Applications and Trends of Machine Learning in Building Energy Optimization: A Bibliometric Analysis
Buildings,
Journal Year:
2025,
Volume and Issue:
15(7), P. 994 - 994
Published: March 21, 2025
With
the
rapid
advancement
of
machine
learning
(ML)
technologies,
their
innovative
applications
in
enhancing
building
energy
efficiency
are
increasingly
prominent.
Utilizing
tools
such
as
VOSviewer
and
Bibliometrix,
this
study
systematically
reviews
body
related
literature,
focusing
on
key
emerging
trends
cutting-edge
ML
techniques,
including
deep
learning,
reinforcement
unsupervised
optimizing
performance
managing
carbon
emissions.
First,
paper
delves
into
role
prediction,
intelligent
management,
sustainable
design,
with
particular
emphasis
how
smart
systems
leverage
real-time
data
analysis
prediction
to
optimize
usage
significantly
reduce
emissions
dynamically.
Second,
summarizes
technological
evolution
future
sector
identifies
critical
challenges
faced
by
field.
The
findings
provide
a
technology-driven
perspective
for
advancing
sustainability
construction
industry
offer
valuable
insights
research
directions.
Language: Английский
Industry 5.0, Towards an Enhanced Built Cultural Heritage Conservation Practice
Journal of Building Engineering,
Journal Year:
2024,
Volume and Issue:
96, P. 110542 - 110542
Published: Aug. 23, 2024
The
rise
of
Industry
4.0
has
led
to
a
rapid
increase
in
digitalization
and
industrial
operations.
However,
it
recently
been
deemed
insufficient
fulfilling
European
objectives
for
2030.
In
response,
counteract
the
unintended
negative
consequences
triggered
by
4.0,
5.0
introduced.
purpose
this
article
is
shed
light
on
how
architecture,
engineering,
construction,
management,
operation,
conservation
industry
can
adapt
better
prepare
embrace
novel
principles
enabling
technologies,
ultimately
resulting
enhanced
practices
built
cultural
heritage
environment.
To
achieve
this,
systematic
literature
review
was
conducted
following
PRISMA
methodology.
principal
results
highlight
work
different
professionals
our
views
potential
enhancing
practices.
Major
conclusions
indicate
that
artificial
intelligence
digital
twins
are
two
most
studied
technologies
field.
Sustainability
broadly
discussed
throughout
analyzed
literature,
whereas
resilience
human
centrism
require
further
research
implementation
efforts
holistic
adoption.
significant
scientific
novelty
lies
comprehensive
scope
terms
with
particular
emphasis
buildings.
Thus,
valuable
practitioners
seeking
best
practices,
policymakers
as
suggests
ways
encourage
adoption
conservation,
researchers
highlights
gaps
stimulates
paths
innovation.
Language: Английский
Innovative AI Strategies for Enhancing Smart Building Operations Through Digital Twins: A Survey
Energy and Buildings,
Journal Year:
2025,
Volume and Issue:
unknown, P. 115567 - 115567
Published: March 1, 2025
Language: Английский
Generalized harmonic fuzzy partition C-means clustering
Chengmao Wu,
No information about this author
Siyu Zhou
No information about this author
The Journal of Supercomputing,
Journal Year:
2025,
Volume and Issue:
81(2)
Published: Jan. 27, 2025
Language: Английский
Explainable domain adaptation for imbalanced occupancy estimation
Naailah Mahamoodally,
No information about this author
Jawher Dridi,
No information about this author
Manar Amayri
No information about this author
et al.
Journal of Building Engineering,
Journal Year:
2024,
Volume and Issue:
unknown, P. 110613 - 110613
Published: Sept. 1, 2024
Multi-Source Domain Adaptation Using Ambient Sensor Data
Applied Artificial Intelligence,
Journal Year:
2024,
Volume and Issue:
38(1)
Published: Nov. 19, 2024
Smart
buildings
have
gained
increasing
interest
recently
by
providing
several
advanced
solutions,
especially
AI-based
solutions.
Activity
recognition
and
occupancy
estimation
are
among
the
outcomes
of
smart
that
can
help
provide
advantages
such
as
energy
management
security
Previously,
domain
adaptation
(DA)
has
been
widely
considered
researchers
to
transfer
knowledge
from
source
domains,
where
we
abundant
labeled
data,
a
target
data
is
scarce.
It
tedious
time-consuming
task
label
with
building
applications
which
why
unsupervised
DA
do
in
unlabeled
domain.
Semi-supervised
(SSDA)
also
small
amount
Most
(UDA)
SSDA
methods
one
target.
However,
it
possible
exploit
multiple
domains
instead
single
enhance
performance
Multi-source
(MSDA)
more
difficult
than
single-source
but
efficient.
In
this
research,
adapt
MDSA
evaluate
them
using
sensorial
datasets.
Language: Английский