Network Computation in Neural Systems,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 33
Published: July 31, 2024
The
rapid
advancements
in
Agriculture
4.0
have
led
to
the
development
of
continuous
monitoring
soil
parameters
and
recommend
crops
based
on
fertility
improve
crop
yield.
Accordingly,
parameters,
such
as
pH,
nitrogen,
phosphorous,
potassium,
moisture
are
exploited
for
irrigation
control,
followed
by
recommendation
agricultural
field.
smart
control
is
performed
utilizing
Interactive
guide
optimizer-Deep
Convolutional
Neural
Network
(Interactive
optimizer-DCNN),
which
supports
decision-making
regarding
nutrients.
Specifically,
optimizer-DCNN
classifier
designed
replace
standard
ADAM
algorithm
through
modeled
interactive
optimizer,
exhibits
alertness
guiding
characters
from
nature-inspired
dog
cat
population.
In
addition,
data
down-sampled
reduce
redundancy
preserve
important
information
computing
performance.
model
attains
an
accuracy
93.11
%
predicting
minerals,
pH
value,
thereby,
exhibiting
a
higher
97.12%
when
training
fixed
at
90%.
Further,
developed
attained
F-score,
specificity,
sensitivity,
values
90.30%,
92.12%,
89.56%,
86.36%
with
k-fold
10
minerals
that
revealed
efficacy
model.
Environmental Science and Pollution Research,
Journal Year:
2024,
Volume and Issue:
31(30), P. 42719 - 42749
Published: June 15, 2024
Accurately
predicting
potential
evapotranspiration
(PET)
is
crucial
in
water
resource
management,
agricultural
planning,
and
climate
change
studies.
This
research
aims
to
investigate
the
performance
of
two
machine
learning
methods,
adaptive
network-based
fuzzy
inference
system
(ANFIS)
deep
belief
network
(DBN),
forecasting
PET,
as
well
explore
hybridizing
ANFIS
approach
with
Snake
Optimizer
(ANFIS-SO)
algorithm.
The
study
utilized
a
comprehensive
dataset
spanning
period
from
1983
2020.
ANFIS,
ANFIS-SO,
DBN
models
were
developed,
their
performances
evaluated
using
statistical
metrics,
including
R
Applied Intelligence,
Journal Year:
2023,
Volume and Issue:
53(21), P. 24765 - 24781
Published: July 28, 2023
Abstract
We
are
witnessing
the
digitalization
era,
where
artificial
intelligence
(AI)/machine
learning
(ML)
models
mandatory
to
transform
this
data
deluge
into
actionable
information.
However,
these
require
large,
high-quality
datasets
predict
high
reliability/accuracy.
Even
with
maturity
of
Internet
Things
(IoT)
systems,
there
still
numerous
scenarios
is
not
enough
quantity
and
quality
successfully
develop
AI/ML-based
applications
that
can
meet
market
expectations.
One
such
scenario
precision
agriculture,
operational
generation
costly
unreliable
due
extreme
remote
conditions
crops.
In
paper,
we
investigated
synthetic
as
a
method
improve
predictions
AI/ML
in
agriculture.
used
generative
adversarial
networks
(GANs)
generate
temperature
for
greenhouse
located
Murcia
(Spain).
The
results
reveal
use
significantly
improves
accuracy
targeted
compared
using
only
ground
truth
data.
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).
