Heliyon,
Год журнала:
2024,
Номер
10(12), С. e32400 - e32400
Опубликована: Июнь 1, 2024
Pests
are
a
significant
challenge
in
paddy
cultivation,
resulting
global
loss
of
approximately
20%
rice
yield.
Early
detection
insects
can
help
to
save
these
potential
losses.
Several
ways
have
been
suggested
for
identifying
and
categorizing
fields,
employing
range
advanced,
noninvasive,
portable
technologies.
However,
none
systems
successfully
incorporated
feature
optimization
techniques
with
Deep
Learning
Machine
Learning.
Hence,
the
current
research
provided
framework
utilizing
detect
categorize
photos
promptly.
Initially,
will
gather
image
dataset
it
into
two
groups:
one
without
other
insects.
Furthermore,
various
pre-processing
techniques,
such
as
augmentation
picture
filtering,
be
applied
enhance
quality
eliminate
any
unwanted
noise.
To
determine
analyze
deep
characteristics
an
image,
architecture
incorporate
5
pre-trained
Convolutional
Neural
Network
models.
Following
that,
selection
including
Principal
Component
Analysis
(PCA),
Recursive
Feature
Elimination
(RFE),
Linear
Discriminant
(LDA),
tool
called
Lion
Optimization,
were
utilized
order
further
reduce
redundant
number
features
that
collected
study.
Subsequently,
process
carried
out
by
7
ML
algorithms.
Finally,
set
experimental
data
analyses
has
conducted
achieve
objectives,
proposed
approach
demonstrates
Extracted
Vectors
ResNet50
Logistic
Regression
PCA
achieved
highest
accuracy,
precisely
99.28%.
present
idea
significantly
impact
how
diagnosed
field.
Computers, materials & continua/Computers, materials & continua (Print),
Год журнала:
2024,
Номер
80(1), С. 1203 - 1233
Опубликована: Янв. 1, 2024
Complex
optimization
problems
hold
broad
significance
across
numerous
fields
and
applications.
However,
as
the
dimensionality
of
such
increases,
issues
like
curse
local
optima
trapping
also
arise.
To
address
these
challenges,
this
paper
proposes
a
novel
Wild
Gibbon
Optimization
Algorithm
(WGOA)
based
on
an
analysis
wild
gibbon
population
behavior.
WGOA
comprises
two
strategies:
community
search
competition.
The
strategy
facilitates
information
exchange
between
families,
generating
multiple
candidate
solutions
to
enhance
algorithm
diversity.
Meanwhile,
competition
reselects
leaders
for
after
each
iteration,
thus
enhancing
precision.
assess
algorithm's
performance,
CEC2017
CEC2022
are
chosen
test
functions.
In
suite,
secures
first
place
in
10
benchmark
functions,
obtained
rank
5
ultimate
experimental
findings
demonstrate
that
outperforms
others
tested
This
underscores
strong
robustness
stability
tackling
complex
single-objective
problems.
Advanced Control for Applications,
Год журнала:
2024,
Номер
6(3)
Опубликована: Апрель 24, 2024
Abstract
Grey
wolf
optimization
algorithm
(GWO)
has
achieved
great
results
in
the
of
neural
network
parameters.
However,
it
some
problems
such
as
insufficient
precision,
poor
robustness,
weak
searching
ability
and
easy
to
fall
into
local
optimal
solution.
Therefore,
a
grey
combining
Levy
flight
nonlinear
inertia
weights
(LGWO)
is
proposed
this
paper.
The
combination
weight
improve
search
efficiency
solve
problem
that
In
summary,
LGWO
solves
optimal.
This
paper
uses
Congress
on
Evolutionary
Computation
benchmark
function
combines
algorithms
with
for
power
line
fault
classification
prediction
verify
effectiveness
each
strategy
improvement
its
comparison
other
excellent
(sine
cosine
algorithm,
tree
seed
wind
driven
optimization,
gravitational
algorithm).
networks
algorithms,
accuracy
been
improved
compared
basic
GWO,
best
performance
multiple
comparisons.
Heliyon,
Год журнала:
2024,
Номер
10(12), С. e32400 - e32400
Опубликована: Июнь 1, 2024
Pests
are
a
significant
challenge
in
paddy
cultivation,
resulting
global
loss
of
approximately
20%
rice
yield.
Early
detection
insects
can
help
to
save
these
potential
losses.
Several
ways
have
been
suggested
for
identifying
and
categorizing
fields,
employing
range
advanced,
noninvasive,
portable
technologies.
However,
none
systems
successfully
incorporated
feature
optimization
techniques
with
Deep
Learning
Machine
Learning.
Hence,
the
current
research
provided
framework
utilizing
detect
categorize
photos
promptly.
Initially,
will
gather
image
dataset
it
into
two
groups:
one
without
other
insects.
Furthermore,
various
pre-processing
techniques,
such
as
augmentation
picture
filtering,
be
applied
enhance
quality
eliminate
any
unwanted
noise.
To
determine
analyze
deep
characteristics
an
image,
architecture
incorporate
5
pre-trained
Convolutional
Neural
Network
models.
Following
that,
selection
including
Principal
Component
Analysis
(PCA),
Recursive
Feature
Elimination
(RFE),
Linear
Discriminant
(LDA),
tool
called
Lion
Optimization,
were
utilized
order
further
reduce
redundant
number
features
that
collected
study.
Subsequently,
process
carried
out
by
7
ML
algorithms.
Finally,
set
experimental
data
analyses
has
conducted
achieve
objectives,
proposed
approach
demonstrates
Extracted
Vectors
ResNet50
Logistic
Regression
PCA
achieved
highest
accuracy,
precisely
99.28%.
present
idea
significantly
impact
how
diagnosed
field.
