PeerJ Computer Science,
Journal Year:
2024,
Volume and Issue:
10, P. e2547 - e2547
Published: Nov. 22, 2024
Purpose
This
study
aims
to
address
the
limitations
of
traditional
data
processing
methods
in
predicting
agricultural
product
prices,
which
is
essential
for
advancing
rural
informatization
enhance
efficiency
and
support
economic
growth.
Methodology
The
RL-CNN-GRU
framework
combines
reinforcement
learning
(RL),
convolutional
neural
network
(CNN),
gated
recurrent
unit
(GRU)
improve
price
predictions
using
multidimensional
time
series
data,
including
historical
weather,
soil
conditions,
other
influencing
factors.
Initially,
model
employs
a
1D-CNN
feature
extraction,
followed
by
GRUs
capture
temporal
patterns
data.
Reinforcement
further
optimizes
model,
enhancing
analysis
accuracy
inputs
more
reliable
predictions.
Results
Testing
on
public
proprietary
datasets
shows
that
significantly
outperforms
models
with
lower
mean
squared
error
(MSE)
absolute
(MAE)
metrics.
Conclusion
contributes
offering
accurate
prediction
tool,
thereby
supporting
improved
decision-making
processes
fostering
development.
Results in Engineering,
Journal Year:
2024,
Volume and Issue:
23, P. 102705 - 102705
Published: Aug. 15, 2024
In
modern
agriculture,
the
threat
of
fire
poses
significant
economic
and
environmental
risks.
Additionally,
traditional
detection
methods
are
inadequate
poorly
integrated
with
advanced
technologies.
It
is
crucial
to
develop
a
more
efficient
reliable
system.
Also,
lack
real-time
accurate
monitoring
in
current
systems
compromises
resilience
sustainability
farming
operations.
This
article
details
developing
implementing
system
tailored
for
smart
agriculture.
integrates
cutting-edge
technologies,
including
Internet
Things
(IoT),
embedded
systems,
Flask-based
web
application,
fortified
by
cybersecurity
measures
such
as
login
authentication
secure
HTTP
protocols.
The
system's
primary
aim
monitor
conditions
continuously
agricultural
fields
detect
signs
smoke
or
flame
swiftly,
facilitating
preventive
actions
safeguard
crops
infrastructure.
architecture
employs
sensors
distributed
across
conditions,
Raspberry
Pi
3
B+
central
processing
unit
data
acquisition
transmission,
interface
developed
using
Flask,
HTML,
CSS
visualization
data.
Critical
components
like
MCP3208
analog-to-digital
converter
ensure
reliability
accuracy.
Experimental
results
confirm
efficacy
early
via
browser.
Enhanced
security
features,
authentication,
protect
sensitive
information,
while
regular
updates
maintain
relevance.
study
advances
prevention
farm
preservation
efforts,
offering
high-performance
technological
solution
proactive
quick
response
risks,
thereby
supporting
food
sustainable
practices.
Faced
with
the
growing
challenges
of
water
management
in
agriculture,
this
paper
explores
shortcomings
traditional
irrigation
methods
and
calls
for
adoption
innovative
technologies
to
meet
these
challenges.
This
proposed
an
solution
by
combining
embedded
systems
(Controllers)
environmental
sensors
create
a
real-time
intelligent
system.
Based
on
technologies,
system
automatically
adjusts
operations
real-time,
according
conditions,
thus
improving
use
efficiency.
Essentially,
study
developed
capable
dynamically
adjusting
based
parameters,
including
soil
moisture
level
thresholds.
approach
aims
reduce
wastage
while
agricultural
productivity.
The
methodology
involves
Arduino
Mega
2560
microcontroller,
advanced
such
as
temperature,
humidity
(DHT22),
moisture,
level,
pumps
actuators.
algorithm
enabled
continuous
monitoring
adaptive
control
pump,
well
data
logging
controller
feedback.
Tests
carried
out
confirm
effectiveness
smart
since
it
has
considerably
reduced
maintaining
optimum
productivity,
compared
methods.
enables
farmers
save
considerable
quantities
guaranteeing
high-quality
harvest.
By
encouraging
more
sustainable
farming
practices,
contributes
preservation
natural
resources
long-term
sustainability
agriculture.
IGI Global eBooks,
Journal Year:
2025,
Volume and Issue:
unknown, P. 267 - 296
Published: Feb. 7, 2025
Automated
plant
disease
detection
using
computer
vision
has
transformed
agriculture
by
addressing
challenges
in
health
management,
productivity,
and
sustainability.
This
chapter
explores
advancements
from
traditional
methods
to
AI-enhanced
deep
learning
multi-modal
imaging,
enabling
early
detection,
real-time
processing,
precise
interventions.
Applications
like
precision
agriculture,
IoT
integration,
data-driven
decision-making
foster
eco-friendly
practices
resource
efficiency.
Despite
such
as
data
quality,
scalability,
accessibility,
future
innovations
collection,
sustainable
hardware,
collaboration
promise
shape
resilient
agricultural
systems.
By
aligning
technology
with
sustainability,
automated
supports
food
security,
environmental
conservation,
the
evolution
of
modern
farming
practices.
