e
rsit
y
,
El
-
M
in
ia,
Eg
y
p
t,
i
n
1
9
9
9
a
n
d
2
0
0
6
re
sp
e
c
ti
v
e
ly
.
He
re
c
e
iv
e
d
a
P
h
.
D.
fro
m
t
h
e
F
a
c
u
lt
y
o
f
Tele
c
o
m
m
u
n
ica
ti
o
n
Ne
two
r
k
s,
S
witch
in
g
S
y
ste
m
s,
a
n
d
C
o
m
p
u
ter
Tec
h
n
o
l
o
g
y
(
F
TN,
S
S
,
a
n
d
CT)
S
T.
P
e
ters
b
u
rg
S
tate
Un
iv
e
r
sity
o
f
Tele
c
o
m
m
u
n
ica
ti
o
n
s
Na
.
P
ro
f.
M
A
B
o
n
c
h
-
Br
u
e
v
ich
.
M
in
istr
y
o
f
Co
m
m
u
n
ica
ti
o
n
s
a
n
d
M
a
ss
M
e
d
ia
o
f
th
e
Ru
ss
ian
F
e
d
e
ra
ti
o
n
F
e
d
e
ra
l
Co
m
m
u
n
ica
ti
o
n
s
Ag
e
n
c
y
in
2
0
1
2
.
No
w,
h
e
is
a
n
a
ss
o
c
i
a
te
p
ro
fe
ss
o
r
a
t
th
e
F
a
c
u
lt
y
o
f
En
g
i
n
e
e
rin
g
,
M
in
ia
Un
iv
e
rsit
y
,
Eg
y
p
t.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
ima
g
e
e
n
h
a
n
c
e
m
e
n
t,
ima
g
e
re
sto
ra
ti
o
n
,
i
m
a
g
e
in
terp
o
latio
n
,
su
p
e
r
-
re
so
lu
t
i
o
n
re
c
o
n
stru
c
ti
o
n
o
f
ima
g
e
s,
d
a
ta
h
i
d
in
g
,
m
u
lt
ime
d
ia
c
o
m
m
u
n
i
c
a
ti
o
n
s,
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
,
o
p
ti
c
a
l
sig
n
a
l
p
r
o
c
e
ss
in
g
,
a
n
d
d
ig
it
a
l
c
o
m
m
u
n
ica
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
e
rg
e
s.s
a
lam
a
@m
u
.
e
d
u
.
e
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.