Plants,
Journal Year:
2024,
Volume and Issue:
13(12), P. 1681 - 1681
Published: June 18, 2024
In
this
study,
an
advanced
method
for
apricot
tree
disease
detection
is
proposed
that
integrates
deep
learning
technologies
with
various
data
augmentation
strategies
to
significantly
enhance
the
accuracy
and
efficiency
of
detection.
A
comprehensive
framework
based
on
adaptive
sampling
latent
variable
network
(ASLVN)
spatial
state
attention
mechanism
was
developed
aim
enhancing
model’s
capability
capture
characteristics
diseases
while
ensuring
its
applicability
edge
devices
through
model
lightweighting
techniques.
Experimental
results
demonstrated
significant
improvements
in
precision,
recall,
accuracy,
mean
average
precision
(mAP).
Specifically,
0.92,
recall
0.89,
0.90,
mAP
0.91,
surpassing
traditional
models
such
as
YOLOv5,
YOLOv8,
RetinaNet,
EfficientDet,
DEtection
TRansformer
(DETR).
Furthermore,
ablation
studies,
critical
roles
ASLVN
performance
were
validated.
These
experiments
not
only
showcased
contributions
each
component
improving
but
also
highlighted
method’s
address
challenges
complex
environments.
Eight
types
detected,
including
Powdery
Mildew
Brown
Rot,
representing
a
technological
breakthrough.
The
findings
provide
robust
technical
support
management
actual
agricultural
production
offer
broad
application
prospects.
ICST Transactions on Scalable Information Systems,
Journal Year:
2023,
Volume and Issue:
unknown
Published: Oct. 3, 2023
Disease
detection
on
a
farm
requires
laborious
and
time-consuming
observation
of
individual
plants,
which
is
made
more
difficult
when
the
large
many
different
plants
are
farmed.
To
address
these
problems,
cutting-edge
technologies,
AI,
Deep
Learning
(DL)
employed
to
provide
accurate
illness
predictions.
When
it
comes
smart
farming
precision
agriculture,
IoT
opens
up
exciting
new
possibilities.
certain
extent,
goal-mouth
"smart
farming"
upsurge
productivity
efficiency
in
agricultural
processes.
Smart
an
approach
agriculture
Internet
Things
devices
interconnected
technologies
used
optimize
existing
methods.
Utilizing
(IoT)
devices,
aids
informed
decision
making.
In
parts
world,
rice
staple
diet.
This
means
that
early
plant
diseases
using
automated
techniques
essential.
Growing
yields
profits
may
be
helped
along
by
DL
model
creation
deployment
agriculture.
Here
we
introduce
DRL,
deep
residual
learning
framework
has
been
trained
photos
leaves
recognize
one
four
classes.
The
suggested
called
WO-DRL,
hyper-parameter
tuning
procedure
DRL
executed
with
help
Whale
Optimization
algorithm.
outcomes
demonstrate
efficacy
our
directing
WO-DRL
learn
important
characteristics.
findings
this
study
will
pave
way
for
sector
quickly
diagnose
treat
AI.
Tropical Plants,
Journal Year:
2024,
Volume and Issue:
3(1), P. 0 - 0
Published: Jan. 1, 2024
This
paper
delves
into
the
realm
of
artificial
intelligence,
where
an
array
deep
learning
techniques
has
proven
effective
in
automating
crop
leaf
disease
identification
and
classification.
The
current
shows
mature
detection
methodologies
for
apple,
tomato,
rice,
mango,
coconut
durian
diseases
with
examples,
while
spotlighting
research
on
tropical
plants.
Through
this
exploration,
valuable
insights
benefits
applications
based
methods
detection.
Highlighting
advantages
automated
feature
extraction
detection,
describes
salient
features
challenges
application
tropics.
In
we
offer
introductory
overview
a
model
factors
influencing
accuracy
speed,
proposing
ways
to
mitigate
inherent
trade-offs
between
these
indicators.
Furthermore,
challenges,
such
as
multi-scale
overlapping,
that
may
occur
plants
tropics,
have
been
examined,
enriching
our
understanding
learning-driven
agriculture.
Plants,
Journal Year:
2024,
Volume and Issue:
13(12), P. 1681 - 1681
Published: June 18, 2024
In
this
study,
an
advanced
method
for
apricot
tree
disease
detection
is
proposed
that
integrates
deep
learning
technologies
with
various
data
augmentation
strategies
to
significantly
enhance
the
accuracy
and
efficiency
of
detection.
A
comprehensive
framework
based
on
adaptive
sampling
latent
variable
network
(ASLVN)
spatial
state
attention
mechanism
was
developed
aim
enhancing
model’s
capability
capture
characteristics
diseases
while
ensuring
its
applicability
edge
devices
through
model
lightweighting
techniques.
Experimental
results
demonstrated
significant
improvements
in
precision,
recall,
accuracy,
mean
average
precision
(mAP).
Specifically,
0.92,
recall
0.89,
0.90,
mAP
0.91,
surpassing
traditional
models
such
as
YOLOv5,
YOLOv8,
RetinaNet,
EfficientDet,
DEtection
TRansformer
(DETR).
Furthermore,
ablation
studies,
critical
roles
ASLVN
performance
were
validated.
These
experiments
not
only
showcased
contributions
each
component
improving
but
also
highlighted
method’s
address
challenges
complex
environments.
Eight
types
detected,
including
Powdery
Mildew
Brown
Rot,
representing
a
technological
breakthrough.
The
findings
provide
robust
technical
support
management
actual
agricultural
production
offer
broad
application
prospects.
