Electronic
medical
record
mining
based
on
relationship
classification
has
become
a
hot
topic
in
the
field
of
healthcare.
However,
existing
models
classification,
most
them
use
single-layer
attention,
it
results
relatively
simple
feature
representation
and
is
easy
to
lose
information
during
training.
Therefore,
this
paper
proposes
method
dual
channel
attention.
Firstly,
1
combines
BERT(Bidirectional
Encoder
Representation
from
Transformers),
GRU(Gate
Recurrent
Unit)
Global
Attention,
while
2
Subject_object_mask_generation
So
Attention.
Specifically,
we
module
specify
corresponding
positions
subject
object
within
text.
And
Attention
used
focus
attention
between
object.
Secondly,
outputs
two
channels
are
concatenated.
Finally,
perform
concatenated
results.
We
evaluated
public
dataset
CMeIE(Chinese
Medical
Information
Extraction),
experimental
showed
that
improved
model's
accuracy,
recall
F1
values
increased
by
2.2%,
0.03%
1.3%
respectively,
compared
baseline.
It
indicates
our
certain
advantages
other
methods.
This
paper
proposes
a
novel
personalized
recommendation
algorithm
for
learning
resources
based
on
differential
evolution(DE)
and
graph
neural
networks(GNN).
By
representing
learners
as
data
incorporating
multi-head
attention
mechanism,
we
have
developed
an
effective
method
recommendation.
The
evolution
is
utilized
to
optimize
model
hyperparameters,
resulting
in
improved
performance.
We
conducted
experiments
widely
used
resource
dataset,
comparing
our
with
several
classical
algorithms.
results
demonstrate
significant
advantages
of
approach
terms
accuracy,
recall,
$\Gamma
1$
score,
RMSE
value.
2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM),
Journal Year:
2023,
Volume and Issue:
3, P. 2269 - 2272
Published: Dec. 5, 2023
Confocal
Laser
Endomicroscopy
(CLE)
has
shown
great
advantages
in
the
diagnosis
of
gastrointestinal
diseases.
To
solve
problems
time-consuming
manual
classification
CLE
video
information
frames
and
insufficient
labeled
data,
we
proposed
a
Spatial-Temporal
Fusion
Pseudo-Labeling
method
(STFPL)
based
on
semi-supervised
learning.
Firstly,
networks
trained
with
limited
data
are
used
to
generate
predictions
unlabeled
images
selected
videos.
Secondly,
videos
fused
obtain
pseudo-labels.
Thirdly,
loss
formed
by
pseudo-labels
combined
update
networks.
Finally,
experimental
results
demonstrated
that
STFPL
outperforms
other
algorithms
dataset.
In
addition,
can
achieve
effectiveness
supervised
dataset
for
evaluating
quality
intestinal
cleaning,
Nerthus
With
the
development
of
educational
informatization
and
continuous
progress
artificial
intelligence
technology,
course
knowledge
graphs
have
gradually
become
a
research
hotspot
in
field
education.
The
teaching
process
Python
courses
faces
following
problems:
there
are
many
points
difficulties
courses,
singular
form
presentation,
content
that
cannot
meet
diverse
learning
needs
students.
In
response
to
these
issues,
this
paper
proposes
application
teaching.
After
one
semester
practical
implementation,
students'
efficiency
performance
showed
significant
improvement.
