Urban Planning,
Journal Year:
2024,
Volume and Issue:
10
Published: Oct. 21, 2024
<p>Energy-efficient
renovation
(EER)
is
a
complex
process
essential
for
reducing
emissions
in
the
built
environment.
This
research
identifies
homeowners
as
main
decision-makers,
whereas
intermediaries
and
social
interactions
between
peers
are
highly
influential
home
renovations.
It
investigates
information
communication
barriers
encountered
during
initial
phases
of
EERs.
The
study
reviews
AI
tools
developed
within
EERs
domain
to
assess
their
capabilities
overcoming
these
areas
needing
improvement.
examines
stakeholders,
barriers,
literature
discussion
compares
functionalities
against
stakeholder
needs
challenges
they
face.
Findings
show
that
often
overlook
methodologies
human–computer
interaction
potential
textual
visual
methods.
Digital
tool
development
also
lacks
insights
from
science
user
feedback,
potentially
limiting
practical
impact
innovations.
article
contributes
by
proposing
an
AI-supported
framework
outlining
future
exploration,
particularly
improving
effectiveness
engagement
scale
up
EER
practice.</p>
Renewable Energy,
Journal Year:
2023,
Volume and Issue:
220, P. 119565 - 119565
Published: Nov. 15, 2023
Polyurethane
(PU)
possesses
excellent
thermal
properties,
making
it
an
ideal
material
for
insulation.
Incorporating
Phase
Change
Materials
(PCMs)
capsules
into
has
proven
to
be
effective
strategy
enhancing
building
envelopes.
This
innovative
design
substantially
enhances
indoor
stability
and
minimizes
fluctuations
in
air
temperature.
To
investigate
the
conductivity
of
Polyurethane-Phase
foam
composite,
we
propose
a
hierarchical
multi-scale
model
utilizing
Physics-Informed
Neural
Networks
(PINNs).
allows
accurate
prediction
analysis
material's
at
both
meso-scale
macro-scale.
By
leveraging
integration
physics-based
knowledge
data-driven
learning
offered
by
Networks,
effectively
tackle
inverse
problems
address
complex
phenomena.
Furthermore,
obtained
data
facilitates
optimization
design.
fully
consider
occupants'
comfort
within
envelope,
conduct
case
study
evaluating
performance
this
optimized
detached
house.
Simultaneously,
predict
energy
consumption
associated
with
scenario.
All
outcomes
demonstrate
promising
nature
design,
enabling
passive
significantly
improving
comfort.
The
successful
development
Networks-based
holds
immense
potential
advancing
our
understanding
Material's
properties.
It
can
contribute
materials
various
practical
applications,
including
storage
systems
insulation
advanced
Underground Space,
Journal Year:
2024,
Volume and Issue:
17, P. 226 - 245
Published: Jan. 21, 2024
We
conducted
a
study
to
evaluate
the
potential
and
robustness
of
gradient
boosting
algorithms
in
rock
burst
assessment,
established
variational
autoencoder
(VAE)
address
imbalance
dataset,
proposed
multilevel
explainable
artificial
intelligence
(XAI)
tailored
for
tree-based
ensemble
learning.
collected
537
data
from
real-world
records
selected
four
critical
features
contributing
occurrences.
Initially,
we
employed
visualization
gain
insight
into
data's
structure
performed
correlation
analysis
explore
distribution
feature
relationships.
Then,
set
up
VAE
model
generate
samples
minority
class
due
imbalanced
distribution.
In
conjunction
with
VAE,
compared
evaluated
six
state-of-the-art
models,
including
classical
logistic
regression
model,
prediction.
The
results
indicated
that
outperformed
single
VAE-classifier
original
classifier,
VAE-NGBoost
yielding
most
favorable
results.
Compared
other
resampling
methods
combined
NGBoost
datasets,
such
as
synthetic
oversampling
technique
(SMOTE),
SMOTE-edited
nearest
neighbours
(SMOTE-ENN),
SMOTE-tomek
links
(SMOTE-Tomek),
yielded
best
performance.
Finally,
developed
XAI
using
sensitivity
analysis,
Tree
Shapley
Additive
exPlanations
(Tree
SHAP),
Anchor
provide
an
in-depth
exploration
decision-making
mechanics
VAE-NGBoost,
further
enhancing
accountability
models
predicting
