Media Elektro,
Год журнала:
2023,
Номер
unknown, С. 111 - 119
Опубликована: Окт. 30, 2023
Untuk
memberikan
informasi
penyebaran
kasus
Covid-19,
Pemerintah
Kota
Kupang,
Provinsi
Nusa
Tenggara
Timur,
telah
membuat
peta
Covid-19
melalui
website
pemerintah
Kota.
Namun,
seperti
kebanyakan
terkait
tersebut
hanya
jumlah
harian.
Informasi
kelurahan
yang
berisiko
terjadi
lonjakan
atau
berpotensi
menyebarkan
ke
lain
belum
terdata
di
laman
web
tersebut.
Oleh
karena
itu,
penelitian
ini
bertujuan
untuk
gambaran
teknik
analisis
sehingga
menghasilkan
lebih
detail
mengenai
pola
penularannya.
Penelitian
menggunakan
Graph
Signal
Processing
(GSP)
menganalisis
berdasarkan
struktur
graph
menghubungkan
51
kecamatan
Kupang.
Berbeda
dengan
metode
data
analysis
lain,
GSP
mampu
mempertimbangkan
relasi
antara
objek,
dalam
hal
jarak
antar
kelurahan.
Data
digunakan
adalah
tercatat
pada
tanggal
6
bulan
Maret
tahun
2021.
Hasil
menunjukkan
bahwa
dapat
mengidentifikasi
tinggi
mengalami
kasus,
yaitu
Nunleu
dan
menjadi
sumber
outbreaks
Airnona.
IEEE Transactions on Signal Processing,
Год журнала:
2024,
Номер
72, С. 4745 - 4781
Опубликована: Янв. 1, 2024
Filters
are
fundamental
in
extracting
information
from
data.
For
time
series
and
image
data
that
reside
on
Euclidean
domains,
filters
the
crux
of
many
signal
processing
machine
learning
techniques,
including
convolutional
neural
networks.
Increasingly,
modern
also
networks
other
irregular
domains
whose
structure
is
better
captured
by
a
graph.
To
process
learn
such
data,
graph
account
for
underlying
domain.
In
this
article,
we
provide
comprehensive
overview
filters,
different
filtering
categories,
design
strategies
each
type,
trade-offs
between
types
filters.
We
discuss
how
to
extend
into
filter
banks
enhance
representational
power;
is,
model
broader
variety
classes,
patterns,
relationships.
showcase
role
applications.
Our
aim
article
provides
unifying
framework
both
beginner
experienced
researchers,
as
well
common
understanding
promotes
collaborations
at
intersections
processing,
learning,
application
domains.
Water Research,
Год журнала:
2024,
Номер
261, С. 121933 - 121933
Опубликована: Июнь 20, 2024
Data-driven
metamodels
reproduce
the
input-output
mapping
of
physics-based
models
while
significantly
reducing
simulation
times.
Such
techniques
are
widely
used
in
design,
control,
and
optimization
water
distribution
systems.
Recent
research
highlights
potential
based
on
Graph
Neural
Networks
as
they
efficiently
leverage
graph-structured
characteristics
Furthermore,
these
possess
inductive
biases
that
facilitate
generalization
to
unseen
topologies.
Transferable
particularly
advantageous
for
problems
require
an
efficient
evaluation
many
alternative
layouts
or
when
training
data
is
scarce.
However,
transferability
GNNs
remains
limited,
due
lack
representation
physical
processes
occur
edge
level,
i.e.
pipes.
To
address
this
limitation,
our
work
introduces
Edge-Based
Networks,
which
extend
set
represent
link-level
more
detail
than
traditional
Networks.
architecture
theoretically
related
constraints
mass
conservation
at
junctions.
verify
approach,
we
test
suitability
edge-based
network
estimate
pipe
flowrates
nodal
pressures
emulating
steady-state
EPANET
simulations.
We
first
compare
effectiveness
several
benchmark
systems
against
Then,
explore
by
evaluating
performance
For
each
configuration,
calculate
model
metrics,
such
coefficient
determination
speed-up
with
respect
original
numerical
model.
Our
results
show
proposed
method
captures
pipe-level
accurately
node-based
models.
When
tested
networks
a
similar
demands,
retains
good
up
0.98
0.95
predicted
heads.
Further
developments
could
include
simultaneous
derivation
flowrates.
ACM Transactions on Sensor Networks,
Год журнала:
2024,
Номер
20(6), С. 1 - 32
Опубликована: Окт. 18, 2024
Water
scarcity
is
nowadays
a
critical
global
concern
and
an
efficient
management
of
water
resources
paramount.
This
paper
presents
original
approach
for
monitoring
Distribution
Systems
(WDSs)
through
Internet
Things
(IoT)
that
involves
the
integration
multiple
sensors
placed
across
distribution
network
to
accurately
measure
flow.
To
enhance
energy
efficiency
green
communication
process,
we
harness
power
graph
theory
signal
processing
represent
in
tunable
accurate
way
flow
simultaneously
minimize
number
IoT
communicating
those
measurements.
We
propose
model
where
represented
as
on
introduce
algorithm,
named
GraphSmart,
designed
reconstruct
when
certain
measurements
are
unknown
or
missing.
Our
framework
applied
synthetic
realistic
environment
within
context
LoRaWAN
(Long
Range
Wide
Area
Network),
infrastructure
protocol
ultra-low-power
devices.
findings
show
GraphSmart
significantly
reduces
consumption
while
ensuring
precise
estimation.
research
demonstrates
high
potential
energy-efficient
monitoring,
paving
improve
WDSs
enabling
operators
address
challenges.