The International Journal of Advanced Manufacturing Technology,
Год журнала:
2023,
Номер
129(5-6), С. 2763 - 2782
Опубликована: Окт. 19, 2023
Abstract
In
the
context
of
Industry
5.0,
characterized
by
human-centred
transformation
manufacturing
processes,
assessing
operator
risk
is
crucial
for
ensuring
workplace
safety
and
well-being.
this
respect,
paper
presents
development
a
human-cyber-physical
system
(HCPS)
capable
estimating
leveraging
diverse
sensing
data.
By
comprehensively
analysing
complex
patterns
interactions
among
physiological,
environmental,
variables,
HCPS
offers
an
advanced
approach
to
assessment.
Through
integration
cutting-edge
technologies,
real-time
data
collection,
sophisticated
analytics
paradigms,
accurately
identifies
meaningful
anomalies.
It
dynamically
adapts
changing
conditions,
generating
profiles
operators
work
processes.
Timely
alerts
notifications
enable
proactive
interventions,
enhancing
measures
optimizing
The
empowers
decision-making
supporting
well-being
productivity
in
5.0
paradigm,
while
maintaining
safe
working
environment.
A
simulated
case
study
reported
validate
proposed
framework
on
variety
industrial
scenarios.
Environmental Pollution,
Год журнала:
2023,
Номер
331, С. 121832 - 121832
Опубликована: Май 18, 2023
There
is
a
growing
need
to
apply
geospatial
artificial
intelligence
analysis
disparate
environmental
datasets
find
solutions
that
benefit
frontline
communities.
One
such
critically
needed
solution
the
prediction
of
health-relevant
ambient
ground-level
air
pollution
concentrations.
However,
many
challenges
exist
surrounding
size
and
representativeness
limited
ground
reference
stations
for
model
development,
reconciling
multi-source
data,
interpretability
deep
learning
models.
This
research
addresses
these
by
leveraging
strategically
deployed,
extensive
low-cost
sensor
(LCS)
network
was
rigorously
calibrated
through
an
optimized
neural
network.
A
set
raster
predictors
with
varying
data
quality
spatial
scales
retrieved
processed,
including
gap-filled
satellite
aerosol
optical
depth
products
airborne
LiDAR-derived
3D
urban
form.
We
developed
multi-scale,
attention-enhanced
convolutional
reconcile
LCS
measurements
estimating
daily
PM2.5
concentration
at
30-m
resolution.
employs
advanced
approach
using
geostatistical
kriging
method
generate
baseline
pattern
multi-scale
residual
identify
both
regional
patterns
localized
events
high-frequency
feature
retention.
further
used
permutation
tests
quantify
importance,
which
has
rarely
been
done
in
DL
applications
science.
Finally,
we
demonstrated
one
application
investigating
inequality
issue
across
within
various
urbanization
levels
block
group
scale.
Overall,
this
demonstrates
potential
AI
provide
actionable
addressing
critical
issues.
Atmospheric measurement techniques,
Год журнала:
2022,
Номер
15(21), С. 6309 - 6328
Опубликована: Ноя. 2, 2022
Abstract.
Ambient
fine
particulate
matter
(PM2.5)
pollution
is
a
major
health
risk.
Networks
of
low-cost
sensors
(LCS)
are
increasingly
being
used
to
understand
local-scale
air
variation.
However,
measurements
from
LCS
have
uncertainties
that
can
act
as
potential
barrier
effective
decision
making.
data
thus
need
adequate
calibration
obtain
good
quality
PM2.5
estimates.
In
order
develop
factors,
one
or
more
typically
co-located
with
reference
monitors
for
short
long
periods
time.
A
model
then
developed
characterizes
the
relationships
between
raw
output
and
monitors.
This
transferred
other
in
network.
Calibration
models
tend
be
evaluated
based
on
their
performance
only
at
co-location
sites.
It
often
implicitly
assumed
conditions
relatively
sparse
sites
representative
network
overall
not
overfitted
Little
work
has
explicitly
how
transferable
rest
an
network,
even
after
appropriate
cross-validation.
Further,
few
studies
sensitivity
key
use
cases,
such
hotspot
detection,
applied.
Finally,
there
been
dearth
research
duration
(short-term
long-term)
impact
these
results.
paper
attempts
fill
gaps
using
dense
Denver
deployed
through
city's
“Love
My
Air”
program.
offers
series
transferability
metrics
networks
some
suggestions
which
would
most
useful
achieving
different
end
goals.
EBioMedicine,
Год журнала:
2023,
Номер
93, С. 104668 - 104668
Опубликована: Июнь 25, 2023
Despite
progress
in
many
countries,
air
pollution,
and
especially
fine
particulate
matter
pollution
(PM2.5)
remains
a
global
health
threat:
over
6
million
premature
cardiovascular
respiratory
deaths/yr.
have
been
attributed
to
household
outdoor
pollution.
In
this
viewpoint,
we
identify
present
gaps
monitoring
regulation,
how
they
could
be
strengthened
future
mitigation
policies
more
optimally
reduce
impacts.
We
conclude
that
there
is
need
move
beyond
simply
regulating
PM2.5
mass
concentrations
at
central
site
stations.
A
greater
emphasis
needed
on:
new
portable
affordable
technologies
measure
personal
exposures
particle
mass;
the
consideration
of
submicron
(PM1)
quality
standard;
further
evaluations
effects
by
composition
source.
emphasize
enable
studies
on
exposure–health
relationships
underserved
populations
are
disproportionately
impacted
but
not
sufficiently
represented
current
studies.
Meteorological Applications,
Год журнала:
2023,
Номер
30(6)
Опубликована: Ноя. 1, 2023
Abstract
The
application
of
low‐cost
air
quality
monitoring
networks
has
substantially
grown
over
the
last
few
years,
following
technological
advances
in
production
cheap
and
portable
pollution
sensors,
thus
potentially
greatly
increasing
limited
spatial
information
on
conditions
provided
by
traditional
stations.
However,
use
sensors
still
presents
many
limitations,
mostly
related
to
reliability
their
measurements.
Despite
number
papers
focusing
these
issues,
some
challenges
connected
are
poorly
investigated
understood,
considering
particular
those
long‐term
applications
integration
within
reference
system.
present
review
aims
at
filling
this
gap,
analysing
characteristics
that
were
run
across
field
campaigns,
including
geographical
location,
pollutants
monitored,
type
stations
employed,
length
campaign,
with
a
attention
assessing
for
deployment
evaluation
official
networks.
Moreover,
critical
analysis
most
insightful
suggestions
recommendations
delivered
literature,
as
well
relevant
is
presented,
highlighting
open
research
areas
outlining
future
challenges.
Engineering Science & Technology Journal,
Год журнала:
2024,
Номер
5(6), С. 2027 - 2038
Опубликована: Июнь 13, 2024
Methane
emissions
from
the
oil
and
gas
industry
are
a
major
contributor
to
climate
change
due
their
high
global
warming
potential.
Accurate
standardized
monitoring
of
these
is
essential
for
effective
mitigation.
This
review
explores
current
state
methane
emission
technologies,
highlighting
strengths
limitations
direct
measurement,
remote
sensing,
modeling
approaches.
It
also
examines
diverse
regulatory
frameworks
practices,
identifying
key
challenges
such
as
accuracy,
consistency,
economic
barriers.
The
paper
proposes
strategies
harmonizing
standards
globally,
including
adopting
international
guidelines,
certification
programs,
centralized
reporting
platforms.
Additionally,
it
advocates
innovative
approaches
that
incentivize
better
practices
emphasizes
need
cooperation
through
data
sharing
capacity
building.
concludes
by
discussing
potential
impact
on
industry,
outlining
future
research
development
directions,
calling
proactive
steps
all
stakeholders
achieve
reduction.
Keywords:
Emissions,
Oil
Gas
Industry,
Monitoring
Technologies
Regulatory
Frameworks.
npj Climate and Atmospheric Science,
Год журнала:
2024,
Номер
7(1)
Опубликована: Ноя. 1, 2024
Low-cost
particulate
matter
sensors
(LCS)
are
vital
for
improving
the
spatial
and
temporal
resolution
of
air
quality
data,
supplementing
sparsely
placed
official
monitoring
stations.
Despite
their
benefits,
LCS
readings
can
be
biased
due
to
physical
properties
aerosol
particles
device
limitations.
An
optimization
model
is
essential
enhance
data
accuracy.
This
paper
presents
a
calibration
study
network
Timișoara,
Romania.
The
began
by
selecting
devices
near
National
Air
Quality
Monitoring
Network
(NAQMN)
stations
developing
parametric
models,
choosing
best
broader
application.
Plantower,
Sensirion,
Honeywell
showed
comparable
Calibration
involved
clusters
within
750
m
radius
around
NAQMN
Models
incorporating
RH
corrections
multiple
linear
regression
(MLR)
were
fitted.
was
validated
against
from
unseen
sensors,
leading
mean
bias
errors
(MBE)
9-17%
RMSEs
33-35%,
sensor
uncertainty
margins.
Applied
city-wide
network,
identified
several
regularly
exceeding
EU
daily
PM10
threshold,
unnoticed
limited
coverage.
highlights
necessity
granular
accurately
capture
urban
variations.
Atmospheric Pollution Research,
Год журнала:
2024,
Номер
15(4), С. 102057 - 102057
Опубликована: Янв. 20, 2024
This
paper
analyses
the
impact
of
urban
mobility
(UM)
on
air
pollution
by
studying
effects
an
intervention
local
quality.
The
study
focuses
PM2.5
level
in
Kampala,
capital
Uganda,
and
considers
COVID-19
as
unintentional
intervention.
city
was
obtained
from
a
network
low-cost
calibrated
sensors,
while
UM
is
characterized
open-access
Google
reports.
period
under
consideration
excludes
weeks
immediately
before
after
first
lockdown.
data
were
deweathered
using
machine
learning
technique
random
forest
(RF)
to
exclude
variation
meteorological
factors,
seasonality,
weekday-weekend
effect,
then
pandemic
parametrised.
traffic
pattern
discussed,
mass
clustering
polar
plots
are
used
analyse
distribution
long-
short-range
sources,
respectively.
percentage
change
baseline
(PCfB)
average
dimensions
assessed
against
that
investigate
level.
Our
analysis
shows
strong
correlation
between
roadside
levels
weaker
relationship
with
levels.
profile
long-range
emission
sources
consistent
over
period,
more
than
61%
modelled
masses
arrived
Kampala
passing
Kenya
Tanzania.
Overall,
reduced
about
10%,
which
relatively
small
compared
other
cities
have
been
studied
around
world.