PeerJ Computer Science,
Год журнала:
2024,
Номер
10, С. e2407 - e2407
Опубликована: Ноя. 27, 2024
Wireless
Sensor
Networks
(WSNs)
have
paved
the
way
for
a
wide
array
of
applications,
forming
backbone
systems
like
smart
cities.
These
support
various
functions,
including
healthcare,
environmental
monitoring,
traffic
management,
and
infrastructure
monitoring.
WSNs
consist
multiple
interconnected
sensor
nodes
base
station,
creating
network
whose
performance
is
heavily
influenced
by
placement
nodes.
Proper
deployment
crucial
as
it
maximizes
coverage
minimizes
unnecessary
energy
consumption.
Ensuring
effective
node
optimal
efficiency
remains
significant
research
gap
in
WSNs.
This
review
article
focuses
on
optimization
strategies
WSN
deployment,
addressing
key
questions
related
to
maximization
energy-efficient
algorithms.
A
common
limitation
existing
single-objective
algorithms
their
focus
optimizing
either
or
efficiency,
but
not
both.
To
address
this,
explores
dual-objective
approach,
formulated
maximizing
Max
∑(i
=
1)
^
N
C
i
minimizing
consumption
Min
E
nodes,
balance
both
objectives.
The
analyses
recent
evaluates
performance,
provides
comprehensive
comparative
analysis,
offering
directions
future
making
unique
contribution
literature.
IEEE Access,
Год журнала:
2024,
Номер
12, С. 109128 - 109156
Опубликована: Янв. 1, 2024
Wheat
is
one
of
the
most
extensively
cultivated
crops
worldwide
that
contributes
significantly
to
global
food
caloric
and
protein
production
grown
on
millions
hectares
yearly.
However,
diseases
like
brown
rust,
septoria,
yellow
other
fungus
pose
notable
threats
wheat
crops,
impacting
quality.
Diagnosing
these
challenging,
especially
in
areas
with
limited
agricultural
experts.
Thus,
creating
computerized
disease
identification
decision-support
technologies
crucial
for
safeguarding
leaf
preservation
crop
loss
mitigation.
The
traditional
approach
integrating
data
gathering
model
training
has
substantial
challenges
terms
confidentiality,
availability,
costs
related
transmission.
To
address
challenges,
federated
learning
(FL)
an
appealing
effective
option.
Our
study
focuses
applying
FL
classify
using
image
analysis.
In
our
study,
we
conduct
experiments
high-parameterized
transfer
(TL)
models
along
proposed
architecture
based
attention
mechanism,
introducing
into
a
distributed
strategy
founded
FL.
leverages
beneficial
interactions
two
cutting-edge
vision
transformer
including
advanced
depthwise
incorporating
self-attention
referred
as
CoAtNets,
enhanced
Swin
Transformer
V2,
resulting
feature
representation.
Moreover,
introduce
weight
pruning
which
further
classified
by
reinforced
linear
mechanism
(LA)
lower
output
dimensions.
pruned
lightweight
(32M
parameters)
considerably
decreases
inference
time
624.249
ms
644.899
devices
low
computational
power,
making
it
highly
efficient
FL-based
systems.
system
outperforms
all
tested
models,
ConvNeXtBase,
ConvNeXtLarge,
EfficientNetV2L,
InceptionResNetV2,
ResNet152,
NASNetLarge,
achieving
accuracies
up
98%
99%,
precision
98%,
recall
F-1
scores
95%
across
multiple
input
dimensions
classification.
Future Internet,
Год журнала:
2024,
Номер
16(10), С. 365 - 365
Опубликована: Окт. 7, 2024
The
evolution
of
network
technologies
has
significantly
transformed
global
communication,
information
sharing,
and
connectivity.
Traditional
networks,
relying
on
static
configurations
manual
interventions,
face
substantial
challenges
such
as
complex
management,
inefficiency,
susceptibility
to
human
error.
rise
artificial
intelligence
(AI)
begun
address
these
issues
by
automating
tasks
like
configuration,
traffic
optimization,
security
enhancements.
Despite
their
potential,
integrating
AI
models
in
engineering
encounters
practical
obstacles
including
configurations,
heterogeneous
infrastructure,
unstructured
data,
dynamic
environments.
Generative
AI,
particularly
large
language
(LLMs),
represents
a
promising
advancement
with
capabilities
extending
natural
processing
translation,
summarization,
sentiment
analysis.
This
paper
aims
provide
comprehensive
review
exploring
the
transformative
role
LLMs
modern
engineering.
In
particular,
it
addresses
gaps
existing
literature
focusing
LLM
applications
design
planning,
implementation,
analytics,
management.
It
also
discusses
current
research
efforts,
challenges,
future
opportunities,
aiming
guide
for
networking
professionals
researchers.
main
goal
is
facilitate
adoption
networking,
promoting
more
efficient,
resilient,
intelligent
systems.
