medRxiv (Cold Spring Harbor Laboratory),
Год журнала:
2021,
Номер
unknown
Опубликована: Июнь 12, 2021
Abstract
In
sectors
like
healthcare,
having
classification
models
that
are
both
reliable
and
accurate
is
vital.
Regrettably,
contemporary
techniques
employing
machine
learning
disregard
the
correlations
between
instances
within
data.
This
research,
to
rectify
this,
introduces
a
basic
but
effective
technique
for
converting
tabulated
data
into
graphs,
incorporating
structural
correlations.
Graphs
have
unique
capacity
capture
data,
allowing
us
gain
deeper
insight
in
comparison
carrying
out
isolated
analysis.
The
suggested
underwent
testing
once
integration
of
graph
structure-related
elements
had
been
carried
returned
superior
results
solely
original
features.
achieved
validity
by
returning
significantly
improved
levels
accuracy.
Data
extracted
topological
features
datasets
available
from:
Big Data Mining and Analytics,
Год журнала:
2023,
Номер
6(2), С. 201 - 217
Опубликована: Янв. 26, 2023
Medical
knowledge
graphs
(MKGs)
are
the
basis
for
intelligent
health
care,
and
they
have
been
in
use
a
variety
of
medical
applications.
Thus,
understanding
research
application
development
MKGs
will
be
crucial
future
relevant
biomedical
field.
To
this
end,
we
offer
an
in-depth
review
MKG
work.
Our
begins
with
examination
four
types
information
sources,
graph
creation
methodologies,
six
major
themes
development.
Furthermore,
three
popular
models
reasoning
from
viewpoint
discussed.
A
implementation
path
(RIP)
is
proposed
as
means
expressing
procedures
MKG.
In
addition,
explore
applications
based
on
RIP
classify
them
into
nine
types.
Finally,
summarize
current
state
more
than
130
publications
challenges
opportunities.
Information Fusion,
Год журнала:
2023,
Номер
102, С. 102040 - 102040
Опубликована: Сен. 27, 2023
Multimodal
medical
data
fusion
has
emerged
as
a
transformative
approach
in
smart
healthcare,
enabling
comprehensive
understanding
of
patient
health
and
personalized
treatment
plans.
In
this
paper,
journey
from
to
information
knowledge
wisdom
(DIKW)
is
explored
through
multimodal
for
healthcare.
We
present
review
focused
on
the
integration
various
modalities.
The
explores
different
approaches
such
feature
selection,
rule-based
systems,
machine
;earning,
deep
learning,
natural
language
processing,
fusing
analyzing
data.
This
paper
also
highlights
challenges
associated
with
By
synthesizing
reviewed
frameworks
theories,
it
proposes
generic
framework
that
aligns
DIKW
model.
Moreover,
discusses
future
directions
related
four
pillars
healthcare:
Predictive,
Preventive,
Personalized,
Participatory
approaches.
components
survey
presented
form
foundation
more
successful
implementation
Our
findings
can
guide
researchers
practitioners
leveraging
power
state-of-the-art
revolutionize
healthcare
improve
outcomes.
IEEE Access,
Год журнала:
2020,
Номер
8, С. 164899 - 164921
Опубликована: Янв. 1, 2020
Context
and
Background:Complex
fuzzy
theory
has
a
strong
practical
implication
in
many
real-world
applications.
Complex
Fuzzy
Inference
System
(CFIS)
is
powerful
technique
to
overcome
the
challenges
of
uncertain,
periodic
data.
However,
question
raised
for
CFIS:
How
can
we
deduce
predict
result
case
there
little
knowledge
about
data
information
rule
base?
This
significance
because
real
applications
do
not
have
enough
base
inference
so
that
performance
systems
may
be
low.
Thus,
it
necessary
an
approximate
reasoning
method
represent
derive
final
results.
Motivation:
Recently,
Mamdani
(M-CFIS)
been
proposed
with
specific
mechanism
according
type.
A
new
improvement
so-called
Rule
Reduction
(M-CFIS-R)
designed
utilize
granular
computing
complex
similarity
measures
reduce
as
gain
better
decision-making
problems.
However
M-CFIS-R,
testing
are
checked
by
matching
each
base,
which
leads
high
cost
computational
time.
Besides,
if
contain
records
inferred
output
cannot
generated.
happens
commerce
small
at
time
creation
needs
feed
rules.
Methodology:
In
order
handle
those
issues,
this
article
first
proposes
Knowledge
Graph
terms
linguistic
labels
their
relationships
set.
An
adjacent
matrix
generated
inference.
When
record
Testing
dataset
given,
would
fuzzified
labelled.
Each
component
called
Fast
Search
Algorithm.
Then,
label
Max-Min
operator.
also
propose
four
extensions
including
Sugeno
Systems,
Tsukamoto
Measures
Integrals
M-CFIS-R.
Results:
The
experiments
on
UCI
Machine
Learning
datasets
show
classifies
samples
correctly
M-CFIS-R
very
lower
run
(6.45
times
average).
performed
through
tests
via
2
main
scenarios.
Conclusion:
system
good
reducing
acceptable
accuracy.
It
ability
work
having
limited
base.
