Energy Science & Engineering,
Journal Year:
2024,
Volume and Issue:
12(11), P. 4932 - 4949
Published: Nov. 1, 2024
Abstract
The
mechanism
of
rock
burst
induced
by
the
superposition
dynamic
and
static
loads
in
multicoal
seam
mining
is
unique.
To
investigate
propagation
attenuation
law
large‐energy
microseismic
events
under
this
condition,
study
employs
FLAC3D's
module
to
simulate
analyze
influence
distance,
overburden
structure
mining,
interlayer
plastic
zone
on
vibration
wave
attenuation.
Results
indicate
that
when
coal
seams
are
mined
at
close
distances,
waves
experience
significant
while
passing
through
between
two
layers
coal.
At
equal
structures
exhibit
greater
effects
Considering
differences
rock‐burst
induction
mechanisms
close‐distance
group
versus
single
a
discriminant
criterion
for
bursts
superimposed
established
along
with
monitoring
early
warning
method
suitable
such
conditions.
Land,
Journal Year:
2025,
Volume and Issue:
14(1), P. 89 - 89
Published: Jan. 5, 2025
Manual
forestland
classification
methods,
which
rely
on
predetermined
scoring
criteria
and
subjective
interpretation,
are
commonly
used
but
suffer
from
limitations
such
as
high
labor
costs,
complexity,
lack
of
scalability.
This
study
proposes
an
innovative
machine
learning-based
approach
to
classification,
utilizing
a
Support
Vector
Machine
(SVM)
model
automate
the
process
enhance
both
efficiency
accuracy.
The
main
contributions
this
work
follows:
A
learning
was
developed
using
integrated
data
Third
National
Land
Survey
China,
including
forestry,
grassland,
wetland
datasets.
Unlike
previous
approaches,
SVM
is
optimized
with
Grid
Search
(GS),
Genetic
Algorithm
(GA),
Particle
Swarm
Optimization
(PSO)
automatically
determine
parameters,
overcoming
manual
rule-based
methods.
performance
evaluated
confusion
matrices,
accuracy,
Matthews
Correlation
Coefficient
(MCC).
comprehensive
comparison
under
different
optimization
techniques
revealed
significant
improvements
in
accuracy
generalization
ability
over
systems.
experimental
results
demonstrated
that
GA-SVM
achieved
accuracies
98.83%
(test
set)
99.65%
(overall
sample),
MCC
values
0.9796
0.990,
respectively,
outpacing
other
algorithms,
(GS)
(PSO).
applied
classify
public
welfare
Kunyu
City,
yielding
detailed
classifications
across
various
categories.
result
provides
more
efficient
accurate
method
for
large-scale
management,
implications
future
land
use
assessments.
findings
underscore
advantages
classification:
it
efficient,
accurate,
easy
operate.
not
only
presents
reliable
alternative
conventional
methods
also
sets
precedent
optimize
applications.
Applied Sciences,
Journal Year:
2025,
Volume and Issue:
15(3), P. 1343 - 1343
Published: Jan. 27, 2025
The
challenge
in
reusing
high-impact
recorders
lies
developing
an
efficient
and
accurate
failure
prediction
model
under
small-sample
conditions.
To
address
this
issue,
study
proposes
IPSO-SVM
model.
First,
the
particle
swarms
IPSO
algorithm
were
grouped
based
on
their
exploration
exploitation
functions,
dynamic
inertia
weight
mechanisms
designed
accordingly.
grouping
ratio
was
dynamically
adjusted
during
iterations
to
enhance
optimization
performance.
Tests
using
benchmark
functions
verified
that
approach
improves
convergence
accuracy
stability
compared
conventional
PSO
algorithms.
Subsequently,
5-fold
cross-validation
of
SVM
used
as
fitness
value,
employed
optimize
penalty
kernel
parameters
Trained
experimental
data,
achieved
a
90.5%,
outperforming
PSO-SVM
model’s
85%.
These
results
demonstrate
potential
addressing
challenges
Applied Sciences,
Journal Year:
2025,
Volume and Issue:
15(8), P. 4127 - 4127
Published: April 9, 2025
This
paper
proposes
a
cloud-edge
collaborative
method
for
operational
situation
assessment
to
ensure
the
efficient
and
reliable
operation
of
space-based
information
networks.
By
analyzing
time-varying
network
topology
characteristics,
we
establish
14-dimensional
factor
system
that
can
characterize
Considering
resource
constraints
satellites,
traditional
on-orbit
methods
often
lead
high
latency
excessive
consumption.
A
is
introduced
enhance
efficiency.
The
proposed
first
applies
principal
component
analysis
dimensionality
reduction,
followed
by
pre-labeling
situational
data
using
an
improved
K-means
clustering
algorithm.
individual
satellites
then
performed
particle
swarm
optimization-support
vector
machine
Finally,
fusion
networks
conducted
at
ground
cloud
center,
incorporating
weighting
factors.
Experimental
results
demonstrate
improves
accuracy
13%
compared
baseline
methods,
significantly
reduces
average
completion
time,
maintains
stable
performance
in
large-scale
satellite
constellations.
Physics of Fluids,
Journal Year:
2025,
Volume and Issue:
37(5)
Published: May 1, 2025
Geological
disasters
such
as
instability
of
surrounding
rock
are
prone
to
occur
in
seepage
environment
during
tunnel
construction,
which
will
not
only
affect
the
construction
progress
but
also
seriously
threaten
lives
workers.
Establishing
intelligent
early
warning
methods
for
disaster
risks
is
great
significance
safe
engineering.
This
paper
proposes
an
indicator
system
rocks
that
covers
geological
information,
geophysical
drilling
and
physical-field
monitoring
information
face.
Second,
model
proposed
based
on
PSO
(particle
swarm
optimization
algorithm)-SVM
(support
vector
machine
algorithm),
realizes
accurate
environment.
Third,
developed.
method
successfully
applied
Haidong
Tunnel
Dali
Section
II
Dianzhong
Water-Diversion
Project,
proving
effectiveness
practicality
method.
