Navigating uncertainty: A dynamic Bayesian network-based risk assessment framework for maritime trade routes
Reliability Engineering & System Safety,
Год журнала:
2024,
Номер
250, С. 110311 - 110311
Опубликована: Июль 1, 2024
Язык: Английский
Embracing imperfect data: A novel data-driven Bayesian network framework for maritime accidents severity risk assessment
Ocean Engineering,
Год журнала:
2025,
Номер
329, С. 121212 - 121212
Опубликована: Апрель 12, 2025
Язык: Английский
Maritime security threats: Classifying and associating patterns in piracy and armed robbery incidents
Ocean & Coastal Management,
Год журнала:
2025,
Номер
266, С. 107685 - 107685
Опубликована: Апрель 15, 2025
Язык: Английский
++Unleashing Data Power: Driving Maritime Risk Analysis with Bayesian Networks
Reliability Engineering & System Safety,
Год журнала:
2025,
Номер
unknown, С. 111310 - 111310
Опубликована: Май 1, 2025
Язык: Английский
Rescue path planning for urban flood: A deep reinforcement learning–based approach
Risk Analysis,
Год журнала:
2024,
Номер
unknown
Опубликована: Авг. 11, 2024
Urban
flooding
is
among
the
costliest
natural
disasters
worldwide.
Timely
and
effective
rescue
path
planning
crucial
for
minimizing
loss
of
life
property.
However,
current
research
on
often
fails
to
adequately
consider
need
assess
area
risk
uncertainties
bypass
complex
obstacles
in
flood
scenarios,
presenting
significant
challenges
developing
optimal
paths.
This
study
proposes
a
deep
reinforcement
learning
(RL)
algorithm
incorporating
four
main
mechanisms
address
these
issues.
Dual-priority
experience
replays
backtrack
punishment
enhance
precise
estimation
risks.
Concurrently,
random
noisy
networks
dynamic
exploration
techniques
encourage
agent
explore
unknown
areas
environment,
thereby
improving
sampling
optimizing
strategies
bypassing
obstacles.
The
constructed
multiple
grid
simulation
scenarios
based
real-world
operations
major
urban
disasters.
These
included
uncertain
values
all
passable
an
increased
presence
elements,
such
as
narrow
passages,
C-shaped
barriers,
jagged
paths,
significantly
raising
challenge
planning.
comparative
analysis
demonstrated
that
only
proposed
could
plan
across
nine
scenarios.
advances
theoretical
progress
by
extending
scale
unprecedented
levels.
It
also
develops
RL
adaptable
various
extremely
Additionally,
it
provides
methodological
insights
into
artificial
intelligence
management.
Язык: Английский
Hotspot analysis of global piracy and armed robbery incidents at sea: A decadal review of regional vulnerabilities and security strategies
Ocean & Coastal Management,
Год журнала:
2024,
Номер
260, С. 107480 - 107480
Опубликована: Ноя. 20, 2024
Язык: Английский
Risk Analysis of Pirate Attacks on Southeast Asian Ships Based on Bayesian Networks
Journal of Marine Science and Engineering,
Год журнала:
2024,
Номер
12(7), С. 1088 - 1088
Опубликована: Июнь 27, 2024
As
a
bridge
for
international
trade,
maritime
transportation
security
is
crucial
to
the
global
economy.
Southeast
Asian
waters
have
become
high-incidence
area
of
piracy
attacks
due
geographic
location
and
complex
situations,
posing
great
threat
development
Maritime
Silk
Road.
In
this
study,
factors
affecting
risk
pirate
are
analyzed
in
depth
by
using
Global
Ship
Piracy
Attacks
Report
from
IMO
Integrated
Shipping
Information
System
(GISIS)
database
(i.e.,
2013–2022)
conjunction
with
Bayesian
Network
(BN)
model,
Expectation
Maximization
algorithm
used
train
model
parameters.
The
results
show
that
behaviors
ship’s
key
attacks,
suggestions
made
reduce
attacks.
This
study
develops
theoretical
basis
preventing
controlling
on
ships,
which
helps
maintain
safety
ship
operations.
Язык: Английский