This
study
proposes
a
nonlinear
mathematical
model
of
virus
transmission
based
on
the
SEIR
model.
In
this
study,
interaction
between
viruses
and
immune
cells
is
investigated
using
phase-space
analysis
Specifically,
it
focused
dynamics
stability
behavior
spread
in
population
its
with
human
systems
cells.
The
endemic
equilibrium
points
are
found
local
all
equilibria
related
obtained.
Further,
global
either,
at
disease-free
equilibria,
or
discussed
by
constructing
Lyapunov
function
which
shows
validity
concern
exists.
Finally,
simulated
solution
achieved
relationship
highlighted.
Economic Theory,
Journal Year:
2023,
Volume and Issue:
77(1-2), P. 127 - 168
Published: April 12, 2023
We
analyze
the
role
of
disease
containment
policy
in
form
treatment
a
stochastic
economic-epidemiological
framework
which
probability
occurrence
random
shocks
is
state-dependent,
namely
it
related
to
level
prevalence.
Random
are
associated
with
diffusion
new
strain
affects
both
number
infectives
and
growth
rate
infection,
such
realization
may
be
either
increasing
or
decreasing
infectives.
determine
optimal
steady
state
framework,
characterized
by
an
invariant
measure
supported
on
strictly
positive
prevalence
levels,
suggesting
that
complete
eradication
never
possible
long
run
outcome
where
instead
endemicity
will
prevail.
Our
results
show
that:
(i)
independently
features
state-dependent
probabilities,
allows
shift
leftward
support
measure;
(ii)
probabilities
affect
shape
spread
distribution
over
its
support,
allowing
for
alternatively
highly
concentrated
low
levels
more
out
larger
range
(possibly
higher)
levels.
ACM Computing Surveys,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Feb. 24, 2025
Infectious
diseases
place
a
heavy
burden
on
public
health
worldwide.
In
this
paper,
we
systematically
investigate
how
machine
learning
(ML)
can
play
an
essential
role
in
quantitatively
characterizing
disease
transmission
patterns
and
accurately
predicting
infectious
risks.
First,
introduce
the
background
motivation
for
using
ML
risk
prediction.
Next,
describe
development
application
of
various
models
prediction,
categorizing
them
according
to
models’
alignment
with
vital
concerns
specific
two
distinct
phases
propagation:
(1)
pandemic
epidemic
(the
P-E
phaseS)
(2)
endemic
elimination
E-E
phaseS),
each
presenting
its
own
set
critical
questions.
Subsequently,
discuss
challenges
encountered
when
dealing
model
inputs,
designing
task-oriented
objectives,
conducting
performance
evaluations.
We
conclude
discussion
open
questions
future
directions.
Mathematics,
Journal Year:
2024,
Volume and Issue:
12(3), P. 493 - 493
Published: Feb. 4, 2024
Due
to
the
non-linear
and
non-stationary
nature
of
daily
new
2019
coronavirus
disease
(COVID-19)
case
time
series,
existing
prediction
methods
struggle
accurately
forecast
number
cases.
To
address
this
problem,
a
hybrid
framework
is
proposed
in
study,
which
combines
ensemble
empirical
mode
decomposition
(EEMD),
fuzzy
entropy
(FE)
reconstruction,
CNN-LSTM-ATT
network
model.
This
framework,
named
EEMD-FE-CNN-LSTM-ATT,
applied
predict
COVID-19
study
focuses
on
dataset
from
United
States
as
research
subject
validate
feasibility
framework.
The
results
show
that
EEMD-FE-CNN-LSTM-ATT
outperforms
other
baseline
models
all
evaluation
metrics,
demonstrating
its
efficacy
handling
epidemic
series.
Furthermore,
generalizability
validated
datasets
France
Russia.
offers
approach
for
predicting
pandemic,
providing
important
technical
support
future
infectious
forecasting.
Biology,
Journal Year:
2023,
Volume and Issue:
12(4), P. 584 - 584
Published: April 11, 2023
When
an
epidemic
breaks
out,
many
health,
economic,
social,
and
political
problems
arise
that
require
a
prompt
effective
solution.
It
would
be
useful
to
obtain
all
information
about
the
virus,
including
epidemiological
ones,
as
soon
possible.
In
previous
study
of
our
group,
analysis
positive-alive
was
proposed
estimate
duration.
stated
every
ends
when
number
(=infected-healed-dead)
glides
toward
zero.
fact,
if
with
contagion
everyone
can
enter
phenomenon,
only
by
healing
or
dying
they
get
out
it.
this
work,
different
biomathematical
model
is
proposed.
A
necessary
condition
for
resolved
mortality
reaches
asymptotic
value,
from
there,
remains
stable.
At
time,
must
also
close
This
seems
allow
us
interpret
entire
development
highlight
its
phases.
more
appropriate
than
one,
especially
spread
infection
so
rapid
increase
in
live
positives
staggering.
Diagnostics,
Journal Year:
2022,
Volume and Issue:
12(11), P. 2861 - 2861
Published: Nov. 18, 2022
East
Africa
was
not
exempt
from
the
devastating
effects
of
COVID-19,
which
led
to
nearly
complete
cessation
social
and
economic
activities
worldwide.
The
objective
this
study
predict
mortality
due
COVID-19
using
an
artificial
intelligence-driven
ensemble
model
in
Africa.
dataset,
spans
two
years,
divided
into
training
verification
datasets.
To
mortality,
three
steps
were
conducted,
included
a
sensitivity
analysis,
modelling
four
single
AI-driven
models,
development
models.
Four
dominant
input
variables
selected
conduct
Hence,
coefficients
determination
ANFIS,
FFNN,
SVM,
MLR
0.9273,
0.8586,
0.8490,
0.7956,
respectively.
non-linear
approaches
performed
better
than
linear
approaches,
ANFIS
best-performing
approach
that
boosted
predicting
performance
This
fact
revealed
promising
capability
models
for
daily
other
parts
globe.
Sensors,
Journal Year:
2024,
Volume and Issue:
24(22), P. 7205 - 7205
Published: Nov. 11, 2024
This
paper
compares
four
time
series
forecasting
algorithms—ARIMA,
SARIMA,
LSTM,
and
SVM—suitable
for
short-term
load
using
Advanced
Metering
Infrastructure
(AMI)
data.
The
primary
focus
is
on
evaluating
the
applicability
performance
of
these
models
in
predicting
electricity
consumption
patterns,
which
a
critical
component
implementing
effective
demand
response
(DR)
strategies.
study
provides
comprehensive
analysis
predictive
accuracy,
computational
efficiency,
scalability
each
algorithm
dataset
real-time
collected
from
AMI
systems
over
designated
period.
Through
extensive
experiments,
we
demonstrate
that
has
distinct
strengths
weaknesses
depending
characteristics
dataset.
Specifically,
SVM
exhibited
superior
handling
nonlinear
patterns
high
volatility,
while
SARIMA
effectively
captured
seasonal
trends.
LSTM
showed
potential
modeling
complex
temporal
dependencies
but
was
sensitive
to
hyperparameter
settings
required
substantial
amount
training
research
offers
practical
guidelines
selecting
optimal
model
based
data
application
needs,
contributing
development
more
efficient
dynamic
energy
management
findings
highlight
importance
integrating
advanced
techniques
into
smart
grid
enhance
reliability
responsiveness
DR
programs.
lays
solid
foundation
future
real-world
applications
support
stability.
Frontiers in Public Health,
Journal Year:
2022,
Volume and Issue:
10
Published: May 25, 2022
India
suffered
from
a
devastating
2021
spring
outbreak
of
coronavirus
disease
2019
(COVID-19),
surpassing
any
other
outbreaks
before.
However,
the
reason
for
acceleration
in
is
still
unknown.
We
describe
statistical
characteristics
infected
patients
first
case
to
June
2021,
and
trace
causes
two
complete
way,
combined
with
data
on
natural
disasters,
environmental
pollution
population
movements
etc.
found
that
water-to-human
transmission
accelerates
COVID-19
spreading.
The
rate
382%
higher
than
human-to-human
during
2020
summer
India.
When
syndrome
2
(SARS-CoV-2)
enters
human
body
directly
through
water-oral
pathway,
virus
particles
nitrogen
salt
water
accelerate
viral
infection
mutation
rates
gastrointestinal
tract.
Based
results
attribution
analysis,
without
current
effective
interventions,
could
have
experienced
third
monsoon
season
this
year,
which
would
increased
severity
disaster
led
South
Asian
economic
crisis.
COVID-19,
the
infectious
disease
caused
by
most
recently
discovered
coronavirus
is
related
to
upper
respiratory
tract
family
of
disorders.It
triggers
asthma,
severe
diseases,
cause
lung
infection
and
bronchiolitis
infections.Though
severity
these
infections
are
getting
obsolete
but
may
remain
in
mild
forms
waves
our
lives.A
thorough
study
about
its
spread
across
globe,
prediction
understanding
transmission
patterns,
through
various
statistical
models
might
be
one
effective
ways
provide
an
insight
aspects
suggest
prevention
strategies.In
light
this,
Auto
Regression
(AR)
developed
for
confirmed
cases
with
5
days
lag,
6
different
states
India.The
data
has
been
trained
from
July
2020
2023
taking
into
account
three
impactful
corona
waves.August
2022
used
testing
&
validating
models.Based
on
population
size
total
number
Indian
have
classified
categories:
Most
affected,
moderately
affected
least
states.Two
selected
each
categories
purpose
research
here.Auto
all
3
waves.Finally,
fourth
wave
done
month
using
third
AR
models.The
results
varies
state
model.