E3S Web of Conferences,
Journal Year:
2024,
Volume and Issue:
511, P. 01039 - 01039
Published: Jan. 1, 2024
This
study
introduces
a
sophisticated
anomaly
detection
system
based
on
machine
learning.
The
is
specifically
developed
to
enhance
the
dependability
and
safeguard
security
of
electric
transportation
networks,
with
particular
emphasis
charging
infrastructure
for
vehicles
(EVs).
Utilizing
extensive
datasets,
research
examines
several
facets
stations,
records,
identified
abnormalities,
following
maintenance
measures.
examination
station
demonstrates
system’s
versatility
in
accommodating
many
circumstances,
as
seen
by
range
power
ratings,
consumption
patterns,
energy
provided.
Further
records
provides
comprehensive
understanding
individual
sessions,
enabling
irregularities
such
atypical
surges
extended
durations.
learning
system,
having
been
trained
verified
using
this
data,
has
commendable
degree
precision
identifying
anomalies,
shown
congruence
between
anticipated
abnormalities
real
results.
repair
measures
carried
out
reaction
highlight
practical
ramifications
proactive
tactics
utilized
reduce
downtime
operations.
performance
measures,
including
accuracy,
recall,
F1
score,
unequivocally
validate
resilience
guaranteeing
precise
identification
while
mitigating
occurrence
false
positives
negatives.
seamless
incorporation
into
results,
not
only
amplifies
safeguarding
EV
but
also
establishes
an
invaluable
instrument
implementations.
research,
addition
offering
thorough
performance,
elucidates
forthcoming
avenues
scalability,
real-time
monitoring,
interpretability,
thereby
making
valuable
contribution
wider
discussion
revolutionary
capabilities
ever-changing
realm
transportation.
Systems,
Journal Year:
2024,
Volume and Issue:
12(2), P. 58 - 58
Published: Feb. 9, 2024
At
the
current
stage
of
development
and
implementation
information
technology
in
various
areas
human
activity,
decisive
changes
are
taking
place,
as
there
powerful
technical
resources
for
accumulation
processing
large
amounts
[...]
Critical
infrastructures,
such
as
power
and
water
networks,
are
vital
for
society
the
economy.
However,
they
vulnerable
to
various
disruptions
component
failures,
cyber-attacks,
natural
disasters.
These
can
cascade
across
critical
infrastructure
networks
(CINs),
causing
significant
socioeconomic
losses.
Decision-makers
face
challenge
of
protecting
CINs
before
restoring
their
functions
afterward,
considering
interdependencies
uncertainties.
Current
methods
struggle
model
big
data,
complex
interactions,
multilayer
dependencies
between
CINs.
Artificial
intelligence
(AI)
machine
learning
(ML)
applications
be
used
overcome
these
challenges,
systems
discover
data
patterns
representing
a
promising
research
trend
that
could
benefit
both
private
companies
governments.
This
article
undertakes
comprehensive
review
literature
on
in
improving
resilience
interdependent
(ICISs).
The
aim
is
address
existing
knowledge
gap
dispersed
articles
this
area,
following
Preferred
Reporting
Items
Systematic
Reviews
Meta-Analyses
(PRISMA)
protocol.
primary
goal
assess
current
state
ML
ICISs
engineering
field
by
examining
available
literature,
order
future
opportunities
trends.
findings
summarized,
potential
trends
listed,
aiming
inspire
practitioners
explore
directions
field.
Franklin Open,
Journal Year:
2024,
Volume and Issue:
8, P. 100137 - 100137
Published: July 14, 2024
Time
series
forecasting
is
crucial
across
various
sectors,
aiding
stakeholders
in
making
informed
decisions,
planning
for
the
short
and
long
term,
managing
risks,
optimizing
profits,
ensuring
safety.
One
significant
application
of
time
predicting
Earth
surface
temperatures,
which
vital
civil
environmental
sectors
such
as
agriculture,
energy,
meteorology.
This
study
proposes
a
hybrid
model
temperature
using
Deep
Learning
(DL).
To
improve
DL
model's
performance,
an
optimization
algorithm
called
Barnacles
Mating
Optimizer
(BMO)
integrated
to
optimize
both
weights
biases.
The
trained
on
global
dataset
with
seven
inputs
compared
models
optimized
by
Particle
Swarm
Optimization
(PSO),
Harmony
Search
Algorithm
(HSA),
Ant
Colony
(ACO).
Additionally,
comparison
made
Autoregressive
Moving
Average
(ARIMA)
method.
Evaluation
Mean
Absolute
Error
(MAE),
Root
Square
(RMSE),
coefficient
determination
(R2)
demonstrates
superior
performance
BMO,
showing
minimal
errors.
