Risk Analysis,
Год журнала:
2024,
Номер
44(9), С. 2025 - 2045
Опубликована: Март 1, 2024
Abstract
Navy
escorts
are
considered
crucial
in
countering
illegal
piracy
attacks.
In
this
paper,
a
novel
approach
is
developed
to
investigate
the
effect
of
navy
on
incidents
by
models
based
two
enhanced
Tree‐Augmented
Naïve
(TAN)
Bayesian
networks.
This
offers
systematic
investigation
into
various
factors
that
influence
pirate
activities,
and
helps
identify
changes
attack
behaviors
when
confronted
assess
effectiveness
anti‐piracy
measures.
An
empirical
study
conducted
utilizing
unique
data
set
compiled
from
multiple
sources
2000
2019.
The
evidence
shows
there
was
gradual
reduction
incidence
attacks
East
Africa
following
implementation
2009,
but
with
surge
2010
2011.
is,
thus,
divided
time
periods
at
point
2009
facilitate
robust
comprehensive
analysis,
resulting
development
TAN
models.
Meanwhile,
geographical
distribution
has
shifted
international
waters
port
areas
territorial
waters.
We
argue
shift
could
be
attributed
calculating
behavior
pirates
they
encounter
external
pressures.
Finally,
Shapely
introduced
evaluate
potential
implemented
risk
management
strategies
Game
Theory
perspective.
new
insights
promotion
contributes
framework
for
assessing
risks
uncertain
dynamic
environments.
Ocean Engineering,
Год журнала:
2023,
Номер
284, С. 115048 - 115048
Опубликована: Июнь 27, 2023
In
order
to
analyse
the
research
evolution
and
knowledge
frontier
in
of
marine
accidents,
491
literatures
on
accidents
Web
Science
database
from
2000
2022
are
taken
as
data
sources.
Integrated
with
literature
analysis
traditional
method,
CiteSpace
VOSviewer
then
jointly
used
for
development
network
map
cluster
analysis,
map,
hotpots,
frontiers
is
obtained.
It
found
that
there
a
close
cooperative
relationship
among
journals,
researchers,
institutions
countries
or
regions.
According
subjects
methods,
study
can
be
divided
into
two
parts:
influential
factors
accident
consequences,
well
methodology
emerging
technology.
this
context,
human
remote-controlled
ships,
prevention
Arctic
waters
have
become
hotspots,
while
methods
such
machine
learning
big
mining
also
shown
powerful
insights
accidents.
terms
innovation,
bibliometric
approach
enhances
ability
handle
large
databases
conduct
analysis.
Moreover,
visualises
collaborative
networks,
analyses
trends,
reveals
conducts
comparison
discussion
mainstream
approaches
research.
As
result,
provides
theoretical
basis
implementation
direction
maritime
safety.
Reliability Engineering & System Safety,
Год журнала:
2023,
Номер
244, С. 109925 - 109925
Опубликована: Дек. 30, 2023
Maritime
casualty
analysis
needs
to
be
addressed
given
the
increasing
safety
demand
in
field
due
accidents'
low-frequency
and
high-consequence
features.
This
paper
aims
delve
deeper
into
factors
that
affect
maritime
accident
casualties
by
establishing
a
new
database
conducting
an
evolution
analysis.
Based
on
refined
dataset,
pure
data-driven
Bayesian
network
(BN)
model
is
developed
conduct
of
accidents
occurred
under
different
ship
operational
conditions.
Methodologically,
it
introduces
risk
improve
accuracy
through
enriched
updated
database.
Furthermore,
categorised
five
datasets
based
temporal
development
trends
better
analyse
casualty.
Five
models
are
individually
constructed
timeframes
illustrate
dynamics
compared
seven
evaluation
indexes
demonstrate
effectiveness
proposed
BN
model.
It,
for
first
time,
investigates
changing
roles
with
time.
The
insights
gained
from
this
invaluable,
contributing
improved
prediction
strategies
acknowledging
patterns
accidents.
Reliability Engineering & System Safety,
Год журнала:
2024,
Номер
248, С. 110148 - 110148
Опубликована: Апрель 21, 2024
Machine
learning
(ML),
particularly,
Automated
machine
(AutoML)
offers
a
range
of
possibilities
for
analysing
large
volume
historical
maritime
accident
records
data
with
advanced
algorithms
integrating
predictive
analytics
in
operational
and
policy
decision
making
improving
safety.
This
study
explores
accidents
Norwegian
waters
over
the
40
years.
The
has
been
utilised
five
major
categories:
grounding,
contact
damage,
fire
or
explosion,
collision,
heavy
weather
damage.
A
total
29
classification
ML
were
trained,
Light
Gradient
Boosted
Trees
Classifier
was
found
best
performing
model
highest
accuracy.
three
most
impactful
factors
risk
are:
category
navigation
waters,
phase
operation,
gross
tonnage
vessel.
Based
on
feature
effect
results,
vessels
sailing
narrow
coastal
along
way
phase,
fishing
are
highly
vulnerable
to
grounding
relative
other
types
accidents.
results
can
be
used
as
input
entire
procedure
analysis,
from
hazard
identification
quantification
consequences,
algorithm
utilized
developing
support
system
real-time
assessment.
Transportation Research Part E Logistics and Transportation Review,
Год журнала:
2024,
Номер
188, С. 103647 - 103647
Опубликована: Июль 2, 2024
Although
many
studies
have
focused
on
the
occurrence
likelihood
of
marine
accidents,
few
analysis
severity
consequences,
and
even
fewer
prediction
severity.
To
this
end,
a
new
research
framework
is
proposed
in
study
to
accurately
predict
accidents.
First,
novel
two-stage
feature
selection
(FS)
method
was
developed
select
rank
Risk
Influential
Factors
(RIFs)
improve
accuracy
Machine
Learning
(ML)
model
interpretability
FS.
Second,
comprehensive
evaluation
measure
performance
FS
methods
based
stability,
predictive
improvement,
statistical
tests.
Third,
six
well-established
ML
models
were
used
compared
different
predictors.
The
Light
Gradient
Boosting
(LightGBM)
found
best
for
accidents
treated
as
benchmark
model.
Finally,
LightGBM
accident
RIFs
selected
by
method,
effect
risk
control
measures
counterfactually
analysed
from
quantitative
perspective.
This
innovative
use
improved
approaches
can
effectively
analyse
providing
methodology
triggering
direction
using
Artificial
Intelligence
(AI)
technologies
safety
assessment
prevention
studies.
source
code
publicly
available
at:
https://github.com/FengYinLeo/PGI-SDMI.
Ocean Engineering,
Год журнала:
2024,
Номер
303, С. 117736 - 117736
Опубликована: Апрель 10, 2024
Maritime
accident
research
has
primarily
focused
on
characteristics
and
risk
analysis,
which
often
overlooks
the
evolution
of
associated
patterns
over
time.
This
study
aims
to
investigate
dynamic
changes
in
maritime
accidents
from
2012
2021
by
employing
a
data-driven
Bayesian
Network
(BN)
model
conducting
systematic
pattern
comparison.
It
presents
two-stage
models
for
two
databases
five
against
different
timeframes
capture
evolving
global
accidents.
Furthermore,
within
context
investigation,
this
pioneers
analysis
effectiveness
network
structures,
namely
layered
BN
Tree-Augmented
Naive
(TAN)
network,
terms
accuracy
predicting
severity.
The
key
findings
regarding
past
decade
include:
(1)
significant
rise
risks
linked
large
ships
(30.8%),
port
areas
(11.67%),
anchoring
(11.82%),
manoeuvering
operations
(3.8%);
(2)
connection
between
poor
practices
fishing
boats
'overboard'
accidents,
inadequate
equipment
tankers
or
chemical
'fire/explosion'
accidents;
(3)
TAN
model's
superior
performance
forecasting
severity
compared
model;
(4)
probability
'very
serious'
ship-related
factors
is
74.7%,
significantly
lower
than
network's
99.4%.
reveals
shifts
time
underscores
importance
continuous
monitoring
effective
safety
management.
Reliability Engineering & System Safety,
Год журнала:
2024,
Номер
249, С. 110187 - 110187
Опубликована: Май 15, 2024
Ship
collision
accidents
are
one
of
the
most
frequent
accident
types
in
global
maritime
transportation.
Nevertheless,
conducting
an
in-depth
analysis
prevention
poses
a
formidable
challenge
due
to
constraints
limited
Risk
Influential
Factors
(RIFs)
and
available
datasets.
This
paper
aims
incorporate
perspective
into
new
data-driven
risk
model,
scrutinize
root
causes
accidents,
advance
measures
for
their
mitigation.
Additionally,
it
seeks
analyze
spatial
distribution
conduct
comprehensive
comparative
study
on
characteristics
both
pre-
post-COVID-19,
utilizing
real
dataset
collected
from
two
reputable
organizations:
Global
Integrated
Shipping
Information
System
(GISIS)
Lloyd's
Register
Fairplay
(LRF).
The
research
findings
implications
encompass
several
crucial
aspects:
1)
constructed
model
demonstrates
its
reliability
accuracy
predicting
as
evident
prediction
performance
various
scenario
analysis;
2)
hazardous
voyage
segment
is
identified
provide
valuable
guidance
different
stakeholders;
3)
hierarchical
significance
ship
context
highlighted
regarding
probable
occurrences;
4)
During
pandemic,
rise
probabilities,
particularly
involving
older
vessels
bulk
carriers,
implies
heightened
operational
challenges
or
maintenance
issues
these
types;
(5)
prominence
favorable
adverse
sea
conditions
reports
underscores
significant
influence
weather
during
pandemic.
These
help
enhance
safety
protocols,
ultimately
reducing
frequency
domain.
Journal of Marine Engineering & Technology,
Год журнала:
2024,
Номер
unknown, С. 1 - 12
Опубликована: Июнь 19, 2024
In
view
of
the
frequent
occurrence
marine
accidents
and
complex
interaction
various
risk-influencing
factors
(RIFs),
a
data-driven
method
to
risk
analysis
that
combines
association
rule
mining
(ARM)
network
(CN)
is
proposed
in
this
study.
The
efficient
FP-Growth
algorithm
applied
facilitate
ARM
examine
patterns
frequently
occur
accidents.
Subsequently,
CN
theory
employed
scrutinise
multifaceted
role
RIFs
their
interactions
accident
system,
which
involves
basic
characteristics
network,
identification
key
through
application
weighted
LeaderRank
(WLR)
algorithm,
robustness
analysis.
results
study
indicate
compared
with
random
networks,
networks
exhibit
higher
level
complexity,
brings
challenges
safety
prevention
control.
Inadequate
regulation,
violations,
deficiencies
management
systems
are
identified
as
RIFs,
stressing
urgency
improving
supervision,
strengthening
law
enforcement
system.
This
may
maritime
traffic
development
methods.
