International Journal of Applied Earth Observation and Geoinformation,
Год журнала:
2024,
Номер
129, С. 103818 - 103818
Опубликована: Апрель 6, 2024
Freeway
traffic
volume
is
strongly
correlated
with
the
intensity
of
regional
socioeconomic
spatial
interactions
and
road
network
structure.
Although
existing
studies
have
proposed
indicators
betweenness
centrality
(BC)
integrated
into
interactions,
socio-economic
drivers
freeway
formation
been
neglected.
More
importantly,
not
established
a
non-linear
response
relationship
among
BC,
city
volume,
which
severely
limits
comprehensive
quantification
role
flow
drivers.
Therefore,
this
study
proposes
inference
method
that
integrates
interaction
to
enhance
BC.
First,
factors
origin
destination
cities
are
incorporated
BC
indicator
create
an
enhanced
(ODBC),
quantifies
strength
between
cities.
Second,
machine
learning
approach
used
develop
ODBC
accurately
infer
volume.
Finally,
utilizing
SHapley
additive
explanation
approach,
vectors
intercity
quantified.
Experiments
conducted
on
data
from
toll
stations
demonstrate
surpasses
baseline
based
weighted
by
considering
only
potential
or
attractiveness,
improvement
in
R2
14%,
4.2%,
4%,
maximum
reduction
RMSE
40%,
24.5%,
26%.
The
yields
higher
accuracy
for
unknown
segments
easily
interpretable.
Heliyon,
Год журнала:
2025,
Номер
11(2), С. e41937 - e41937
Опубликована: Янв. 1, 2025
Road
freight
modeling
was
conducted
to
project
flow
and
greenhouse
gas
(GHG)
emissions
in
16
administrative
regions
of
South
Korea
through
2050.
Origin-destination
matrices
were
constructed
using
a
gravity
model
for
each
region.
The
covered
seven
product
categories
both
inter-regional
intra-regional
transportation
validated
2017
data.
total
future
is
projected
increase
from
1399
million
tons
2019
1701
by
2035.
However,
after
peaking
2035,
it
expected
decline
1618
2050,
indicating
that
population
will
impact
demand,
causing
reduction
despite
continued
economic
growth.
GHG
are
slightly
decrease
19.0
kgCO2eq.
2025
18.6
followed
steeper
15.5
This
attributed
long-term
reductions
emission
factors.
Changes
between
2050
be
more
pronounced
within
five
the
capital
extended
areas,
which
account
approximately
50.3
%
due
concentration.
As
result,
these
contribute
26.5
potential.
minimum
growth
rates
required
maintain
same
volume
as
2035
estimated
at
5
2040,
13
2045,
26
WSEAS TRANSACTIONS ON BUSINESS AND ECONOMICS,
Год журнала:
2025,
Номер
22, С. 832 - 844
Опубликована: Май 2, 2025
This
is
particularly
important
in
logistics,
where
path
planning
critical
for
adequate
transport
and
distribution
processes.
That
why
classical
approaches
like
Dijkstra’s
algorithm
have
been
essential,
though
they
are
too
weak
to
handle
the
complications
typical
of
actual
logistics
networks.
To
this
end,
paper
proposes
a
new
framework
called
DeepShortest,
which
improves
optimization
process
using
deep
learning
methods.
DeepShortest
uses
neural
network
training
flexibility
complexity
various
logistical
contexts.
Thus,
successfully
implements
within
base
deliver
high
result
finding
shortest
most
effective
paths
transporting
goods
through
global
chains.
In
paper,
DEEP
Define
strategy
describes
how
methodologies
cast
into
component
approach.
addition,
real-world
case
studies
substantiate
effectiveness
advantage
compared
with
previous
methods,
generally
providing
stepped-up
route
performance
resource
management.
an
innovative
approach
solving
problems
creative
solution
issues
today’s
supply
chain.
With
their
capacity
work
areas
conditions
change
often
suggest
optimal
delivery
vehicles,
presents
itself
as
invaluable
that
could
drastically
transform
worldwide.
