Architectural Science Review,
Journal Year:
2023,
Volume and Issue:
67(4), P. 291 - 308
Published: Oct. 17, 2023
AbstractRecent
studies
showed
that
deep
learning
techniques
and
image
processing
can
identify
the
distinguishing
design
principles
in
architectural
façades.
However,
predicting
strength
of
a
principle
is
still
challenging
task,
as
it
requires
huge
amount
annotated
variations.
The
difficulties
both
searching
such
big
numbers
data
–
its
labelling
by
experts
slow
down
research.
This
paper
proposes
computation
approach
for
obtaining
this
type
faster.
With
help
parametric
modelling
evolutionary
algorithms,
we
could
manipulate
elements,
thereby
generate
different
solutions.
An
integrated
fuzzy
logic
decision
mechanism
enable
to
carry
human
knowledge
judging
alternatives
automatically.
final
synthetic
developed
from
real
building
images
be
used
machine
applications
enhance
our
understanding
artistic
expression.KEYWORDS:
Façade
designVisual
principlesFuzzy
LogicParametric
modellingData
generationAutomated
AcknowledgementThe
author
wishes
thank
Sinem
Kırkan
Tuğrul
Agrikli
their
valuable
support
visualization
parts.
Thanks
are
due
esteemed
raters,
whose
profound
expertise
greatly
enriched
verification
phase.
Lastly,
would
like
anonymous
reviewers
constructive
comments.
received
no
financial
research,
authorship
and/or
publication
article.Disclosure
statementNo
potential
conflict
interest
was
reported
author(s).Data
availabilityThe
findings
study
available
corresponding
author,
Cekmis,
A.,
upon
reasonable
request.
Smart and Sustainable Built Environment,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Aug. 2, 2024
Purpose
Predictive
digital
twin
technology,
which
amalgamates
twins
(DT),
the
internet
of
Things
(IoT)
and
artificial
intelligence
(AI)
for
data
collection,
simulation
predictive
purposes,
has
demonstrated
its
effectiveness
across
a
wide
array
industries.
Nonetheless,
there
is
conspicuous
lack
comprehensive
research
in
built
environment
domain.
This
study
endeavours
to
fill
this
void
by
exploring
analysing
capabilities
individual
technologies
better
understand
develop
successful
integration
use
cases.
Design/methodology/approach
uses
mixed
literature
review
approach,
involves
using
bibliometric
techniques
as
well
thematic
critical
assessments
137
relevant
academic
papers.
Three
separate
lists
were
created
Scopus
database,
covering
AI
IoT,
DT,
since
IoT
are
crucial
creating
DT.
Clear
criteria
applied
create
three
lists,
including
limiting
results
only
Q1
journals
English
publications
from
2019
2023,
order
include
most
recent
highest
quality
publications.
The
collected
was
analysed
package
R
Studio.
Findings
reveal
asymmetric
attention
various
components
twin’s
system.
There
relatively
greater
body
on
representing
43
47%,
respectively.
In
contrast,
direct
net-zero
solutions
constitutes
10%.
Similarly,
findings
underscore
necessity
integrating
these
carbon
emission
prediction.
Practical
implications
indicate
that
clear
need
more
case
studies
investigating
large-scale
networks
collect
buildings
construction
sites.
Furthermore,
development
advanced
precise
models
imperative
predicting
production
renewable
energy
sources
demand
housing.
Originality/value
paper
makes
significant
contribution
field
providing
strong
theoretical
foundation.
It
also
serves
catalyst
future
within
For
practitioners
policymakers,
offers
reliable
point
reference.
Buildings,
Journal Year:
2024,
Volume and Issue:
14(5), P. 1241 - 1241
Published: April 27, 2024
Urban
building
energy
models
(UBEMs),
developed
to
understand
the
performance
of
stocks
a
region,
can
aid
in
key
decisions
related
policy
and
climate
change
solutions.
However,
creating
city-scale
UBEM
is
challenging
due
requirements
diverse
geometric
non-geometric
datasets.
Thus,
we
aimed
further
elucidate
process
with
disparate
scarce
data
based
on
bottom-up,
physics-based
approach.
We
focused
three
typically
overlooked
but
functionally
important
commercial
stocks,
which
are
sales
shopping,
healthcare
facilities,
food
services,
region
Pittsburgh,
Pennsylvania.
harvested
relevant
local
information
employed
photogrammetry
image
processing.
created
archetypes
for
types,
designed
3D
buildings
SketchUp,
performed
an
analysis
using
EnergyPlus.
The
average
annual
simulated
use
intensities
(EUIs)
were
528
kWh/m2,
822
2894
kWh/m2
respectively.
In
addition
variations
found
pattern
among
considerable
observed
within
same
stock.
About
9%
11%
errors
shopping
facilities
when
validating
results
actual
data.
suggested
conservation
measures
could
reduce
EUI
by
10–26%
depending
type.
assist
finding
energy-efficient
retrofit
solutions
respect
carbon
reduction
goal
at
city
scale.
limitations
highlighted
may
be
considered
higher
accuracy,
has
high
potential
integrate
urban
models,
circular
economy,
life
cycle
assessment
sustainable
planning.
Residential
building
material
stock
constitutes
a
significant
part
of
the
built
environment,
providing
crucial
shelter
and
habitat
services.
The
hypothesis
concerning
mass
composition
has
garnered
considerable
attention
over
past
decade.
While
previous
research
mainly
focused
on
spatial
analysis
masses,
it
often
neglected
component-level
or
where
heavy
labor
cost
for
onsite
survey
is
required.
This
paper
presents
novel
approach
efficient
residential
accounting
in
United
Kingdom,
utilizing
drive-by
street
view
images
footprint
data.
We
assessed
four
major
construction
materials:
brick,
stone,
mortar,
glass.
Compared
to
traditional
approaches
that
utilize
surveyed
intensity
data,
developed
method
employs
automatically
extracted
physical
dimensions
components
incorporating
predicted
types
calculate
mass.
not
only
improves
efficiency
but
also
enhances
accuracy
managing
heterogeneity
structures.
results
revealed
error
rates
5
22%
mortar
glass
estimations
8
7%
brick
stone
estimations,
with
known
wall
types.
These
findings
represent
advancements
characterization
suggest
our
potential
further
practical
applications.
Especially,
establishes
basis
evaluating
reuse,
serving
objectives
circular
economy.
Applied Sciences,
Journal Year:
2025,
Volume and Issue:
15(4), P. 1995 - 1995
Published: Feb. 14, 2025
This
research
paper
aims
to
develop
an
approach
for
the
digitalization
of
non-heritage
building
stock.
Existing
stocks
in
need
rehabilitation
are
still
not
subject
optimized,
massive
digital
surveying
processes.
Thus,
it
is
difficult
assess
performance
stock
its
current
state
and
after
potential
retrofitting.
While
data
capture
being
used
model
heritage
cases
with
high
precision
preservation
documentation
projects,
this
that
allows
broader
implementation,
quicker
results,
higher
scalability,
reducing
time
required
but
precise
enough
The
novel
combines
a
laser
scanner,
thermal
infrared
sensing,
high-quality
pictures
(HQPs),
automatic
frame
extraction
(AFE)
from
video.
Data
preparation
three-dimensional
reconstruction
main
novelty
approach,
which
has
been
validated
obtain
surroundings
information
(BIM)
reference
Barcelona
schools.
results
coincide
previous
projects
regarding
scanner
coverage
photogrammetry.
New
findings
indicate
HQPs
highly
efficient
method.
Its
combination
AFE
provides
levels
coverage.
proposed
moves
forward
manually
modeled
BIM
misalignments
enables
modeling
entire
clusters
twin
ease
future
management
existing
buildings.
