2021 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech),
Год журнала:
2022,
Номер
unknown, С. 1 - 6
Опубликована: Сен. 12, 2022
The
fifth
industrial
revolution
brings
the
focus
to
well-being,
sustainability,
and
resilient
human-centric
manufacturing
systems.
To
this
end,
quality
quantity
of
light
in
work
environment
plays
a
fundamental
role
for
management
human
body's
circadian
clock,
hence
psychophysical
well-being
worker.
In
we
propose
lighting
control
system
based
on
wireless
sensor
network
able
realize
an
architecture
fully
compliant
Internet
Things
requirements,
inclusive
focused
worker's
physical
mental
well-being.
particular,
ad-hoc
node
with
suitable
interface
has
been
developed
interoperate
standard
systems
extend
their
functionality
remote
monitoring
through
web
platform.
proposed
solution
tested
critical
scenario
such
as
one
which
performance
analyzed
terms
Round
Trip
Time,
packet
loss
goodput.
obtained
results
show
that
value
is
its
versatility
scalability
relatively
number
density
nodes,
typology
sensing
units.
IEEE Access,
Год журнала:
2023,
Номер
11, С. 64697 - 64712
Опубликована: Янв. 1, 2023
Our
previous
research
applied
a
classification-integrated
moving
average
(CIMA).
This
intelligence
method
improves
the
performance
of
passive
infrared
(PIR)
sensors
in
smart
lighting
to
make
control
more
comfortable
for
user.
However,
intelligence,
synonymous
with
use
cloud
and
large
latency,
contradicts
real-time
nature
demanded
by
lighting.
paper
proposes
edge
(EdgeSL)
architecture,
an
edge-computing
architecture
improved
CIMA
control.
We
developed
novel
intelligent
using
permutation
importance
feature
selection
improve
algorithm.
Three
model
compression
methods
k-nearest
neighbor
(KNN)
are
compared,
including
knowledge
distillation
on
KNN
called
DistilKNN.
The
is
basis
CIMA.
allows
run
environment.
experiment
was
carried
out
evaluating
processing
time
three
different
environments,
namely
edge,
fog,
architecture.
test
results
show
that
DistilKNN
has
best
accuracy
compared
other
methods,
pruning
quantization,
which
0.93.
After
deploying
compressed
NodeMCU,
computing
lower
than
fog
computing,
9.0,
60.1,
207.6
ms,
respectively.
going
through
Shapiro-Wilk
test,
we
learned
times
not
normally
distributed.
So
after
testing
Wilcoxon
it
proved
EdgeSL
performance,
where
architectures
significant
differences.
Sensors,
Год журнала:
2022,
Номер
22(21), С. 8523 - 8523
Опубликована: Ноя. 5, 2022
This
paper
proposes
energy-efficient
solutions
for
the
smart
light-emitting
diode
(LED)
lighting
system,
which
provides
minimal
energy
consumption
while
simultaneously
satisfying
illuminance
requirements
of
users
in
a
typical
office
space.
In
addition
to
artificial
light
from
dimmable
LED
lamps,
natural
daylight
coming
external
sources,
such
as
windows,
is
considered
source
illumination
an
indoor
environment.
order
reduce
total
consumption,
system
has
possibility
dim
resulting
reduced
output
power.
Additionally,
various
lamps'
functionality,
semi-angle
half
and
tilting,
are
introduced
additional
parameter
be
optimized
achieve
greater
saving
designed
system.
properly
exploit
lighting,
idea
overall
intensity
at
users'
location
realized
by
option
windows
with
shading
factor.
Based
on
desired
level
illumination,
proposed
optimization
problems
can
solved
implementing
different
algorithms.
The
obtained
able
give
instructions
manage
control
parameters
(LEDs
dimming
levels,
semi-angles
illuminance,
orientation
LEDs,
factor)
design
ensures
satisfaction
related
requirements.
Lighting Research & Technology,
Год журнала:
2023,
Номер
56(4), С. 381 - 402
Опубликована: Июль 26, 2023
Visual
fatigue
has
become
a
public
health
issue,
while
the
relevant
retinal
mechanism
and
characteristics
of
blue
light
that
induce
visual
have
been
rarely
studied.
In
retina,
both
short
wavelength-sensitive
(S)
cones
melanopsin-containing
intrinsically
photoreceptive
ganglion
cells
(ipRGCs)
are
sensitive
to
light,
their
responses
opposite
in
pupil
mediation.
Thus,
effects
blue-enriched
white
with
different
S-cone-opic
Equivalent
Daylight
Illuminance
(EDI)
on
was
investigated,
maintaining
same
melanopic
EDI
avoid
interferences
ipRGCs.
Two
illuminants
(one
low
EDI,
other
high
EDI)
were
characterized
based
α-opic
correlated
colour
temperature
illuminance.
Melanopic
lower
than
these
two
illuminants.
Psychological,
visual,
physiological
cognitive
performances
measured
investigate
fatigue.
Results
showed
can
Participants
felt
more
discomfort
eyes
under
along
decline
tear
film
stability
changes
heart
rhythm.
Furthermore,
reaction
time
memory
task
increased
significantly
EDI.
The
findings
provide
new
insights
into
optimization
indoor
lighting
environments
for
human
health.
FUDMA Journal of Sciences,
Год журнала:
2024,
Номер
8(2), С. 390 - 398
Опубликована: Апрель 30, 2024
Lighting
control
systems
are
essential
in
modern
building
automation
and
smart
homes,
efficiently
managing
illumination
to
enhance
energy
conservation
user
comfort.
This
project
tackles
consumption
challenges
hospital
buildings
by
introducing
Intelligent
Control
Systems
(ILCS)
that
take
natural
light
occupancy
into
account,
driven
Artificial
Neural
Networks
(ANN)
diverse
machine
learning
algorithms.
In
our
study,
we
collected
sensor
data,
processed
it,
designed
a
lighting
system
employing
feedforward
neural
network
various
Surprisingly,
research
found
linear
regression
algorithm
surpassed
the
ANN-based
this
context.
We
implemented
prototype,
tested
it
on
hardware,
obtained
expected
results.
marks
progress
towards
optimizing
use
contributing
sustainability
endeavors.
By
combining
ILCS
learning,
offers
promising
approach
for
more
efficient
eco-friendly
Frontiers in Built Environment,
Год журнала:
2023,
Номер
9
Опубликована: Дек. 15, 2023
Introduction:
This
study
investigated
the
influence
of
indoor
lighting
environments
on
paper
reading
efficiency
and
brain
fatigue
to
explore
parameters
that
benefit
users
during
various
durations.
Methods:
The
was
conducted
in
Smart
Lighting
Lab,
where
12
participants
were
tested
under
different
illuminance
levels
correlated
color
temperatures
(CCT)
for
three
distinct
Reading
task
tests
objective
measures
activity
by
monitoring
participants’
electroencephalograms
(EEGs)
used
as
key
factors
assess
levels.
Results:
By
analyzing
subjective
results,
we
found
significantly
affected
changes
environment.
Also,
based
results
this
study,
propose
recommendations
tasks
For
a
15
min
task,
condition
500
lux-6,500
K
most
efficient
reading;
30
lux-4,000
be
effective;
750
best
environment
60
duration.
Discussion:
These
suggestions
can
serve
reference
designing
In
addition,
they
provide
guidance
researchers
reviewers
conducting
similar
studies.
Electric
lighting
plays
a
critical
role
in
buildings,
not
only
impacting
the
well-being,
satisfaction,
and
performance
of
building
occupants
but
also
accounting
for
significant
portion
energy
consumption.
The
commonly
used
efficiency
metrics
lighting,
such
as
luminous
efficacy
or
power
density,
fall
short
quantifying
effective
light
architectural
spaces.
To
address
shortcomings
existing
measures,
application
that
characterizes
efficient
delivery
from
source
to
target
should
be
utilized.
Lighting
can
account
efficiencies
temporal,
electrical,
visual,
spatial
dimensions.
This
study
outlines
method
quantify
electric
buildings.
As
proof
concept,
simulated
data
are
analyzed
two
targets
(horizontal
work
plane
level
occupant
field
view)
based
on
primary
characteristics
built
environment
systems.
findings
indicate
design
variables
(e.g.,
room
size,
luminaire
distribution
type,
reflectance
surfaces,
significantly
affect
specified
settings.
Therefore,
values
exhibit
considerable
variation
among
distinct
systems
spaces
customized
suit
unique
requirements
each
setting.
Future
research
will
investigate
establish
complementary
components
framework.
