This
thesis
explores
how
recent
technological
trends
such
as
low-cost
hardware,
data
science
and
AI
can
be
used
to
improve
personalise
thermal
comfort
modelling.
It
integrates
the
design
of
a
personal
monitoring
device,
longitudinal
field
study
development
new
framework
for
data-driven
personalised
long-term
The
underscores
importance
accommodating
individual
preferences
spatial
variations
in
dynamic
indoor
environments
offers
perspective
on
integration
open-source
technologies,
methodologies,
rethinking
role
contemporary
building
design.
Energy and Buildings,
Journal Year:
2024,
Volume and Issue:
308, P. 113958 - 113958
Published: Feb. 14, 2024
Over
the
past
few
decades,
attention
in
buildings’
design
and
operation
has
gradually
shifted
from
promoting
only
energy
efficiency
objectives
to
also
addressing
human
comfort
well-being.
Researchers
have
developed
a
wide
range
of
control
algorithms
ranging
rule-based
controls
complex
learning
approaches
that
can
fully
capture
occupants’
personalized
preferences
smart
buildings.
This
direction
occupant-centric
building
bridge
gap
between
satisfaction
sustainability
objectives.
However,
most
these
promising
technologies
not
yet
found
their
way
into
real-world
applications.
study
will
perform
critical
review
on
thermal
lighting
studies
aiming
(i)
analyze
strengths
weaknesses
different
approaches;
(ii)
identify
requirements
for
techniques
be
implemented
systems;
(iii)
propose
new
research
directions
promote
usability
such
catalyst
towards
adoption.
Computational
complexity,
integration
with
Building
Automation
Systems
(BAS),
data
availability
quality,
scalability,
lack
more
featuring
actual
implementation
emerge
as
barriers.
Addressing
challenges
is
imperative
successful
deployment
Building and Environment,
Journal Year:
2023,
Volume and Issue:
234, P. 110148 - 110148
Published: March 1, 2023
Personal
thermal
comfort
models
are
used
to
predict
individual-level
responses
inform
design
and
control
decisions
of
buildings
achieve
optimal
conditioning
for
improved
energy
efficiency.
However,
the
development
data-driven
requires
collecting
a
large
amount
sensor-related
measurements
user-labelled
data
(i.e.,
user
feedback)
accurate
predictions,
which
can
be
highly
intrusive
labour
intensive
in
real-world
applications.
In
this
work,
we
propose
hybrid
active
learning
framework
reduce
collection
costs
developing
data-efficient
robust
personal
that
users'
air
movement
preferences.
Through
proposed
framework,
evaluated
performance
two
algorithms
Uncertainty
Sampling
Query-by-Committee)
labelling
strategies
(Independent
Joint
Labelling
strategies)
reduction
effort
modelling.
The
effectiveness
was
demonstrated
on
dataset
involving
58
participants
collected
over
10
working
days
with
2,727
under
16
conditions.
final
results
showed
46%
35%
preference
models,
respectively,
increasing
reductions
occurring
time
when
encountering
new
users.
insights
gained
study,
future
studies
adopt
as
viable
effective
solution
address
high
cost
while
maintaining
model's
scalability
predictive
performance.
Building and Environment,
Journal Year:
2023,
Volume and Issue:
240, P. 110418 - 110418
Published: May 22, 2023
Standardized
methods
for
thermal
comfort
assessment
already
exist,
namely
the
predicted
mean
vote
(PMV)
and
adaptive
model,
both
valid
groups
of
people.
To
identify
whether
a
specific
person
is
comfortable
under
different
factors
such
as
thermal,
air
quality,
lighting,
acoustics,
only
current
reliable
method
subjective
evaluation.
reduce
need
occupant
feedback,
personal
models
are
currently
being
developed
that
aim
to
predict
response
based
on
information
from
its
surroundings.
These
leverage
machine
learning
tools
have
been
found
provide
suitable
estimations
responses.
According
literature,
an
average
prediction
accuracy
70–80%
attainable.
Therefore,
these
promoted
innovative
efficient
ways
comfort-based
HVAC
control.
The
challenge
however
identifying
most
relevant
indicators
acquiring
them
in
simple
way.
Integrating
anthropometric
data,
e.g.,
age,
sex,
body
mass
index
may
represent
generating
model.
Including
physiological
data
skin
temperature,
heart
rate,
signal
transformation
could
increase
performance.
Strong
relationships
were
identified
between
indicators,
their
variation
was
not
be
governed
solely
by
thermoregulation.
Few
automatic
control
implementation
examples
using
shows
challenges
still
exist.
In
order
achieve
accurate
control,
certain
issues
remain
regarding
acceptable
thresholds
model
performance
optimum
set
combination
it.
Indoor Air,
Journal Year:
2022,
Volume and Issue:
32(11)
Published: Nov. 1, 2022
Personal
thermal
comfort
models
are
a
paradigm
shift
in
predicting
how
building
occupants
perceive
their
environment.
Previous
work
has
critical
limitations
related
to
the
length
of
data
collected
and
diversity
spaces.
This
paper
outlines
longitudinal
field
study
comprising
20
participants
who
answered
Right-Here-Right-Now
surveys
using
smartwatch
for
180
days.
We
more
than
1080
field-based
per
participant.
Surveys
were
matched
with
environmental
physiological
measured
variables
indoors
homes
offices.
then
trained
tested
seven
machine
learning
participant
predict
preferences.
Participants
indicated
58%
time
want
no
change
environment
despite
completing
75%
these
at
temperatures
higher
26.6°C.
All
but
one
personal
model
had
median
prediction
accuracy
0.78
(F1-score).
Skin,
indoor,
near
body
temperatures,
heart
rate
most
valuable
accurate
prediction.
found
that
≈250–300
points
needed
We,
however,
identified
strategies
significantly
reduce
this
number.
Our
provides
quantitative
evidence
on
improve
models,
prove
benefits
wearable
devices
preference,
validate
results
from
previous
studies.
Journal of Physics Conference Series,
Journal Year:
2023,
Volume and Issue:
2600(14), P. 142003 - 142003
Published: Nov. 1, 2023
Abstract
Collecting
feedback
from
people
in
indoor
and
outdoor
environments
is
traditionally
challenging
complex
to
achieve
a
reliable,
longitudinal,
non-intrusive
way.
This
paper
introduces
Cozie
Apple,
an
open-source
mobile
smartwatch
application
for
iOS
devices.
platform
allows
complete
watch-based
micro-survey
provide
real-time
about
environmental
conditions
via
their
Apple
Watch.
It
leverages
the
inbuilt
sensors
of
collect
physiological
(e.g.,
heart
rate,
activity)
(sound
level)
data.
outlines
data
collected
48
research
participants
who
used
report
perceptions
urban-scale
comfort
(noise
thermal)
contextual
factors
such
as
they
were
with
what
activity
doing.
The
results
2,400
micro-surveys
across
various
urban
settings
are
illustrated
this
paper,
showing
variability
noise-related
distractions,
thermal
comfort,
associated
context.
show
that
experienced
at
least
little
noise
distraction
58%
time,
talking
being
most
common
reason
(46%).
effort
novel
due
its
focus
on
spatial
temporal
scalability
collection
noise,
distraction,
information.
These
set
stage
larger
deployments,
deeper
analysis,
more
helpful
prediction
models
toward
better
understanding
occupants’
needs
perceptions.
innovations
could
result
control
signals
building
systems
or
nudges
change
behavior.
Journal of Computing in Civil Engineering,
Journal Year:
2024,
Volume and Issue:
38(2)
Published: Jan. 3, 2024
Maintaining
the
quality
of
indoor
environments
in
educational
facilities
is
crucial
for
student
comfort,
health,
well-being,
and
students'
learning
performance.
Current
environment
maintenance
practices
building
systems
facility
spaces
often
fail
to
include
feedback
from
students
exhibit
limited
adaptability
their
needs.
To
address
this
problem,
paper
introduces
a
novel
artificial
intelligence
things
(AIoT)-based
framework
predict
multidimensional
(IEQ)
conditions.
The
proposed
integrates
internet
(IoT)
with
deep
algorithms
systematically
incorporate
IEQ
data
multimodal
occupants.
By
collecting,
fusing,
analyzing
real-time
occupant
data,
predicts
future
condition
based
on
current
This
yields
insights
into
conditions
potential
impacts
thereby
facilitating
development
climate-adaptive,
data-driven,
human-centric
facilities.
was
deployed,
validated,
tested
selected
at
Virginia
Tech
Blacksburg
campus,
encouraging
results.
