Discrete Dynamics in Nature and Society,
Год журнала:
2023,
Номер
2023, С. 1 - 11
Опубликована: Ноя. 16, 2023
Urban
regional
risk
is
a
complex
nonlinear
problem
that
encounters
insufficient
information,
randomness,
and
uncertainty.
To
accurately
assess
the
overall
urban
risk,
assessment
model
for
public
safety
was
proposed
by
using
information
diffusion
theory.
The
entropy
theory
employed
to
optimize
reduce
A
framework
of
based
on
constructed.
Finally,
case
study
Hangzhou
city
in
China
presented
demonstrate
performance
method.
Results
showed
method
could
successfully
estimate
city.
levels
probabilities
different
hazard
indicators
were
basically
consistent
with
reality.
hazards
respect
industrial
mining
accidents
road
traffic
extremely
serious.
More
than
80
deaths
from
would
occur
almost
every
3
years,
more
400
RTA
2.6
years.
Moreover,
centralized
intervals
level
associated
five
found,
where
risks
likely
happen
had
higher
vulnerability.
It
provide
guidance
government’s
management
policy-making.
Journal of Computational Design and Engineering,
Год журнала:
2023,
Номер
11(1), С. 305 - 324
Опубликована: Дек. 28, 2023
Abstract
The
morphological
design
of
urban
space
affects
the
quality
environment.
traditional
experience-based
approach
was
greatly
improved
by
introducing
computational
tools.
However,
existing
tools
are
mostly
developed
on
pre-set
rules
or
given
targets,
which
have
few
contributions
to
enhance
creativity
generate
inspiring
schemes.
Therefore,
this
paper
proposes
a
new
named
UDGAN,
integrating
generative
adversarial
networks
(GANs)
and
multi-objective
optimization
algorithms.
This
model
utilizes
scheme
plans
over
past
20
years
from
particular
designer
as
training
datasets.
Four
preference
models
were
trained
autonomously
stylized
Eight
parameters
used
analyze
performance
comparing
generated
results
with
ground
truth.
GAN-based
surrogate
is
combined
indicator
alignment
process
using
obtain
better
results.
result
shows
that
R2
predicted
Pix2Pix
reaches
0.798,
similarity
can
be
stably
distributed
between
0.7
0.8,
so
preferred
style
effectively
learned.
At
same
time,
pre-trained
reduces
time
consumption
generation,
taking
5
min
approximately
complete
generation
process.
quickly
features,
supporting
saving
creation,
transforming
into
an
inspiration-driven
iScience,
Год журнала:
2024,
Номер
27(6), С. 110125 - 110125
Опубликована: Май 27, 2024
The
UN
(United
Nations)
collects
global
data
on
the
country-level
Percentage
of
Population
Residing
in
Urban
Area
(PPRUA).
However,
variations
urban
definitions
make
these
incomparable
across
countries.
This
study
assesses
national
defined
PPRUA
within
statistics
against
estimates
we
derived
using
comparable
definitions.
Refer
to
UN's
Degree
Urbanization
framework,
propose
90
harmonized
methods
for
estimating
by
combining
different
configurations
three
population
datasets,
six
total
thresholds,
and
five
density
thresholds.
approach
demonstrated
significant
estimations,
with
wide
95%
confidence
intervals
Sustainability,
Год журнала:
2022,
Номер
14(21), С. 14341 - 14341
Опубликована: Ноя. 2, 2022
The
COVID-19
pandemic
has
led
to
a
re-examination
of
the
urban
space,
and
field
planning
architecture
is
no
exception.
In
this
study,
conditional
generative
adversarial
network
(CGAN)
used
construct
method
for
deriving
distribution
texture
through
hotspots
epidemic.
At
same
time,
relationship
between
form
epidemic
established,
so
that
machine
can
automatically
deduce
calculate
appearance
forms
are
prone
epidemics
may
have
high
risks,
which
application
value
potential
in
design.
taking
Macau
as
an
example,
was
conduct
model
training,
image
generation,
comparison
derivation
results
different
assumed
degrees.
implications
study
follows:
(1)
there
correlation
epidemics,
CGAN
be
predict
with
risk;
(2)
large-scale
buildings
high-density
promote
epidemic;
(3)
green
public
open
spaces
squares
inhibitory
effect
on
(4)
reducing
volume
density
increasing
area
help
reduce
International Journal of Applied Earth Observation and Geoinformation,
Год журнала:
2023,
Номер
121, С. 103376 - 103376
Опубликована: Июнь 3, 2023
Infectious
disease
spreading
is
a
spatial
interaction
process.
Assessing
community
vulnerability
to
infectious
diseases
thus
requires
not
only
information
on
local
demographic
and
built
environmental
conditions,
but
also
insights
into
human
activity
interactions
with
neighboring
areas
that
can
lead
the
transition
of
from
locations
locations.
This
study
presented
an
analytical
framework
based
Particle
Swarm
Optimization
model
estimate
weights
factors
for
modeling,
proportional
parameter
use
in
integration
area
risks.
A
country
five
cross-region
validation
models
were
developed
case
Singapore
assess
COVID-19.
The
results
showed
identified
robust
throughout
optimization
process
across
various
models.
could
be
set
slightly
higher
between
0.6
0.8
(out
1),
signifying
effect
was
than
effect.
Computation
optimal
solutions
integrated
index
intensity
accessibility
amenities
had
much
weights,
at
0.5
0.3,
respectively.
Conversely,
population
density,
elderly
population,
social
economic
status
land
diversity
lower.
These
findings
underscored
importance
considering
non-equal
incorporating
provide
more
comprehensive
assessment
diseases.
Applied Sciences,
Год журнала:
2024,
Номер
14(9), С. 3845 - 3845
Опубликована: Апрель 30, 2024
Amid
escalating
urbanization,
devising
rational
commercial
space
layouts
is
a
critical
challenge.
By
leveraging
machine
learning,
this
study
used
backpropagation
(BP)
neural
network
to
optimize
spaces
in
Weinan
City’s
central
urban
area.
The
results
indicate
an
increased
number
of
facilities
with
trend
multi-centered
agglomeration
and
outward
expansion.
Based
on
these
findings,
we
propose
strategic
framework
for
development
that
emphasizes
aggregation
centers,
axes,
spatial
guidelines.
This
strategy
provides
valuable
insights
planners
small-
medium-sized
cities
the
Yellow
River
Basin
metropolitan
areas,
ultimately
showcasing
power
learning
enhancing
planning.
