Multi-spectra combined with Bayesian optimized machine learning algorithms for rapid and non-destructive detection of adulterated functional food Panax notoginseng powder
Huanhuan Guan,
No information about this author
Zhi‐Tong Zhang,
No information about this author
Lei Bai
No information about this author
et al.
Journal of Food Composition and Analysis,
Journal Year:
2024,
Volume and Issue:
133, P. 106412 - 106412
Published: June 7, 2024
Language: Английский
Research on millet origin identification model based on improved parrot optimizer optimized regularized extreme learning machine
Peng Gao,
No information about this author
Na Wang,
No information about this author
Yang Lü
No information about this author
et al.
Journal of Food Composition and Analysis,
Journal Year:
2025,
Volume and Issue:
unknown, P. 107354 - 107354
Published: Feb. 1, 2025
Language: Английский
Online detection of Q-marker concentrations in the Xuefu Zhuyu oral liquid extraction process using a multi-source cross-scale NIR attention fusion neural network
D Liu,
No information about this author
Lele Gao,
No information about this author
Zihao Cui
No information about this author
et al.
Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy,
Journal Year:
2025,
Volume and Issue:
339, P. 126293 - 126293
Published: April 24, 2025
Language: Английский
Spectroscopic techniques combined with DD-SIMCA model and explainable artificial intelligence for rapidly and accurately identifying the quality of Astragali Radix
Lei Bai,
No information about this author
Zhi‐Tong Zhang,
No information about this author
Dongping Yuan
No information about this author
et al.
Industrial Crops and Products,
Journal Year:
2025,
Volume and Issue:
231, P. 121140 - 121140
Published: May 9, 2025
Language: Английский
Accurate and intelligent quantification of adulterated Angelicae Sinensis Radix by a novel ensemble method with near-infrared spectroscopy
Journal of Applied Research on Medicinal and Aromatic Plants,
Journal Year:
2025,
Volume and Issue:
unknown, P. 100640 - 100640
Published: May 1, 2025
Language: Английский
Rapid Identification of Continuous Asexual Reproduction of Gastrodia elata Blume Using Near-Infrared Spectroscopy (NIRS) and Neural Network Algorithms
Analytical Letters,
Journal Year:
2025,
Volume and Issue:
unknown, P. 1 - 19
Published: May 19, 2025
Language: Английский
Estimation of lithium battery state of charge using the LTG-SABO-GRU model
Yanjun Xiao,
No information about this author
Weihan Song,
No information about this author
Weiling Liu
No information about this author
et al.
Measurement Science and Technology,
Journal Year:
2024,
Volume and Issue:
35(11), P. 115106 - 115106
Published: July 31, 2024
Abstract
Accurate
estimation
of
the
state
charge
(SOC)
in
lithium
batteries
is
crucial
for
optimizing
energy
utilization
and
ensuring
battery
safety
within
management
systems
(BMSs).
While
deep
learning
techniques
have
made
significant
progress,
time-series
models
based
on
gate
recurrent
unit
(GRU)
gained
widespread
application
SOC
estimation.
However,
their
performance
heavily
hinges
initial
hyperparameter
settings,
impacting
both
precision
range.
To
address
this
challenge,
we
propose
a
novel
algorithm—the
logistic-tent-gold
subtraction
average-based
optimizer
(LTG-SABO)—which
combines
composite
chaotic
mapping
with
golden
sine
algorithm.
The
LTG-SABO
algorithm
aims
to
optimize
key
hyperparameters
GRU
model,
thereby
enhancing
robustness
By
leveraging
Logistic-tent
population
initialization,
our
approach
not
only
expands
search
space
but
also
effectively
prevents
convergence
local
optima.
Additionally,
integrating
Gold-SA
strategy
further
enhances
global
capability
SABO
algorithm,
significantly
reducing
time.
computational
results
reveal
that
proposed
LTG-SABO-GRU
model
outperforms
traditional
estimating
under
normal
extreme
temperature
conditions.
Specifically,
root
mean
square
error
absolute
show
substantial
improvement,
increasing
by
over
50%
compared
model.
Moreover,
exhibits
fewer
iterations
than
existing
typical
optimization
algorithms.
This
study
introduces
novel,
efficient,
practical
BMS
applications.
Language: Английский
Deep Learning for Accurate Diagnosis of Benign Paroxysmal Positional Vertigo
Jiaoxuan Dong,
No information about this author
Ling Li,
No information about this author
Ivan Milanov
No information about this author
et al.
Advances in medical technologies and clinical practice book series,
Journal Year:
2024,
Volume and Issue:
unknown, P. 143 - 152
Published: June 7, 2024
Benign
paroxysmal
positional
vertigo
(BPPV)
is
characterized
by
paroxysms
of
and
nystagmus
triggered
head
position
changes.
The
diagnosis
BPPV
can
be
objectively
determined
through
the
objective
analysis
nystagmus,
making
it
a
promising
approach
towards
artificial
intelligence
(AI)
-assisted
diagnosis.
diagnostic
criteria
for
have
been
clearly
defined,
standardized
protocols
data
collection
established.
Video-oculography
utilizing
infrared
cameras
has
employed
quantification
nystagmus.
These
used
to
train
AI
algorithms.
Utilizing
deep
learning
models
allows
accurate
tracking
pupil
movement
trajectories,
facilitating
identification
types,
automated
possible.
This
chapter
summarizes
recent
advances
in
AI-assisted
discusses
limitations
challenges
clinical
practice.
Language: Английский
Rapid Detection of Stabilizer Content in Double‐Base Propellant Based on Artificial Neural Network Combined With Near‐Infrared Spectroscopy
Dihua Ouyang,
No information about this author
Tianyu Cui,
No information about this author
Qiantao Zhang
No information about this author
et al.
Journal of Chemometrics,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Nov. 17, 2024
ABSTRACT
During
long‐term
storage,
double‐base
propellants
are
prone
to
chemical
decomposition
of
internal
nitrate
esters,
leading
decreased
burn
rate,
reduced
strength,
and
degraded
ballistic
performance.
Adding
an
appropriate
amount
Centralite‐II
is
crucial
for
ensuring
storage
safety.
This
study
proposes
a
novel
method
combining
near‐infrared
spectroscopy
(NIRS)
with
artificial
intelligence
rapidly
non‐destructively
detect
the
content
in
propellants.
The
optimal
modeling
wavelength
ranges
4000–4600
cm
−1
5700–6100
were
identified,
raw
spectral
data
preprocessed
using
standard
normal
variate
(SNV)
transformation
improve
signal‐to‐noise
ratio.
Principal
component
analysis
(PCA)
was
then
applied
reduce
dimensionality,
first
three
principal
components
used
as
inputs
backpropagation
(BP‐ANN)
neural
network.
resulting
PCA‐BP‐ANN
model
showed
excellent
performance
on
training
set,
0.9830
0.0376%.
independent
validation,
demonstrated
strong
generalization
ability,
achieving
0.9824
0.3179%,
comparative
other
models,
including
BP,
PLS,
ELM,
SVR,
LSTM,
indicated
that
exhibited
superior
prediction
accuracy
capability.
provides
rapid
non‐destructive
approach
assessing
stabilizer
expands
application
NIRS
AI
techniques
field
energetic
materials.
Language: Английский
Application of Angelica Sinensis in Gynecological Diseases
Feng Pei,
No information about this author
Yunliang Zang,
No information about this author
Pronaya Bhattacharya
No information about this author
et al.
Advances in medical technologies and clinical practice book series,
Journal Year:
2024,
Volume and Issue:
unknown, P. 153 - 168
Published: June 7, 2024
Angelica
sinensis
is
an
herbal
medicine
commonly
used
for
gynecological
diseases
in
traditional
Chinese
medicine.
This
chapter
aims
to
systematically
review
the
prescriptions
ancient
classics
and
analyze
compatibility
of
with
other
medicines,
categorize
treatment,
understand
applicability
from
a
clinical
view.
The
recorded
Shennong
Bencao
Jing
Jingyue
Quanshu
that
are
related
were
summarized,
characteristics
analyzed.
According
classification
medicine,
such
as
breast
disease,
offspring,
meridians,
postpartum,
role
was
analyzed
based
on
properties,
tastes,
channel
distribution.
processing
methods
recent
development
biochemical
approaches
extracting
active
ingredients
also
briefly
reviewed.
provides
comprehensive
reference
practitioners,
researchers,
biomedical
engineers.
Language: Английский