Machines,
Journal Year:
2024,
Volume and Issue:
12(12), P. 906 - 906
Published: Dec. 10, 2024
During
the
ignition
process
of
a
solid
rocket
motor,
pressure
changes
dramatically
and
is
very
complex
as
it
includes
multiple
reactions.
Successful
completion
essential
for
proper
operation
motors.
However,
measurement
becomes
extremely
challenging
due
to
several
issues
such
enormity
high
cost
conducting
tests
on
Therefore,
needs
be
investigated
using
numerical
calculations
other
methods.
Currently,
fundamental
theories
concerning
have
not
been
fully
developed.
In
addition,
simulations
require
significant
simplifications.
To
address
these
issues,
this
study
proposes
motor
prediction
method
based
bidirectional
long
short-term
memory
(CBiLSTM)
combined
with
adaptive
Gaussian
noise
(AGN).
The
utilizes
experimental
data
simulated
inputs
co-training
predict
under
new
operating
conditions.
By
comparison,
AGN-CBiLSTM
has
higher
accuracy
percentage
error
3.27%
between
predicted
actual
data.
This
provides
an
effective
way
evaluate
performance
motors
wide
range
applications
in
aerospace
field.
International Journal of Information Management Data Insights,
Journal Year:
2024,
Volume and Issue:
4(2), P. 100255 - 100255
Published: May 25, 2024
In
the
dynamic
restaurant
industry,
we
introduce
"Genie,"
an
AI-powered
chatbot,
represents
advancement
in
customer
service
efficiency
through
technological
innovation.
Designed
to
enhance
operations
including
order
processing,
reservations,
and
FAQs
management,
Genie
leverages
advanced
Natural
Language
Processing
(NLP)
techniques.
By
converting
input
queries
into
word
embeddings
applying
a
sophisticated
tag
classification
system,
precisely
interprets
intents
generates
accurate
responses,
thereby
markedly
improving
dining
experience.
Our
thorough
examination
of
various
classifiers—Word2Vec,
Glove,
BERT,
Gaussian
Naive
Bayes,
XGB,
Artificial
Neural
Networks
(ANN),
Recurrent
Networks—revealed
that
combination
Word2Vec
ANN
is
most
effective,
achieving
impressive
accuracy
rate
88.9
%.
This
discovery
highlights
Genie's
capability
not
only
streamline
but
also
satisfaction
by
minimizing
wait
times
facilitating
contactless
options.
Additionally,
this
study
enriches
understanding
AI's
application
industries
explores
potential
future
impact
generative
AI
technologies
on
chatbot
interactions.
As
technology
advances,
its
integration
essential
for
deliver
increasingly
personalized
experiences,
aligning
with
evolving
demands
digital
era.
research
emphasizes
transformative
providing
valuable
insights
practical
applications
prospects
automated
solutions.
Urbanization, sustainability and society.,
Journal Year:
2025,
Volume and Issue:
2(1), P. 196 - 228
Published: March 25, 2025
Purpose
The
construction
industry
is
under
increasing
pressure
to
improve
risk
management
due
the
complexity
and
uncertainty
inherent
in
its
projects.
Generative
artificial
intelligence
(GenAI)
has
emerged
as
a
promising
tool
address
these
challenges;
however,
there
remains
limited
understanding
of
benefits
risks
(CRM).
This
study
aims
conduct
bibliometric
analysis
current
research
on
GenAI
CRM,
exploring
publication
trends,
citations,
keywords,
intellectual
linkages,
key
contributors
methodologies.
Design/methodology/approach
A
review
Scopus
publications
from
2014
2024
identifies
categories
GenAI’s
for
CRM.
Using
VOSViewer,
visual
maps
illustrate
collaboration
networks
citation
patterns.
Findings
findings
reveal
notable
increase
interest
with
classified
into
technical,
operational,
technological
integration
categories.
Risks
are
grouped
nine
areas,
including
social,
security,
data
performance.
Research
limitations/implications
Despite
comprehensive
scope,
this
focuses
exclusively
peer-reviewed
studies
published
between
2024,
potentially
excluding
relevant
outside
period
or
non-peer-reviewed
sources.
Additionally,
relied
specific
set
which
may
have
excluded
using
alternative
terminology
categorised
related
fields.
Practical
implications
categorisation
CRM
provides
foundation
critical
processes,
such
analysis,
evaluation
response
planning.
identified
benefits,
improved
prediction,
alongside
associated
risks,
ethical
security
issues,
enables
practitioners
balance
innovation
caution,
ensuring
effective
responsible
adoption
technologies.
Originality/value
offers
novel
providing
field’s
evolution
global
landscape.
Through
lays
groundwork
developing
models.
it
methodologies
enabling
academics
refine
approaches
bridge
gaps.
work
not
only
enhances
theoretical
insights
but
also
actionable
strategies
integrating
practices
effectively
responsibly.
Engineering Construction & Architectural Management,
Journal Year:
2025,
Volume and Issue:
unknown
Published: April 30, 2025
Purpose
Achieving
smart
question-answering
(QA)
for
construction
laws
(CLs)
holds
significant
promise
in
aiding
domain
professionals
with
legal
inquiries.
Existing
studies
of
law
(CLQA)
rely
on
learning-based
models,
which
require
extensive
training
data
and
are
limited
to
a
narrow
QA
scope.
Meanwhile,
general-purpose
large
language
models
(GPLLMs)
possess
great
potential
CLQA
but
fall
short
domain-specific
knowledge.
This
study
aims
propose
data-driven
expertise-based
approach
develop
knowledge
repository
(CLKR)
validate
its
effectiveness
enhancing
the
performance
GPLLMs.
Design/methodology/approach
methodology
includes
(1)
recognizing
702
candidate
CL
documents
from
374,992
official
judgments,
(2)
building
CLKR
387
filtered
covering
eight
areas,
(3)
integrating
seven
representative
GPLLMs
(4)
constructing
2,140-question
dataset
Professional
Construction
Engineer
Qualification
Examinations
(PCEQEs)
during
2014–2023
compare
between
pairs
without
CLKR.
Findings
The
significantly
enhances
GPLLMs,
yielding
an
impressive
average
accuracy
increase
21.1%,
individual
improvements
ranging
9.9
44.9%.
Furthermore,
boosts
single-answer
questions
by
14.9%
multiple-answer
38.3%.
Additionally,
enhancements
across
8
areas
14.5
28.2%.
Originality/value
proposes
developing
external
base
empower
expanding
scope
while
bypassing
complex
traditional
models.
Moreover,
this
confirms
augmenting
GPLLM
offers
reusable
test
as
benchmark.
