Electronics,
Год журнала:
2024,
Номер
14(1), С. 24 - 24
Опубликована: Дек. 25, 2024
This
study
presents
a
predictive
maintenance
system
designed
for
industrial
Internet
of
Things
(IoT)
environments,
focusing
on
resource
efficiency
and
adaptability.
The
utilizes
Nicla
Sense
ME
sensors,
Raspberry
Pi-based
concentrator
real-time
monitoring,
Long
Short-Term
Memory
(LSTM)
machine-learning
model
analysis.
Notably,
the
LSTM
algorithm
is
an
example
how
system’s
sandbox
environment
can
be
used,
allowing
external
users
to
easily
integrate
custom
models
without
altering
core
platform.
In
laboratory,
achieved
Root
Mean
Squared
Error
(RMSE)
0.0156,
with
high
accuracy
across
all
detecting
intentional
anomalies
99.81%
rate.
real-world
phase,
maintained
robust
performance,
sensors
recording
maximum
Absolute
(MAE)
0.1821,
R-squared
value
0.8898,
Percentage
(MAPE)
0.72%,
demonstrating
precision
even
in
presence
environmental
interferences.
Additionally,
architecture
supports
scalability,
accommodating
up
64
sensor
nodes
compromising
performance.
enhances
platform’s
versatility,
enabling
customization
diverse
applications.
results
highlight
significant
benefits
contexts,
including
reduced
downtime,
optimized
use,
improved
operational
efficiency.
These
findings
underscore
potential
integrating
Artificial
Intelligence
(AI)
driven
into
constrained
offering
reliable
solution
dynamic,
operations.
Applied Sciences,
Год журнала:
2024,
Номер
14(21), С. 9848 - 9848
Опубликована: Окт. 28, 2024
The
adoption
and
use
of
the
Internet
Things
(IoT)
have
increased
rapidly
over
recent
years,
cyber
threats
in
IoT
devices
also
become
more
common.
Thus,
development
a
system
that
can
effectively
identify
malicious
attacks
reduce
security
has
topic
great
importance.
One
most
serious
comes
from
botnets,
which
commonly
attack
by
interrupting
networks
required
for
to
run.
There
are
number
methods
be
used
improve
identifying
unknown
patterns
networks,
including
deep
learning
machine
approaches.
In
this
study,
an
algorithm
named
genetic
with
hybrid
learning-based
anomaly
detection
(GA-HDLAD)
is
developed,
aim
improving
botnets
within
environment.
GA-HDLAD
technique
addresses
problem
high
dimensionality
using
during
feature
selection.
Hybrid
detect
botnets;
approach
combination
recurrent
neural
(RNNs),
extraction
techniques
(FETs),
attention
concepts.
Botnet
involve
complex
(HDL)
method
detect.
Moreover,
FETs
model
ensures
features
extracted
spatial
data,
while
temporal
dependencies
captured
RNNs.
Simulated
annealing
(SA)
utilized
select
hyperparameters
necessary
HDL
approach.
experimentally
assessed
benchmark
botnet
dataset,
findings
reveal
provides
superior
results
comparison
existing
methods.
World Journal of Advanced Engineering Technology and Sciences,
Год журнала:
2024,
Номер
11(2), С. 454 - 475
Опубликована: Апрель 18, 2024
The
TCP/IP
protocol
suite,
a
cornerstone
of
modern
networking,
faces
escalating
threats
from
evolving
attack
vectors
targeting
its
headers.
This
survey
explores
emerging
trends
in
header
attacks,
assessing
their
potential
impact
and
outlining
future
directions
for
defense
strategies.
By
scrutinizing
recent
research
real-world
incidents,
the
paper
aims
to
offer
insights
into
threat
landscape
provide
recommendations
enhancing
network
security.
Key
areas
investigation
include
historical
evolution
vulnerabilities,
adaptation
attackers'
techniques
over
time,
development
novel
mechanisms
counteract
these
threats.
underscores
critical
importance
understanding
attacks
contemporary
cybersecurity
highlights
necessity
proactive
measures
safeguard
infrastructures.
addressing
challenges
posed
by
identifying
further
development,
this
contributes
ongoing
efforts
strengthen
defenses
mitigate
risks
associated
with
cyber
protocols.
Electronics,
Год журнала:
2024,
Номер
14(1), С. 24 - 24
Опубликована: Дек. 25, 2024
This
study
presents
a
predictive
maintenance
system
designed
for
industrial
Internet
of
Things
(IoT)
environments,
focusing
on
resource
efficiency
and
adaptability.
The
utilizes
Nicla
Sense
ME
sensors,
Raspberry
Pi-based
concentrator
real-time
monitoring,
Long
Short-Term
Memory
(LSTM)
machine-learning
model
analysis.
Notably,
the
LSTM
algorithm
is
an
example
how
system’s
sandbox
environment
can
be
used,
allowing
external
users
to
easily
integrate
custom
models
without
altering
core
platform.
In
laboratory,
achieved
Root
Mean
Squared
Error
(RMSE)
0.0156,
with
high
accuracy
across
all
detecting
intentional
anomalies
99.81%
rate.
real-world
phase,
maintained
robust
performance,
sensors
recording
maximum
Absolute
(MAE)
0.1821,
R-squared
value
0.8898,
Percentage
(MAPE)
0.72%,
demonstrating
precision
even
in
presence
environmental
interferences.
Additionally,
architecture
supports
scalability,
accommodating
up
64
sensor
nodes
compromising
performance.
enhances
platform’s
versatility,
enabling
customization
diverse
applications.
results
highlight
significant
benefits
contexts,
including
reduced
downtime,
optimized
use,
improved
operational
efficiency.
These
findings
underscore
potential
integrating
Artificial
Intelligence
(AI)
driven
into
constrained
offering
reliable
solution
dynamic,
operations.
