Frontiers in Public Health,
Journal Year:
2023,
Volume and Issue:
11
Published: Jan. 24, 2023
Pillar
stability
is
an
important
condition
for
safe
work
in
room-and-pillar
mines.
The
instability
of
pillars
will
lead
to
large-scale
collapse
hazards,
and
the
accurate
estimation
induced
stresses
at
different
positions
pillar
helpful
design
guaranteeing
stability.
There
are
many
modeling
methods
evaluate
their
stability,
including
empirical
numerical
method.
However,
difficult
be
applied
places
other
than
original
environmental
characteristics,
often
simplify
boundary
conditions
material
properties,
which
cannot
guarantee
design.
Currently,
machine
learning
(ML)
algorithms
have
been
successfully
assessment
with
higher
accuracy.
Thus,
study
adopted
a
back-propagation
neural
network
(BPNN)
five
elements
sparrow
search
algorithm
(SSA),
gray
wolf
optimizer
(GWO),
butterfly
optimization
(BOA),
tunicate
swarm
(TSA),
multi-verse
(MVO).
Combining
metaheuristic
algorithms,
hybrid
models
were
developed
predict
stress
within
pillar.
weight
threshold
BPNN
model
optimized
by
mean
absolute
error
(MAE)
utilized
as
fitness
function.
A
database
containing
149
data
samples
was
established,
where
input
variables
angle
goafline
(A),
depth
working
coal
seam
(H),
specific
gravity
(G),
distance
point
from
center
(C),
(D),
output
variable
stress.
Furthermore,
predictive
performance
proposed
evaluated
metrics,
namely
coefficient
determination
(R
2
),
root
squared
(RMSE),
variance
accounted
(VAF),
(MAE),
percentage
(MAPE).
results
showed
that
good
prediction
performance,
especially
GWO-BPNN
performed
best
(Training
set:
R
=
0.9991,
RMSE
0.1535,
VAF
99.91,
MAE
0.0884,
MAPE
0.6107;
Test
0.9983,
0.1783,
99.83,
0.1230,
0.9253).
Underground Space,
Journal Year:
2023,
Volume and Issue:
14, P. 70 - 98
Published: July 22, 2023
The
technical
challenges
associated
with
deep
underground
space
activities
have
become
increasingly
significant.
Among
these
challenges,
one
major
concern
is
the
assessment
of
rockburst
risks
and
instability
rock
masses.
Extensive
research
has
been
conducted
by
numerous
scholars
to
mitigate
prevent
occurrences
through
various
methods.
Rockburst
incidents
commonly
occur
during
excavation
hard
in
environments,
posing
severe
threats
personnel
safety,
equipment
integrity,
operational
continuity.
Thus,
it
crucial
systematically
document
real
cases
rockburst,
allowing
for
a
comprehensive
understanding
underlying
mechanisms
triggering
conditions.
This
will
contribute
advancement
prediction
prevention
Proper
selection
an
appropriate
method
fundamental
aspect
operations.
However,
there
limited
number
studies
that
summarize
compare
different
methods
rockburst.
paper
aims
address
this
gap
analyzing
global
trends
using
CiteSpace
software
since
1990.
It
discusses
classification
characteristics,
comprehensively
reviews
findings
related
prediction,
including
empirical,
simulation,
mathematical
modeling,
microseismic
monitoring
Additionally,
presents
compilation
current
measures.
Notably,
emphasizes
significance
control
strategies,
which
provide
key
insights
into
effective
utilization
stored
energy
within
rock.
Finally,
concludes
suggesting
six
directions
implementing
intelligent
management
techniques
hazards
operations
reduce
probability
incidents.
Buildings,
Journal Year:
2024,
Volume and Issue:
14(3), P. 591 - 591
Published: Feb. 22, 2024
Landscape
geopolymer
concrete
(GePoCo)
with
environmentally
friendly
production
methods
not
only
has
a
stable
structure
but
can
also
effectively
reduce
environmental
damage.
Nevertheless,
GePoCo
poses
challenges
its
intricate
cementitious
matrix
and
vague
mix
design,
where
the
components
their
relative
amounts
influence
compressive
strength.
In
response
to
these
challenges,
application
of
accurate
applicable
soft
computing
techniques
becomes
imperative
for
predicting
strength
such
composite
matrix.
This
research
aimed
predict
using
waste
resources
through
novel
ensemble
ML
algorithm.
The
dataset
comprised
156
statistical
samples,
15
variables
were
selected
prediction.
model
employed
combination
RF,
GWO
algorithm,
XGBoost.
A
stacking
strategy
was
implemented
by
developing
multiple
RF
models
different
hyperparameters,
combining
outcome
predictions
into
new
dataset,
subsequently
XGBoost
model,
termed
RF–XGBoost
model.
To
enhance
accuracy
errors,
algorithm
optimized
hyperparameters
resulting
in
RF–GWO–XGBoost
proposed
compared
stand-alone
models,
hybrid
GWO–XGBoost
system.
results
demonstrated
significant
performance
improvement
strategies,
particularly
assistance
exhibited
better
effectiveness,
an
RMSE
1.712
3.485,
R2
0.983
0.981.
contrast,
(RF
XGBoost)
lower
performance.
Mathematical Biosciences & Engineering,
Journal Year:
2023,
Volume and Issue:
21(1), P. 1413 - 1444
Published: Jan. 1, 2023
<abstract>
<p>The
green
concretes
industry
benefits
from
utilizing
gel
to
replace
parts
of
the
cement
in
concretes.
However,
measuring
compressive
strength
geo-polymer
(CSGPoC)
needs
a
significant
amount
work
and
expenditure.
Therefore,
best
idea
is
predicting
CSGPoC
with
high
level
accuracy.
To
do
this,
base
learner
super
machine
learning
models
were
proposed
this
study
anticipate
CSGPoC.
The
decision
tree
(DT)
applied
as
learner,
random
forest
extreme
gradient
boosting
(XGBoost)
techniques
are
used
system.
In
regard,
database
was
provided
involving
259
data
samples,
which
four-fifths
considered
for
training
model
one-fifth
selected
testing
models.
values
fly
ash,
ground-granulated
blast-furnace
slag
(GGBS),
Na2SiO3,
NaOH,
fine
aggregate,
gravel
4/10
mm,
10/20
water/solids
ratio,
NaOH
molarity
input
estimate
evaluate
reliability
performance
(DT),
XGBoost,
(RF)
models,
12
evaluation
metrics
determined.
Based
on
obtained
results,
highest
degree
accuracy
achieved
by
XGBoost
mean
absolute
error
(MAE)
2.073,
percentage
(MAPE)
5.547,
Nash–Sutcliffe
(NS)
0.981,
correlation
coefficient
(R)
0.991,
R<sup>2</sup>
0.982,
root
square
(RMSE)
2.458,
Willmott's
index
(WI)
0.795,
weighted
(WMAPE)
0.046,
Bias
(SI)
0.054,
p
0.027,
relative
(MRE)
-0.014,
a<sup>20</sup>
0.983
MAE
2.06,
MAPE
6.553,
NS
0.985,
R
0.993,
0.986,
RMSE
2.307,
WI
0.818,
WMAPE
0.05,
SI
0.056,
0.028,
MRE
-0.015,
0.949
model.
By
importing
set
into
trained
0.8969,
0.9857,
0.9424
DT,
RF,
respectively,
show
superiority
estimation.
conclusion,
capable
more
accurately
than
DT
RF
models.</p>
</abstract>
Sensors,
Journal Year:
2024,
Volume and Issue:
24(4), P. 1285 - 1285
Published: Feb. 17, 2024
This
research
addresses
the
paramount
issue
of
enhancing
safety
and
health
conditions
in
underground
mines
through
selection
optimal
sensor
technologies.
A
novel
hybrid
MEREC-CoCoSo
system
is
proposed,
integrating
strengths
MEREC
(Method
for
Eliciting
Relative
Weights)
Combined
Compromise
Solution
(CoCoSo)
methods.
The
study
involves
a
three-stage
framework:
criteria
discernment,
weight
determination
using
MEREC,
prioritization
framework.
Fifteen
ten
sensors
were
identified,
comprehensive
analysis,
including
MEREC-based
determination,
led
to
“Ease
Installation”
as
most
critical
criterion.
Proximity
identified
choice,
followed
by
biometric
sensors,
gas
temperature
humidity
sensors.
To
validate
effectiveness
proposed
model,
rigorous
comparison
was
conducted
with
established
methods,
VIKOR,
TOPSIS,
TODIM,
ELECTRE,
COPRAS,
EDAS,
TRUST.
encompassed
relevant
metrics
such
accuracy,
sensitivity,
specificity,
providing
understanding
model’s
performance
relation
other
methodologies.
outcomes
this
comparative
analysis
consistently
demonstrated
superiority
model
accurately
selecting
best
ensuring
mining.
Notably,
exhibited
higher
accuracy
rates,
increased
improved
specificity
compared
alternative
These
results
affirm
robustness
reliability
establishing
it
state-of-the-art
decision-making
framework
mine
safety.
inclusion
these
actual
enhances
clarity
credibility
our
research,
valuable
insights
into
superior
existing
main
objective
develop
robust
mines,
focus
on
conditions.
seeks
identify
prioritize
context
strives
contribute
mining
industry
offering
structured
effective
approach
selection,
prioritizing
operations.
Buildings,
Journal Year:
2024,
Volume and Issue:
14(1), P. 225 - 225
Published: Jan. 14, 2024
The
present
study
utilized
machine
learning
(ML)
techniques
to
investigate
the
effects
of
eggshell
powder
(ESP)
and
recycled
glass
(RGP)
on
cement
composites
subjected
an
acidic
setting.
A
dataset
acquired
from
published
literature
was
employed
develop
learning-based
predictive
models
for
mortar’s
compressive
strength
(CS)
decrease.
Artificial
neural
network
(ANN),
K-nearest
neighbor
(KNN),
linear
regression
(LR)
were
chosen
modeling.
Also,
RreliefF
analysis
performed
relevance
variables.
total
234
data
points
train/test
ML
algorithms.
Cement,
sand,
water,
silica
fume,
superplasticizer,
powder,
90
days
CS
considered
as
input
outcomes
research
showed
that
could
be
applied
evaluate
reduction
percentage
in
composites,
including
ESP
RGP,
after
being
exposed
acid.
Based
R2
values
(0.87
ANN,
0.81
KNN,
0.78
LR),
well
assessment
variation
between
test
anticipated
errors
(1.32%
1.57%
1.69%
it
determined
accuracy
ANN
model
superior
KNN
LR.
sieve
diagram
exhibited
a
correlation
amongst
predicted
target
results.
suggested
RGP
significantly
influenced
loss
samples
with
scores
0.26
0.21,
respectively.
research,
approach
suitable
predicting
mortar
environments,
thereby
eliminating
lab
testing
trails.