Buildings,
Год журнала:
2024,
Номер
14(1), С. 284 - 284
Опубликована: Янв. 20, 2024
The
thermal
comfort
evaluation
of
the
urban
environment
arouses
widespread
concern
among
scholars,
and
research
in
this
field
is
mostly
based
on
indexes
such
as
PMV,
PET,
SET,
UTCI,
etc.
These
index
models
are
complex
calculation
process
poor
operability,
which
makes
it
difficult
for
people
who
lack
a
relevant
knowledge
background
to
understand,
calculate,
apply
them.
purpose
study
provide
simple,
efficient,
easy-to-operate
outdoor
model
severe
cold
areas
China
using
machine
learning
method.
In
study,
physical
parameters
obtained
by
measurement,
individual
information
questionnaire
survey.
applicability
four
studied.
A
total
320
questionnaires
collected.
results
show
that
correlation
coefficients
between
predicted
values
voting
extreme
gradient
lifting
model,
random
forest
neural
network
0.9313,
0.7148,
0.9115,
0.5325,
respectively.
Further
analysis
with
highest
coefficient
shows
factors
(such
residence
time,
distance
hometown
residence,
clothing,
age,
height,
weight)
environmental
air
humidity
(RH),
wind
speed
(v),
temperature
(Ta),
black
bulb
(Tg))
have
different
influences
evaluation.
summary,
method
evaluate
simpler,
more
direct,
can
make
up
consideration
index.
reference
value
application
China.
Energy and Built Environment,
Год журнала:
2024,
Номер
unknown
Опубликована: Март 1, 2024
The
role
of
skin
temperature
as
a
determinant
human
thermal
sensation
and
comfort
has
gained
increasing
recognition,
prompting
need
for
systematic
review.
This
review
examines
the
relationship
between
sensation,
synthesizing
insights
from
172
studies
published
since
2000.
It
uniquely
focuses
on
indispensable
roles
local
mean
temperatures,
perspective
not
comprehensively
explored
in
previous
literature.
reveals
that
most
common
measurement
points
are
face
hands,
attributed
to
their
higher
sensitivity
practical
ease
measurement.
establishes
clear
linear
user
though
affected
by
choice
locations
number
points.
A
notable
finding
is
varying
impact
overall
changing
environments,
with
heating
less
influential
than
cooling.
also
uncovers
significant
demographic
variations
strongly
influenced
differing
temperatures
across
age
groups,
genders,
climatic
regions.
For
example,
elderly
populations
exhibit
decreased
sensitivity,
especially
towards
warmth.
Gender
differences
significant,
females
experiencing
warmer
environments
lower
colder
ones.
Machine
learning
(ML)-based
methods,
classification
tree-based
support
vector
machine
(SVM)
techniques,
dominate
predicting
comfort,
leveraging
data.
While
ML
methods
prevalent,
statistical
regression-based
approaches
offer
valuable
empirical
insights.
Thermo-physiological
model-based
provide
reliable
results
incorporating
detailed
dynamics.
identifies
gap
understanding
how
gender,
age,
regional
influence
diverse
environments.
study
recommends
conducting
more
nuanced
experiments
dissect
these
factors
proposes
integration
individual
variables
into
models
personalize
predictions.
