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
6
1
9
~
6
6
2
7
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
6
6
1
9
-
6
6
2
7
6619
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Neutroso
phic
enh
a
nced
co
nv
o
lutiona
l neural ne
twor
k
for
o
ccupa
ncy
det
ec
ti
o
n:
struc
tured
m
o
del develo
pment
and
ev
a
lua
tion
Ra
nje
et
a
M
it
t
a
l
1
,
Su
re
s
h K
u
m
a
r
1
,
Urv
a
s
hi Chug
h
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
M
a
n
a
v
R
a
c
h
n
a
I
n
t
e
r
n
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
R
e
se
a
r
c
h
a
n
d
S
t
u
d
i
e
s,
F
a
r
i
d
a
b
a
d
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
a
n
d
Te
c
h
n
o
l
o
g
y
,
K
r
i
sh
n
a
I
n
st
i
t
u
t
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
G
h
a
z
i
a
b
a
d
,
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
Ap
r
3
0
,
2
0
2
4
R
ev
is
ed
J
u
l 1
9
,
2
0
2
4
Acc
ep
ted
Au
g
6
,
2
0
2
4
Th
is
st
u
d
y
i
n
tro
d
u
c
e
s
a
n
a
d
v
a
n
c
e
d
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(CNN
)
m
o
d
e
l
tail
o
re
d
f
o
r
b
u
il
d
i
n
g
o
c
c
u
p
a
n
c
y
d
e
tec
ti
o
n
t
h
a
t
a
c
c
o
m
m
o
d
a
tes
th
e
in
h
e
re
n
t
u
n
c
e
rtain
ti
e
s
a
n
d
c
o
n
tr
a
d
icto
ry
i
n
fo
rm
a
ti
o
n
o
fte
n
e
n
c
o
u
n
tere
d
i
n
se
n
so
r
d
a
ta.
By
in
te
g
ra
ti
n
g
n
e
u
tr
o
so
p
h
ic
lay
e
rs
in
t
o
th
e
CNN
a
rc
h
it
e
c
tu
re
,
we
e
n
a
b
le
t
h
e
m
o
d
e
l
t
o
e
ffe
c
ti
v
e
ly
h
a
n
d
le
in
d
e
term
in
a
c
y
,
v
a
g
u
e
n
e
ss
,
a
n
d
in
c
o
n
siste
n
c
y
p
re
se
n
t
in
re
a
l
-
wo
r
ld
se
n
s
o
r
re
a
d
i
n
g
s.
T
h
e
a
p
p
ro
a
c
h
e
m
p
lo
y
s
n
e
u
tro
s
o
p
h
ic
c
o
n
v
o
l
u
ti
o
n
a
l,
m
a
x
-
p
o
o
li
n
g
,
a
n
d
lo
g
ic
lay
e
rs,
p
r
o
v
i
d
in
g
a
c
o
m
p
re
h
e
n
siv
e
fra
m
e
wo
rk
f
o
r
fe
a
tu
re
e
x
trac
ti
o
n
a
n
d
d
e
c
isio
n
-
m
a
k
i
n
g
.
Th
ro
u
g
h
a
stru
c
t
u
re
d
m
e
th
o
d
o
l
o
g
y
e
n
c
o
m
p
a
ss
in
g
d
a
ta
p
re
p
r
o
c
e
ss
in
g
,
m
o
d
e
l
in
it
ializa
ti
o
n
,
train
i
n
g
,
e
v
a
l
u
a
ti
o
n
,
a
n
d
o
p
ti
m
iza
ti
o
n
,
we
d
e
m
o
n
stra
te
th
e
e
ffica
c
y
o
f
th
e
p
ro
p
o
se
d
m
o
d
e
l
in
a
c
c
u
ra
tely
d
e
tec
ti
n
g
o
c
c
u
p
a
n
c
y
sta
tu
s
with
in
re
sid
e
n
ti
a
l
e
n
v
iro
n
m
e
n
ts.
Th
is
e
n
h
a
n
c
e
d
CNN
m
o
d
e
l
o
ffe
rs
imp
ro
v
e
d
a
c
c
u
ra
c
y
,
ro
b
u
stn
e
ss
,
a
n
d
i
n
terp
r
e
tab
il
it
y
,
t
h
e
re
b
y
fa
c
il
it
a
ti
n
g
it
s
i
n
teg
ra
ti
o
n
in
to
sm
a
rt
b
u
il
d
i
n
g
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s
a
n
d
b
u
i
ld
i
n
g
a
u
to
m
a
ti
o
n
a
p
p
li
c
a
ti
o
n
s,
t
o
e
n
h
a
n
c
e
e
fficie
n
c
y
,
c
o
m
fo
r
t,
a
n
d
e
n
e
rg
y
sa
v
i
n
g
s.
K
ey
w
o
r
d
s
:
C
o
n
tr
ad
icto
r
y
i
n
f
o
r
m
atio
n
Ho
u
s
e
o
cc
u
p
a
n
cy
d
etec
tio
n
Neu
tr
o
s
o
p
h
ic
c
o
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
Sm
ar
t
h
o
m
e
s
y
s
t
em
Un
ce
r
tain
ty
h
an
d
lin
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
an
jeeta
Mittal
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Sch
o
o
l o
f
E
n
g
in
ee
r
in
g
a
n
d
T
ec
h
n
o
lo
g
y
,
Ma
n
av
R
ac
h
n
a
I
n
ter
n
atio
n
al
I
n
s
titu
te
o
f
R
esear
ch
an
d
Stu
d
ies
Su
r
ajk
u
n
d
R
o
ad
,
Far
id
ab
a
d
,
H
ar
y
an
a,
I
n
d
ia
E
m
ail:
r
an
jeeta
m
ittal@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
O
cc
u
p
an
cy
d
etec
tio
n
,
also
k
n
o
wn
as
o
cc
u
p
an
cy
s
en
s
in
g
o
r
o
cc
u
p
an
c
y
m
o
n
ito
r
in
g
,
is
a
f
u
n
d
am
en
tal
asp
ec
t
o
f
s
m
ar
t b
u
ild
in
g
a
u
to
m
atio
n
s
y
s
tem
s
,
en
ab
lin
g
v
ar
i
o
u
s
ap
p
licatio
n
s
s
u
ch
as in
tr
u
s
io
n
d
etec
tio
n
,
p
o
wer
an
d
d
ev
ices
m
an
ag
e
m
en
t,
w
aste
m
an
ag
em
en
t,
ef
f
ec
tiv
ely
m
an
ag
in
g
s
ec
u
r
ity
,
p
ar
k
i
n
g
s
p
ac
es,
em
er
g
en
cy
ex
its
,
an
d
p
er
s
o
n
alize
d
u
s
er
e
x
p
er
ien
ce
s
[
1
]
.
T
h
e
a
b
ilit
y
to
ac
cu
r
ately
d
etec
t
o
cc
u
p
an
cy
i
n
r
esid
en
tial
s
p
ac
es
allo
ws
f
o
r
th
e
au
to
m
atio
n
o
f
lig
h
tin
g
,
h
ea
tin
g
,
v
en
tila
tio
n
,
an
d
air
c
o
n
d
itio
n
in
g
(
HVAC)
s
y
s
tem
s
,
co
n
tr
ib
u
tin
g
to
war
d
s
en
er
g
y
s
av
in
g
s
as
well
as
im
p
r
o
v
ed
co
m
f
o
r
t
f
o
r
o
cc
u
p
a
n
ts
[
2
]
.
I
n
r
ec
en
t
y
ea
r
s
,
th
e
p
r
o
life
r
atio
n
o
f
i
n
ter
n
et
o
f
t
h
in
g
s
(
I
o
T
)
d
e
v
ices
an
d
s
en
s
o
r
s
h
as
f
ac
ilit
ated
th
e
co
lle
ctio
n
o
f
d
ata
f
r
o
m
r
esid
en
tial
en
v
ir
o
n
m
e
n
ts
,
o
f
f
er
in
g
n
ew
o
p
p
o
r
tu
n
ities
f
o
r
o
cc
u
p
an
c
y
d
etec
tio
n
.
T
h
ese
s
en
s
o
r
s
ca
n
in
clu
d
e
p
ass
iv
e
in
f
r
ar
ed
(
PIR)
m
o
tio
n
s
en
s
o
r
s
,
d
o
o
r
an
d
win
d
o
w
s
en
s
o
r
s
,
lig
h
t
s
en
s
o
r
s
,
ac
o
u
s
tic
s
en
s
o
r
s
,
an
d
ev
en
d
ev
ices
s
u
ch
as
lap
to
p
s
,
ta
b
lets
,
d
ig
ital
as
s
is
tan
t
s
,
s
m
a
r
tp
h
o
n
es,
an
d
s
m
ar
t
wea
r
ab
le
d
ev
ices
[
3
]
.
B
y
lev
er
ag
in
g
th
e
d
ata
co
llected
f
r
o
m
th
ese
s
en
s
o
r
s
,
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
ca
n
b
e
em
p
lo
y
e
d
to
in
f
er
o
cc
u
p
an
c
y
s
tatu
s
an
d
m
a
k
e
in
t
ellig
en
t d
ec
is
io
n
s
in
r
ea
l tim
e.
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
6
1
9
-
6
6
2
7
6620
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etw
o
r
k
s
(
C
NNs)
ap
p
ar
en
tly
ar
e
a
p
o
wer
f
u
l
to
o
l
in
th
e
f
ield
o
f
o
cc
u
p
an
c
y
d
etec
tio
n
,
p
a
r
ticu
lar
ly
w
h
en
d
ea
lin
g
with
s
en
s
o
r
d
ata.
C
NNs
is
a
s
p
ec
ialized
tech
n
iq
u
e
th
at
b
elo
n
g
s
to
th
e
b
r
o
ad
e
r
ca
teg
o
r
y
o
f
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
.
C
NNs
ar
e
c
u
r
ated
to
r
ec
o
g
n
ize
p
atter
n
s
i
n
s
p
atial
d
ata.
T
h
is
p
r
o
p
er
t
y
m
a
k
es
th
em
an
a
p
t
c
h
o
ice
f
o
r
a
p
p
licatio
n
s
lik
e
im
ag
e
r
ec
o
g
n
itio
n
,
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
,
an
d
tim
e
-
s
er
ies
an
aly
s
is
[
4
]
.
I
n
t
h
e
co
n
tex
t
o
f
o
cc
u
p
an
c
y
d
etec
tio
n
,
C
NNs
ca
n
an
aly
ze
s
en
s
o
r
d
ata
s
tr
ea
m
s
to
id
en
tify
p
atter
n
s
ass
o
ciate
d
with
o
cc
u
p
an
cy
a
n
d
n
o
n
-
o
cc
u
p
an
cy
s
tates.
T
h
is
p
ap
er
p
r
esen
ts
an
en
h
an
ce
d
C
NN
-
b
ased
ap
p
r
o
ac
h
f
o
r
o
cc
u
p
an
cy
d
etec
tio
n
u
s
in
g
s
en
s
o
r
d
ata.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
a
im
s
to
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
o
cc
u
p
a
n
cy
d
e
tectio
n
in
s
m
ar
t
en
v
ir
o
n
m
en
t
s
,
b
y
im
p
r
o
v
i
n
g
m
o
d
el
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
,
th
er
eb
y
en
h
a
n
cin
g
t
h
e
p
e
r
f
o
r
m
an
ce
o
f
b
u
ild
in
g
au
to
m
atio
n
s
y
s
tem
s
.
T
h
e
r
e
m
ain
d
er
o
f
th
is
in
tr
o
d
u
ctio
n
p
r
o
v
id
es
an
o
v
er
v
iew
o
f
th
e
s
ig
n
if
ican
ce
o
f
o
cc
u
p
an
c
y
d
ete
ctio
n
,
th
e
ch
allen
g
es
in
v
o
lv
e
d
,
an
d
th
e
s
tate
-
of
-
th
e
-
ar
t te
ch
n
iq
u
es in
th
e
f
ield
.
a.
Sig
n
if
ican
ce
o
f
h
o
u
s
e
o
cc
u
p
an
cy
d
etec
tio
n
:
Acc
u
r
ate
o
cc
u
p
an
cy
d
etec
tio
n
is
ess
en
tial
f
o
r
o
p
tim
izin
g
en
er
g
y
co
n
s
u
m
p
tio
n
i
n
r
esid
e
n
tial
b
u
ild
in
g
s
.
B
y
au
to
m
atic
ally
ad
ju
s
tin
g
h
ea
ti
n
g
,
c
o
o
lin
g
,
an
d
lig
h
tin
g
s
y
s
tem
s
b
ased
o
n
o
cc
u
p
an
cy
s
tatu
s
,
en
er
g
y
wastag
e
ca
n
b
e
m
in
im
ized
,
lea
d
in
g
to
r
ed
u
ce
d
u
tili
ty
b
ills
an
d
en
v
ir
o
n
m
en
tal
im
p
ac
t
[
5
]
.
A
d
d
itio
n
ally
,
o
cc
u
p
an
c
y
d
etec
t
io
n
p
lay
s
a
cr
u
cial
r
o
le
in
s
ec
u
r
ity
s
y
s
tem
s
,
allo
win
g
f
o
r
th
e
tim
ely
d
et
ec
tio
n
o
f
in
t
r
u
d
e
r
s
an
d
u
n
a
u
th
o
r
ized
ac
c
ess
[
6
]
Mo
r
e
o
v
er
,
o
cc
u
p
an
c
y
in
f
o
r
m
atio
n
ca
n
b
e
lev
e
r
ag
e
d
to
p
r
o
v
id
e
p
e
r
s
o
n
alize
d
e
x
p
er
ien
ce
s
f
o
r
o
cc
u
p
an
ts
.
Sm
ar
t
au
to
m
atio
n
s
y
s
tem
s
ca
n
ad
ap
t
th
e
b
eh
av
io
r
b
ased
o
n
th
e
p
r
esen
ce
o
r
ab
s
en
ce
o
f
o
cc
u
p
an
ts
,
o
f
f
e
r
in
g
co
n
v
en
ien
ce
an
d
co
m
f
o
r
t
tailo
r
ed
to
in
d
iv
id
u
al
p
r
ef
er
en
ce
s
[
7
]
.
Fo
r
ex
am
p
le
,
lig
h
ts
ca
n
b
e
d
im
m
ed
o
r
tu
r
n
ed
o
f
f
wh
en
a
r
o
o
m
is
u
n
o
cc
u
p
ied
,
an
d
tem
p
er
atu
r
e
s
ettin
g
s
ca
n
b
e
ad
ju
s
te
d
b
ased
o
n
o
cc
u
p
an
cy
p
atter
n
s
th
r
o
u
g
h
o
u
t
th
e
d
ay
.
b.
C
h
allen
g
es
in
o
cc
u
p
an
cy
d
etec
tio
n
:
Desp
ite
th
e
p
o
te
n
tial
b
en
ef
its
,
o
cc
u
p
an
cy
d
ete
ctio
n
in
s
m
ar
t
en
v
ir
o
n
m
en
ts
p
o
s
es
s
ev
er
al
c
h
allen
g
es.
On
e
o
f
th
e
p
r
im
ar
y
ch
allen
g
es
is
th
e
d
iv
e
r
s
ity
an
d
co
m
p
lex
ity
o
f
s
en
s
o
r
d
ata
co
llected
in
s
m
ar
t
en
v
ir
o
n
m
en
ts
.
Sen
s
o
r
d
ata
s
tr
ea
m
s
m
ay
ex
h
ib
it
v
ar
iab
ilit
y
d
u
e
to
f
ac
to
r
s
s
u
ch
as
s
en
s
o
r
p
lace
m
e
n
t,
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
,
an
d
o
cc
u
p
an
t
b
eh
av
io
r
[
8
]
.
As
a
r
e
s
u
lt,
d
ev
elo
p
in
g
r
o
b
u
s
t
an
d
ac
cu
r
ate
o
cc
u
p
an
c
y
d
etec
tio
n
m
o
d
els
r
eq
u
ir
es
h
an
d
lin
g
n
o
is
y
an
d
h
ete
r
o
g
e
n
e
o
u
s
d
ata
s
o
u
r
ce
s
ef
f
ec
tiv
ely
.
An
o
th
e
r
ch
allen
g
e
is
th
e
n
ee
d
to
b
alan
ce
ac
cu
r
ac
y
with
p
r
iv
ac
y
co
n
c
er
n
s
.
Occ
u
p
an
cy
d
etec
tio
n
s
y
s
tem
s
m
u
s
t
r
esp
e
ct
th
e
p
r
i
v
ac
y
a
n
d
s
ec
u
r
ity
o
f
o
cc
u
p
a
n
ts
,
p
ar
ticu
la
r
ly
in
r
es
id
en
tial
s
ettin
g
s
.
T
h
er
ef
o
r
e,
it
is
ess
en
tial
to
d
esig
n
alg
o
r
ith
m
s
th
at
ca
n
i
n
f
er
o
cc
u
p
a
n
cy
s
tatu
s
with
o
u
t
co
m
p
r
o
m
is
in
g
in
d
iv
id
u
al
p
r
i
v
ac
y
o
r
co
llecti
n
g
s
en
s
itiv
e
in
f
o
r
m
atio
n
[
9
]
.
Fu
r
th
er
m
o
r
e
,
d
ep
lo
y
in
g
o
cc
u
p
an
cy
d
etec
tio
n
s
y
s
tem
s
in
r
ea
l
-
wo
r
ld
en
v
ir
o
n
m
en
ts
in
tr
o
d
u
c
es
ch
allen
g
es
r
elate
d
to
s
y
s
tem
in
teg
r
atio
n
,
s
ca
lab
ilit
y
,
an
d
r
eliab
ilit
y
.
Sm
ar
t
b
u
ild
in
g
au
to
m
atio
n
s
y
s
tem
s
o
f
ten
co
n
s
is
t
o
f
h
eter
o
g
en
e
o
u
s
d
ev
ices
an
d
p
latf
o
r
m
s
,
r
eq
u
ir
in
g
s
ea
m
less
in
teg
r
atio
n
o
f
o
cc
u
p
an
c
y
d
etec
tio
n
alg
o
r
ith
m
s
with
in
th
e
ex
is
tin
g
in
f
r
astru
ctu
r
e
[
1
0
]
.
Mo
r
eo
v
er
,
o
cc
u
p
an
c
y
d
etec
ti
o
n
s
y
s
tem
s
m
u
s
t
b
e
s
ca
lab
le
to
ac
co
m
m
o
d
ate
lar
g
e
-
s
ca
le
d
ep
lo
y
m
en
ts
in
d
iv
er
s
e
o
cc
u
p
an
cy
s
ettin
g
s
wh
ile
en
s
u
r
in
g
r
o
b
u
s
t p
er
f
o
r
m
a
n
ce
u
n
d
er
v
ar
y
in
g
c
o
n
d
itio
n
s
.
c.
State
-
of
-
th
e
-
ar
t
tech
n
iq
u
es
:
Var
io
u
s
tech
n
iq
u
es
h
av
e
b
ee
n
p
r
o
p
o
s
ed
f
o
r
o
cc
u
p
an
cy
d
ete
ctio
n
in
s
m
ar
t
b
u
ild
in
g
s
.
T
h
ese
tech
n
iq
u
es
r
an
g
e
f
r
o
m
tr
ad
itio
n
al,
s
im
p
le
r
u
le
-
b
ased
ap
p
r
o
ac
h
es
to
s
o
p
h
is
ticated
,
in
tr
icate
,
an
d
ad
v
a
n
ce
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
.
R
u
le
-
b
ased
m
eth
o
d
s
r
ely
o
n
p
r
ed
e
f
in
ed
h
eu
r
is
tics
an
d
th
r
esh
o
ld
s
to
i
n
f
er
o
cc
u
p
an
cy
s
tatu
s
f
r
o
m
s
en
s
o
r
d
ata.
W
h
ile
th
e
tech
n
iq
u
e
is
s
im
p
le
an
d
in
ter
p
r
etab
le,
r
u
le
-
b
ased
ap
p
r
o
ac
h
es
m
ay
s
tr
u
g
g
le
to
ca
p
tu
r
e
co
m
p
lex
p
atter
n
s
an
d
ad
ap
t
to
ch
an
g
in
g
en
v
ir
o
n
m
en
ts
[
1
1
]
.
Ma
ch
in
e
l
ea
r
n
in
g
tech
n
iq
u
es,
p
ar
ticu
lar
l
y
s
u
p
er
v
is
ed
lear
n
in
g
al
g
o
r
ith
m
s
,
h
av
e
g
ain
ed
p
o
p
u
lar
ity
f
o
r
o
cc
u
p
an
cy
d
ete
ctio
n
task
s
.
T
h
ese
alg
o
r
ith
m
s
lear
n
p
atter
n
s
f
r
o
m
la
b
eled
tr
ain
in
g
d
ata
a
n
d
ca
n
g
en
e
r
alize
to
u
n
s
ee
n
in
s
tan
ce
s
th
u
s
f
ac
ilit
atin
g
th
eir
ap
p
licatio
n
to
r
ea
l
-
wo
r
ld
a
p
p
licatio
n
s
[
1
2
]
.
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SV
Ms)
,
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANNs)
,
an
d
r
a
n
d
o
m
f
o
r
ests
(
R
Fs
)
ar
e
a
f
ew
o
f
th
e
co
m
m
o
n
l
y
u
s
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
f
o
r
o
cc
u
p
an
cy
d
etec
tio
n
.
R
ec
en
t
ad
v
an
ce
m
en
ts
in
d
e
ep
lear
n
in
g
,
s
p
ec
if
ically
C
NNs,
h
av
e
s
h
o
wn
p
r
o
m
is
in
g
r
esu
lts
in
o
cc
u
p
an
c
y
d
etec
tio
n
task
s
.
C
NNs
ca
n
au
to
m
atica
lly
lea
r
n
h
ier
ar
c
h
ical
r
ep
r
esen
tatio
n
s
o
f
s
en
s
o
r
d
ata,
ca
p
tu
r
in
g
in
tr
icate
p
atter
n
s
a
n
d
co
r
r
elatio
n
s
[
1
3
]
.
B
y
lev
e
r
ag
in
g
th
e
s
p
atial
an
d
tem
p
o
r
al
ch
ar
ac
ter
is
tics
o
f
s
en
s
o
r
d
ata,
C
NN
-
b
ased
m
o
d
e
ls
ca
n
ac
h
iev
e
h
ig
h
er
a
cc
u
r
ac
y
an
d
r
o
b
u
s
tn
ess
co
m
p
ar
ed
t
o
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
e
liter
atu
r
e
o
n
s
m
ar
t
b
u
ild
i
n
g
o
cc
u
p
a
n
cy
d
etec
tio
n
e
n
co
m
p
ass
es
a
wid
e
r
an
g
e
o
f
r
esear
ch
ef
f
o
r
ts
aim
ed
at
d
ev
elo
p
in
g
e
f
f
icien
t
an
d
ac
cu
r
ate
m
eth
o
d
s
f
o
r
id
e
n
tify
in
g
o
cc
u
p
a
n
cy
s
tatu
s
in
s
m
ar
t
en
v
ir
o
n
m
en
ts
.
s
m
ar
t
en
v
ir
o
n
m
e
n
ts
ar
e
d
esig
n
ed
to
k
ee
p
s
u
s
tain
ab
ilit
y
as
th
e
f
o
ca
l
p
o
i
n
t
o
f
in
ter
est,
al
o
n
g
s
id
e
f
ac
ilit
atin
g
h
u
m
an
co
m
f
o
r
t
b
y
m
an
ag
i
n
g
s
er
v
ices,
s
ec
u
r
ity
,
an
d
r
eso
u
r
c
es.
T
h
is
liter
atu
r
e
r
ev
iew
is
a
r
ec
ap
itu
latio
n
o
f
th
e
s
ig
n
if
ican
t
r
esear
ch
,
r
ef
in
em
en
ts
,
an
d
b
r
ea
k
th
r
o
u
g
h
s
in
th
e
f
ield
,
em
p
h
asizin
g
d
if
f
er
en
t
ap
p
r
o
ac
h
es,
ch
allen
g
es,
an
d
e
m
er
g
in
g
tr
en
d
s
.
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
N
eu
tr
o
s
o
p
h
ic
en
h
a
n
ce
d
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
fo
r
o
cc
u
p
a
n
cy
…
(
R
a
n
jeeta
Mit
ta
l
)
6621
2
.
1
.
Rule
-
ba
s
ed
a
pp
ro
a
ches
E
ar
ly
s
tu
d
ies
o
n
o
cc
u
p
an
cy
d
etec
tio
n
o
f
te
n
em
p
l
o
y
ed
r
u
l
e
-
b
ased
ap
p
r
o
ac
h
es,
w
h
er
e
o
cc
u
p
an
cy
s
tatu
s
wa
s
in
f
er
r
ed
u
s
in
g
p
r
e
d
ef
in
ed
h
e
u
r
is
tics
an
d
th
r
esh
o
ld
s
.
Petr
o
s
an
u
et
a
l.
[
1
4
]
h
av
e
co
m
p
ar
e
d
an
d
h
ig
h
lig
h
ted
th
e
wo
r
k
o
f
n
u
m
er
o
u
s
s
cien
tis
ts
to
p
r
o
p
o
s
e
a
r
u
le
-
b
ased
m
et
h
o
d
th
at
c
o
m
b
in
ed
i
n
p
u
ts
f
r
o
m
m
o
tio
n
s
en
s
o
r
s
,
d
o
o
r
co
n
tacts,
an
d
lig
h
t
s
en
s
o
r
s
to
d
eter
m
i
n
e
o
cc
u
p
a
n
cy
.
W
h
ile
r
u
le
-
b
as
ed
ap
p
r
o
ac
h
es
ar
e
in
tu
itiv
e,
s
im
p
le
to
u
n
d
er
s
tan
d
,
an
d
s
tr
aig
h
tf
o
r
war
d
to
im
p
lem
en
t,
th
ey
m
ay
lack
f
lex
ib
i
lity
,
an
d
s
tr
u
g
g
le
to
ad
ap
t
to
d
iv
er
s
e
e
n
v
ir
o
n
m
en
ta
l
co
n
d
itio
n
s
.
Ad
ap
tab
ilit
y
i
n
r
u
le
-
b
ased
s
y
s
tem
s
in
v
o
l
v
es
m
an
u
al
ad
ju
s
tm
en
t
o
f
th
e
p
r
e
-
d
ef
in
ed
r
u
les,
i
n
r
esp
o
n
s
e
to
ch
a
n
g
es
in
t
h
e
s
itu
atio
n
s
;
th
u
s
,
m
ak
in
g
th
e
s
y
s
tem
s
ta
tic,
in
f
lex
ib
le,
a
n
d
non
-
s
ca
lab
le.
2
.
2
.
M
a
chine
lea
rning
t
ec
hn
iqu
es
W
ith
th
e
ad
v
en
t o
f
m
ac
h
in
e
le
ar
n
in
g
,
r
esear
c
h
er
s
b
eg
an
ex
p
l
o
r
in
g
s
u
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
s
f
o
r
o
cc
u
p
an
c
y
d
etec
tio
n
task
s
.
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVMs),
d
ec
is
io
n
t
r
ee
s
(
DT
)
,
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
n
aïv
e
B
ay
es
(
NB
)
,
an
d
r
an
d
o
m
f
o
r
ests
(
R
Fs
)
ar
e
am
o
n
g
th
e
c
o
m
m
o
n
ly
u
s
e
d
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
es
in
th
is
c
o
n
tex
t.
Fo
r
in
s
tan
ce
,
Djen
o
u
r
i
et
a
l
.
[
1
5
]
an
d
Dai
et
a
l.
[
1
6
]
ap
p
lied
SV
Ms
to
s
en
s
o
r
d
ata
co
llected
f
r
o
m
s
m
ar
t
h
o
m
es
an
d
ac
h
iev
e
d
p
r
o
m
is
in
g
r
esu
lts
in
o
cc
u
p
a
n
cy
class
if
icatio
n
.
Si
m
ilar
ly
,
Ko
k
lu
an
d
T
u
tu
n
cu
[
1
7
]
u
tili
ze
d
DT
wh
er
ea
s
Sar
k
er
et
a
l.
[
1
8
]
d
e
p
lo
y
ed
d
ee
p
n
e
u
r
al
n
etwo
r
k
s
(
DNN)
to
in
f
er
o
cc
u
p
an
c
y
s
tatu
s
b
ased
o
n
f
ea
tu
r
es e
x
tr
ac
ted
f
r
o
m
s
en
s
o
r
d
a
ta
s
tr
ea
m
s
.
2
.
3
.
Dee
p
lea
rning
a
pp
ro
a
ch
es
I
n
r
ec
en
t
y
ea
r
s
,
d
ee
p
lear
n
in
g
tech
n
iq
u
es,
p
ar
ticu
lar
l
y
C
NNs,
h
av
e
g
ain
ed
attr
ac
tio
n
in
o
cc
u
p
an
c
y
d
etec
tio
n
r
esear
ch
.
C
NNs
h
av
e
s
h
o
wn
r
em
ar
k
a
b
le
ca
p
a
b
ilit
ies
in
ca
p
tu
r
in
g
c
o
m
p
lex
p
atter
n
s
an
d
s
p
atial
d
ep
en
d
e
n
cies
in
s
en
s
o
r
d
ata.
Fo
r
ex
am
p
le,
Yu
et
a
l.
[
1
9
]
p
r
o
p
o
s
ed
a
C
NN
-
b
ased
ap
p
r
o
ac
h
f
o
r
o
cc
u
p
an
cy
d
etec
tio
n
u
s
in
g
d
ata
f
r
o
m
m
o
tio
n
s
en
s
o
r
s
a
n
d
ac
h
iev
e
d
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
c
o
m
p
ar
ed
t
o
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
.
H
u
n
g
an
d
C
h
ak
r
a
b
ar
ti
[
2
0
]
an
d
Mtib
aa
et
a
l.
[
2
1
]
h
a
v
e
d
ev
elo
p
ed
a
d
ee
p
lear
n
in
g
m
o
d
el
b
ased
o
n
l
o
n
g
s
h
o
r
t
-
te
r
m
m
em
o
r
y
(
L
STM
)
n
etwo
r
k
s
f
o
r
r
ea
l
-
tim
e
o
cc
u
p
a
n
cy
p
r
e
d
ictio
n
in
p
ar
k
in
g
s
p
ac
es a
n
d
s
m
ar
t b
u
ild
in
g
s
.
2
.
4
.
Sens
o
r
f
us
io
n t
ec
hn
iqu
e
s
An
o
th
er
a
r
ea
o
f
i
n
ter
est
in
o
c
cu
p
an
cy
d
etec
tio
n
r
esear
ch
is
s
en
s
o
r
f
u
s
io
n
,
wh
er
e
d
ata
f
r
o
m
m
u
ltip
le
s
en
s
o
r
m
o
d
alities
ar
e
in
teg
r
at
ed
to
im
p
r
o
v
e
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
.
R
o
s
ely
n
et
a
l.
[
2
2
]
an
d
T
an
et
a
l.
[
2
3
]
in
v
esti
g
ated
th
e
f
u
s
io
n
o
f
d
at
a
f
r
o
m
m
o
tio
n
s
en
s
o
r
s
,
lig
h
t
s
en
s
o
r
s
,
an
d
d
o
o
r
c
o
n
tacts
u
s
in
g
a
p
r
o
b
ab
ilis
tic
f
r
am
ewo
r
k
an
d
d
em
o
n
s
tr
ated
en
h
an
ce
d
p
er
f
o
r
m
an
ce
in
o
cc
u
p
an
cy
d
etec
tio
n
.
C
h
an
et
a
l.
[
2
4
]
a
n
d
Nes
a
an
d
B
an
er
jee
[
2
5
]
h
av
e
p
r
o
p
o
s
ed
a
s
en
s
o
r
f
u
s
io
n
ap
p
r
o
ac
h
b
ased
o
n
B
ay
esian
in
f
er
en
ce
f
o
r
o
cc
u
p
an
cy
esti
m
atio
n
in
s
m
ar
t o
f
f
ices.
3.
DATAS
E
T
T
h
e
UC
I
Occ
u
p
an
cy
Data
s
et
p
r
o
v
id
es
a
r
ich
c
o
llectio
n
o
f
s
en
s
o
r
d
ata,
in
clu
d
i
n
g
f
ea
tu
r
e
s
s
u
ch
as
d
ate,
tem
p
er
atu
r
e
,
h
u
m
i
d
ity
,
lig
h
t,
C
O
2
lev
els,
h
u
m
id
ity
r
atio
,
an
d
o
cc
u
p
an
c
y
s
tatu
s
.
T
h
is
d
ataset
o
f
f
er
s
v
alu
ab
le
in
s
ig
h
ts
in
to
o
cc
u
p
an
cy
p
atter
n
s
with
in
s
m
ar
t
en
v
ir
o
n
m
en
ts
,
f
ac
ilit
atin
g
th
e
d
ev
elo
p
m
en
t
o
f
o
cc
u
p
an
c
y
d
etec
tio
n
m
o
d
els a
n
d
s
m
ar
t b
u
il
d
in
g
a
u
to
m
atio
n
s
y
s
tem
s
.
a.
Date
:
T
h
e
tim
estam
p
i
n
d
icate
s
wh
en
s
en
s
o
r
r
ea
d
i
n
g
s
wer
e
r
ec
o
r
d
e
d
,
p
r
o
v
i
d
in
g
tem
p
o
r
al
in
f
o
r
m
atio
n
f
o
r
an
aly
zin
g
o
cc
u
p
a
n
cy
p
atter
n
s
o
v
er
tim
e.
b.
T
em
p
er
atu
r
e:
C
o
n
tin
u
o
u
s
m
ea
s
u
r
em
en
ts
o
f
tem
p
e
r
atu
r
e
ca
p
tu
r
ed
b
y
s
en
s
o
r
s
d
ep
l
o
y
ed
with
in
th
e
h
o
u
s
e.
c.
T
em
p
er
atu
r
e
f
lu
ctu
atio
n
s
m
a
y
in
d
icate
ch
an
g
es in
o
cc
u
p
an
c
y
o
r
e
n
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
d.
Hu
m
id
ity
:
T
h
e
le
v
el
o
f
h
u
m
i
d
ity
in
th
e
air
,
m
ea
s
u
r
e
d
b
y
h
u
m
id
ity
s
en
s
o
r
s
.
Hu
m
id
ity
v
ar
i
atio
n
s
ca
n
af
f
ec
t
o
cc
u
p
an
t c
o
m
f
o
r
t a
n
d
in
d
o
o
r
a
ir
q
u
ality
.
e.
L
ig
h
t:
B
in
ar
y
v
alu
es
r
ep
r
esen
tin
g
th
e
p
r
esen
ce
o
r
a
b
s
en
ce
o
f
lig
h
t
in
d
if
f
e
r
en
t
ar
ea
s
o
f
t
h
e
h
o
u
s
e.
L
ig
h
t
s
en
s
o
r
r
ea
d
in
g
s
ca
n
h
elp
in
f
er
o
cc
u
p
an
c
y
s
tatu
s
an
d
ac
tiv
ity
p
atter
n
s
.
f.
CO
2
l
ev
el
s
:
Me
asu
r
em
en
ts
o
f
ca
r
b
o
n
d
i
o
x
id
e
(
C
O
2
)
co
n
ce
n
t
r
atio
n
in
th
e
air
,
in
d
icatin
g
in
d
o
o
r
air
q
u
ality
an
d
o
cc
u
p
an
c
y
-
r
elate
d
C
O
2
e
m
is
s
io
n
s
.
g.
Hu
m
id
ity
r
atio
:
A
ca
lcu
lated
p
ar
am
eter
d
er
i
v
ed
f
r
o
m
tem
p
e
r
atu
r
e
an
d
h
u
m
id
ity
m
ea
s
u
r
e
m
en
ts
,
p
r
o
v
id
i
n
g
ad
d
itio
n
al
in
s
ig
h
ts
in
to
in
d
o
o
r
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
h.
Occ
u
p
an
cy
:
B
in
ar
y
lab
els
in
d
icatin
g
wh
eth
er
a
p
a
r
ticu
lar
ar
ea
o
r
r
o
o
m
in
th
e
h
o
u
s
e
is
o
cc
u
p
ied
o
r
u
n
o
cc
u
p
ied
.
T
h
is
tar
g
et
v
ar
iab
le
is
cr
u
cial
f
o
r
tr
ain
i
n
g
o
cc
u
p
an
cy
d
etec
tio
n
m
o
d
els.
An
aly
zin
g
all
th
ese
f
ea
tu
r
es
co
llectiv
ely
h
as
led
to
th
e
d
ev
elo
p
m
en
t
o
f
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els
to
p
r
ed
ict
o
cc
u
p
an
cy
s
tatu
s
b
ased
o
n
s
en
s
o
r
d
ata.
Ad
d
itio
n
ally
,
th
e
d
ataset
en
ab
les
ex
p
lo
r
a
to
r
y
d
ata
a
n
aly
s
is
,
f
ea
tu
r
e
en
g
in
ee
r
in
g
,
m
o
d
el
tr
ain
in
g
,
an
d
ev
alu
atio
n
to
u
n
c
o
v
er
o
cc
u
p
an
c
y
p
atter
n
s
,
o
p
ti
m
ize
en
er
g
y
u
s
ag
e,
an
d
en
h
an
ce
h
o
m
e
au
t
o
m
atio
n
s
y
s
tem
s
'
ef
f
icien
cy
.
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
6
1
9
-
6
6
2
7
6622
4.
P
RO
P
O
SE
D
M
O
D
E
L
I
n
th
e
co
n
te
x
t
o
f
th
e
UC
I
Ho
u
s
e
Occ
u
p
an
cy
Data
s
et,
we
p
r
o
p
o
s
e
a
m
ac
h
in
e
-
lear
n
in
g
m
o
d
el
f
o
r
o
cc
u
p
an
c
y
d
etec
tio
n
b
ased
o
n
th
e
p
r
o
v
id
ed
s
en
s
o
r
d
ata.
T
h
e
m
o
d
el
aim
s
to
ac
cu
r
ately
p
r
e
d
ict
wh
eth
e
r
a
p
ar
ticu
lar
ar
ea
with
in
a
h
o
u
s
e
is
o
cc
u
p
ied
o
r
u
n
o
cc
u
p
ied
at
an
y
g
iv
en
tim
e
.
I
t
lev
er
ag
i
n
g
f
ea
tu
r
es
s
u
ch
as
tem
p
er
atu
r
e,
h
u
m
id
ity
,
lig
h
t,
C
O
2
lev
els,
h
u
m
id
ity
r
atio
,
an
d
tim
estam
p
s
.
4
.
1
.
M
o
del
a
rc
hite
ct
ure
a
nd
princip
le
s
o
f
Neut
ro
s
o
ph
y
T
h
is
m
o
d
el
p
r
o
p
o
s
es
a
f
r
am
ewo
r
k
th
at
in
teg
r
ates
n
eu
tr
o
s
o
p
h
ic
co
n
v
o
lu
tio
n
,
n
eu
tr
o
s
o
p
h
ic
m
ax
-
p
o
o
lin
g
,
an
d
n
eu
tr
o
s
o
p
h
ic
lo
g
ic
lay
er
s
i
n
to
a
C
NN
ar
ch
it
ec
tu
r
e.
T
h
e
n
eu
tr
o
s
o
p
h
ic
c
o
n
v
o
lu
tio
n
al
lay
er
is
d
esig
n
ed
to
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
in
p
u
t
d
ata
wh
ile
co
n
s
id
er
i
n
g
in
d
eter
m
in
ac
y
,
u
n
ce
r
tain
ty
,
an
d
co
n
t
r
ad
icto
r
y
in
f
o
r
m
atio
n
.
T
h
e
n
eu
tr
o
s
o
p
h
i
c
m
ax
-
p
o
o
lin
g
lay
e
r
ag
g
r
eg
at
es
th
e
ex
tr
ac
ted
f
ea
tu
r
es
to
r
e
d
u
ce
d
im
en
s
io
n
ality
an
d
e
n
h
an
ce
co
m
p
u
tatio
n
al
ef
f
icien
cy
.
T
h
e
n
eu
tr
o
s
o
p
h
ic
lo
g
ic
lay
er
h
a
n
d
les
r
ea
s
o
n
i
n
g
a
n
d
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es b
y
in
co
r
p
o
r
atin
g
n
e
u
tr
o
s
o
p
h
ic
l
o
g
ic
p
r
i
n
cip
les.
T
h
e
C
NN
m
o
d
el
ar
ch
itectu
r
e
co
n
s
is
ts
o
f
:
i)
A
co
n
v
o
lu
tio
n
a
l
lay
er
with
1
6
k
er
n
els
an
d
a
k
er
n
el
s
ize
o
f
3
×
3
,
f
o
llo
wed
b
y
a
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U)
ac
tiv
atio
n
f
u
n
ctio
n
;
ii)
A
m
ax
-
p
o
o
lin
g
lay
er
with
a
p
o
o
lin
g
s
ize
o
f
2
×
2
to
d
o
wn
s
am
p
le
t
h
e
f
ea
tu
r
e
m
a
p
s
;
iii)
A
f
latten
in
g
lay
er
to
c
o
n
v
e
r
t
th
e
2
D
f
ea
tu
r
e
m
ap
s
in
to
a
1
D
v
ec
to
r
;
an
d
iv
)
T
wo
f
u
lly
c
o
n
n
ec
ted
d
en
s
e
lay
e
r
s
with
6
4
a
n
d
1
n
eu
r
o
n
s
,
r
esp
ec
tiv
ely
,
ac
tiv
ated
b
y
R
eL
U
an
d
s
ig
m
o
id
f
u
n
ctio
n
s
.
Af
ter
co
m
p
ilin
g
th
e
m
o
d
el
u
s
in
g
th
e
Ad
am
o
p
tim
izer
an
d
b
in
a
r
y
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
,
it
is
tr
ain
ed
u
s
in
g
e
x
am
p
le
in
p
u
t
d
ata
r
ep
r
esen
ted
as
n
eu
tr
o
s
o
p
h
ic
s
ets.
T
h
e
in
p
u
t
d
ata
in
c
lu
d
es
tem
p
er
atu
r
e,
h
u
m
id
ity
,
lig
h
t,
C
O
2
,
an
d
h
u
m
id
ity
r
atio
.
Su
b
s
eq
u
en
tly
,
th
e
m
o
d
el
p
r
e
d
icts
lab
els
b
ased
o
n
th
e
in
p
u
t
d
ata.
Gr
o
u
n
d
tr
u
th
la
b
els
(
1
d
esig
n
atin
g
o
cc
u
p
ied
s
tate
an
d
0
d
e
s
ig
n
atin
g
u
n
o
cc
u
p
ie
d
s
tate)
ar
e
u
s
ed
to
c
o
m
p
u
te
th
e
ev
alu
atio
n
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
Fin
ally
,
th
e
p
r
ed
icted
lab
els
an
d
ev
alu
atio
n
m
etr
ics ar
e
p
r
in
ted
f
o
r
an
al
y
s
is
.
4
.
2
.
M
o
del
t
ra
ini
ng
T
h
e
s
tep
-
by
-
s
tep
alg
o
r
ith
m
f
o
r
tr
ain
in
g
a
n
eu
r
al
n
etwo
r
k
m
o
d
el
u
s
in
g
n
e
u
tr
o
s
o
p
h
ic
lay
er
s
i
s
s
h
o
wn
:
a.
Data
p
r
ep
ar
atio
n
−
Or
g
an
ize
th
e
d
ataset
co
n
tain
in
g
in
p
u
t
f
ea
tu
r
es a
n
d
tar
g
et
lab
els.
−
E
n
s
u
r
e
th
e
d
ataset
is
p
r
o
p
er
ly
f
o
r
m
atted
a
n
d
clea
n
e
d
.
−
Sp
lit th
e
d
ataset
in
to
tr
ain
in
g
a
n
d
test
in
g
s
ets.
b.
Mo
d
el
i
n
itializatio
n
−
I
m
p
o
r
t t
h
e
n
ec
ess
ar
y
lib
r
ar
ies,
in
clu
d
in
g
n
eu
tr
o
s
o
p
h
ic
lay
e
r
s
,
T
en
s
o
r
Flo
w,
an
d
Nu
m
Py
.
−
I
n
itialize
n
eu
tr
o
s
o
p
h
ic
co
n
v
o
l
u
tio
n
al,
m
ax
-
p
o
o
lin
g
,
a
n
d
lo
g
ic
lay
er
s
.
−
Def
in
e
th
e
ar
ch
itectu
r
e
o
f
t
h
e
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
m
o
d
el
u
s
in
g
T
en
s
o
r
Flo
w'
s
Ke
r
as API
.
−
Sp
ec
if
y
th
e
n
u
m
b
er
o
f
k
er
n
els
,
k
er
n
el
s
ize,
p
o
o
lin
g
s
ize,
ac
tiv
atio
n
f
u
n
ctio
n
s
,
an
d
in
p
u
t sh
ap
e.
c.
Mo
d
el
c
o
m
p
ilatio
n
−
C
o
m
p
ile
th
e
C
NN
m
o
d
el
b
y
s
p
ec
if
y
in
g
:
i)
T
h
e
o
p
tim
izer
(
e.
g
.
,
Ad
am
,
SGD)
to
m
in
im
ize
th
e
l
o
s
s
f
u
n
ctio
n
;
ii)
T
h
e
lo
s
s
f
u
n
ctio
n
(
e.
g
.
,
b
in
ar
y
cr
o
s
s
-
en
tr
o
p
y
,
m
ea
n
s
q
u
ar
e
d
e
r
r
o
r
)
to
m
ea
s
u
r
e
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
;
a
n
d
iii)
E
v
alu
ati
o
n
m
etr
ics (
e.
g
.
,
ac
cu
r
ac
y
,
p
r
e
cisi
o
n
,
r
ec
all)
to
m
o
n
ito
r
d
u
r
in
g
tr
ain
in
g
.
d.
Mo
d
el
t
r
ain
in
g
−
Use th
e
tr
ain
in
g
d
ataset
to
tr
ai
n
th
e
m
o
d
el.
−
I
ter
ate
o
v
er
m
u
ltip
le
e
p
o
ch
s
(
co
m
p
lete
p
ass
es
th
r
o
u
g
h
th
e
en
tire
d
ataset)
to
o
p
tim
ize
t
h
e
m
o
d
el's
p
ar
am
eter
s
.
−
Sp
ec
if
y
th
e
b
atch
s
ize
a
n
d
t
h
e
n
u
m
b
er
o
f
e
p
o
ch
s
.
B
atch
r
ef
er
s
to
th
e
n
u
m
b
er
o
f
s
am
p
l
es
p
r
o
ce
s
s
ed
b
ef
o
r
e
u
p
d
atin
g
th
e
m
o
d
el
an
d
ep
o
ch
s
r
ef
e
r
s
to
th
e
iter
atio
n
s
o
v
er
th
e
e
n
tire
d
ataset
d
u
r
in
g
t
r
ain
in
g
.
−
Du
r
in
g
ea
c
h
ep
o
ch
,
f
ee
d
b
atch
es
o
f
in
p
u
t
d
ata
in
to
t
h
e
m
o
d
el
an
d
ad
j
u
s
t
th
e
w
eig
h
ts
u
s
in
g
b
ac
k
p
r
o
p
ag
atio
n
.
e.
Mo
d
el
e
v
alu
atio
n
−
E
v
alu
ate
th
e
tr
ain
e
d
m
o
d
el'
s
p
er
f
o
r
m
a
n
ce
u
s
in
g
t
h
e
test
in
g
d
ataset.
−
Ass
es
s
th
e
m
o
d
el
'
s
ef
f
ec
tiv
en
ess
b
y
co
m
p
u
tin
g
ev
alu
atio
n
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
−
C
o
m
p
ar
e
th
e
p
r
e
d
icted
lab
el
s
with
th
e
g
r
o
u
n
d
tr
u
th
lab
e
ls
to
m
ea
s
u
r
e
th
e
m
o
d
el'
s
ac
cu
r
ac
y
an
d
g
en
er
aliza
tio
n
a
b
ilit
y
.
f.
Mo
d
el
o
p
tim
izatio
n
−
Mo
d
el
m
a
y
b
e
f
in
e
-
tu
n
e
d
b
y
ad
ju
s
tin
g
d
if
f
er
en
t
h
y
p
er
p
a
r
a
m
eter
s
(
e.
g
.
,
lear
n
in
g
r
ate,
d
r
o
p
o
u
t
r
ate)
o
r
ex
p
lo
r
in
g
d
if
f
e
r
en
t a
r
c
h
itectu
r
es (
e.
g
.
,
ad
d
in
g
m
o
r
e
lay
e
r
s
,
c
h
an
g
in
g
ac
tiv
atio
n
f
u
n
ctio
n
s
)
.
−
Utilize
tech
n
iq
u
es
s
u
ch
as
r
e
g
u
lar
izatio
n
,
d
r
o
p
o
u
t,
o
r
b
atc
h
n
o
r
m
aliza
tio
n
to
p
r
ev
e
n
t
o
v
er
f
itti
n
g
an
d
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
.
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
N
eu
tr
o
s
o
p
h
ic
en
h
a
n
ce
d
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
fo
r
o
cc
u
p
a
n
cy
…
(
R
a
n
jeeta
Mit
ta
l
)
6623
g.
Mo
d
el
d
ep
lo
y
m
en
t
−
Dep
lo
y
th
e
m
o
d
el
f
o
r
r
ea
l
-
wo
r
ld
o
cc
u
p
an
c
y
d
etec
tio
n
ap
p
licatio
n
s
,
o
n
ce
it
d
eliv
er
s
s
atis
f
ac
to
r
y
p
er
f
o
r
m
an
ce
.
−
Use th
e
tr
ain
ed
m
o
d
el
to
m
ak
e
p
r
ed
ictio
n
s
o
n
n
ew,
u
n
s
ee
n
d
ata.
−
C
o
n
tin
u
o
u
s
ly
m
o
n
ito
r
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
a
n
d
p
er
io
d
i
ca
lly
r
etr
ain
to
ac
co
m
m
o
d
ate
ch
an
g
es
in
th
e
d
ata
d
is
tr
ib
u
tio
n
.
T
h
is
alg
o
r
ith
m
o
u
tlin
es
th
e
k
ey
s
tep
s
in
v
o
lv
ed
in
tr
ain
in
g
a
n
eu
r
al
n
etwo
r
k
m
o
d
el
with
n
eu
tr
o
s
o
p
h
ic
lay
er
s
an
d
p
r
o
v
id
es a
s
tr
u
ctu
r
ed
ap
p
r
o
ac
h
to
d
ev
elo
p
i
n
g
an
d
ev
alu
a
tin
g
th
e
m
o
d
el.
4
.
3
.
M
o
del
w
o
rk
ing
On
ce
tr
ain
ed
an
d
v
alid
ated
,
t
h
e
o
cc
u
p
an
c
y
d
etec
tio
n
m
o
d
el
ca
n
b
e
d
ep
l
o
y
ed
i
n
r
ea
l
-
wo
r
l
d
s
ce
n
ar
io
s
.
Giv
en
n
ew
s
en
s
o
r
d
ata
as
in
p
u
t,
th
e
m
o
d
el
co
m
p
u
tes
th
e
p
r
o
b
ab
ilit
y
o
f
o
cc
u
p
a
n
cy
f
o
r
th
e
tar
g
et
ar
ea
.
I
f
th
e
p
r
ed
icted
p
r
o
b
a
b
ilit
y
ex
ce
ed
s
a
p
r
ed
ef
in
e
d
th
r
esh
o
l
d
(
e.
g
.
,
0
.
5
)
,
th
e
m
o
d
el
class
if
ies
th
e
ar
ea
as
o
cc
u
p
ied
;
o
th
er
wis
e,
it c
lass
if
ies it a
s
u
n
o
cc
u
p
ied
.
B
y
co
n
tin
u
o
u
s
ly
m
o
n
ito
r
in
g
s
en
s
o
r
d
ata
a
n
d
m
a
k
in
g
r
ea
l
-
ti
m
e
o
cc
u
p
an
cy
p
r
ed
ictio
n
s
,
th
e
m
o
d
el
ca
n
s
u
p
p
o
r
t
v
a
r
io
u
s
ap
p
licatio
n
s
,
in
clu
d
in
g
s
m
ar
t
en
e
r
g
y
m
a
n
ag
em
en
t,
s
ec
u
r
ity
s
y
s
tem
s
,
an
d
p
er
s
o
n
alize
d
b
u
ild
in
g
au
to
m
atio
n
.
Ad
d
itio
n
ally
,
th
e
m
o
d
el'
s
p
er
f
o
r
m
a
n
c
e
ca
n
b
e
p
er
io
d
ically
e
v
alu
ate
d
an
d
f
in
e
-
tu
n
e
d
t
o
m
ak
e
it
ad
ap
tab
le
to
f
r
eq
u
e
n
t
ch
an
g
es
in
o
cc
u
p
a
n
cy
p
atter
n
s
an
d
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
.
A
m
ath
em
atica
l
m
o
d
el
f
o
r
tr
ain
in
g
a
C
NN
f
o
r
o
cc
u
p
an
c
y
d
etec
tio
n
is
s
h
o
wn
in
Alg
o
r
ith
m
1
.
Alg
o
r
ith
m
1
.
C
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
f
o
r
o
cc
u
p
an
cy
d
etec
tio
n
Input:
Training
datase
t:
{
(
(
)
,
(
)
)
}
=
1
w
h
e
r
e
(
)
i
s
t
h
e
i
n
pu
t
f
e
a
tu
r
e
ma
t
r
i
x
o
f
si
z
e
(
,
,
and
ℎ
)
a
n
d
(
)
i
s
t
h
e
co
r
re
s
p
o
n
d
i
ng
b
i
n
a
ry
o
c
c
up
a
n
cy
l
a
b
e
l
v
ec
t
o
r
o
f
s
i
ze
(
,
1).
Testing dataset: {
(
(
)
,
(
)
)
}
=
1
test for evaluation.
Output:
Trained CNN model
for occupancy detection.
Algorithm:
1.
Initialization:
•
Initialize the CNN architecture with neutrosophic layers:
−
Neutrosophic
convolutional layer
:
ℎ
−
Neutrosophic
max
-
pooling layer
:
ℎ
−
Neutrosophic
logic layer
:
ℎ
2.
Define CNN
architecture
:
•
Define the architecture of the CNN model using the neutrosophic layers:
−
ℎ
w
i
t
h
k
e
r
n
e
ls
,
k
e
r
n
e
l
s
iz
e
(
ℎ
ℎ
,
ℎ
)
,
a
nd
R
eL
U
a
c
t
i
v
at
i
on
function
.
−
ℎ
with pooling size (
ℎ
ℎ
,
ℎ
).
−
Flatten layer to convert the 2D feature maps into a 1D vector.
−
Fully connected Dense layer with
units
neurons and ReLU
activation function.
−
Output layer with 1 neuron and sigmoid activation function.
3.
Compile the
model
:
−
Compile the model using the Adam optimizer.
−
Use binary cross
-
entropy loss function for binary classification.
−
Monitor accuracy as the evaluation
metric.
4.
Model
training
:
•
Train the model on the training dataset:
−
Feed batches of input data
(
)
into the model.
−
Model parameters may be optimized using backpropagation and gradient descent.
−
Repeat for multiple epochs until convergence.
5.
Model
evaluation
:
•
Measure the performance of the trained model using the testing dataset:
−
As
se
ss
th
e
mo
de
l'
s
ef
fe
ct
iv
en
es
s
in
oc
cu
pa
nc
y
de
te
ct
io
n
by
ca
lc
ul
at
in
g
ac
cu
ra
cy
,
precision, recall, and F1
-
score.
−
Compare the predicted occupancy labels with the ground truth
labels.
6.
Model
optimization
:
−
Fine
-
t
u
ne
t
h
e
m
o
d
e
l
b
y
a
dj
u
s
t
i
n
g
hy
p
e
r
p
ar
a
m
e
te
r
s
o
r
e
x
p
l
o
r
i
ng
d
i
f
fe
r
e
n
t
a
r
c
h
it
e
c
t
u
r
e
s
.
−
Utilize techniques such as regularization or dropout to prevent overfitting.
7.
Model Deployment:
−
On satisfactory performance, deploy the
model for occupancy detection applications.
−
Use the trained model to predict occupancy status based on input sensor data.
−
Monitor
the
model's
perf
ormance
and
update
it
as
needed
to
adapt
to
chan
ges
in
the
environment.
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
6
1
9
-
6
6
2
7
6624
T
h
is
alg
o
r
ith
m
o
u
tlin
es
th
e
s
tep
-
by
-
s
tep
p
r
o
ce
s
s
o
f
tr
ain
in
g
a
C
NN
with
n
eu
tr
o
s
o
p
h
ic
la
y
er
s
f
o
r
o
cc
u
p
an
cy
d
etec
tio
n
,
in
clu
d
in
g
m
o
d
el
i
n
itializatio
n
,
ar
ch
itectu
r
e
d
e
f
in
itio
n
,
tr
ain
in
g
,
ev
alu
atio
n
,
o
p
tim
izatio
n
,
an
d
d
ep
lo
y
m
e
n
t.
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Var
iatio
n
s
in
o
cc
u
p
an
c
y
d
at
aset
p
ar
am
eter
s
(
tem
p
er
atu
r
e,
h
u
m
id
ity
,
lig
h
t
,
C
O
2
lev
els,
h
u
m
id
ity
r
atio
,
an
d
o
cc
u
p
a
n
cy
)
h
av
e
b
e
en
s
tu
d
ied
o
v
er
tim
e.
Fig
u
r
e
1
s
h
o
ws
th
e
Hea
t
m
ap
o
f
t
h
e
co
r
r
elate
d
p
ar
am
ete
r
s
in
th
e
m
o
d
el.
Her
e'
s
a
b
r
ea
k
d
o
wn
o
f
th
e
a
n
aly
s
is
:
a.
T
em
p
er
atu
r
e:
T
h
e
tem
p
e
r
atu
r
e
f
lu
ctu
ates sli
g
h
tly
ar
o
u
n
d
2
1
.
7
6
to
2
1
.
8
9
d
eg
r
ee
s
C
elsi
u
s
o
v
er
tim
e
b.
Hu
m
id
ity
: H
u
m
id
ity
r
a
n
g
es f
r
o
m
3
0
.
2
9
% to
3
1
.
8
9
% with
m
in
o
r
f
lu
ct
u
atio
n
s
o
v
e
r
tim
e.
c.
L
ig
h
t:
L
ig
h
t
i
n
ten
s
ity
r
em
ain
s
r
elativ
ely
co
n
s
tan
t,
m
o
s
tly
ar
o
u
n
d
4
2
9
to
4
4
9
.
5
u
n
its
,
with
o
cc
asio
n
al
f
lu
ctu
atio
n
s
.
d.
CO
2
L
ev
els:
C
O
2
lev
els
v
ar
y
f
r
o
m
7
9
3
.
5
to
1
1
1
0
p
ar
ts
p
er
m
illi
o
n
(
p
p
m
)
th
r
o
u
g
h
o
u
t
th
e
o
b
s
er
v
atio
n
p
er
io
d
.
e.
Hu
m
id
ity
r
atio
:
T
h
e
h
u
m
id
ity
r
atio
r
an
g
es
f
r
o
m
0
.
0
0
4
9
0
8
to
0
.
0
0
5
1
8
5
,
in
d
icatin
g
s
o
m
e
v
ar
iab
ilit
y
b
u
t
g
en
er
ally
s
tab
le
co
n
d
itio
n
s
.
f.
Occ
u
p
an
cy
:
Occ
u
p
an
c
y
s
tatu
s
is
p
r
im
ar
ily
o
cc
u
p
ied
(
1
)
th
r
o
u
g
h
o
u
t
t
h
e
r
ec
o
r
d
e
d
tim
e,
with
th
e
last
f
e
w
en
tr
ies s
h
o
win
g
b
o
t
h
o
cc
u
p
ied
an
d
u
n
o
cc
u
p
ied
s
tates.
−
T
e
m
p
e
r
a
t
u
r
e
,
h
u
m
i
d
i
t
y
,
a
n
d
C
O
2
l
e
v
e
ls
d
e
m
o
n
s
t
r
a
t
e
m
i
n
o
r
f
lu
c
t
u
a
t
i
o
n
s
w
i
t
h
i
n
r
el
a
t
i
v
el
y
n
a
r
r
o
w
r
a
n
g
e
s
.
−
L
ig
h
t in
ten
s
ity
r
em
ain
s
f
air
l
y
co
n
s
is
ten
t.
−
T
h
e
o
cc
u
p
a
n
cy
s
tatu
s
is
p
r
ed
o
m
in
an
tly
o
cc
u
p
ied
,
with
in
t
er
m
itten
t
u
n
o
cc
u
p
ied
p
er
io
d
s
to
war
d
s
th
e
en
d
o
f
th
e
d
ata.
g.
Ad
d
itio
n
al
i
n
s
ig
h
ts
:
i)
Fu
r
th
er
an
aly
s
is
co
u
ld
ex
p
lo
r
e
c
o
r
r
elatio
n
s
b
etwe
en
d
if
f
er
en
t
v
a
r
iab
les
an
d
th
eir
im
p
ac
t
o
n
o
cc
u
p
an
c
y
s
tatu
s
;
a
n
d
ii)
An
o
m
alies
o
r
p
atter
n
s
m
ay
em
er
g
e
wh
en
an
aly
zin
g
th
e
d
ata
o
v
er
lo
n
g
er
p
er
io
d
s
o
r
co
m
p
a
r
in
g
it
with
ex
ter
n
al
f
ac
to
r
s
s
u
ch
as
tim
e
o
f
d
ay
o
r
o
cc
u
p
a
n
cy
p
atter
n
s
in
th
e
b
u
ild
in
g
.
Fig
u
r
e
1
.
C
o
r
r
elatio
n
o
f
f
ea
tu
r
es u
s
ed
as in
p
u
t to
m
o
d
el
o
v
er
all
tr
en
d
s
Fig
u
r
e
2
d
ep
icts
th
e
m
o
d
el
p
e
r
f
o
r
m
an
ce
in
ter
m
s
o
f
ac
cu
r
ac
y
v
er
s
u
s
lo
s
s
.
T
h
e
m
o
d
el
h
as a
ch
iev
ed
an
im
p
r
ess
iv
e
ac
cu
r
ac
y
s
co
r
e
o
f
9
9
.
1
8
%,
in
d
icatin
g
th
at
th
e
i
n
teg
r
atio
n
o
f
Neu
r
to
s
o
p
h
y
in
t
o
th
e
C
NN
m
o
d
el
co
r
r
ec
tly
class
if
ies
th
e
o
cc
u
p
an
cy
s
tatu
s
in
th
e
test
d
atase
t
with
h
ig
h
p
r
ec
is
io
n
T
h
is
h
ig
h
ac
cu
r
ac
y
s
u
g
g
ests
th
at
th
e
m
o
d
el
h
as
ef
f
ec
tiv
el
y
lear
n
ed
f
r
o
m
th
e
tr
ai
n
in
g
d
ata
an
d
ac
cu
r
ately
p
r
e
d
icts
f
o
r
u
n
s
ee
n
d
ata.
T
h
e
m
o
d
el
p
er
f
o
r
m
s
ex
ce
p
ti
o
n
ally
well
in
b
o
th
class
es.
Fo
r
clas
s
0
(
u
n
o
cc
u
p
ied
)
,
it
ac
h
ie
v
es
a
p
r
ec
is
io
n
,
r
ec
all,
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
N
eu
tr
o
s
o
p
h
ic
en
h
a
n
ce
d
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
fo
r
o
cc
u
p
a
n
cy
…
(
R
a
n
jeeta
Mit
ta
l
)
6625
an
d
F1
-
s
co
r
e
o
f
1
.
0
0
,
in
d
icati
n
g
p
er
f
ec
t
p
er
f
o
r
m
a
n
ce
.
Fo
r
class
1
(
o
cc
u
p
ied
)
,
it
ac
h
iev
e
s
s
lig
h
tly
lo
wer
b
u
t
s
till
ex
ce
llen
t
p
r
ec
is
io
n
(
0
.
9
7
)
,
r
ec
all
(
0
.
9
9
)
,
an
d
F1
-
s
co
r
e
(
0
.
9
8
)
.
T
h
ese
m
etr
ics
in
d
ica
te
th
at
th
e
m
o
d
el
ac
cu
r
ately
id
en
tifie
s
b
o
th
u
n
o
cc
u
p
ied
an
d
o
cc
u
p
ied
i
n
s
tan
ce
s
,
with
v
er
y
f
ew
m
is
class
if
i
ca
tio
n
s
.
T
h
e
m
o
d
el
d
em
o
n
s
tr
ates
r
o
b
u
s
t
p
er
f
o
r
m
a
n
ce
in
p
r
ed
ictin
g
o
cc
u
p
a
n
cy
s
tatu
s
,
s
h
o
wca
s
in
g
its
ef
f
ec
tiv
en
ess
in
h
an
d
lin
g
u
n
ce
r
tain
ties
with
in
th
e
d
ata
s
et
an
d
alig
n
in
g
with
t
h
e
p
r
i
n
cip
les
o
f
N
eu
tr
o
s
o
p
h
y
b
y
a
ck
n
o
wled
g
i
n
g
an
d
n
av
ig
atin
g
u
n
ce
r
tain
ties
with
in
its
p
r
ed
ictio
n
s
.
Fig
u
r
e
3
s
h
o
ws
th
e
p
lo
t
o
f
p
r
ed
icted
p
r
o
b
a
b
ilit
ies
an
d
u
n
ce
r
tain
ties
o
f
th
e
s
am
p
les.
T
h
is
an
aly
s
is
p
r
o
v
id
es
a
b
asic
o
v
er
v
iew
o
f
th
e
p
r
o
v
i
d
ed
d
ata.
Fu
r
th
er
in
s
ig
h
ts
an
d
co
n
clu
s
io
n
s
ca
n
b
e
d
r
awn
b
y
ap
p
l
y
in
g
a
d
v
an
ce
d
s
tatis
tic
al
tech
n
iq
u
es o
r
d
o
m
ai
n
-
s
p
ec
i
f
ic
k
n
o
wled
g
e.
Fig
u
r
e
2
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
in
ter
m
s
o
f
ac
cu
r
ac
y
v
s
lo
s
s
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
Fig
u
r
e
3
.
Plo
t d
e
p
ictin
g
p
r
ed
ic
tio
n
u
n
ce
r
tain
ties
an
d
p
r
e
d
icted
p
r
o
b
ab
ilit
ies o
v
er
th
e
s
am
p
le
r
an
g
e
6.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
o
p
o
s
ed
an
im
p
r
o
v
is
ed
C
NN
m
o
d
el
f
o
r
o
cc
u
p
a
n
cy
d
etec
tio
n
b
ased
o
n
s
en
s
o
r
d
ata.
T
h
e
m
o
d
el
ar
c
h
itectu
r
e,
d
esig
n
ed
with
th
e
p
r
in
cip
les
o
f
N
eu
t
r
o
s
o
p
h
y
in
m
in
d
,
d
em
o
n
s
tr
ates
p
r
o
wess
in
th
e
h
an
d
lin
g
o
f
u
n
ce
r
tain
ties
in
h
er
en
t
in
b
o
th
th
e
d
ataset
an
d
m
o
d
el
p
r
e
d
ictio
n
s
.
T
h
r
o
u
g
h
th
e
u
tili
za
tio
n
o
f
a
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
ML
P)
ar
ch
itectu
r
e,
th
e
co
n
s
tr
u
cted
m
o
d
el
is
ca
p
ab
le
o
f
ef
f
ec
tiv
e
ly
h
an
d
lin
g
tab
u
lar
d
ata
an
d
b
in
ar
y
class
if
icatio
n
task
s
.
T
h
e
m
o
d
el
co
m
p
r
is
es
in
p
u
t,
h
id
d
e
n
,
an
d
o
u
tp
u
t
lay
er
s
,
ea
ch
m
eticu
lo
u
s
ly
cr
af
ted
to
n
av
ig
ate
an
d
en
ca
p
s
u
late
u
n
ce
r
tain
ties
with
in
th
e
d
ata
an
d
p
r
ed
ictio
n
s
.
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
6
1
9
-
6
6
2
7
6626
Du
r
in
g
tr
ai
n
in
g
a
n
d
e
v
alu
atio
n
,
th
e
m
o
d
el
e
x
h
ib
ited
ex
ce
p
ti
o
n
al
p
er
f
o
r
m
a
n
ce
,
ac
h
iev
in
g
a
n
ac
cu
r
ac
y
s
co
r
e
o
f
ap
p
r
o
x
im
ately
9
9
.
1
8
%.
T
h
is
h
ig
h
ac
cu
r
ac
y
u
n
d
e
r
s
co
r
es
th
at
th
e
m
o
d
el
ca
n
g
en
er
alize
well
an
d
m
ak
e
f
au
ltles
s
p
r
ed
ictio
n
s
o
n
u
n
k
n
o
wn
test
d
ata,
th
u
s
i
n
s
till
in
g
co
n
f
id
en
ce
in
its
p
r
ed
ictiv
e
c
ap
ab
ilit
ies.
Fu
r
th
er
an
aly
s
is
o
f
th
e
class
if
icatio
n
r
ep
o
r
t
r
ev
ea
ls
th
at
th
e
m
o
d
el
p
er
f
o
r
m
s
e
x
ce
p
tio
n
ally
well
in
id
en
tify
i
n
g
b
o
th
o
cc
u
p
ied
an
d
u
n
o
cc
u
p
ied
in
s
t
an
ce
s
.
W
ith
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
m
etr
ics
r
an
g
in
g
f
r
o
m
0
.
9
7
to
1
.
0
0
,
th
e
m
o
d
el
d
e
m
o
n
s
tr
ates
a
r
o
b
u
s
t
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
u
n
d
er
ly
in
g
p
atter
n
s
a
n
d
r
elatio
n
s
h
ip
s
in
t
h
e
d
ata.
I
n
co
n
clu
s
io
n
,
th
e
Neu
tr
o
s
o
p
h
ic
-
en
h
an
ce
d
C
NN
m
o
d
el
n
o
t
o
n
ly
p
r
o
v
id
es
ac
cu
r
ate
o
cc
u
p
a
n
cy
p
r
e
d
ictio
n
s
b
u
t
also
n
av
ig
ates
an
d
em
b
r
ac
es
u
n
ce
r
tain
ties
in
h
er
en
t
i
n
th
e
d
ataset
an
d
m
o
d
el
p
r
e
d
ictio
n
s
.
B
y
alig
n
in
g
with
th
e
p
r
in
cip
les
o
f
N
eu
tr
o
s
o
p
h
y
,
t
h
e
m
o
d
el
s
er
v
es
as
a
test
am
en
t
to
th
e
im
p
o
r
tan
ce
o
f
ac
k
n
o
wled
g
i
n
g
an
d
ex
p
lo
r
in
g
u
n
ce
r
tain
ties
in
th
e
p
u
r
s
u
it o
f
r
o
b
u
s
t a
n
d
r
eliab
le
p
r
ed
ictiv
e
m
o
d
els.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
S
i
n
g
h
,
V
.
K
a
n
sa
l
,
M
.
G
a
u
r
,
a
n
d
M
.
S
.
P
a
n
d
e
y
,
“
P
r
e
d
i
c
t
i
n
g
s
mart
b
u
i
l
d
i
n
g
o
c
c
u
p
a
n
c
y
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
L
e
c
t
u
re
N
o
t
e
s
i
n
N
e
t
w
o
r
k
s
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
4
7
9
,
p
p
.
1
4
5
–
1
5
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
19
-
3
1
4
8
-
2
_
1
2
.
[
2
]
M
.
Esr
a
f
i
l
i
a
n
-
N
a
j
a
f
a
b
a
d
i
a
n
d
F
.
H
a
g
h
i
g
h
a
t
,
“
O
c
c
u
p
a
n
c
y
-
b
a
se
d
H
V
A
C
c
o
n
t
r
o
l
s
y
st
e
ms
i
n
b
u
i
l
d
i
n
g
s:
a
s
t
a
t
e
-
of
-
t
h
e
-
a
r
t
r
e
v
i
e
w
,
”
Bu
i
l
d
i
n
g
a
n
d
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
1
9
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
u
i
l
d
e
n
v
.
2
0
2
1
.
1
0
7
8
1
0
.
[
3
]
H
.
Y
a
r
,
A
.
S
.
I
mr
a
n
,
Z.
A
.
K
h
a
n
,
M
.
S
a
j
j
a
d
,
a
n
d
Z.
K
a
s
t
r
a
t
i
,
“
T
o
w
a
r
d
s sma
r
t
h
o
me
a
u
t
o
mat
i
o
n
u
s
i
n
g
I
o
T
-
e
n
a
b
l
e
d
e
d
g
e
-
c
o
m
p
u
t
i
n
g
p
a
r
a
d
i
g
m
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
1
4
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
1
4
4
9
3
2
.
[
4
]
N
.
S
o
mu
,
G
.
R
a
ma
n
M
R
,
a
n
d
K
.
R
a
ma
mr
i
t
h
a
m,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
f
o
r
b
u
i
l
d
i
n
g
e
n
e
r
g
y
c
o
n
s
u
mp
t
i
o
n
f
o
r
e
c
a
s
t
,
”
Re
n
e
w
a
b
l
e
a
n
d
S
u
st
a
i
n
a
b
l
e
En
e
rg
y
R
e
v
i
e
w
s
,
v
o
l
.
1
3
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
ser.2
0
2
0
.
1
1
0
5
9
1
.
[
5
]
N
.
S
.
F
a
y
e
d
,
M
.
M
.
El
mo
g
y
,
A
.
A
t
w
a
n
,
a
n
d
E.
E
l
-
D
a
y
d
a
mo
n
y
,
“
Ef
f
i
c
i
e
n
t
o
c
c
u
p
a
n
c
y
d
e
t
e
c
t
i
o
n
s
y
st
e
m
b
a
se
d
o
n
n
e
u
t
r
o
so
p
h
i
c
w
e
i
g
h
t
e
d
se
n
s
o
r
s
d
a
t
a
f
u
si
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
3
4
0
0
–
1
3
4
2
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
4
6
3
4
6
.
[
6
]
Z.
C
h
e
n
,
C
.
Ji
a
n
g
,
M
.
K
.
M
a
so
o
d
,
Y
.
C
.
S
o
h
,
M
.
W
u
,
a
n
d
X
.
L
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
b
u
i
l
d
i
n
g
o
c
c
u
p
a
n
c
y
e
st
i
mat
i
o
n
u
si
n
g
e
n
v
i
r
o
n
m
e
n
t
a
l
s
e
n
s
o
r
s,
”
S
t
u
d
i
e
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
8
6
5
,
p
p
.
3
3
5
–
3
5
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
3
1
7
6
0
-
7
_
1
1
.
[
7
]
G
.
G
a
o
,
J.
L
i
,
a
n
d
Y
.
W
e
n
,
“
E
n
e
r
g
y
-
e
f
f
i
c
i
e
n
t
t
h
e
r
mal
c
o
mf
o
r
t
c
o
n
t
r
o
l
i
n
s
mart
b
u
i
l
d
i
n
g
s
v
i
a
d
e
e
p
r
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
,
”
a
rX
i
v
p
re
p
ri
n
t
a
rXi
v
:
1
9
0
1
.
0
4
6
9
3
,
2
0
1
9
.
[
8
]
L.
R
u
e
d
a
,
K
.
A
g
b
o
sso
u
,
A
.
C
a
r
d
e
n
a
s,
N
.
H
e
n
a
o
,
a
n
d
S
.
K
e
l
o
u
w
a
n
i
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
a
p
p
r
o
a
c
h
e
s
t
o
b
u
i
l
d
i
n
g
o
c
c
u
p
a
n
c
y
d
e
t
e
c
t
i
o
n
,
”
B
u
i
l
d
i
n
g
a
n
d
E
n
v
i
ro
n
m
e
n
t
,
v
o
l
.
1
8
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
u
i
l
d
e
n
v
.
2
0
2
0
.
1
0
6
9
6
6
.
[
9
]
H
.
W
a
n
g
,
J.
Z
h
a
n
g
,
C
.
Lu
,
a
n
d
C
.
W
u
,
“
P
r
i
v
a
c
y
p
r
e
s
e
r
v
i
n
g
i
n
n
o
n
-
i
n
t
r
u
s
i
v
e
l
o
a
d
m
o
n
i
t
o
r
i
n
g
:
a
d
i
f
f
e
r
e
n
t
i
a
l
p
r
i
v
a
c
y
p
e
r
sp
e
c
t
i
v
e
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
S
m
a
rt
G
ri
d
,
v
o
l
.
1
2
,
n
o
.
3
,
p
p
.
2
5
2
9
–
2
5
4
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TSG
.
2
0
2
0
.
3
0
3
8
7
5
7
.
[
1
0
]
A
.
S
o
l
e
i
ma
n
i
j
a
v
i
d
,
I
.
K
o
n
s
t
a
n
t
z
o
s,
a
n
d
X
.
Li
u
,
“
C
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s
o
f
o
c
c
u
p
a
n
t
-
c
e
n
t
r
i
c
b
u
i
l
d
i
n
g
c
o
n
t
r
o
l
s
i
n
r
e
a
l
-
w
o
r
l
d
i
mp
l
e
m
e
n
t
a
t
i
o
n
:
a
c
r
i
t
i
c
a
l
r
e
v
i
e
w
,
”
E
n
e
rg
y
a
n
d
B
u
i
l
d
i
n
g
s
,
v
o
l
.
3
0
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
b
u
i
l
d
.
2
0
2
4
.
1
1
3
9
5
8
.
[
1
1
]
M
.
S
.
A
l
i
e
r
o
e
t
a
l
.
,
“
N
o
n
-
i
n
t
r
u
si
v
e
r
o
o
m
o
c
c
u
p
a
n
c
y
p
r
e
d
i
c
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
s
i
s u
s
i
n
g
d
i
f
f
e
r
e
n
t
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
En
e
r
g
i
e
s
,
v
o
l
.
1
5
,
n
o
.
2
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
5
2
3
9
2
3
1
.
[
1
2
]
P
.
W
.
Ti
e
n
,
S
.
W
e
i
,
J.
D
a
r
k
w
a
,
C
.
W
o
o
d
,
a
n
d
J.
K
.
C
a
l
a
u
t
i
t
,
“
M
a
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
met
h
o
d
s
f
o
r
e
n
h
a
n
c
i
n
g
b
u
i
l
d
i
n
g
e
n
e
r
g
y
e
f
f
i
c
i
e
n
c
y
a
n
d
i
n
d
o
o
r
e
n
v
i
r
o
n
men
t
a
l
q
u
a
l
i
t
y
–
a
r
e
v
i
e
w
,
”
E
n
e
r
g
y
a
n
d
AI
,
v
o
l
.
1
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
a
i
.
2
0
2
2
.
1
0
0
1
9
8
.
[
1
3
]
C
.
F
e
n
g
,
A
.
M
e
h
ma
n
i
,
a
n
d
J.
Z
h
a
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
r
e
a
l
-
t
i
m
e
b
u
i
l
d
i
n
g
o
c
c
u
p
a
n
c
y
d
e
t
e
c
t
i
o
n
u
s
i
n
g
A
M
I
d
a
t
a
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
S
m
a
rt
G
ri
d
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
4
4
9
0
–
4
5
0
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TSG
.
2
0
2
0
.
2
9
8
2
3
5
1
.
[
1
4
]
D
.
M
.
P
e
t
r
o
sa
n
u
,
G
.
C
a
r
u
t
a
s
u
,
N
.
L
.
C
a
r
u
t
a
s
u
,
a
n
d
A
.
P
î
r
j
a
n
,
“
A
r
e
v
i
e
w
o
f
t
h
e
r
e
c
e
n
t
d
e
v
e
l
o
p
me
n
t
s
i
n
i
n
t
e
g
r
a
t
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
w
i
t
h
se
n
s
o
r
d
e
v
i
c
e
s
i
n
t
h
e
sm
a
r
t
b
u
i
l
d
i
n
g
s
sec
t
o
r
w
i
t
h
a
v
i
e
w
t
o
a
t
t
a
i
n
i
n
g
e
n
h
a
n
c
e
d
se
n
si
n
g
,
e
n
e
r
g
y
e
f
f
i
c
i
e
n
c
y
,
a
n
d
o
p
t
i
m
a
l
b
u
i
l
d
i
n
g
ma
n
a
g
e
me
n
t
,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
2
,
n
o
.
2
4
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
2
2
4
4
7
4
5
.
[
1
5
]
D
.
D
j
e
n
o
u
r
i
,
R
.
La
i
d
i
,
Y
.
D
j
e
n
o
u
r
i
,
a
n
d
I
.
B
a
l
a
s
i
n
g
h
a
m,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
sm
a
r
t
b
u
i
l
d
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
:
r
e
v
i
e
w
a
n
d
t
a
x
o
n
o
my
,
”
AC
M
C
o
m
p
u
t
i
n
g
S
u
r
v
e
y
s
,
v
o
l
.
5
2
,
n
o
.
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
1
1
9
5
0
.
[
1
6
]
X
.
D
a
i
,
J.
L
i
u
,
a
n
d
X
.
Zh
a
n
g
,
“
A
r
e
v
i
e
w
o
f
s
t
u
d
i
e
s
a
p
p
l
y
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
t
o
p
r
e
d
i
c
t
o
c
c
u
p
a
n
c
y
a
n
d
w
i
n
d
o
w
-
o
p
e
n
i
n
g
b
e
h
a
v
i
o
u
r
s i
n
sm
a
r
t
b
u
i
l
d
i
n
g
s
,
”
En
e
rg
y
a
n
d
B
u
i
l
d
i
n
g
s
,
v
o
l
.
2
2
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
b
u
i
l
d
.
2
0
2
0
.
1
1
0
1
5
9
.
[
1
7
]
M
.
K
o
k
l
u
a
n
d
K
.
T
u
t
u
n
c
u
,
“
Tr
e
e
b
a
sed
c
l
a
ssi
f
i
c
a
t
i
o
n
m
e
t
h
o
d
s
f
o
r
o
c
c
u
p
a
n
c
y
d
e
t
e
c
t
i
o
n
,
”
i
n
I
O
P
C
o
n
f
e
r
e
n
c
e
S
e
r
i
e
s:
Ma
t
e
r
i
a
l
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
2
0
1
9
,
v
o
l
.
6
7
5
,
n
o
.
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
6
7
5
/
1
/
0
1
2
0
3
2
.
[
1
8
]
A
.
S
a
r
k
e
r
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
p
r
e
d
i
c
t
i
o
n
t
o
w
a
r
d
s
d
e
si
g
n
i
n
g
a
s
mart
b
u
i
l
d
i
n
g
a
ssi
s
t
a
n
t
sy
s
t
e
m
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
2
0
2
0
I
EEE
1
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Mo
b
i
l
e
Ad
H
o
c
a
n
d
S
m
a
r
t
S
y
st
e
m
s,
M
AS
S
2
0
2
0
,
2
0
2
0
,
p
p
.
2
0
2
–
2
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
M
A
S
S
5
0
6
1
3
.
2
0
2
0
.
0
0
0
3
4
.
[
1
9
]
J.
Y
u
,
A
.
d
e
A
n
t
o
n
i
o
,
a
n
d
E.
V
i
l
l
a
l
b
a
-
M
o
r
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
(
C
N
N
,
R
N
N
)
a
p
p
l
i
c
a
t
i
o
n
s
f
o
r
sm
a
r
t
h
o
m
e
s:
a
s
y
s
t
e
ma
t
i
c
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
1
1
,
n
o
.
2
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
e
r
s
1
1
0
2
0
0
2
6
.
[
2
0
]
B
.
T.
H
u
n
g
a
n
d
P
.
C
h
a
k
r
a
b
a
r
t
i
,
“
P
a
r
k
i
n
g
I
o
T
o
c
c
u
p
a
n
c
y
d
e
t
e
c
t
i
o
n
u
si
n
g
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
C
N
N
-
LST
M
a
p
p
r
o
a
c
h
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
2
n
d
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
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
:
Ad
v
a
n
c
e
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(
I
C
AI
A
A
2
0
2
1
)
,
2
0
2
2
,
p
p
.
5
0
1
–
5
0
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
6
3
3
2
-
1
_
4
3
.
[
2
1
]
F
.
M
t
i
b
a
a
,
K
.
K
.
N
g
u
y
e
n
,
M
.
A
z
a
m,
A
.
P
a
p
a
c
h
r
i
st
o
u
,
J.
S
.
V
e
n
n
e
,
a
n
d
M
.
C
h
e
r
i
e
t
,
“
LSTM
-
b
a
s
e
d
i
n
d
o
o
r
a
i
r
t
e
mp
e
r
a
t
u
r
e
p
r
e
d
i
c
t
i
o
n
f
r
a
mew
o
r
k
f
o
r
H
V
A
C
sy
st
e
ms
i
n
smar
t
b
u
i
l
d
i
n
g
s
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
2
,
n
o
.
2
3
,
p
p
.
1
7
5
6
9
–
1
7
5
8
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
2
1
-
0
2
0
-
0
4
9
2
6
-
3.
[
2
2
]
J.
P
.
R
o
s
e
l
y
n
,
R
.
A
.
U
t
h
r
a
,
A
.
R
a
j
,
D
.
D
e
v
a
r
a
j
,
P
.
B
h
a
r
a
d
w
a
j
,
a
n
d
S
.
V
.
D
.
K
r
i
sh
n
a
K
a
k
i
,
“
D
e
v
e
l
o
p
m
e
n
t
a
n
d
i
mp
l
e
me
n
t
a
t
i
o
n
o
f
n
o
v
e
l
se
n
s
o
r
f
u
si
o
n
a
l
g
o
r
i
t
h
m
f
o
r
o
c
c
u
p
a
n
c
y
d
e
t
e
c
t
i
o
n
a
n
d
a
u
t
o
ma
t
i
o
n
i
n
e
n
e
r
g
y
e
f
f
i
c
i
e
n
t
b
u
i
l
d
i
n
g
s,
”
S
u
s
t
a
i
n
a
b
l
e
C
i
t
i
e
s
a
n
d
S
o
c
i
e
t
y
,
v
o
l
.
4
4
,
p
p
.
8
5
–
9
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
scs
.
2
0
1
8
.
0
9
.
0
3
1
.
[
2
3
]
S
.
Y
.
T
a
n
,
M
.
Jac
o
b
y
,
H
.
S
a
h
a
,
A
.
F
l
o
r
i
t
a
,
G
.
H
e
n
z
e
,
a
n
d
S
.
S
a
r
k
a
r
,
“
M
u
l
t
i
mo
d
a
l
se
n
s
o
r
f
u
s
i
o
n
f
r
a
m
e
w
o
r
k
f
o
r
r
e
si
d
e
n
t
i
a
l
b
u
i
l
d
i
n
g
o
c
c
u
p
a
n
c
y
d
e
t
e
c
t
i
o
n
,
”
E
n
e
r
g
y
a
n
d
B
u
i
l
d
i
n
g
s
,
v
o
l
.
2
5
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
b
u
i
l
d
.
2
0
2
1
.
1
1
1
8
2
8
.
[
2
4
]
Z.
C
h
e
n
,
C
.
Ji
a
n
g
,
a
n
d
L
.
X
i
e
,
“
B
u
i
l
d
i
n
g
o
c
c
u
p
a
n
c
y
e
s
t
i
m
a
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
:
a
r
e
v
i
e
w
,
”
E
n
e
r
g
y
a
n
d
Bu
i
l
d
i
n
g
s
,
v
o
l
.
1
6
9
,
p
p
.
2
6
0
–
2
7
0
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
b
u
i
l
d
.
2
0
1
8
.
0
3
.
0
8
4
.
[
2
5
]
N
.
N
e
sa
a
n
d
I
.
B
a
n
e
r
j
e
e
,
“
I
o
T
-
b
a
s
e
d
sen
s
o
r
d
a
t
a
f
u
s
i
o
n
f
o
r
o
c
c
u
p
a
n
c
y
se
n
si
n
g
u
si
n
g
D
e
m
p
st
e
r
-
S
h
a
f
e
r
e
v
i
d
e
n
c
e
t
h
e
o
r
y
f
o
r
smar
t
b
u
i
l
d
i
n
g
s,
”
I
EEE
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
4
,
n
o
.
5
,
p
p
.
1
5
6
3
–
1
5
7
0
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
1
7
.
2
7
2
3
4
2
4
.
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
N
eu
tr
o
s
o
p
h
ic
en
h
a
n
ce
d
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
fo
r
o
cc
u
p
a
n
cy
…
(
R
a
n
jeeta
Mit
ta
l
)
6627
BIO
G
RA
PH
IES
O
F
AU
TH
O
R
S
Ra
n
je
e
ta
Mi
tt
a
l
re
c
e
iv
e
d
t
h
e
B.
E.
d
e
g
re
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
fro
m
De
e
n
b
a
n
d
h
u
Ch
h
o
t
u
Ra
m
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
M
u
rth
a
l
,
In
d
ia
i
n
1
9
9
8
.
S
h
e
re
c
e
iv
e
d
t
h
e
M
.
E.
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
fr
o
m
th
e
Na
ti
o
n
a
l
I
n
stit
u
te
o
f
Tec
h
n
ica
l
Tea
c
h
e
rs
Train
in
g
a
n
d
Re
se
a
rc
h
,
Ch
a
n
d
ig
a
rh
,
In
d
ia
in
2
0
0
9
.
C
u
rre
n
tl
y
,
sh
e
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
th
e
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
M
a
n
a
v
Ra
c
h
n
a
In
tern
a
ti
o
n
a
l
I
n
stit
u
te
o
f
Re
se
a
rc
h
a
n
d
S
t
u
d
ies
,
F
a
rid
a
b
a
d
,
In
d
i
a
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
tell
ig
e
n
c
e
a
n
d
e
n
e
r
g
y
c
o
n
se
rv
a
ti
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
n
jee
tam
it
tal@g
m
a
il
.
c
o
m
.
S
u
r
e
sh
K
u
m
a
r
is
a
d
isti
n
g
u
i
sh
e
d
a
c
a
d
e
m
icia
n
a
n
d
p
r
o
fe
ss
io
n
a
l
a
ss
o
c
iate
d
with
th
e
M
a
n
a
v
Ra
c
h
n
a
I
n
tern
a
ti
o
n
a
l
In
sti
tu
te
o
f
Re
se
a
rc
h
a
n
d
S
tu
d
i
e
s
(M
RIIRS
).
He
is
a
l
ife
m
e
m
b
e
r
o
f
t
h
e
In
d
ian
S
o
c
iety
o
f
Tec
h
n
ica
l
Ed
u
c
a
ti
o
n
(IS
T
E)
a
n
d
Co
m
p
u
ter
S
o
c
iety
In
d
ia
(CS
I).
He
is
a
lso
a
S
e
n
io
r
m
e
m
b
e
r
o
f
IEE
E,
USA,
a
n
d
IACS
IT,
S
in
g
a
p
o
re
.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
e
i
g
h
t
y
re
se
a
rc
h
p
a
p
e
rs
in
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
s
a
n
d
C
o
n
fe
re
n
c
e
s.
Th
e
He
li
x
S
m
a
rtL
a
b
s
a
sta
rtu
p
in
c
u
b
a
ted
a
t
M
a
n
a
v
Ra
c
h
n
a
u
n
d
e
r
h
is
s
u
p
e
rv
isi
o
n
a
n
d
is
re
g
istere
d
a
s
a
P
v
t.
Lt
d
c
o
m
p
a
n
y
.
He
h
a
s
p
u
b
li
sh
e
d
two
p
a
ten
ts
a
n
d
a
tec
h
n
o
lo
g
y
tran
sfe
r
i
n
a
r
u
les
p
a
c
k
a
g
e
o
f
R
d
a
ta
a
n
a
ly
t
ics
so
f
twa
re
(in
c
lu
d
e
d
in
v
e
rsi
o
n
1
.
5
.
5
o
n
wa
rd
s).
Th
e
p
a
c
k
a
g
e
is
a
v
a
il
a
b
le
a
t
h
tt
p
s://
c
ra
n
.
r
-
p
ro
je
c
t.
o
rg
/
p
a
c
k
a
g
e
=
a
ru
les
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
n
th
u
v
s@
g
m
a
il
.
c
o
m
.
Ur
v
a
shi
C
h
u
g
h
is
c
u
rre
n
tl
y
wo
rk
i
n
g
a
s
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
i
n
t
h
e
KIET
g
ro
u
p
o
f
I
n
stit
u
ti
o
n
s,
G
h
a
z
iab
a
d
,
In
d
i
a
.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
D
fr
o
m
th
e
Ja
y
P
e
e
Un
i
v
e
rsity
o
f
In
fo
rm
a
ti
o
n
a
n
d
Tec
h
n
o
lo
g
y
,
Wa
k
n
a
g
h
a
t,
In
d
ia.
S
h
e
d
i
d
M
.
Tec
h
.
a
n
d
BTec
h
fro
m
M
DU
a
n
d
Ku
ru
k
s
h
e
tra
Un
iv
e
rsit
y
re
sp
e
c
ti
v
e
ly
.
He
r
a
re
a
s
o
f
in
tere
st
a
re
se
n
so
r
n
e
two
r
k
s
,
n
a
n
o
n
e
two
r
k
s
,
a
n
d
m
o
lec
u
lar
n
a
n
o
c
o
m
m
u
n
ic
a
ti
o
n
s.
S
h
e
h
a
s
v
a
ri
o
u
s
p
a
ten
ts,
a
n
d
re
se
a
rc
h
p
a
p
e
rs
in
c
o
n
fe
re
n
c
e
s a
n
d
j
o
u
r
n
a
ls
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
u
r
v
a
sh
ich
u
g
h
.
fe
t@m
riu
.
e
d
u
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.