Explainable models for predicting crab weight based on genetic programming
Ecological Informatics,
Год журнала:
2025,
Номер
unknown, С. 103131 - 103131
Опубликована: Апрель 1, 2025
Язык: Английский
Underwater Weight Estimation of Three Sea Cucumber Species in Culture Tanks Using Image Analysis and ArUco Markers
Animals,
Год журнала:
2025,
Номер
15(8), С. 1121 - 1121
Опубликована: Апрель 13, 2025
Sea
cucumbers
play
a
vital
role
in
marine
and
coastal
ecosystems,
with
some
species
holding
significant
economic
value.
Accurate
growth
assessment,
particularly
weight
estimation,
is
crucial
for
their
management
conservation.
However,
direct
measurement
poses
challenges,
as
sea
expel
internal
fluids
when
handled,
altering
body
size
weight.
This
study
evaluates
the
effectiveness
of
image
analysis
combined
ArUco
markers
to
estimate
three
economically
ecologically
important
cucumber
found
Thailand:
black
(Holothuria
leucospilota),
pink
warty
(Cercodemas
anceps),
sandfish
scabra).
The
proposed
method
demonstrated
high
accuracy,
R2
values
0.9699,
0.9774,
0.9882,
respectively.
Furthermore,
no
differences
(p
>
0.05)
were
observed
between
traditional
hand
measurements
image-based
assessments,
relative
errors
7.71
±
4.30%
cucumber,
5.06
3.37%
4.50
3.23%
sandfish.
Unlike
deep
learning,
which
requires
large
datasets
computation,
this
simple,
cost-effective,
adaptable
highlights
potential
non-invasive
accurate
tool
estimating
approach
minimizes
stress
on
animals
can
be
extended
other
aquatic
species.
challenges
such
shadows,
water
turbidity,
presence
similarly
shaped
objects
near
should
considered
applying
technique
field
conditions.
Язык: Английский
100 Years of Penaeid Domestication and Meta-Analysis of Breeding Traits
Reviews in Fisheries Science & Aquaculture,
Год журнала:
2025,
Номер
unknown, С. 1 - 20
Опубликована: Май 7, 2025
Язык: Английский
Deep Learning for Sustainable Aquaculture: Opportunities and Challenges
Alex Wu,
Ke-Lei Li,
Ziying Song
и другие.
Sustainability,
Год журнала:
2025,
Номер
17(11), С. 5084 - 5084
Опубликована: Июнь 1, 2025
With
the
rising
global
demand
for
aquatic
products,
aquaculture
has
become
a
cornerstone
of
food
security
and
sustainability.
This
review
comprehensively
analyzes
application
deep
learning
in
sustainable
aquaculture,
covering
key
areas
such
as
fish
detection
counting,
growth
prediction
health
monitoring,
intelligent
feeding
systems,
water
quality
forecasting,
behavioral
stress
analysis.
The
study
discusses
suitability
architectures,
including
CNNs,
RNNs,
GANs,
Transformers,
MobileNet,
under
complex
environments
characterized
by
poor
image
severe
occlusion.
It
highlights
ongoing
challenges
related
to
data
scarcity,
real-time
performance,
model
generalization,
cross-domain
adaptability.
Looking
forward,
paper
outlines
future
research
directions
multimodal
fusion,
edge
computing,
lightweight
design,
synthetic
generation,
digital
twin-based
virtual
farming
platforms.
Deep
is
poised
drive
toward
greater
intelligence,
efficiency,
Язык: Английский