Applied Artificial Intelligence,
Journal Year:
2024,
Volume and Issue:
38(1)
Published: Nov. 10, 2024
One
of
the
issues
addressed
by
machine
learning,
with
applications
in
various
disciplines
or
fields
such
as
health
sector
and
agricultural
among
others,
involves
data
classification.
For
this
purpose,
models
within
supervised
learning
have
been
proposed
developed
that
allow
for
classification
these
data.
However,
one
implications
No-Free-Lunch
theorems
is
there
no
optimal
general-purpose
model,
i.e.
classifier
model
achieves
best
results
all
problems
presented.
Hence
importance
proposing
implementing
new
models,
evaluating
their
performance,
comparing
them
other
order
to
achieve
good
specific
problems.
This
work
presents
a
that,
constructing
hyperplanes
from
training
set,
generates
decision
tree
partitions
dimensional
space.
The
was
applied
different
XOR
logical
function
problem,
where
managed
solve
it
also
Iris
Dataset
trees
generated
classify
100%
accuracy
test
finally,
Pima
Indians
Diabetes
Database
compared
using
value.
obtained
an
81.81%,
achieving
result
same
way
Random
Forest
Classifier.
show
manages
partition
space
adequately
set
thus
competitively
state-of-the-art
models.
Information,
Journal Year:
2024,
Volume and Issue:
15(5), P. 280 - 280
Published: May 14, 2024
This
research
paper
presents
a
comprehensive
study
on
optimizing
the
critical
artificial
intelligence
(AI)
factors
influencing
cost
management
in
civil
engineering
projects
using
multi-criteria
decision-making
(MCDM)
approach.
The
problem
addressed
revolves
around
need
to
effectively
manage
costs
endeavors
amidst
growing
complexity
of
and
increasing
integration
AI
technologies.
methodology
employed
involves
utilization
three
MCDM
tools,
specifically
Delphi,
interpretive
structural
modeling
(ISM),
Cross-Impact
Matrix
Multiplication
Applied
Classification
(MICMAC).
A
total
17
factors,
categorized
into
eight
broad
groups,
were
identified
analyzed.
Through
application
different
techniques,
relative
importance
interrelationships
among
these
determined.
key
findings
reveal
role
certain
such
as
risk
mitigation
components,
processes.
Moreover,
hierarchical
structure
generated
through
ISM
influential
via
MICMAC
provide
insights
for
prioritizing
strategic
interventions.
implications
this
extend
informing
decision-makers
domain
about
effective
strategies
leveraging
their
practices.
By
adopting
systematic
approach,
stakeholders
can
enhance
project
outcomes
while
resource
allocation
mitigating
financial
risks.
Water,
Journal Year:
2024,
Volume and Issue:
16(19), P. 2748 - 2748
Published: Sept. 27, 2024
Groundwater
salinization
poses
a
critical
threat
to
sustainable
development
in
arid
and
semi-arid
rurbanizing
regions,
exemplified
by
Kerman
Province,
Iran.
This
region
experiences
groundwater
ecosystem
degradation
as
result
of
the
rapid
conversion
rural
agricultural
land
urban
areas
under
chronic
drought
conditions.
study
aims
enhance
Pollution
Risk
(GwPR)
mapping
integrating
DRASTIC
index
with
machine
learning
(ML)
models,
including
Random
Forest
(RF),
Boosted
Regression
Trees
(BRT),
Generalized
Linear
Model
(GLM),
Support
Vector
Machine
(SVM),
Multivariate
Adaptive
Splines
(MARS),
alongside
hydrogeochemical
investigations,
promote
water
management
Province.
The
RF
model
achieved
highest
accuracy
an
Area
Under
Curve
(AUC)
0.995
predicting
GwPR,
outperforming
BRT
(0.988),
SVM
(0.977),
MARS
(0.951),
GLM
(0.887).
RF-based
map
identified
new
high-vulnerability
zones
northeast
northwest
showed
expanded
moderate
vulnerability
zone,
covering
48.46%
area.
Analysis
revealed
exceedances
WHO
standards
for
total
hardness
(TH),
sodium,
sulfates,
chlorides,
electrical
conductivity
(EC)
these
areas,
indicating
contamination
from
mineralized
aquifers
unsustainable
practices.
findings
underscore
model’s
effectiveness
prediction
highlight
need
stricter
monitoring
management,
regulating
extraction
improving
use
efficiency
riverine
aquifers.
Mathematics,
Journal Year:
2025,
Volume and Issue:
13(7), P. 1156 - 1156
Published: March 31, 2025
This
study
introduces
the
GWO-FNN
model,
an
improvement
of
fuzzy
neural
network
(FNN)
architecture
that
aims
to
balance
high
performance
with
improved
interpretability
in
artificial
intelligence
(AI)
systems.
The
model
leverages
Grey
Wolf
Optimizer
(GWO)
fine-tune
consequents
rules
and
uses
mutual
information
(MI)
initialize
weights
input
layer,
resulting
greater
classification
accuracy
transparency.
A
distinctive
aspect
is
its
capacity
transform
logical
neurons
hidden
layer
into
comprehensible
rules,
thereby
elucidating
reasoning
behind
outputs.
model’s
were
rigorously
evaluated
through
statistical
methods,
benchmarks,
real-world
dataset
testing.
These
evaluations
demonstrate
strong
capability
extract
clearly
express
intricate
patterns
within
data.
By
combining
advanced
rule
mechanisms
a
comprehensive
framework,
contributes
meaningful
advancement
interpretable
AI
approaches.
