Depression
is
a
severe
mental
health
problem
for
people
around
the
world,
regardless
of
age,
gender,
or
race.
It
cause
psychological
disability,
and
these
disorders
can
have
an
impact
on
person's
interpersonal
connections,
such
as
work
environment
family
life,
well
their
overall
routines,
irregular
eating
sleeping
patterns.
However,
unfortunately,
majority
cases
depression
go
undiagnosed
and,
therefore,
untreated.
Depression,
when
not
detected
at
earlier
stage,
become
illness
may
lead
to
suicide
later
stages.
Consequently,
it
becomes
crucial
identify
prevent
stage.
The
data
this
study
are
collected
through
survey
from
undergraduates
in
consultation
with
psychiatrists
professors.Further,
Natural
Language
Processing(NLP)
techniques
Machine
learning
methodologies
were
used
train
evaluate
efficiency
proposed
model.
This
looked
various
feature
selection
(FS)
filter
method
Maximum
Relevance
Minimum
Redundancy-mRMR,
wrapper
Recursive
Feature
Elimination-RFE,
Boruta,
Embedded
method:
Least
Absolute
Shrinkage
Selection
Operator-LASSO
extract
most
significant
features
profile
information
user
responsible
forming
depression.
Adaboost
model
produced
accuracy
94%
considering
all
elements
dataset.
different
techniques,
applied,
we
found
mRMR
FS
using
Optuna
Hypertuning
96%.
Results in Engineering,
Год журнала:
2024,
Номер
21, С. 101894 - 101894
Опубликована: Фев. 12, 2024
Heart
disease
is
one
of
the
most
recurrent
and
worrying
health
problems
today,
due
to
its
multiple
complications,
including:
stroke,
cardiac
arrest,
retinopathy,
etc.
Propose
a
method
4
Stacking
models
based
on
hyperparameters
diagnose
heart
disease.
In
addition,
web
interface
was
developed
with
best
model
proposed
in
this
study.
First,
dataset
used
from
Disease
Cleveland
ICU,
which
918
patient
records
12
attributes.
Therefore,
paper
composed
following
stages:
Cleaning
Pre-processing;
Describe
data;
Training
testing
Cross
validation;
Calibration
models;
modelling
evaluation,
also
compare
different
techniques
predict
using
ensemble
taking
into
account
performance
evaluation
parameters.
1
(Logistic
regression)
oversampling
AdaBoost-SVM
hyperparameter
test
obtained
higher
Accuracy
(88.24%),
ROC
Curve
(92.00%),
while
too
reached
better
Precision
(88.54%),
but
algorithm
achieved
high
value
Sensitivity
(88.14%)
F1-Score
(88.19%).
Implementing
stacking
hyperparameters,
it
helps
make
an
early
diagnosis
greater
precision,
decrease
quantity
deceases
caused
by
it.
combined
method,
improvement
prediction
observed,
surpassing
independent
algorithms
used.
International Journal of Energy Economics and Policy,
Год журнала:
2023,
Номер
13(5), С. 303 - 314
Опубликована: Сен. 16, 2023
The
publication
trends
and
bibliometric
analysis
of
the
research
landscape
on
applications
machine
deep
learning
in
energy
storage
(MDLES)
were
examined
this
study
based
published
documents
Elsevier
Scopus
database
between
2012
2022.
PRISMA
technique
employed
to
identify,
screen,
filter
related
publications
MDLES
recovered
969
comprising
articles,
conference
papers,
reviews
English.
results
showed
that
count
topic
increased
from
3
385
(or
a
12,733.3%
increase)
along
with
citations
high
rate
was
ascribed
impact,
co-authorships/collaborations,
as
well
source
title/journals’
reputation,
multidisciplinary
nature,
funding.
top/most
prolific
researcher,
institution,
country,
funding
body
are;
is
Yan
Xu,
Tsinghua
University,
China,
National
Natural
Science
Foundation
respectively.
Keywords
occurrence
revealed
three
clusters
or
hotspots
learning,
digital
storage,
Energy
Storage.
Further
currently
largely
focused
application
machine/deep
for
predicting,
operating,
optimising
design
materials
renewable
technologies
such
wind,
PV
solar.
However,
future
will
presumably
include
focus
advanced
development,
operational
systems
monitoring
control
techno-economic
address
challenges
associated
efficiency
analysis,
costing
electricity
pricing,
trading,
revenue
prediction
Journal of Information Systems Engineering and Business Intelligence,
Год журнала:
2024,
Номер
10(1), С. 38 - 50
Опубликована: Фев. 28, 2024
Background:
Parkinson's
disease
(PD)
is
a
critical
neurodegenerative
disorder
affecting
the
central
nervous
system
and
often
causing
impaired
movement
cognitive
function
in
patients.
In
addition,
its
diagnosis
early
stages
requires
complex
time-consuming
process
because
all
existing
tests
such
as
electroencephalography
or
blood
examinations
lack
effectiveness
accuracy.
Several
studies
explored
PD
prediction
using
sound,
with
specific
focus
on
development
of
classification
models
to
enhance
The
majority
these
neglected
crucial
aspects
including
feature
extraction
proper
parameter
tuning,
leading
low
Objective:
This
study
aims
optimize
performance
voice-based
through
extraction,
goal
reducing
data
dimensions
improving
model
computational
efficiency.
Additionally,
appropriate
parameters
will
be
selected
for
enhancement
ability
identify
both
cases
healthy
individuals.
Methods:
proposed
new
applied
an
OpenML
dataset
comprising
voice
recordings
from
31
individuals,
namely
23
patients
8
participants.
experimental
included
initial
use
SVM
algorithm,
followed
by
implementing
PCA
machine
learning
Subsequently,
balancing
SMOTE
was
conducted,
GridSearchCV
used
best
combination
based
predicted
characteristics.
Result:
Evaluation
showed
impressive
accuracy
97.44%,
sensitivity
100%,
specificity
85.71%.
excellent
result
achieved
limited
10-fold
cross-validation
rendering
sensitive
training
data.
Conclusion:
successfully
enhanced
SVM+PCA+GridSearchCV+CV
method.
However,
future
investigations
should
consider
number
folds
small
dataset,
explore
alternative
methods,
expand
generalizability.
Keywords:
GridSearchCV,
Parkinson
Disaese,
SVM,
PCA,
SMOTE,
Voice/Speech
Informatics in Medicine Unlocked,
Год журнала:
2023,
Номер
43, С. 101391 - 101391
Опубликована: Янв. 1, 2023
Anxiety
is
considered
one
of
the
most
common
pathologies
that
people
go
through
frequently,
this
being
main
cause
illness
and
disability
in
students
since
it
more
women
with
7.7%
than
men
3.6%.
Moreover,
stress
also
causes
some
health-related
problems,
such
as
cardiovascular
diseases
mental
disorders.
The
purpose
study
to
gain
a
deeper
understanding
methodologies,
attributes,
selection
algorithms,
well
techniques,
tools
or
programming
languages,
metrics
machine
learning
algorithms
have
been
applied
prediction
anxiety
college
students.
An
exhaustive
search
29
articles
was
performed,
using
keywords
from
7
databases:
ScienceDirect,
IEEE
Xplore,
ACM,
Scopus,
Springer
Link,
InderScience
Wiley
2019
2023.
This
article
based
on
Preferred
Reporting
Items
for
Systematic
Reviews
Meta-Analyses
(PRISMA)
methodology,
taking
into
account
inclusion
exclusion
criteria.
To
then
make
synthesis
findings
studies
about
following
aspects
languages
metrics.
methodology
used
sequence
steps,
important
attributes
were
age
gender,
do
not
use
variable
techniques;
other
hand,
efficient
techniques
Support
Vector
Machine
(SVM)
Logistic
regression
(LR),
language
develop
models
Python
finally
essential
determine
effectiveness
model
Precision
Accuracy.
systematic
review
provides
scientific
evidence,
results
describing
how
help
predict
stress.
For
this,
are
compared
perform
broad
analysis
these
Programming
metrics,
variables
influential
factors,
which
will
medical
fields
detection
Journal of Soft Computing Exploration,
Год журнала:
2024,
Номер
5(1), С. 38 - 45
Опубликована: Март 18, 2024
In
today's
digital
era,
user
reviews
on
the
Playstore
platform
are
an
invaluable
source
of
information
for
developers,
offering
insights
that
critical
service
improvement.
Previous
research
has
explored
application
stacking
ensemble
methods,
such
as
in
context
predicting
depression
among
university
students,
to
enhance
prediction
accuracy.
However,
these
studies
often
do
not
explicitly
detail
data
acquisition
process,
leaving
a
gap
understanding
applicability
methods
different
domains.
This
aims
bridge
this
by
applying
approach
improve
accuracy
sentiment
classification
reviews,
with
clear
exposition
collection
method.
Utilizing
Logistic
Regression
meta
classifier,
methodology
is
executed
several
stages.
Initially,
was
collected
from
online
loan
applications
Google
Playstore,
ensuring
transparency
process.
The
then
classified
using
three
basic
models:
Random
Forest,
Naive
Bayes,
and
SVM.
outputs
models
serve
inputs
model.
A
comparison
each
base
model
output
subsequently
carried
out.
test
results
review
dataset
demonstrated
increase
accuracy,
precision,
recall,
F1
score
compared
single
model,
achieving
87.05%,
which
surpasses
Forest
(85.6%),
Bayes
(85.55%),
SVM
(86.5%).
indicates
effectiveness
method
providing
deeper
more
accurate
into
sentiment,
overcoming
limitations
previous
addressing
methods.