Robotic Intelligence and Automation,
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 26, 2025
Purpose
This
paper
aims
to
investigate
the
problem
of
adaptive
neural
finite-time
self-triggered
tracking
control
for
interconnected
large
scale
nonlinear
systems
in
nonstrict-feedback
forms
with
sensor
faults.
Design/methodology/approach
To
begin
with,
by
combining
backstepping
techniques
and
networks
(NNs),
an
NN
controller
is
designed
compensate
Then,
command
filters
are
introduced
deal
complexity
explosion
design
processes.
Moreover,
reduce
unnecessary
data
transmissions,
a
strategy
presented.
Findings
Based
on
strategy,
scheme
large-scale
faults
proposed.
Originality/value
article
considers
forms.
introduction
not
only
effectively
avoids
arising
from
repetitive
differentiation
virtual
inputs,
but
also
simplifies
process.
Besides,
this
proposes
mechanism
that
calculates
next
trigger
point
based
current
system
data,
overcoming
need
continuous
monitoring
measurement
errors
event-triggered
mechanisms.
Furthermore,
guarantees
stability
systems,
error
converging
small
neighborhood
origin
within
finite
time
frame.
Asian Journal of Control,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Jan. 21, 2025
Summary
This
paper
addresses
the
problem
of
a
hierarchical
sliding
mode
surface
(HSMS)
control
design
for
nonlinear
systems
via
dynamic
event‐triggered
mechanism.
Initially,
HSMS
containing
system
states
is
constructed
to
enhance
system's
response
rate
and
robustness.
By
assigning
cost
function
associated
with
HSMS,
such
an
equivalently
transformed
into
zero‐sum
game
problem,
where
policy
exogenous
disturbance
are
treated
as
two
players
opposite
interests.
Afterwards,
novel
mechanism
designed,
triggering
condition
depends
on
variables.
To
solve
corresponding
Hamilton–Jacobi–Isaacs
equation,
single‐critic
reinforcement
learning
algorithm
developed,
which
removes
error
generated
by
approximating
actor
network
in
actor‐critic
network.
According
Lyapunov
stability
theory,
all
signals
considered
strictly
proved
be
bounded.
Finally,
validity
proposed
method
demonstrated
through
simulations
tunnel
diode
circuit
mass‐spring‐damper
system.
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: March 1, 2025
Graph
clustering
is
a
fundamental
task
in
network
analysis,
aimed
at
uncovering
meaningful
groups
of
nodes
based
on
structural
and
attribute-based
similarities.
Traditional
Nonnegative
Matrix
Factorization
(NMF)
methods
have
shown
promise
tasks
by
providing
low-dimensional
representations
data.
However,
most
existing
NMF-based
approaches
are
highly
sensitive
to
noise
outliers,
leading
suboptimal
performance
real-world
scenarios.
Additionally,
these
often
struggle
capture
the
underlying
nonlinear
structures
complex
networks,
which
can
significantly
impact
accuracy.
To
address
limitations,
this
paper
introduces
Robust
Self-Supervised
Symmetric
NMF
(R3SNMF)
improve
graph
clustering.
The
proposed
algorithm
leverages
robust
principal
component
model
handle
outliers
effectively.
By
incorporating
self-supervised
learning
mechanism,
R3SNMF
iteratively
refines
process,
enhancing
quality
learned
increasing
resilience
data
imperfections.
symmetric
factorization
ensures
preservation
structures,
while
approach
allows
adaptively
its
over
successive
iterations.
In
addition,
integrates
graph-boosting
method
how
relationships
within
represented.
Extensive
experimental
evaluations
various
datasets
demonstrate
that
outperforms
state-of-the-art
terms
both
accuracy
robustness.
Deleted Journal,
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 1, 2025
Microarray
technology
has
become
a
vital
tool
in
cardiovascular
research,
enabling
the
simultaneous
analysis
of
thousands
gene
expressions.
This
capability
provides
robust
foundation
for
heart
disease
classification
and
biomarker
discovery.
However,
high
dimensionality,
noise,
sparsity
microarray
data
present
significant
challenges
effective
analysis.
Gene
selection,
which
aims
to
identify
most
relevant
subset
genes,
is
crucial
preprocessing
step
improving
accuracy,
reducing
computational
complexity,
enhancing
biological
interpretability.
Traditional
selection
methods
often
fall
short
capturing
complex,
nonlinear
interactions
among
limiting
their
effectiveness
tasks.
In
this
study,
we
propose
novel
framework
that
leverages
deep
neural
networks
(DNNs)
optimizing
using
data.
DNNs,
known
ability
model
patterns,
are
integrated
with
feature
techniques
address
high-dimensional
The
proposed
method,
DeepGeneNet
(DGN),
combines
DNN-based
into
unified
framework,
ensuring
performance
meaningful
insights
underlying
mechanisms.
Additionally,
incorporates
hyperparameter
optimization
innovative
U-Net
segmentation
further
enhance
accuracy.
These
optimizations
enable
DGN
deliver
scalable
results,
outperforming
traditional
both
predictive
accuracy
Experimental
results
demonstrate
approach
significantly
improves
compared
other
methods.
By
focusing
on
interplay
between
learning,
work
advances
field
genomics,
providing
interpretable
future
applications.
