Image
classification
poses
a
significant
challenge
in
agriculture.
However,
the
utilization
of
popular
algorithms
such
as
vision
transformers
and
convolutional
neural
networks
has
often
fallen
short
numerous
agricultural
tasks
owing
to
scarcity
extensively
labelled
data
reliance
on
pretrained
models
trained
generic
datasets.
To
address
this,
our
study
details
pretraining
ViTs
using
224,228
images,
employing
masked
image
modeling
for
preprocessing.
The
model
was
then
fine-tuned
three
independent
datasets
performed
better
than
state-of-the-art
methods.
For
example,
method
achieved
highest
accuracy
rates
76.18%,
98.49%,
88.56%
IP102,
DeepWeeds,
Tsinghua
Dogs
datasets,
respectively.
This
enhancement
can
be
attributed
robust
strategy
we
have
developed
through
extensive
experimentation
with
MIM
model.
Our
encompasses
advanced
models,
leveraging
histogram
oriented
gradient
features
reconstruction
target,
selecting
an
appropriate
mask
ratio.
We
hope
that
this
research
will
prompt
application
self-supervised
learning
techniques,
represented
by
model,
wide
range
image-related
future.
IntechOpen eBooks,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Feb. 24, 2025
Ensuring
the
reliability,
safety,
and
efficiency
of
electric
vehicles
(EVs)
necessitates
precise
diagnostics
battery
life,
as
degradation
batteries
directly
influences
both
performance
sustainability.
The
transformative
role
artificial
intelligence
(AI)
in
advancing
EV
is
explored
herein,
with
an
emphasis
placed
on
complexities
predicting
managing
health.
Initially,
we
provide
overview
challenges
associated
lifetime
diagnostics,
such
issues
accuracy,
generalization,
model
training.
following
sections
delve
into
advanced
AI
methodologies
that
enhance
diagnostic
capabilities.
These
methods
include
extensive
time-series
AI,
which
improves
predictive
accuracy;
end-to-end
simplifies
system
complexity;
multi-model
ensures
generalization
across
varied
operating
conditions;
adaptable
strategies
for
dynamic
environments.
In
addition,
explore
use
federated
learning
decentralized,
privacy-preserving
discuss
automated
machine
streamlining
development
AI-based
models.
By
integrating
these
sophisticated
techniques,
present
a
comprehensive
roadmap
future
AI-driven
prognostics
health
management.
This
underscores
critical
importance
scalability,
sustainability
fostering
advancement.
Our
interdisciplinary
framework
offers
valuable
insights
can
accelerate
electrification
transportation
advance
evolution
energy
storage
systems,
tackling
key
at
intersection
technology
AI.
Mathematics,
Journal Year:
2025,
Volume and Issue:
13(5), P. 887 - 887
Published: March 6, 2025
DeepFake
detection
models
play
a
crucial
role
in
ambient
intelligence
and
smart
environments,
where
systems
rely
on
authentic
information
for
accurate
decisions.
These
integrating
interconnected
IoT
devices
AI-driven
systems,
face
significant
threats
from
DeepFakes,
potentially
leading
to
compromised
trust,
erroneous
decisions,
security
breaches.
To
mitigate
these
risks,
neural-network-based
have
been
developed.
However,
their
substantial
computational
requirements
long
training
times
hinder
deployment
resource-constrained
edge
devices.
This
paper
investigates
compression
transfer
learning
techniques
reduce
the
demands
of
deploying
models,
while
preserving
performance.
Pruning,
knowledge
distillation,
quantization,
adapter
modules
are
explored
enable
efficient
real-time
detection.
An
evaluation
was
conducted
four
benchmark
datasets:
“SynthBuster”,
“140k
Real
Fake
Faces”,
“DeepFake
Images”,
“ForenSynths”.
It
compared
compressed
with
uncompressed
baselines
using
widely
recognized
metrics
such
as
accuracy,
precision,
recall,
F1-score,
model
size,
time.
The
results
showed
that
at
10%
original
size
retained
only
56%
baseline
but
fine-tuning
similar
scenarios
increased
this
nearly
98%.
In
some
cases,
accuracy
even
surpassed
original’s
performance
by
up
12%.
findings
highlight
feasibility
computing
scenarios.
