Electronics,
Год журнала:
2025,
Номер
14(5), С. 1040 - 1040
Опубликована: Март 5, 2025
The
state
monitoring
of
power
load
equipment
plays
a
crucial
role
in
ensuring
its
normal
operation.
However,
densely
deployed
environments,
the
target
often
exhibits
low
clarity,
making
real-time
warnings
challenging.
In
this
study,
segmentation
and
assessment
method
based
on
multi-source
tensor
feature
fusion
(LSA-MT)
is
proposed.
First,
lightweight
residual
block
attention
mechanism
introduced
into
backbone
network
to
emphasize
key
features
devices
enhance
efficiency.
Second,
3D
edge
detail
perception
module
designed
facilitate
multi-scale
while
preserving
boundary
different
devices,
thereby
improving
local
recognition
accuracy.
Finally,
decomposition
reorganization
are
employed
guide
visual
reconstruction
conjunction
with
images,
mapping
data
utilized
for
automated
fault
classification.
experimental
results
demonstrate
that
LSE-MT
produces
visually
clearer
segmentations
compared
models
such
as
classic
UNet++
more
recent
EGE-UNet
when
segmenting
multiple
achieving
Dice
mIoU
scores
92.48
92.90,
respectively.
Regarding
classification
across
four
datasets,
average
accuracy
can
reach
92.92%.
These
findings
fully
effectiveness
LSA-MT
alarms
grid
operation
maintenance.
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Янв. 3, 2025
Due
to
the
low
contrast
of
abdominal
CT
(Computer
Tomography)
images
and
similar
color
shape
liver
other
organs
such
as
spleen,
stomach,
kidneys,
segmentation
presents
significant
challenges.
Additionally,
2D
obtained
from
different
angles
(such
sagittal,
coronal,
transverse
planes)
increase
diversity
morphology
complexity
segmentation.
To
address
these
issues,
this
paper
proposes
a
Detail
Enhanced
Convolution
(DE
Conv)
improve
feature
learning
thereby
enhance
performance.
Furthermore,
enable
model
better
learn
features
at
scales,
Multi-Scale
Feature
Fusion
module
(MSFF)
is
added
skip
connections
in
model.
The
MSFF
enhances
capture
global
features,
thus
improving
accuracy
Through
aforementioned
research,
network
based
on
detail
enhancement
multi-scale
fusion
(DEMF-Net).
We
conducted
extensive
experiments
LiTS17
dataset,
results
demonstrate
that
DEMF-Net
achieved
improvements
across
various
evaluation
metrics.
Therefore,
proposed
can
achieve
precise
IEEE Transactions on Geoscience and Remote Sensing,
Год журнала:
2023,
Номер
61, С. 1 - 15
Опубликована: Янв. 1, 2023
Current
methods
for
remote
sensing
image
dehazing
confront
noteworthy
computational
intricacies
and
yield
suboptimal
dehazed
outputs,
thereby
circumscribing
their
pragmatic
applicability.
To
this
end,
we
propose
EMPF-Net,
a
novel
encoder-free
multi-axis
physics-aware
fusion
network
that
exhibits
both
light-weighted
characteristics
efficiency.
In
our
pipeline,
contend
conventional
u-shaped
networks
allocate
substantial
resources
to
encode
haze-degraded
features,
which
play
subordinate
role
in
the
reconstruction
process.
Consequently,
encoder
stages
solely
incorporate
down-sampling
operations.
improve
representation
efficiency
enhance
generalization
capabilities,
devise
partial
queried
learning
block
(MPQLB)
primarily
concentrates
on
dimension-wise
queries,
instead
of
relying
strictly-correlated
content
input
features.
Furthermore,
augment
procedure
by
incorporating
ground
truth
supervision
into
each
stage
via
supervised
cross-scale
transposed
attention
module
(SCTAM).
It
calculates
maps
under
guidance
clean
images,
suppressing
less
informative
features
propagate
subsequent
level.
addition,
address
challenge
ineffective
intral-level
feature
fusion,
result
insufficient
elimination
information
negatively
impact
quality
reconstructed
introduce
intra-level
(PIFM).
This
harnesses
physical
inversion
model
facilitate
interaction
alleviate
interference
dehazing-irrelevant
information.
Our
proposed
EMPF-Net
is
evaluated
12
publicly
available
datasets,
experimental
results
substantiate
superiority
terms
metrical
scores
visual
quality,
despite
being
equipped
with
modest
parameter
count
300
K.
approach
readily
accessible
at
https://github.com/chdwyb/EMPF-Net.
Proceedings of the AAAI Conference on Artificial Intelligence,
Год журнала:
2024,
Номер
38(4), С. 3819 - 3827
Опубликована: Март 24, 2024
Medical
image
segmentation
methods
based
on
deep
learning
network
are
mainly
divided
into
CNN
and
Transformer.
However,
struggles
to
capture
long-distance
dependencies,
while
Transformer
suffers
from
high
computational
complexity
poor
local
feature
learning.
To
efficiently
extract
fuse
features
long-range
this
paper
proposes
Rolling-Unet,
which
is
a
model
combined
with
MLP.
Specifically,
we
propose
the
core
R-MLP
module,
responsible
for
dependency
in
single
direction
of
whole
image.
By
controlling
combining
modules
different
directions,
OR-MLP
DOR-MLP
formed
dependencies
multiple
directions.
Further,
Lo2
block
proposed
encode
both
context
information
without
excessive
burden.
has
same
parameter
size
as
3×3
convolution.
The
experimental
results
four
public
datasets
show
that
Rolling-Unet
achieves
superior
performance
compared
state-of-the-art
methods.
IET Image Processing,
Год журнала:
2024,
Номер
unknown
Опубликована: Сен. 2, 2024
Abstract
Melanoma,
a
highly
prevalent
and
lethal
form
of
skin
cancer,
has
significant
impact
globally.
The
chances
recovery
for
melanoma
patients
substantially
improve
with
early
detection.
Currently,
deep
learning
(DL)
methods
are
gaining
popularity
in
assisting
the
identification
melanoma.
Despite
their
high
performance,
relying
solely
on
an
image
classifier
undermines
credibility
application
makes
it
difficult
to
understand
rationale
behind
model's
predictions
highlighting
need
Explainable
AI
(XAI).
This
study
provides
survey
cancer
using
DL
techniques
utilized
studies
from
2017
2024.
Compared
existing
studies,
authors
address
latest
related
covering
several
public
datasets
focusing
segmentation,
classification
based
convolutional
neural
networks
vision
transformers,
explainability.
analysis
comparisons
will
be
beneficial
researchers
developers
this
area,
identify
suitable
used
automated
classification.
Thereby,
findings
can
implement
support
applications
advancing
diagnosis
process.
Sensors,
Год журнала:
2024,
Номер
24(23), С. 7473 - 7473
Опубликована: Ноя. 23, 2024
Accurate
polyp
image
segmentation
is
of
great
significance,
because
it
can
help
in
the
detection
polyps.
Convolutional
neural
network
(CNN)
a
common
automatic
method,
but
its
main
disadvantage
long
training
time.
Transformer
another
method
that
be
adapted
to
by
employing
self-attention
mechanism,
which
essentially
assigns
different
importance
weights
each
piece
information,
thus
achieving
high
computational
efficiency
during
segmentation.
However,
potential
drawback
with
risk
information
loss.
The
study
reported
this
paper
employed
well-known
hybridization
principle
propose
combine
CNN
and
retain
strengths
both.
Specifically,
applied
early
colonic
polyps
implement
model
called
MugenNet
for
We
conducted
comprehensive
experiment
compare
other
models
on
five
publicly
available
datasets.
An
ablation
was
as
well.
experimental
results
showed
achieve
mean
Dice
0.714
ETIS
dataset,
optimal
performance
dataset
compared
models,
an
inference
speed
56
FPS.
overall
outcome
optimally
two
methods
machine
learning
are
complementary
other.
Remote Sensing,
Год журнала:
2025,
Номер
17(5), С. 760 - 760
Опубликована: Фев. 22, 2025
Arable
land
is
fundamental
to
agricultural
production
and
a
crucial
component
of
ecosystems.
However,
its
complex
texture
distribution
in
remote
sensing
images
make
it
susceptible
interference
from
other
cover
types,
such
as
water
bodies,
roads,
buildings,
complicating
accurate
identification.
Building
on
previous
research,
this
study
proposes
an
efficient
lightweight
CNN-based
network,
U-MGA,
address
the
challenges
feature
similarity
between
arable
non-arable
areas,
insufficient
fine-grained
extraction,
underutilization
multi-scale
information.
Specifically,
Multi-Scale
Adaptive
Segmentation
(MSAS)
designed
during
extraction
phase
provide
multi-feature
information,
supporting
model’s
reconstruction
stage.
In
phase,
introduction
Contextual
Module
(MCM)
Group
Aggregation
Bridge
(GAB)
significantly
enhances
efficiency
accuracy
utilization.
The
experiments
conducted
dataset
based
GF-2
imagery
publicly
available
show
that
U-MGA
outperforms
mainstream
networks
(Unet,
A2FPN,
Segformer,
FTUnetformer,
DCSwin,
TransUnet)
across
six
evaluation
metrics
(Overall
Accuracy
(OA),
Precision,
Recall,
F1-score,
Intersection-over-Union
(IoU),
Kappa
coefficient).
Thus,
provides
precise
solution
for
recognition
task,
which
significant
importance
resource
monitoring
ecological
environmental
protection.