Computation,
Год журнала:
2024,
Номер
12(12), С. 232 - 232
Опубликована: Ноя. 26, 2024
Cervical
cancer
(CC)
remains
a
significant
health
issue,
especially
in
low-
and
middle-income
countries
(LMICs).
While
Pap
smears
are
the
standard
screening
method,
they
have
limitations,
like
low
sensitivity
subjective
interpretation.
Liquid-based
cytology
(LBC)
offers
improvements
but
still
relies
on
manual
analysis.
This
study
explored
potential
of
deep
learning
(DL)
for
automated
cervical
cell
classification
using
both
LBC
samples.
A
novel
image
segmentation
algorithm
was
employed
to
extract
single-cell
patches
training
ResNet-50
model.
The
model
trained
images
achieved
remarkably
high
(0.981),
specificity
(0.979),
accuracy
(0.980),
outperforming
previous
CNN
models.
However,
smear
dataset
significantly
lower
performance
(0.688
sensitivity,
0.762
specificity,
0.8735
accuracy).
suggests
that
noisy
poor
definition
pose
challenges
classification,
whereas
provides
better
classifiable
cells
patches.
These
findings
demonstrate
AI-powered
improving
CC
screening,
particularly
with
LBC.
efficiency
DL
models
combined
effective
can
contribute
earlier
detection
more
timely
intervention.
Future
research
should
focus
implementing
explainable
AI
increase
clinician
trust
facilitate
adoption
AI-assisted
LMICs.
Sustainability,
Год журнала:
2024,
Номер
16(19), С. 8336 - 8336
Опубликована: Сен. 25, 2024
This
paper
explores
new
sensor
technologies
and
their
integration
within
Connected
Autonomous
Vehicles
(CAVs)
for
real-time
road
condition
monitoring.
Sensors
like
accelerometers,
gyroscopes,
LiDAR,
cameras,
radar
that
have
been
made
available
on
CAVs
are
able
to
detect
anomalies
roads,
including
potholes,
surface
cracks,
or
roughness.
also
describes
advanced
data
processing
techniques
of
detected
with
sensors,
machine
learning
algorithms,
fusion,
edge
computing,
which
enhance
accuracy
reliability
in
assessment.
Together,
these
support
instant
safety
long-term
maintenance
cost
reduction
proactive
strategies.
Finally,
this
article
provides
a
comprehensive
review
the
state-of-the-art
future
directions
monitoring
systems
traditional
smart
roads.
it - Information Technology,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 30, 2025
Abstract
As
artificial
intelligence
(AI)
increasingly
permeates
high-stakes
domains
such
as
healthcare,
transportation,
and
law
enforcement,
ensuring
its
trustworthiness
has
become
a
critical
challenge.
This
article
proposes
an
integrative
Explainable
AI
(XAI)
framework
to
address
the
challenges
of
interpretability,
explainability,
interactivity,
robustness.
By
combining
XAI
methods,
incorporating
human-AI
interaction
using
suitable
evaluation
techniques,
implementation
this
serves
holistic
approach.
The
discusses
framework’s
contribution
trustworthy
gives
outlook
on
open
related
interdisciplinary
collaboration,
generalization
evaluation.
Sensors,
Год журнала:
2023,
Номер
23(24), С. 9890 - 9890
Опубликована: Дек. 18, 2023
Participatory
exposure
research,
which
tracks
behaviour
and
assesses
to
stressors
like
air
pollution,
traditionally
relies
on
time-activity
diaries.
This
study
introduces
a
novel
approach,
employing
machine
learning
(ML)
empower
laypersons
in
human
activity
recognition
(HAR),
aiming
reduce
dependence
manual
recording
by
leveraging
data
from
wearable
sensors.
Recognising
complex
activities
such
as
smoking
cooking
presents
unique
challenges
due
specific
environmental
conditions.
In
this
we
combined
environment/ambient
wrist-worn
activity/biometric
sensors
for
an
urban
stressor
study,
measuring
parameters
particulate
matter
concentrations,
temperature,
humidity.
Two
groups,
Group
H
(88
individuals)
M
(18
individuals),
wore
the
devices
manually
logged
their
hourly
minutely,
respectively.
Prioritising
accessibility
inclusivity,
selected
three
classification
algorithms:
k-nearest
neighbours
(IBk),
decision
trees
(J48),
random
forests
(RF),
based
on:
(1)
proven
efficacy
existing
literature,
(2)
understandability
transparency
laypersons,
(3)
availability
user-friendly
platforms
WEKA,
(4)
efficiency
basic
office
laptops
or
smartphones.
Accuracy
improved
with
finer
temporal
resolution
detailed
categories.
However,
when
compared
other
published
our
accuracy
rates,
particularly
less
activities,
were
not
competitive.
Misclassifications
higher
vague
(resting,
playing),
while
well-defined
(smoking,
cooking,
running)
had
few
errors.
Including
sensor
increased
all
especially
playing,
smoking,
running.
Future
work
should
consider
exploring
explainable
algorithms
available
diverse
tools
platforms.
Our
findings
underscore
ML's
potential
studies,
emphasising
its
adaptability
significance
also
highlighting
areas
improvement.
International Journal of Advanced Technology and Engineering Exploration,
Год журнала:
2024,
Номер
11(111)
Опубликована: Фев. 29, 2024
The
ocean,
serving
as
a
vast
reservoir
of
resources
crucial
for
the
economy
and
human
sustenance,
plays
pivotal
role
in
influencing
economies
specific
countries.This
impact
is
particularly
evident
through
expansion
fisheries
sector
related
marine
industries
[1].To
strategically
develop
ensure
sustainable
growth
these
industries,
application
data
mining,
classification,
analyses
becomes
indispensable.Data
set
techniques
focused
on
extracting
pertinent
information
from
extensive
databases
across
diverse
business
domains,
stands
key
tool
informed
decision-making
[2].However,
existing
literature
this
field
faces
challenges
that
warrant
careful
consideration.
