ACM Computing Surveys,
Journal Year:
2025,
Volume and Issue:
unknown
Published: May 7, 2025
Intelligent
transportation
systems
are
vital
for
modern
traffic
management
and
optimization,
greatly
improving
efficiency
safety.
With
the
rapid
development
of
generative
artificial
intelligence
(Generative
AI)
technologies
in
areas
like
image
generation
natural
language
processing,
AI
has
also
played
a
crucial
role
addressing
key
issues
intelligent
(ITS),
such
as
data
sparsity,
difficulty
observing
abnormal
scenarios,
modeling
uncertainty.
In
this
review,
we
systematically
investigate
relevant
literature
on
techniques
different
types
tasks
ITS
tailored
specifically
road
transportation.
First,
introduce
principles
techniques.
Then,
classify
into
four
types:
perception,
prediction,
simulation,
decision-making.
We
illustrate
how
addresses
these
tasks.
Finally,
summarize
challenges
faced
applying
to
systems,
discuss
future
research
directions
based
application
scenarios.
Molecules,
Journal Year:
2024,
Volume and Issue:
29(15), P. 3512 - 3512
Published: July 26, 2024
The
rational
design,
activity
prediction,
and
adaptive
application
of
biological
elements
(bio-elements)
are
crucial
research
fields
in
synthetic
biology.
Currently,
a
major
challenge
the
field
is
efficiently
designing
desired
bio-elements
accurately
predicting
their
using
vast
datasets.
advancement
artificial
intelligence
(AI)
technology
has
enabled
machine
learning
deep
algorithms
to
excel
uncovering
patterns
bio-element
data
performance.
This
review
explores
AI
design
bio-elements,
regulation
transcription-factor-based
biosensor
response
performance
AI-designed
elements.
We
discuss
advantages,
adaptability,
challenges
addressed
by
various
applications,
highlighting
powerful
potential
analyzing
data.
Furthermore,
we
propose
innovative
solutions
faced
suggest
future
directions.
By
consolidating
current
demonstrating
practical
applications
biology,
this
provides
valuable
insights
for
advancing
both
academic
biotechnology.
Proceedings of the Institution of Mechanical Engineers Part H Journal of Engineering in Medicine,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Feb. 4, 2025
Generative
deep
learning
has
emerged
as
a
promising
data
augmentation
technique
in
recent
years.
This
approach
becomes
particularly
valuable
areas
such
motion
analysis,
where
it
is
challenging
to
collect
substantial
amounts
of
data.
The
objective
the
current
study
introduce
strategy
that
relies
on
variational
autoencoder
generate
synthetic
kinetic
and
kinematic
variables.
variables
consist
hip
knee
joint
angles
moments,
respectively,
both
sagittal
frontal
plane,
ground
reaction
forces.
Statistical
parametric
mapping
(SPM)
did
not
detect
significant
differences
between
real
for
each
biomechanical
considered.
To
further
evaluate
effectiveness
this
approach,
long-short
term
model
(LSTM)
was
trained
only
(R)
combination
(R&S);
performance
these
two
models
then
assessed
test
unseen
during
training.
principal
findings
included
achieving
comparable
results
terms
nRMSE
when
predicting
moments
(R&S:
9.86%
vs
R:
10.72%)
plane
9.21%
9.75%),
16.93%
16.79%)
13.29%
14.60%).
main
novelty
lies
introducing
an
effective
analysis
settings.
ACM Transactions on Embedded Computing Systems,
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 24, 2025
With
the
advent
of
Industrial
4.0
and
push
towards
Industry
5.0,
data
generated
by
industries
have
become
surprisingly
large.
This
abundance
significantly
boosts
machine
deep
learning
models
for
Predictive
Maintenance
(PdM).
The
PdM
plays
a
vital
role
in
extending
lifespan
industrial
equipment
machines
while
also
helping
to
reduce
risk
unscheduled
downtime.
Given
its
multidisciplinary
nature,
field
has
been
approached
from
many
different
angles:
this
comprehensive
survey
aims
provide
an
up-to-date
overview
focused
on
all
learning-based
strategies,
discussing
weaknesses
strengths.
is
based
Preferred
Reporting
Items
Systematic
Reviews
Meta-Analyses
(PRISMA)
methodological
flow,
allowing
systematic
complete
review
literature.
In
particular,
firstly,
we
explore
main
used
PdM,
mainly
Convolutional
Neural
Networks
(ConvNets),
Autoencoders
(AEs),
Generative
Adversarial
(GANs),
Transformers,
giving
newest
such
as
diffusion
foundation
models.
Then,
discuss
paradigms
applied
i.e.
,
supervised,
unsupervised,
ensemble,
transfer,
federated,
reinforcement
learning.
Furthermore,
work
discusses
pipeline
data-driven
benefits,
practical
applications,
datasets,
benchmarks.
addition,
evaluation
metrics
each
stage
state-of-the-art
hardware
devices
are
discussed.
Finally,
challenges
future
presented.
ACM Computing Surveys,
Journal Year:
2025,
Volume and Issue:
unknown
Published: May 7, 2025
Intelligent
transportation
systems
are
vital
for
modern
traffic
management
and
optimization,
greatly
improving
efficiency
safety.
With
the
rapid
development
of
generative
artificial
intelligence
(Generative
AI)
technologies
in
areas
like
image
generation
natural
language
processing,
AI
has
also
played
a
crucial
role
addressing
key
issues
intelligent
(ITS),
such
as
data
sparsity,
difficulty
observing
abnormal
scenarios,
modeling
uncertainty.
In
this
review,
we
systematically
investigate
relevant
literature
on
techniques
different
types
tasks
ITS
tailored
specifically
road
transportation.
First,
introduce
principles
techniques.
Then,
classify
into
four
types:
perception,
prediction,
simulation,
decision-making.
We
illustrate
how
addresses
these
tasks.
Finally,
summarize
challenges
faced
applying
to
systems,
discuss
future
research
directions
based
application
scenarios.
