Applied Sciences,
Journal Year:
2024,
Volume and Issue:
15(1), P. 221 - 221
Published: Dec. 30, 2024
To
address
the
issue
of
user
empathy
throughout
emotional
experience
process,
this
study
presents
a
method
to
evaluate
efficacy
cultural
evoked
based
on
fuzzy-FMEA.
The
focuses
symbolic
culture
and
creative
products,
constructing
an
evaluation
index
system
decision-making
framework
in
terms
empathic
evoking.
It
utilizes
thematic
analysis
discover
categorize
factors
that
influence
empathy,
as
well
improve
Failure
Mode
Effects
Analysis
framework.
effectively
solves
limitations
traditional
FMEA,
such
single
weighting
uncertainty.
According
assessment
report,
cognitive
association
failure
scenario
restoration
are
significant
risk
for
empathy-evoking
failure.
This
study’s
findings
provide
designers
with
realistic
proposals
imagery
serialized
design
forms,
scientific
tools
resources
industries
policymakers.
Journal of Engineering Design,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 31
Published: Oct. 17, 2024
In
order
to
improve
the
attractiveness
of
social
robot
serving
health
interventions
in
public
workspace,
we
propose
a
product
design
method
with
combination
Style-generative
adversarial
network
(StyleGAN)
model
and
particle
swarm
optimisation-support
vector
regression
(PSO-SVR).
This
paper
aims
explore
modelling
generation
robots
for
intervention
based
on
artificial
intelligence
generated
content
(AIGC)
mapping
between
shape
characteristics
users'
visual
perception
Kansei
Engineering
(KE).
Firstly,
address
defects
typical
KE
over-reliance
existing
samples,
introduce
StyleGAN
AIGC
learn
train
robots'
samples
generate
new
sample
images.
Secondly,
morphological
deconstruction
is
used
deconstruct
features
sample.
Factor
analysis
(FA)
also
reduce
dimension
cluster
emotional
words
establish
Likert
scale
vocabulary.
Finally,
(PSO-SVR)
images
users,
thus
obtaining
most
attractive
scheme.
The
research
results
showed
that
can
be
assist
industrial
designers
creative
expression
provide
rich
sources
KE;
PSO-SVR
machine
learning
build
among
feelings,
features.
end,
designed
an
intervention.
Frontiers in Neuroscience,
Journal Year:
2025,
Volume and Issue:
19
Published: May 21, 2025
Backgrounds
This
study
innovatively
enhances
personalized
emotional
responses
and
user
experience
quality
in
traditional
Chinese
folding
armchair
(Jiaoyi
chair)
design
through
an
interdisciplinary
methodology.
Goal
To
systematically
extract
characteristics,
we
developed
a
hybrid
research
framework
integrating
web-behavior
data
mining.
Methods
1)
the
KJ
method
combined
with
semantic
crawlers
extracts
descriptors
from
multi-source
social
data;
2)
expert
evaluation
fuzzy
comprehensive
assessment
reduce
feature
dimensionality;
3)
random
forest
K-prototype
clustering
identify
three
core
preference
factors:
“Flexible
Refinement,”
“Uncompromising
Quality,”
“ergonomic
stability.”
Discussion
A
CNN-GRU-Attention
deep
learning
model
was
constructed,
incorporating
dynamic
convolutional
kernels
gated
residual
connections
to
address
degradation
long-term
sequences.
Experimental
validation
demonstrated
superior
performance
of
our
chair
prediction
tasks
(RMSE
=
0.038953,
0.066123,
0.0069777),
outperforming
benchmarks
(CNN,
SVM,
LSTM).
Based
on
top-ranked
encoding,
designed
new
Jiaoyi
prototype,
achieving
significantly
reduced
errors
final
testing
0.0034127,
0.0026915,
0.0035955).
Conclusion
establishes
quantifiable
intelligent
paradigm
for
modernizing
cultural
heritage
computational
design.
Buildings,
Journal Year:
2024,
Volume and Issue:
14(12), P. 3950 - 3950
Published: Dec. 12, 2024
This
study
proposes
an
optimization
method
based
on
Rough
Set
Theory
(RST)
and
Particle
Swarm
Optimization–Support
Vector
Regression
(PSO-SVR),
aimed
at
enhancing
the
emotional
dimension
of
outdoor
micro-space
(OMS)
design,
thereby
improving
users’
activity
duration
preferences
experiences.
OMS,
as
a
key
element
in
modern
urban
significantly
enhances
residents’
quality
life
promotes
public
health.
Accurately
understanding
predicting
needs
is
core
challenge
optimizing
OMS.
In
this
study,
Kansei
Engineering
(KE)
framework
applied,
using
fuzzy
clustering
to
reduce
dimensionality
descriptors,
while
RST
employed
for
attribute
reduction
select
five
design
features
that
influence
emotions.
Subsequently,
PSO-SVR
model
applied
establish
nonlinear
mapping
relationship
between
these
emotions,
optimal
configuration
OMS
design.
The
results
indicate
optimized
intention
stay
space,
reflected
by
higher
ratings
descriptors
increased
longer
duration,
all
exceeding
median
score
scale.
Additionally,
comparative
analysis
shows
outperforms
traditional
methods
(e.g.,
BPNN,
RF,
SVR)
terms
accuracy
generalization
predictions.
These
findings
demonstrate
proposed
effectively
improves
performance
offers
solid
along
with
practical
guidance
future
space
innovative
contribution
lies
data-driven
integrates
machine
learning
KE.
not
only
new
theoretical
perspective
but
also
establishes
scientific
accurately
incorporate
into
process.
contributes
knowledge
field
health
well-being,
provides
foundation
applications
different
environments.
