Construction
project
management
involves
proper
scheduling
and
estimation
of
resources
such
that
projects
meet
their
time
budgetary
allocations.
Traditional
methods
rely
on
manual
processes
or
fixed
rules
cannot
keep
up
with
the
dynamics
variability
conditions.
This
paper
proposes
a
data-driven
approach
incorporating
machine
learning
models,
Support
Vector
Machines,
Random
Forests
to
enhance
accuracy
in
resource
allocation.
Several
historical
data
points
need
be
analyzed
terms
task
duration,
usage,
cost
variables
frame
predictive
models.
In
this
direction,
SVM
is
applied
classify
risks
regarding
likely
delays
respect
weather
conditions,
labor
availability,
discrepancies
supply
chain.
Simultaneously,
are
utilized
predict
requirements
possible
fluctuations
costs.
The
framework
also
allows
for
real-time
integration
continuous
updates,
thereby
increasing
reliability
prediction.
A
case
study
based
achieved
reduction
about
18%
delays,
improvement
25%
over
traditional
approaches.
results
demonstrate
into
construction
through
practical
insights
enable
decision-makers
more
proactive
better
informed.
research
highlights
importance
leveraging
advanced
analytics
tools
address
high-level
challenges
within
industry.
Building and Environment,
Journal Year:
2024,
Volume and Issue:
252, P. 111295 - 111295
Published: Feb. 12, 2024
Architectural
design
variables
(ADVs)
highly
influence
a
building's
sustainability
performance.
Thus,
identifying
which
ADVs
are
most
influential
in
early
stages
is
of
great
significance,
especially
when
using
computational
building
optimization
tools.
Currently,
sensitivity
analysis
based
on
computer
simulations
the
commonly
used
means
to
identify
stages.
However,
we
suggest
that
stakeholder
perspective
should
also
be
considered
as
stakeholders
possess
domain-specific
knowledge
and
expertise
well
contextual
understanding
can
greatly
enhance
development
deployment
To
explore
above,
combined
literature
review
with
survey
data
from
24
architects
consultants
Nordics.
Surprisingly,
found
do
not
always
align
those
our
surveyed
stakeholders.
For
example,
considers
plan,
window-to-wall-ratio
(WWR),
wall
material
ADVs,
contrasts
storey
number,
height,
WWR,
roof
by
influential.
We
differ
across
different
objectives,
these
literature.
Despite
limited
sample,
study
provides
insights
into
such
has
implications
for
development,
use,
performance
Heliyon,
Journal Year:
2024,
Volume and Issue:
10(17), P. e36846 - e36846
Published: Aug. 26, 2024
The
construction
industry
is
witnessing
a
transformative
shift
towards
sustainable
and
intelligent
housing
solutions
driven
by
advancements
in
3D
printing,
Artificial
Intelligence
(AI),
the
Internet
of
Things
(IoT).
Several
architectural
firms
have
adopted
innovative
technologies
to
make
easier,
sustainable,
efficient,
cheap,
fast,
low
generation
waste
etc.
This
explorative
review
critically
examines
integration
these
eco-friendly
homes.
Drawing
on
comprehensive
analysis
literature
spanning
from
2010
2024,
explores
synergistic
potential
challenges
associated
with
amalgamating
AI,
IoT
processes.
increase
need
smart
homes
equipped
sensors
that
can
sense
regulate
temperature,
prevent
or
control
fire,
gas
leakage,
motion
detectors
alarms
for
security
other
application
high
demand.
These
types
only
be
achieved
integrating
different
together
which
include
printing
(3DP),
AI
Despite
growing
research
field
automated
construction,
there
are
few
articles
attempt
integrate
futuristic
cities.
study
aim
at
providing
up-to-date
advancement
technological
innovation
within
sector
regards
applications
3DP,
IoT,
AI.
Key
findings
highlight
how
enables
rapid
prototyping
customization
building
components,
enhances
energy
efficiency
occupant
comfort
through
predictive
analytics
automation,
while
facilitates
real-time
monitoring
systems.
Furthermore,
discusses
environmental
benefits,
cost-effectiveness,
societal
implications
adopting
such
integrated
approaches.
However,
as
regulatory
barriers,
limitations,
skilled
labor
identified
critical
barriers
widespread
implementation.
Future
directions
proposed
address
further
optimize
In
this
article,
3DP
advantage
disadvantage
(AI)
addressing
regarding
promoting
sustainability
industries
were
comprehensively
explored.
Construction
project
management
involves
proper
scheduling
and
estimation
of
resources
such
that
projects
meet
their
time
budgetary
allocations.
Traditional
methods
rely
on
manual
processes
or
fixed
rules
cannot
keep
up
with
the
dynamics
variability
conditions.
This
paper
proposes
a
data-driven
approach
incorporating
machine
learning
models,
Support
Vector
Machines,
Random
Forests
to
enhance
accuracy
in
resource
allocation.
Several
historical
data
points
need
be
analyzed
terms
task
duration,
usage,
cost
variables
frame
predictive
models.
In
this
direction,
SVM
is
applied
classify
risks
regarding
likely
delays
respect
weather
conditions,
labor
availability,
discrepancies
supply
chain.
Simultaneously,
are
utilized
predict
requirements
possible
fluctuations
costs.
The
framework
also
allows
for
real-time
integration
continuous
updates,
thereby
increasing
reliability
prediction.
A
case
study
based
achieved
reduction
about
18%
delays,
improvement
25%
over
traditional
approaches.
results
demonstrate
into
construction
through
practical
insights
enable
decision-makers
more
proactive
better
informed.
research
highlights
importance
leveraging
advanced
analytics
tools
address
high-level
challenges
within
industry.
