INTENSIF Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi,
Journal Year:
2025,
Volume and Issue:
9(1), P. 60 - 75
Published: Feb. 23, 2025
Background:
The
World
Health
Organization
(WHO)
defines
health
as
a
state
of
physical,
mental,
and
social
well-being,
not
just
the
absence
disease.
Mental
health,
essential
for
overall
is
often
neglected,
leading
to
disorders
like
depression,
major
cause
suicide.
In
Indonesia,
suicide
cases
have
surged,
with
971
reported
from
January
October
2023.
Objective:
This
study
aims
analyze
public
sentiment
regarding
rise
in
Indonesia
using
analysis
methods,
specifically
Support
Vector
Machine
(SVM)
Naive
Bayes
Classifier
(NBC).
findings
are
expected
raise
awareness
provide
policy
recommendations
support
mental
initiatives.
Methods:
One
method
used
understand
perception
issue
text
mining.
research
employs
mining
techniques
algorithms
related
Indonesia.
Data
was
collected
tweets
on
media
platform
X
crawling
methods
snscrape
Python,
totaling
1,175
tweets.
Results:
results
indicate
that
Linear
SVM
model
achieved
higher
accuracy
than
classifying
tweet
sentiments,
an
rate
80%.
Conclusion:
algorithm
linear
kernel
80%
identical
ROC-AUC
score.
Word
cloud
visualization
highlighted
terms
"kill,"
"self,"
"depression,"
"stress"
key
negative
sentiments.
better
policies
Revista Latino-Americana de Enfermagem,
Journal Year:
2024,
Volume and Issue:
32
Published: Jan. 1, 2024
Objective:
to
describe
the
development
of
a
predictive
nursing
workload
classifier
model,
using
artificial
intelligence.
Method:
retrospective
observational
study,
secondary
sources
electronic
patient
records,
machine
learning.
The
convenience
sample
consisted
43,871
assessments
carried
out
by
clinical
nurses
Perroca
Patient
Classification
System,
which
served
as
gold
standard,
and
data
from
medical
records
11,774
patients,
constituted
variables.
In
order
organize
carry
analysis,
Dataiku®
science
platform
was
used.
Data
analysis
occurred
in
an
exploratory,
descriptive
manner.
study
approved
Ethics
Research
Committee
institution
where
out.
Results:
use
intelligence
enabled
assessment
identifying
variables
that
most
contributed
its
prediction.
algorithm
correctly
classified
72%
area
under
Receiver
Operating
Characteristic
curve
82%.
Conclusion:
model
developed,
demonstrating
it
is
possible
train
algorithms
with
patient’s
record
predict
tools
can
be
effective
automating
this
activity.
Artificial
Intelligence
(AI)
is
a
leading
technology
of
the
current
age
Fourth
Industrial
Revolution
(Industry
4.0
or
4IR),
with
capability
incorporating
human
behavior
and
intelligence
into
machines
systems.
Thus
AI-based
modeling
key
to
building
automated,
intelligent,
smart
systems
according
today's
needs.
To
solve
real-world
issues
various
types
AI
such
as
analytical,
functional,
interactive,
textual,
visual
can
be
applied
enhance
capabilities
an
application.
However,
developing
effective
model
challenging
task
due
dynamic
nature
variation
in
problems
data.
In
this
paper,
we
present
comprehensive
view
on
"AI-based
Modeling"
principles
potential
techniques
that
play
important
role
intelligent
application
areas
including
business,
finance,
healthcare,
agriculture,
cities,
cybersecurity
many
more.
We
also
emphasize
highlight
research
within
scope
our
study.
Overall,
goal
paper
provide
broad
overview
used
reference
guide
by
academics
industry
people
well
decision-makers
scenarios
domains.
PLoS ONE,
Journal Year:
2022,
Volume and Issue:
17(7), P. e0271227 - e0271227
Published: July 28, 2022
Introduction
Identifying
COVID-19
patients
that
are
most
likely
to
progress
a
severe
infection
is
crucial
for
optimizing
care
management
and
increasing
the
likelihood
of
survival.
This
study
presents
machine
learning
model
predicts
cases
COVID-19,
defined
as
presence
Acute
Respiratory
Distress
Syndrome
(ARDS)
highlights
different
risk
factors
play
significant
role
in
disease
progression.
Methods
A
cohort
composed
289,351
diagnosed
with
April
2020
was
created
using
US
administrative
claims
data
from
Oct
2015
Jul
2020.
For
each
patient,
information
about
817
diagnoses,
were
collected
medical
history
ahead
infection.
The
primary
outcome
ARDS
4
months
following
randomly
split
into
training
set
used
development,
test
evaluation
validation
real-world
performance
estimation.
Results
We
analyzed
three
classifiers
predict
ARDS.
Among
algorithms
considered,
Gradient
Boosting
Decision
Tree
had
highest
an
AUC
0.695
(95%
CI,
0.679–0.709)
AUPRC
0.0730
0.0676
–
0.0823),
showing
40%
increase
against
baseline
classifier.
panel
five
clinicians
also
compare
predictive
ability
clinical
experts.
comparison
indicated
our
on
par
or
outperforms
predictions
made
by
clinicians,
both
terms
precision
recall.
Conclusion
uses
patient
perform
its
have
been
extensively
linked
severity
specialized
literature.
contributing
diagnosis
can
be
easily
retrieved
early
screening
infected
patients.
Overall,
proposed
could
promising
tool
deploy
healthcare
setting
facilitate
optimize
Computer Modeling in Engineering & Sciences,
Journal Year:
2024,
Volume and Issue:
139(3), P. 2451 - 2477
Published: Jan. 1, 2024
Federated
Learning
(FL),
as
an
emergent
paradigm
in
privacy-preserving
machine
learning,
has
garnered
significant
interest
from
scholars
and
engineers
across
both
academic
industrial
spheres.
Despite
its
innovative
approach
to
model
training
distributed
networks,
FL
vulnerabilities;
the
centralized
server-client
architecture
introduces
risks
of
single-point
failures.
Moreover,
integrity
global
model—a
cornerstone
FL—is
susceptible
compromise
through
poisoning
attacks
by
malicious
actors.
Such
potential
for
privacy
leakage
via
inference
starkly
undermine
FL's
foundational
security
goals.
For
these
reasons,
some
participants
unwilling
use
their
private
data
train
a
model,
which
is
bottleneck
development
industrialization
federated
learning.
Blockchain
technology,
characterized
decentralized
ledger
system,
offers
compelling
solution
issues.
It
inherently
prevents
failures
and,
incentive
mechanisms,
motivates
contribute
computing
power.
Thus,
blockchain-based
(BCFL)
emerges
natural
progression
address
challenges.
This
study
begins
with
concise
introductions
learning
blockchain
technologies,
followed
formal
analysis
specific
problems
that
encounters.
discusses
challenges
combining
two
technologies
presents
overview
latest
cryptographic
solutions
prevent
during
communication
incentives
BCFL.
In
addition,
this
research
examines
BCFL
various
fields,
such
Internet
Things
Vehicles.
Finally,
it
assesses
effectiveness
solutions.
INTENSIF Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi,
Journal Year:
2025,
Volume and Issue:
9(1), P. 60 - 75
Published: Feb. 23, 2025
Background:
The
World
Health
Organization
(WHO)
defines
health
as
a
state
of
physical,
mental,
and
social
well-being,
not
just
the
absence
disease.
Mental
health,
essential
for
overall
is
often
neglected,
leading
to
disorders
like
depression,
major
cause
suicide.
In
Indonesia,
suicide
cases
have
surged,
with
971
reported
from
January
October
2023.
Objective:
This
study
aims
analyze
public
sentiment
regarding
rise
in
Indonesia
using
analysis
methods,
specifically
Support
Vector
Machine
(SVM)
Naive
Bayes
Classifier
(NBC).
findings
are
expected
raise
awareness
provide
policy
recommendations
support
mental
initiatives.
Methods:
One
method
used
understand
perception
issue
text
mining.
research
employs
mining
techniques
algorithms
related
Indonesia.
Data
was
collected
tweets
on
media
platform
X
crawling
methods
snscrape
Python,
totaling
1,175
tweets.
Results:
results
indicate
that
Linear
SVM
model
achieved
higher
accuracy
than
classifying
tweet
sentiments,
an
rate
80%.
Conclusion:
algorithm
linear
kernel
80%
identical
ROC-AUC
score.
Word
cloud
visualization
highlighted
terms
"kill,"
"self,"
"depression,"
"stress"
key
negative
sentiments.
better
policies
