Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: Jan. 2, 2025
Colorectal
cancer
(CRC)
is
a
form
of
that
impacts
both
the
rectum
and
colon.
Typically,
it
begins
with
small
abnormal
growth
known
as
polyp,
which
can
either
be
non-cancerous
or
cancerous.
Therefore,
early
detection
colorectal
second
deadliest
after
lung
cancer,
highly
beneficial.
Moreover,
standard
treatment
for
locally
advanced
widely
accepted
around
world,
chemoradiotherapy.
Then,
in
this
study,
seven
artificial
intelligence
models
including
decision
tree,
K-nearest
neighbors,
Adaboost,
random
forest,
Gradient
Boosting,
multi-layer
perceptron,
convolutional
neural
network
were
implemented
to
detect
patients
responder
non-responder
radiochemotherapy.
For
finding
potential
predictors
(genes),
three
feature
selection
strategies
employed
mutual
information,
F-classif,
Chi-Square.
Based
on
models,
four
different
scenarios
developed
five,
ten,
twenty
thirty
features
selected
designing
more
accurate
classification
paradigm.
The
results
study
confirm
neighbors
provided
terms
accuracy,
by
93.8%.
Among
methods,
information
F-classif
showed
best
results,
while
Chi-Square
produced
worst
results.
suggested
successfully
applied
robust
approach
response
radiochemotherapy
medical
studies.
Scientific Reports,
Journal Year:
2023,
Volume and Issue:
13(1)
Published: Nov. 21, 2023
As
an
important
hydrological
parameter,
dissolved
oxygen
(DO)
concentration
is
a
well-accepted
indicator
of
water
quality.
This
study
deals
with
introducing
and
evaluating
four
novel
integrative
methods
for
the
prediction
DO.
To
this
end,
teaching-learning-based
optimization
(TLBO),
sine
cosine
algorithm,
cycle
algorithm
(WCA),
electromagnetic
field
(EFO)
are
appointed
to
train
commonly-used
predictive
system,
namely
multi-layer
perceptron
neural
network
(MLPNN).
The
records
USGS
station
called
Klamath
River
(Klamath
County,
Oregon)
used.
First,
networks
fed
by
data
between
October
01,
2014,
September
30,
2018.
Later,
their
competency
assessed
using
belonging
subsequent
year
(i.e.,
from
2018
2019).
reliability
all
models,
as
well
superiority
WCA-MLPNN,
was
revealed
mean
absolute
errors
(MAEs
0.9800,
1.1113,
0.9624,
0.9783)
in
training
phase.
calculated
Pearson
correlation
coefficients
(RPs
0.8785,
0.8587,
0.8762,
0.8815)
plus
root
square
(RMSEs
1.2980,
1.4493,
1.3096,
1.2903)
showed
that
EFO-MLPNN
TLBO-MLPNN
perform
slightly
better
than
WCA-MLPNN
testing
Besides,
analyzing
complexity
time
pointed
out
most
efficient
tool
predicting
In
comparison
relevant
previous
literature
indicated
suggested
models
provide
accuracy
improvement
machine
learning-based
DO
modeling.
Research Square (Research Square),
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 30, 2025
Abstract
Leachate
management
in
landfill
site
is
a
major
issue
both
environmental
conservation
and
facility
operation.
With
recent
climate
change,
extremely
heavy
rains
have
caused
sites
to
exceed
their
drainage
capacity.
This
could
lead
leakage
of
leachate
serious
damage
on
the
surrounding
environment.
We
proposed
models
predict
volume,
electric
conductivity
temperature,
then
investigated
how
control
waste
layer
conditions
reduce
load
treatment
facility.
In
models,
we
set
rainfall
temperature
as
explanatory
variables
used
Auto-Regressive
with
eXogenous
(ARX)
Gaussian
Process
Regression
(GPR).
Under
non-linear
or
unexpected
conditions,
GPR
predicted
electrical
conductivity,
higher
accuracy
fewer
relearing
process
than
ARX.
having
such
characteristics
was
considered
relatively
suitable
for
condition.
It
means
necessary
collect
training
data
continuously
refine
model.
PLoS ONE,
Journal Year:
2023,
Volume and Issue:
18(12), P. e0293751 - e0293751
Published: Dec. 27, 2023
Changes
in
soil
temperature
(ST)
play
an
important
role
the
main
mechanisms
within
soil,
including
biological
and
chemical
activities.
For
instance,
they
affect
microbial
community
composition,
speed
at
which
organic
matter
breaks
down
becomes
minerals.
Moreover,
growth
physiological
activity
of
plants
are
directly
influenced
by
ST.
Additionally,
ST
indirectly
affects
plant
influencing
accessibility
nutrients
soil.
Therefore,
designing
efficient
tool
for
estimating
different
depths
is
useful
studies
considering
meteorological
parameters
as
input
parameters,
maximal
air
temperature,
minimal
relative
humidity,
precipitation,
wind
speed.
This
investigation
employed
various
statistical
metrics
to
evaluate
efficacy
implemented
models.
These
encompassed
correlation
coefficient
(r),
root
mean
square
error
(RMSE),
Nash-Sutcliffe
(NS)
efficiency,
absolute
(MAE).
Hence,
this
study
presented
several
artificial
intelligence-based
models,
MLPANN,
SVR,
RFR,
GPR
building
robust
predictive
tools
daily
scale
estimation
05,
10,
20,
30,
50,
100cm
depths.
The
suggested
models
evaluated
two
stations
(i.e.,
Sulaimani
Dukan)
located
Kurdistan
region,
Iraq.
Based
on
assessment
outcomes
study,
exhibited
exceptional
capabilities
comparison
results
showed
that
among
proposed
frameworks,
yielded
best
depths,
with
RMSE
values
1.814°C,
1.652°C,
1.773°C,
2.891°C,
respectively.
Also,
50cm
depth,
MLPANN
performed
2.289°C
station
using
during
validation
phase.
Furthermore,
produced
most
superior
10cm,
30cm,
1.753°C,
2.270°C,
2.631°C,
In
addition,
05cm
SVR
achieved
highest
level
performance
1.950°C
Dukan
station.
obtained
research
confirmed
have
potential
be
effectively
used
