The
daily
production
of
a
single
well
in
an
oil
field
can
reflect
the
changes
and
water
reservoir
it
is
important
basis
for
formulating
stimulation
measures.
However,
factors
that
affect
are
complex,
there
currently
no
standard
calculation
method.
In
recent
years,
BP
neural
networks
have
been
widely
used
yield
prediction,
but
they
problems
such
as
slow
convergence
speed
easy
to
fall
into
local
optima.
response
above
issues,
this
paper
proposes
backpropagation
network
model
WOA-BP
based
on
whale
optimization
algorithm.
Firstly,
Spearman
Pearson
correlation
coefficient
methods
screen
feature
attributes
related
input
parameters
network,
with
output
parameter;
Then,
Whale
Optimization
Algorithm
(WOA)
optimize
initial
learning
rate,
weight
bias,
number
hidden
layer
neurons
network;
Finally,
optimized
parameters,
prediction
constructed.
Train
evaluate
established
using
real
oilfield
data,
compare
models
BP,
GA-BP,
PSO-BP.
experimental
results
show
has
good
performance,
determination
(R2)
0.9633
mean
square
error
(MSE)
0.0017.
It
effectively
predict
aid
predicting
blocks.
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: April 3, 2025
This
paper
introduces
a
novel
approach
to
enhancing
the
architecture
of
deep
convolutional
neural
networks,
addressing
issues
self-design.
The
proposed
strategy
leverages
grey
wolf
optimizer
and
multi-scale
fractal
chaotic
map
search
scheme
as
fundamental
components
enhance
exploration
exploitation,
thereby
improving
classification
task.
Several
experiments
validate
method,
demonstrating
an
impressive
87.37%
accuracy
across
95
random
trials,
outperforming
23
state-of-the-art
classifiers
in
study's
nine
datasets.
work
underscores
potential
chaotic/fractal
bio-inspired
paradigms
advancing
architecture.
Biomimetics,
Journal Year:
2024,
Volume and Issue:
9(10), P. 602 - 602
Published: Oct. 7, 2024
The
whale
optimization
algorithm
(WOA)
is
constructed
on
a
whale's
bubble-net
scavenging
pattern
and
emulates
encompassing
prey,
devouring
stochastic
capturing
for
prey
to
establish
the
global
optimal
values.
Nevertheless,
WOA
has
multiple
deficiencies,
such
as
restricted
precision,
sluggish
convergence
acceleration,
insufficient
population
variety,
easy
premature
convergence,
operational
efficiency.
sine
cosine
(SCA)
oscillation
attributes
of
coefficients
in
mathematics
methodology.
SCA
upgrades
amplifies
search
region,
accelerates
international
investigation
regional
extraction.
Therefore,
hybrid
nonlinear
with
(SCWOA)
emphasized
estimate
benchmark
functions
engineering
designs,
ultimate
intention
investigate
reasonable
solutions.
Compared
other
algorithms,
BA,
CapSA,
MFO,
MVO,
SAO,
MDWA,
WOA,
SCWOA
exemplifies
superior
effectiveness
greater
computation
profitability.
experimental
results
emphasize
that
not
only
integrates
extraction
avoid
realize
most
appropriate
solution
but
also
exhibits
superiority
practicability
locate
precision
faster
speed.
Optics Express,
Journal Year:
2023,
Volume and Issue:
31(12), P. 20200 - 20200
Published: May 18, 2023
It
is
recognized
that
unknown
emissivity
and
ill-posed
radiation
equations
present
significant
challenges
to
light-field
multi-wavelength
pyrometry.
Furthermore,
range
choice
of
initial
value
also
have
a
impact
upon
the
measurement
results.
This
paper
demonstrates
novel
chameleon
swarm
algorithm
approach
could
be
used
ascertain
temperature
information
from
data
at
higher
accuracy
level
without
prior
knowledge.
The
performance
was
experimentally
tested
compared
with
traditional
internal
penalty
function
generalized
inverse
matrix-exterior
algorithms.
Comparisons
calculation
error,
time,
values
for
each
channel
show
superior
in
terms
both
computational
efficiency.
Scientific Reports,
Journal Year:
2024,
Volume and Issue:
14(1)
Published: Aug. 23, 2024
Golden
jackal
optimization
(GJO)
is
inspired
by
mundane
characteristics
and
collaborative
hunting
behaviour,
which
mimics
foraging,
trespassing
encompassing,
capturing
prey
to
refresh
a
jackal's
position.
However,
the
GJO
has
several
limitations,
such
as
slow
convergence
rate,
low
computational
accuracy,
premature
convergence,
poor
solution
efficiency,
weak
exploration
exploitation.
To
enhance
global
detection
ability
this
paper
proposes
novel
complex-valued
encoding
golden
(CGJO)
achieve
function
engineering
design.
The
strategy
deploys
dual-diploid
organization
encode
real
imaginary
portions
of
converts
dual-dimensional
region
single-dimensional
manifestation
region,
increases
population
diversity,
restricts
search
stagnation,
expands
area,
promotes
information
exchange,
fosters
collaboration
efficiency
improves
accuracy.
CGJO
not
only
exhibits
strong
adaptability
robustness
supplementary
advantages
but
also
balances
local
exploitation
promote
precision
determine
best
solution.
CEC
2022
test
suite
six
real-world
designs
are
utilized
evaluate
effectiveness
feasibility
CGJO.
compared
with
three
categories
existing
algorithms:
(1)
WO,
HO,
NRBO
BKA
recently
published
algorithms;
(2)
SCSO,
GJO,
RGJO
SGJO
highly
cited
(3)
L-SHADE,
LSHADE-EpsSin
CMA-ES
performing
algorithms.
experimental
results
reveal
that
superior
those
other
superiority
reliability
quicker
greater
computation
precision,
stability
robustness.
Frontiers in Oncology,
Journal Year:
2024,
Volume and Issue:
14
Published: Dec. 23, 2024
Introduction
Lung
cancer
is
one
of
the
main
causes
rising
death
rate
among
expanding
population.
For
patients
with
lung
to
have
a
higher
chance
survival
and
fewer
deaths,
early
categorization
essential.
The
goal
thisresearch
enhance
machine
learning
increase
precision
quality
classification.
Methods
dataset
was
obtained
from
an
open-source
database
utilized
for
testing
training.
suggested
system
used
CT
scan
picture
as
its
input
image,
it
underwent
variety
image
processing
operations,
including
segmentation,
contrast
enhancement,
feature
extraction.
Results
training
process
produces
chameleon
swarm-based
supportvector
that
can
identify
between
benign,
malignant,
normal
nodules.
Conclusion
performance
evaluated
in
terms
false-positive
(FPR),
sensitivity,
specificity,
recognition
time
accuracy.
