Integrating AIoT Technologies in Aquaculture: A Systematic Review
Future Internet,
Год журнала:
2025,
Номер
17(5), С. 199 - 199
Опубликована: Апрель 30, 2025
The
increasing
global
demand
for
seafood
underscores
the
necessity
sustainable
aquaculture
practices.
However,
several
challenges,
including
rising
operational
costs,
variable
environmental
conditions,
and
threat
of
disease
outbreaks,
impede
progress
in
this
field.
This
review
explores
transformative
role
Artificial
Intelligence
Things
(AIoT)
mitigating
these
challenges.
We
analyse
current
research
on
AIoT
applications
aquaculture,
with
a
strong
emphasis
use
IoT
sensors
real-time
data
collection
AI
algorithms
effective
analysis.
Our
focus
areas
include
monitoring
water
quality,
implementing
smart
feeding
strategies,
detecting
diseases,
analysing
fish
behaviour,
employing
automated
counting
techniques.
Nevertheless,
gaps
remain,
particularly
regarding
integration
broodstock
management,
development
multimodal
systems,
challenges
model
generalization.
Future
advancements
should
prioritise
adaptability,
cost-effectiveness,
sustainability
while
emphasizing
importance
advanced
biosensing
capabilities,
digital
twin
technologies.
In
conclusion,
presents
substantial
opportunities
enhancing
practices,
successful
implementation
will
depend
overcoming
related
to
scalability,
cost,
technical
expertise,
improving
models’
ensuring
sustainability.
Язык: Английский
AASNet: A Novel Image Instance Segmentation Framework for Fine-Grained Fish Recognition via Linear Correlation Attention and Dynamic Adaptive Focal Loss
Applied Sciences,
Год журнала:
2025,
Номер
15(7), С. 3986 - 3986
Опубликована: Апрель 4, 2025
Smart
fisheries,
integrating
advanced
technologies
such
as
the
Internet
of
Things
(IoT),
artificial
intelligence
(AI),
and
image
processing,
are
pivotal
in
enhancing
aquaculture
efficiency,
sustainability,
resource
management
by
enabling
real-time
environmental
monitoring,
precision
feeding,
disease
prevention.
However,
underwater
fish
recognition
faces
challenges
complex
aquatic
environments,
which
hinder
accurate
detection
behavioral
analysis.
To
address
these
issues,
we
propose
a
novel
instance
segmentation
framework
based
on
deep
learning
neural
network,
defined
AASNet
(Agricultural
Aqua
Segmentation
Network).
In
order
to
improve
accuracy
availability
fine-grained
recognition,
introduce
Linear
Correlation
Attention
(LCA)
mechanism,
uses
Pearson
correlation
coefficients
capture
linear
correlations
between
features.
This
helps
resolve
inconsistencies
caused
lighting
changes
color
variations,
significantly
improving
extraction
semantic
information
for
similar
objects.
Additionally,
Dynamic
Adaptive
Focal
Loss
(DAFL)
is
designed
classification
under
extreme
data
imbalance
conditions.
Abundant
experiments
two
datasets
demonstrated
that
proposed
obtains
an
optimal
balance
performance
efficiency.
Concretely,
achieves
mAP
scores
31.7
47.4,
respectively,
UIIS
USIS
dataset,
outperforming
existing
state-of-the-art
methods.
Moreover,
inference
speed
up
28.9
ms/per,
suitable
practical
agricultural
applications
smart
farming.
Язык: Английский
Computation and Analysis of Phenotypic Parameters of Scylla paramamosain Based on YOLOv11-DYPF Keypoint Detection
Aquacultural Engineering,
Год журнала:
2025,
Номер
111, С. 102571 - 102571
Опубликована: Май 21, 2025
Язык: Английский
An Evolutionary Game Analysis of the Aquatic Product Traceability System from a Multi-Actor Perspective
Water,
Год журнала:
2025,
Номер
17(11), С. 1656 - 1656
Опубликована: Май 29, 2025
This
study
employs
an
evolutionary
game
theory
framework
to
analyze
the
interactive
learning,
imitation,
and
strategic
evolution
among
multiple
actors
within
China’s
aquatic
product
traceability
system.
It
focuses
on
four
types
of
interactions:
between
fishers
government,
consumers,
who
adopt
system
those
do
not,
consumers
purchase
traceable
products
not.
The
evolutionarily
stable
strategies
equilibrium
outcomes
in
each
depend
net
benefits
obtained
various
costs
borne
by
party.
Among
these
factors,
transaction
play
a
particularly
critical
role
shaping
stakeholder
behavior.
lower
costs,
more
likely
stakeholders
are
that
support
or
enhance
functioning
Therefore,
reducing
operational
should
be
key
policy
focus
for
government.
includes
efforts
regulatory
development,
platform
infrastructure
construction,
improvement
information
exchange
mechanisms
foster
sustainable
development
aquaculture.
Язык: Английский