Artificial Intelligence in Educational Data Mining and Human-in-the-Loop Machine Learning and Machine Teaching: Analysis of Scientific Knowledge
Applied Sciences,
Год журнала:
2025,
Номер
15(2), С. 772 - 772
Опубликована: Янв. 14, 2025
This
study
explores
the
integration
of
artificial
intelligence
(AI)
into
educational
data
mining
(EDM),
human-assisted
machine
learning
(HITL-ML),
and
machine-assisted
teaching,
with
aim
improving
adaptive
personalized
environments.
A
systematic
review
scientific
literature
was
conducted,
analyzing
370
articles
published
between
2006
2024.
The
research
examines
how
AI
can
support
identification
patterns
individual
student
needs.
Through
EDM,
are
analyzed
to
predict
performance
enable
timely
interventions.
HITL-ML
ensures
that
educators
remain
in
control,
allowing
them
adjust
system
according
their
pedagogical
goals
minimizing
potential
biases.
Machine-assisted
teaching
allows
processes
be
structured
around
specific
criteria,
ensuring
relevance
outcomes.
findings
suggest
these
applications
significantly
improve
learning,
tracking,
resource
optimization
institutions.
highlights
ethical
considerations,
such
as
need
protect
privacy,
ensure
transparency
algorithms,
promote
equity,
inclusive
fair
Responsible
implementation
methods
could
quality.
Язык: Английский
Visual Data and Pattern Analysis for Smart Education: A Robust Drl-Based Early Warning System for Student Performance Prediction
Опубликована: Апрель 29, 2024
Artificial
Intelligence
(AI)
and
Deep
Reinforcement
Learning
(DRL)
have
revolutionised
e-learning
by
creating
personalised,
adaptive,
secure
environments.
However,
challenges
such
as
privacy,
bias,
data
limitations
persist.
E-FedCloud
aims
to
address
these
issues
providing
more
agile,
experiences.
This
study
introduces
E-FedCloud,
an
AI-assisted
adaptive
system
that
automates
personalised
recommendations
tracking,
thereby
enhancing
student
performance.
It
employs
federated
learning-based
authentication
ensure
private
access
for
both
course
instructors
students.
Intelligent
Software
Agents
(ISAs)
evaluate
weekly
engagement
using
the
Shannon
Entropy
method,
classifying
students
into
either
engaged
or
not-engaged
clusters.
utilises
status,
demographic
information,
innovative
DRL-based
early
warning
system,
specifically
ID2QN,
predict
performance
of
Based
on
predictions,
categorises
three
groups:
risk
dropping
out,
scoring
lower
in
final
exam,
failing
end
exam.
a
multi-disciplinary
ontology
graph
attention-based
capsule
network
automated,
recommendations.
The
also
integrates
tracking
enhance
engagement.
Data
is
securely
stored
blockchain
LWEA
encryption
method.
Язык: Английский