ACM Transactions on Internet of Things,
Год журнала:
2024,
Номер
5(4), С. 1 - 25
Опубликована: Окт. 14, 2024
The
development
of
the
Digital
Twin
(DT)
approach
is
tilting
research
from
initial
approaches
that
aim
at
promoting
early
adoption
to
sophisticated
attempts
develop,
deploy,
and
maintain
applications
based
on
DTs.
In
this
context,
we
propose
a
highly
dynamic
distributed
ecosystem
where
containerized
DTs
co-evolve
with
an
orchestration
middleware.
provide
digitalized
representations
targeted
physical
systems,
while
middleware
monitors
re-configures
deployed
in
light
application
constraints,
available
resources,
quality
cyber-physical
entanglement.
First,
lay
out
reference
scenario.
Then,
discuss
limitations
current
identify
set
requirements
shape
both
Subsequently,
describe
blueprint
architecture
meets
those
requirements.
Finally,
report
empirical
evidence
feasibility
effectiveness
proof-of-concept
implementation
proposed
ecosystem.
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Май 27, 2024
Abstract
The
term
“Internet
of
Things”
(IoT)
refers
to
a
system
networked
computing
devices
that
may
work
and
communicate
with
one
another
without
direct
human
intervention.
It
is
the
most
exciting
areas
nowadays,
its
applications
in
multiple
sectors
like
cities,
homes,
wearable
equipment,
critical
infrastructure,
hospitals,
transportation.
security
issues
surrounding
IoT
increase
as
they
expand.
To
address
these
issues,
this
study
presents
novel
model
for
enhancing
systems
using
machine
learning
(ML)
classifiers.
proposed
approach
analyzes
recent
technologies,
security,
intelligent
solutions,
vulnerabilities
ML
IoT-based
an
essential
technology
improve
security.
illustrates
benefits
limitations
applying
environment
provides
based
on
manages
autonomously
rising
number
related
domain.
paper
proposes
ML-based
handles
growing
associated
This
research
made
significant
contribution
by
developing
cyberattack
detection
solution
ML.
used
seven
algorithms
identify
accurate
classifiers
their
AI-based
reaction
agent’s
implementation
phase,
which
can
attack
activities
patterns
networks
connected
IoT.
Compared
previous
research,
achieved
99.9%
accuracy,
99.8%
average,
99.9
F1
score,
perfect
AUC
score
1.
highlights
outperforms
earlier
learning-based
models
terms
both
execution
speed
accuracy.
suggested
time
