IEEE Computational Intelligence Magazine - November 2020 - 9

intelligence techniques for prevention of
COVID-19.
The second paper, titled "A Bayesian
Updating Scheme for Pandemics:
-Estimating the Infection Dynamics of
COVID-19" by S. Wang et al., tackles
the important topic of assessing the
impacts of different intervention strategies against COVID-19 by applying the
technology of data assimilation to estimate epidemiological parameters using
observable information. A Bayesian
updating scheme for reliable and timely
estimation of parameters in epidemic
models is proposed. Unlike conventional
compartmental models which did not
work well for emerging pandemic, a
concise renewal model with new parameters has been proposed for modeling
the transmission dynamics. The proposed parameters were designed by disentangling the reduction of instantaneous
reproduction into mitigation and suppression factors such that the proposed
concise renewal model can quantify
intervention impacts at a finer granularity. Several promising results are also
reported on applying the proposed concise renewal model to estimate the effects
of interventions in European countries,
the United States, Wuhan as well as the
resurgence risk in the USA.
In the third paper, "COVID-19 Time
Series Forecast Using Transmission Rate
and Meteorological Parameters as Features," M. Mousavi et al. tackle the challenge of forecasting future cases of the
virus for a targeted region. The proposed
model identifies past transmission rate,
temperature, and humidity as key predictive features. They decompose each
feature into stationary and non-stationary modes, train two recurrent neural
networks (RNNs) with Long ShortTerm Memory (LSTM) cells based on
the corresponding modes, and sum the
two RNN predictions to create a forecasted number of future COVID-19
cases. The proposed approach was validated through the evaluation on predicting transmission based on historic
numbers of confirmed virus cases for
two states in India. Several insights were
provided through the evaluation results,
in particular on that the data complex-

Moreover, integration of computational intelligence
mechanisms with various types of medical systems/
devices is essential for practical deployment in existing
healthcare environments.
ity and predictability varies between
regions, which points to the need to
further investigate the dependencies
between transmission and meteorological factors in understanding spread of
the virus.
The fourth paper, "Meaningful Big
Data Integration for a Global COVID-19
Strategy" by J. Pita Costa et al., presents
the Meaningful Integration of Data Analytics and Services (MIDAS) platform
they developed to connect and integrate
heterogeneous data sources including
open and social media data, etc., which is
ready for deep analytics, event monitoring
and research. MIDAS includes the governance and ethnic review organization
structure to ensure patient privacy and
ethical issues are properly addressed.
Such a technology platform can play
important and helpful roles for broad
spectrum of COVID-19 public health
studies, including better understanding
of the spread and geosocial impact of the
disease, locating the origin of the disease
and tracking its mutations, monitoring
and following the pandemic across global regions and diverse populations, particularly for health disparities and
vulnerable populations; and helping earlier preparation for disease prevention or
containment. The large database accumulated in MIDAS also allows the
experimentation and development of
novel computational intelligent algorithms and tools in analyzing and predicting the COVID-19 pandemic as
well as events of the next outbreak.
During the COVID-19 pandemic,
community prevention and control can
be quintessential in reducing the risks of
viral infection and spread. As such, Traditional Chinese medicine (TCM), best
known for its holistic approach to treatment and prevention of acute and
chronic disorders, can play an important
role in that it pays special attention to

improving the inherent self-resistance
and hence mitigating the likelihood of
disease onset. In this regard, the fifth
paper entitled "Intelligent Optimization
of Diversified Community Prevention
of COVID-19 using Traditional Chinese Medicine" by Y. Zheng et al.
-d emonstrates the TCM principle of
"treatment based on syndrome differentiation" when developing targeted TCM
prevention programs for people with
different needs, as opposed to a onesize-fits-all prevention program. In
doing so, the authors have utilized an
improved fuzzy clustering method to
differentiate the population based on
TCM health and medicine related characteristics. Thereafter, for each of the
clusters identified, TCM experts would
recommend a specific prevention program. The authors have employed a
bio-inspired heuristic algorithm to further optimize the programs, so as to
make the best use of the available
resources. This article reports several
promising results of applying the proposed method on TCM-based prevention of COVID-19 in 12 communities
in Zhejiang province, China, during the
peak of the pandemic.
We sincerely thank all of the authors
who submitted their papers to this special issue, and to a large number of
reviewers who dedicated their time and
expertise for materializing a high-quality special issue on this very important
and timely topic. In particular, we
would also like to thank Prof. ChuanKang Ting, the Editor-in-Chief of
IEEE Computational Intelligence Magazine (IEEE CIM) for his great efforts
in initiating and developing this special
issue together, and all members of the
editorial team for their enthusiastic
support during the editing process of
this special issue.

NOVEMBER 2020 | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE

IEEE Computational Intelligence Magazine - November 2020

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - November 2020