AI in Thyroid Cancer Diagnosis: Techniques, Trends, and Future Directions
Systems,
Journal Year:
2023,
Volume and Issue:
11(10), P. 519 - 519
Published: Oct. 17, 2023
Artificial
intelligence
(AI)
has
significantly
impacted
thyroid
cancer
diagnosis
in
recent
years,
offering
advanced
tools
and
methodologies
that
promise
to
revolutionize
patient
outcomes.
This
review
provides
an
exhaustive
overview
of
the
contemporary
frameworks
employed
field,
focusing
on
objective
AI-driven
analysis
dissecting
across
supervised,
unsupervised,
ensemble
learning.
Specifically,
we
delve
into
techniques
such
as
deep
learning,
artificial
neural
networks,
traditional
classification,
probabilistic
models
(PMs)
under
supervised
With
its
prowess
clustering
dimensionality
reduction,
unsupervised
learning
(USL)
is
explored
alongside
methods,
including
bagging
potent
boosting
algorithms.
The
datasets
(TCDs)
are
integral
our
discussion,
shedding
light
vital
features
elucidating
feature
selection
extraction
critical
for
diagnostic
systems.
We
lay
out
standard
assessment
criteria
regression,
statistical,
computer
vision,
ranking
metrics,
punctuating
discourse
with
a
real-world
example
detection
using
AI.
Additionally,
this
study
culminates
analysis,
current
limitations
delineating
path
forward
by
highlighting
open
challenges
prospective
research
avenues.
Through
comprehensive
exploration,
aim
offer
readers
panoramic
view
AI’s
transformative
role
diagnosis,
underscoring
potential
pointing
toward
optimistic
future.
Language: Английский
Exploring 2D representation and transfer learning techniques for indoor localization
Multimedia Tools and Applications,
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 26, 2025
Language: Английский
Uncovering the Potential of Indoor Localization: Role of Deep and Transfer Learning
Published: June 30, 2023
Indoor
localization
(IL)
is
a
significant
topic
of
study
with
several
practical
applications.
The
area
IL
has
evolved
greatly
in
recent
years
due
to
the
introduction
numerous
technologies
such
as
WiFi,
Bluetooth,
cameras,
and
other
sensors.
Despite
growing
interest
this
field,
there
are
challenges
drawbacks
that
must
be
addressed
develop
more
accurate
sustainable
systems
for
its
real-life
This
review
gives
an
in-depth
look
into
IL,
covering
most
promising
artificial
intelligence-based
hybrid
strategies
have
shown
excellent
potential
overcoming
some
limitations
classic
methods.
In
addition,
paper
investigates
significance
high-quality
datasets
evaluation
metrics
design
assessment
algorithms.
Furthermore,
overview
emphasizes
crucial
role
machine
learning
techniques,
deep
transfer
learning,
play
advancement
IL.
A
focus
on
importance
various
technologies,
methods,
techniques
being
used
improve
it.
Finally,
survey
highlights
need
continued
research
development
create
scalable
can
applied
across
range
industries,
evacuation-egress
routes,
hazard-crime
detection,
smart
occupancy-driven
energy
reduction
asset
tracking
management.
Language: Английский
Exploring 2D Representation and Transfer Learning Techniques for People Identification in Indoor Localization
Published: Nov. 8, 2023
Indoor
localization
is
a
crucial
aspect
of
various
disciplines
in
our
daily
lives.
It
enables
efficient
administration
tasks
and
improves
safety
by
identifying
the
position
items
or
people
inside
spaces,
making
it
useful
for
activities
like
interior
navigation,
asset
tracking,
rescue,
building
security.
However,
traditional
systems
have
limited
performance
due
to
phenomena.
In
this
paper,
novel
system
proposed
identify
users
using
transfer
learning
algorithm
received
signal
strength
indicator
as
an
image.
The
utilizes
pre-trained
models
scalogram
technique
increase
localizing
converted
data
RSSI
results
demonstrate
that
two
can
recognize
with
90%
accuracy
GoogleNet
86%
SqueezNet
model.
Language: Английский
Node localization in WSN using the slime mould algorithm
Published: Nov. 8, 2023
In
the
pursuit
of
optimizing
environmental
management
within
specific
areas,
Wireless
Sensor
Networks
(WSNs)
have
become
indispensable.
Determining
exact
location
each
WSN
sensor
node
is
crucial
for
effective
data
routing
across
network.
This
paper
introduces
slime
mould
algorithm
(SMA),
an
innovative
meta-heuristic
optimization
technique,
tailored
to
address
localization
challenge.
Notably,
literature
review
revealed
no
previous
applications
SMA
this
problem.
Our
simulation
results
indicate
that
proposed
excels
in
accurately
localizing
nodes.
We
also
evaluate
several
key
performance
metrics
underscore
algorithm's
advantages
over
existing
techniques.
Particularly,
when
considering
factors
like
number
anchor
nodes,
iteration
count,
and
population
size,
our
method
consistently
delivers
superior
accuracy
compared
other
established
algorithms.
Language: Английский