Applied and Computational Engineering,
Год журнала:
2024,
Номер
39(1), С. 277 - 281
Опубликована: Фев. 20, 2024
Machine
learning
has
endless
application
possibilities,
with
many
algorithms
worth
in
depth.
Different
can
be
flexibly
applied
to
a
variety
of
vertical
fields,
such
as
the
most
common
neural
network
for
face
recognition,
garbage
classification,
picture
and
other
scenarios
image
recognition
computer
vision,
hottest
recent
natural
language
processing
recommendation
different
applications
are
from
it.
In
field
financial
analysis,
decision
tree
algorithm
its
derivative
random
forest
mainstream.
As
well
support
vector
machines,
naive
Bayes,
K-nearest
neighbor
algorithms,
so
on.
From
traditional
regression
algorithm.
This
paper
discusses
principle
lists
some
corresponding
applications.
Linear
regression,
trees,
supervised
learning,
etc.,
while
have
been
replaced
by
more
powerful
flexible
methods,
studying
understanding
these
foundational
depth,
models
better
designed
optimized,
how
they
work
obtained.
Remote Sensing,
Год журнала:
2025,
Номер
17(2), С. 200 - 200
Опубликована: Янв. 8, 2025
Anthropogenic
heat
is
the
generated
by
human
activities
such
as
industry,
construction,
transport,
and
metabolism.
Accurate
estimates
of
anthropogenic
are
essential
for
studying
impacts
on
climate
atmospheric
environment.
Commonly
applied
methods
estimating
include
inventory
method,
energy
balance
equation
building
model
simulation
method.
In
recent
years,
rapid
development
computer
technology
availability
massive
data
have
made
machine
learning
a
powerful
tool
fluxes
assessing
its
effects.
Multi-source
remote
sensing
also
been
widely
used
to
obtain
more
details
spatial
temporal
distribution
characteristics
heat.
This
paper
reviews
main
approaches
emissions.
The
typical
algorithms
abovementioned
three
introduced,
their
advantages
limitations
evaluated.
Moreover,
progress
in
application
discussed
well.
Based
big
techniques,
research
feature
engineering
fusion
will
bring
about
major
changes
analysis
modeling
More
in-depth
this
issue
recommended
provide
important
support
curbing
global
warming,
mitigating
air
pollution,
achieving
national
goals
carbon
peak
neutrality
strategy.
Environmental Pollution,
Год журнала:
2025,
Номер
372, С. 125993 - 125993
Опубликована: Март 14, 2025
Airborne
microplastics
(AMPs)
are
prevalent
in
both
indoor
and
outdoor
environments,
posing
potential
health
risks
to
humans.
Automating
the
process
of
spotting
them
micrographs
can
significantly
enhance
research
monitoring.
Although
deep
learning
has
shown
substantial
promise
microplastic
analysis,
existing
studies
have
primarily
focused
on
high-resolution
images
samples
collected
from
marine
freshwater
environments.
In
contrast,
this
work
introduces
a
novel
approach
by
employing
enhanced
U-Net
models
(Attention
Dynamic
RU-NEXT)
along
with
Mask
Region
Convolutional
Neural
Network
(Mask
R-CNN)
identify
classify
AMPs
lower-resolution
(256
×
256
pixels)
obtained
A
key
innovation
involves
integrating
classification
directly
within
U-Net-based
segmentation
frameworks,
thereby
streamlining
workflow
improving
computational
efficiency
which
is
an
advancement
over
previous
where
were
performed
separately.
The
attained
average
F1-scores
exceeding
85%
scores
above
77%.
Additionally,
R-CNN
model
achieved
bounding
box
precision
73.32%
test
set,
F1-score
84.29%,
mask
71.31%,
demonstrating
robust
performance.
proposed
method
provides
faster
more
accurate
means
identifying
compared
thresholding
techniques.
It
also
functions
effectively
as
pre-screening
tool,
substantially
reducing
number
particles
requiring
labour-intensive
chemical
analysis.
By
advanced
strategies
into
research,
study
paves
way
for
efficient
monitoring
characterisation
microplastics.
