Foods,
Journal Year:
2024,
Volume and Issue:
13(11), P. 1662 - 1662
Published: May 25, 2024
The
quality
of
fresh
foods
tends
to
deteriorate
rapidly
during
harvesting,
storage,
and
transportation.
Intelligent
detection
equipment
is
designed
monitor
ensure
product
in
the
supply
chain,
measure
appropriate
food
parameters
real
time,
thus
minimize
degradation
potential
financial
losses.
Through
various
available
tracking
devices,
consumers
can
obtain
actionable
information
about
products.
This
paper
reviews
recent
progress
intelligent
for
sensing
deterioration
foods,
including
computer
vision
equipment,
electronic
nose,
smart
colorimetric
films,
hyperspectral
imaging
(HSI),
near-infrared
spectroscopy
(NIR),
nuclear
magnetic
resonance
(NMR),
ultrasonic
non-destructive
testing,
tracing
equipment.
These
devices
offer
advantages
high
speed,
operation,
precision,
sensitivity.
BMC Plant Biology,
Journal Year:
2024,
Volume and Issue:
24(1)
Published: Jan. 2, 2024
Abstract
The
ability
of
a
data
fusion
system
composed
computer
vision
(CVS)
and
an
electronic
nose
(e-nose)
was
evaluated
to
predict
key
physiochemical
attributes
distinguish
red-fleshed
kiwifruit
produced
in
three
distinct
regions
northern
Iran.
Color
morphological
features
from
whole
middle-cut
kiwifruits,
along
with
the
maximum
responses
13
metal
oxide
semiconductor
(MOS)
sensors
e-nose
system,
were
used
as
inputs
system.
Principal
component
analysis
(PCA)
revealed
that
first
two
principal
components
(PCs)
extracted
could
effectively
differentiate
samples
different
regions.
PCA-SVM
algorithm
achieved
93.33%
classification
rate
for
kiwifruits
based
on
individual
CVS.
Data
increased
SVM
model
100%
improved
performance
Support
Vector
Regression
(SVR)
predicting
indices
compared
systems.
fusion-based
PCA-SVR
models
validation
R
2
values
ranging
90.17%
Brix-Acid
Ratio
(BAR)
98.57%
pH
prediction.
These
results
demonstrate
high
potential
fusing
artificial
visual
olfactory
systems
quality
monitoring
identifying
geographical
growing
kiwifruits.
Scientific African,
Journal Year:
2024,
Volume and Issue:
24, P. e02153 - e02153
Published: March 5, 2024
This
study
introduced
a
metal-oxide-semiconductor
(MOS)
based
electronic
nose
(E-nose)
to
perform
on-the-spot
classification
of
superior-quality
black
tea.
A
piecewise
feature
method
on
line-fitting
model
was
extract
comprehensive
features
E-nose
sensor
response
curves.
Principal
component
analysis
(PCA)
and
linear
discriminant
(LDA)
were
used
for
data
dimensionality
reduction
structure
visualization.
Support
vector
machine
(SVM)
with
Radial
kernel
function
assess
the
performance
E-nose.
The
results
indicated
that
SVM
coupled
performed
better
achieved
best
rates
99.50%,
95.30%,
96.50%,
training,
validation,
testing
datasets
respectively,
sensitivity
specificity
up
98.6%
99.10%.
result
further
correlated
compound
concentrations
in
tea,
measured
using
gas
chromatography-mass
spectrometry
(GC-MS).
Based
its
enhanced
evaluation,
lab-built
system
yielded
promising
assessing
