Building Resilience Against Covid-19 Pandemic Using Artificial Intelligence, Machine Learning, and Iot: A Survey of Recent Progress

IoT
Review
Building Resilience against COVID-19 Pandemic
Using Artificial Intelligence, Machine Learning,
and IoT: A Survey of Recent Progress
S. M. Abu Adnan Abir 1 , Shama Naz Islam 2 , Adnan Anwar 3 , Abdun Naser Mahmood 4, *
and Aman Maung Than Oo 2
1 IGW Operators Forum, Dhaka 1212, Bangladesh; adnanabir.iut@gmail.com
2 School of Engineering, Deakin University, Geelong, VIC 3216, Australia; shama.i@deakin.edu.au (S.N.I.);
aman.m@deakin.edu.au (A.M.T.O.)
3 Strategic Centre for Cyber Security Research & Innovation (CSRI), School of Information Technology,
Deakin University, Geelong, VIC 3216, Australia; adnan.anwar@deakin.edu.au
4 School of Engineering and Mathematical Sciences, La Trobe University, Melbourne, VIC 3086, Australia
* Correspondence: A.Mahmood@latrobe.edu.au; Tel.: +61-3-9479-2145

Received: 6 November 2020; Accepted: 4 December 2020; Published: 6 December 2020
Abstract: Coronavirus disease 2019 (COVID-19) has significantly impacted the entire world today and
stalled off regular human activities in such an unprecedented way that it will have an unforgettable
footprint on the history of mankind. Different countries have adopted numerous measures to build
resilience against this life-threatening disease. However, the highly contagious nature of this pandemic
has challenged the traditional healthcare and treatment practices. Thus, artificial intelligence (AI)
and machine learning (ML) open up new mechanisms for effective healthcare during this pandemic.
AI and ML can be useful for medicine development, designing efficient diagnosis strategies and
producing predictions of the disease spread. These applications are highly dependent on real-time
monitoring of the patients and effective coordination of the information, where the Internet of
Things (IoT) plays a key role. IoT can also help with applications such as automated drug delivery,
responding to patient queries, and tracking the causes of disease spread. This paper represents a
comprehensive analysis of the potential AI, ML, and IoT technologies for defending against the
COVID-19 pandemic. The existing and potential applications of AI, ML, and IoT, along with a
detailed analysis of the enabling tools and techniques are outlined. A critical discussion on the risks
and limitations of the aforementioned technologies are also included.
Keywords: COVID-19; coronavirus; machine learning; artificial intelligence; Internet of Things
1. Introduction
Humanity is now encountering a global crisis, perhaps the greatest crisis of this generation:
The COVID-19 pandemic. People all over the world came to know this disease first on 31 December 2019,
when the Wuhan Municipal Health Commission, China, reported a cluster of cases of pneumonia in
Wuhan, Hubei Province which was ultimately identified as a novel virus named SARS-COV-2 resulting
in the disease named “coronavirus disease 2019”, also known as COVID-19. On 13 January 2020,
officials confirmed the first recorded COVID-19 case outside of China. After the disease started
spreading all over the world, the World Health Organization (WHO) categorized this epidemic as a
pandemic on 11 March 2020 [1]. As of 24 August 2020, COVID-19 has spread over 213 countries and
territories around the world, resulting in over 23,586,023 reported cases of confirmed contamination
and 812,527 deaths [2,3]. Figure 1 illustrates COVID-19 spreading over time, which is very alarming
as the rate of the new victims is rising at a significantly higher rate. Some of the countries, such as
IoT 2020, 1, 506–528; doi:10.3390/iot1020028 www.mdpi.com/journal/iot

IoT 2020, 1, FOR PEER REVIEW 2
IoT 2020, 1 507
confirmed contamination and 812,527 deaths [2,3]. Figure 1 illustrates COVID-19 spreading over time,
which is very alarming as the rate of the new victims is rising at a significantly higher rate. Some of
Australia, that experienced a decreasing number due to social distancing, are also facing a second
the countries, such as Australia, that experienced a decreasing number due to social distancing, are
wave of the COVID-19 pandemic.
also facing a second wave of the COVID-19 pandemic.
(a) Cumulative Confirmed Case (b) Cumulative death toll
25 900
800
20
700
Cumulative Confirmed Case
600
Cumulative death toll

15
Millions
Thousands
500
400
10
300
200
5
100
- -
week-0
week-2
week-4
week-6
week-8
week-10
week-12
week-14
week-16
week-18
week-20
week-22
week-24
week-26
week-28
week-30
week-32
Time duration
Figure 1. The statistics of the coronavirus disease 2019 (COVID-19) disease outbreak over the world,
Figure 1. The statistics of the coronavirus disease 2019 (COVID-19) disease outbreak over the world,
the figure shows (a) the accumulative figure of confirmed infected cases and (b) the accumulative
the figure shows (a) the accumulative figure of confirmed infected cases and (b) the accumulative figure
figure of deaths.
of deaths.
The healthcare sector has put a great effort into COVID-19 diagnosis, screening and treating the
The healthcare sector has put a great effort into COVID-19 diagnosis, screening and treating
infected individuals to address this pandemic. Governments and international organizations are
the infected individuals to address this pandemic. Governments and international organizations are
aiming to organize an appropriate level of healthcare to mitigate the disease. To date, no medicine or
aiming to organize an appropriate level of healthcare to mitigate the disease. To date, no medicine or
vaccine has been invented to encounter this disease with complete assurance. So, different treatment
vaccine has been invented to encounter this disease with complete assurance. So, different treatment
methods and different medicines are applied as appropriate to remedy against this disease. On the
methods and different
other hand, authorities medicines
are imposingare applied
measures assuch
appropriate
as social to remedy against
distancing, this disease.
area lockdown, the useOnofthe
other hand,
proper authorities
sanitization, are
etc. toimposing
prevent the measures such as social
further spreading of thisdistancing, area lockdown,
pandemic. Therefore, to preventthe use
the of
spreading of this disease, a collective effort is needed from all social entities such as the internationalthe
proper sanitization, etc. to prevent the further spreading of this pandemic. Therefore, to prevent
organizations,
spreading governments,
of this disease, healthcare
a collective systems,
effort is neededandfrommore essentially
all social entities from
such as thethecommunity.
international
Moreover, the
organizations, widespread
governments, integration
healthcare of prospective
systems, technologies
and more essentially fromwith effective healthcare
the community. Moreover,
themanagement
widespreadand resilient governance
integration of prospectivewill technologies
reinforce the capacity to protect
with effective the society
healthcare from COVID-and
management
19 disease
resilient [4].
governance will reinforce the capacity to protect the society from COVID-19 disease [4].
With
With thethe emergence
emergence ofofintelligent
intelligenttechnologies
technologies in in this
thisage
ageofofinformation
information from
fromthethe
global
globalcontext,
context,
advanced
advanced artificial
artificial intelligence(AI)
intelligence (AI)techniques
techniques promise
promisemassive
massiveapplications
applications in in
a variety
a variety of sectors.
of sectors.
Figure
Figure 2 exhibits
2 exhibits artificialintelligence
artificial intelligenceandand its
its subsections,
subsections, especially
especiallyfromfroma amachine
machine learning
learning(ML)
(ML)
point of view [4]. Although social distancing and the use of masks/gloves have been
point of view [4]. Although social distancing and the use of masks/gloves have been proven effective to proven effective
to slow down the spread, effective countermeasures and defense strategies need to be developed to
slow down the spread, effective countermeasures and defense strategies need to be developed to build
build resilience against the pandemic through better monitoring and control. AI and ML, which have
resilience against the pandemic through better monitoring and control. AI and ML, which have been
been successfully applied in a wide range of research areas, may have numerous prospective
successfully applied in a wide range of research areas, may have numerous prospective applications
applications for achieving protection from COVID-19 disease. AI and ML can play a significant role
for achieving protection from COVID-19 disease. AI and ML can play a significant role in addressing
in addressing the healthcare and social sector challenges caused by the COVID-19 pandemic. On a
the healthcare and social sector challenges caused by the COVID-19 pandemic. On a molecular level,
AI can be utilized to approximate the construction of SARS-COV-2 associated proteins, classify present
medications that can possibly be used as a remedy for the disease, suggest novel composites that
IoT 2020, 1 508

can possibly contribute to the medicine development, design the potential objectives of the vaccine,
and develop
molecularidentification
level, AI can procedures
be utilized to asapproximate
well as better therealization
constructionofofthe virus contamination
SARS-COV-2 associated and
proteins, classify present medications that can possibly be used as
severity level. From a medical viewpoint, AI can help improve the COVID-19 identification a remedy for the disease, suggest by
novel composites that can possibly contribute to the medicine development,
analyzing medical imaging, offer different methods to study disease progression utilizing appropriate design the potential
tools,objectives
and produceof theforecasts
vaccine, and develop identification
on infection spread based procedures
on compound as wellstatistical
as better realization
feedback,of the
including
virus contamination and severity level. From a medical viewpoint, AI can help improve the COVID-
digital medical history. From a societal standpoint, AI can be utilized for epidemiological exploration
19 identification by analyzing medical imaging, offer different methods to study disease progression
modeling, experiential statistics, including predicting the number of cases given different public policy
utilizing appropriate tools, and produce forecasts on infection spread based on compound statistical
choices. Sharing
feedback, and presenting
including research
digital medical ideas,
history. along
From with extracting
a societal standpoint,insights
AI can from statistics
be utilized for and
simulations,
epidemiological exploration modeling, experiential statistics, including predicting the number of of
are vital to speed up the response against the pandemic [5]. In such cases, the Internet
Things (IoT)
cases can different
given play a majorpublicrole. AI coupled
policy with IoTand
choices. Sharing is more powerful
presenting in terms
research ideas,ofalong
the intelligent
with
decision making
extracting and can
insights fromhelp fight against
statistics this pandemic.
and simulations, are vital to speed up the response against the
pandemic
The Allen[5]. In such cases,
Institute the Internet
for Artificial of Things (IoT)
Intelligence is nowcan play a major
sharing role. AI library
a digital coupled ofwith IoT is that
articles
morefree
provides powerful
access in to
terms of the intelligent
COVID-19 data [6]. decision making and
This database can help comprises
presently fight againstoverthis pandemic.
44,000 articles;
among them, The Allen
29,000 Institute for Artificial
are full-text journals.Intelligence
Conjoining is nowthissharing
databasea digital
with library
other rawof articles thatfrom
statistics
provides free access to COVID-19 data [6]. This database presently comprises over 44,000 articles;
web links or social media can reveal further information and insights about the early detection and
among them, 29,000 are full-text journals. Conjoining this database with other raw statistics from web
control of future outbreaks of SARS-COV-2 virus. Outbreak Response Management and Analysis
links or social media can reveal further information and insights about the early detection and control
System (SORMAS)
of future outbreaksand ofHealthMap
SARS-COV-2 are virus.
examples of surveillance-mapping
Outbreak Response Management tools
andthat workSystem
Analysis online and
allow(SORMAS)
early detection of contagious diseases in contrast to commonly used epidemiological
and HealthMap are examples of surveillance-mapping tools that work online and allow methods.
At this time,
early SORMAS
detection and HealthMap
of contagious diseasesare utilized to
in contrast forcommonly
the observation of the COVID-19
used epidemiological situation
methods. At [7].
On thethisother
time,hand,
SORMAS Theand British Societyare
HealthMap of utilized
Thoracic forImaging (BSTI) and
the observation of theCimar UK’ssituation
COVID-19 Imaging[7]. Cloud
On the other hand, The British Society of Thoracic Imaging (BSTI) and Cimar
Technology [8] have deployed an easy to access, open for all encrypted web platform to share imaging UK’s Imaging Cloud
Technology
of patients [8] have
identified deployed an
or suspected easy to
to have access, open
COVID-19 [9]. for
TheallBSTI
encrypted web aplatform
is creating database to containing
share
imaging of patients identified or suspected to have COVID-19 [9]. The BSTI is creating a database
imaging of confirmed patients with COVID-19 from these uploaded cases for further research. The goal
containing imaging of confirmed patients with COVID-19 from these uploaded cases for further
is to broadcast new medical and investigative guidance quickly to medical service providers all over
research. The goal is to broadcast new medical and investigative guidance quickly to medical service
the country, utilizing these actual imaging samples [9].
providers all over the country, utilizing these actual imaging samples [9].
Figure 2. The relation between artificial intelligence and its components [10].
IoT 2020, 1 509
From the above discussion, we can summarize that organizations and researchers across different
countries are putting their best effort to build resilience against this pandemic. As AI, ML, and IoT have
been proven effective in a wide range of application areas, this paper concentrates on evaluating the
scope of these emerging technologies and recent progress in developing the countermeasures against
COVID-19 pandemic. Specifically, this paper addresses the following key research questions:
i. What are the emerging applications of AI and ML that can help toward building resilience
against the COVID-19 pandemic? The answer of this question has been explored in Section 2.
ii. What are the social and information science-related applications of AI and ML that played an
important role during this crisis? The answer of this question has been elaborated in Section 3.
iii. What are the roles of emerging technologies such as IoT for COVID-19 control and prevention?
The answer of this question has been identified in Section 4.
iv. Is there any potential risk due to the integration of emerging intelligent techniques such as AI,
ML, and IoT? The answer to this question has been explored in Section 5.
Organization and Contents of the Paper

In this paper, we summarize the impact of the emerging AI and ML technologies basically from
two perspectives: (i) medical service-related applications and (ii) social science-related applications,
as discussed in Sections 2 and 3, respectively. In Section 2.1, we provide insights on how medical imaging
using AI and ML can help identify the presence of COVID-19 disease symptoms. Patient condition
monitoring using AI and ML-based data analytics is presented in Section 2.2. In Section 2.3, we discuss
how drug development and delivery can be automated and effectively performed using these
technologies. Virus propagation modeling using AI and ML has been focused in Section 2.4. Based on
the literature review, we highlight that the early prediction and detection can be beneficial to slow
down the progress of this pandemic in Section 2.5. The medical sector has experienced that healthcare
workers are highly vulnerable to COVID-19 disease, and therefore, in Section 2.6, we summarize some
possible AI and ML-driven countermeasures to protect the valuable personnel who are contributing
significantly to help fight against the pandemic.
Social and Information Science-related applications of AI and ML are presented in Section 3.
Effective forecasting and prediction based on the COVID-19 statistics can help the society and nation to
build important strategies and public policies. Section 3.1 discusses how AI and ML can be leveraged to
help predict COVID-19 statistics. These emerging tools and techniques can also identify the influential
service provider of the healthcare sector, as discussed in Section 3.2. These intelligent techniques can
also help in measuring and deploying social distancing, as summarized in Section 3.3. To achieve
protection against this pandemic, data availability can bring significant benefits. AI and ML-based
applications can help in advanced data sharing, hosting, and analytics (presented in Section 3.4).
AI governance is discussed in Section 3.5, and finally, Section 3.6 presents AI and ML-based social
awareness improvement capabilities.
IoT-based applications gained its importance for COVID-19 patient identification and tracking.
For example, contact tracing applications have helped to slow down the spread of the pandemic.
Section 4 discusses the existing IoT-based COVID tracing mechanisms, as well as IoT-based drone
applications, wearable technologies, telemedicine, etc., to demonstrate how IoT can help build resilience
against the pandemic. Although AI, ML, and IoT have enormous potentials and prospects, misuses of
these technologies can be very risky and cause significant loss. Therefore, potential risk factors and
some new technologies to address these risks more effectively are also discussed in Section 5. Finally,
the paper concludes with some brief remarks in Section 6.
2. Application of AI and ML for the Medical Sector

AI and ML in the medical sector have a broad range of applications, including the prediction
and classification of statistical information. In particular, BlueDot Toronto, which was developed
IoT 2020, 1 510
by infectious disease scientists to research innovative solutions for mitigating the initial SARS
outbreak, designed the first risk-based solution for detecting the outbreak of SARS-COV-2 virus [11].
This successful demonstration of AI and ML in predicting disease outbreaks applied BlueDot’s prior
research on the SARS outbreak to implement advanced technologies. A report stated that BlueDot
employed a disease-monitoring framework that scrutinized over 100,000 online documents globally
in 65 languages every 15 min [4]. This system identified unusual statistics of pneumonia cases
with unidentified cause in Wuhan, the ninth most populated city in China, and it warned about the
occurrence of the disease considerably earlier than when it was formally recognized as COVID-19 [4].
Therefore, these advanced technologies can forecast such epidemics and create awareness among
people to take the required pre-cautions for encountering the outbreaks.
Artificial intelligence application in detecting infectious diseases is extremely valuable in the
medical sector and can bring revolutions to the healthcare practices. Integrating AI in the imaging
processes has received significant attention within the healthcare sector. Machine-learning prototypes
can scrutinize the medical images to identify the sickness at an initial phase. Such prototypes are
driven by big data and deep learning algorithms to achieve the particular task. The prospective
sectors where this image-oriented learning is possibly applied are pathology, ophthalmology, radiology,
and dermatology [4]. The mitigation of diseases such as COVID-19 massively depends on the screening
of people through pathogenic testing, which is a time-consuming process, and hence, precision is
a must. In a study, the author introduced a medical identification process for COVID-19 based on
radiographic variations in computerized tomography (CT) scans by implementing the deep learning
process, which achieve 85.2% accuracy in the testing and validation stage. [4].
Machine learning can assist the work of medical professionals by analyzing and organizing an
enormous amount of patient information stored in digital medical records. Moreover, Machine Learning
is applied in different medical applications that include detecting patients with severe conditions
who urgently require intensive care unit (ICU) facilities, identifying early symptoms of diseases,
understanding the breathing condition of the patient by analyzing chest X-rays, etc. Therefore,
AI and ML improves the performance of identification and prediction process and how administrative
decisions are made in the medical sector [4]. In these circumstances of the COVID-19 pandemic,
the aforementioned technologies have already aided medical professionals encountering the situations
in a significantly effective manner.
2.1. Medical Imaging for COVID-19 Patients

Medical imaging such as CT scan and X-rays are widely used for diagnostic and treatment
purposes. During the COVID-19 pandemic, the role of CT scan and X-ray imaging are very important
for SARS-COV-2 virus detection. For this purpose, the emerging technologies such as AI and
ML reinforce the imaging analysis by intelligent detection and classification of the abnormalities.
For instance, AI-enabled disease type classification will help toward automation of the screening
process, and this automatic process will reduce human interaction among the doctors and the patients.
Thus, it acts as a safeguard to the medical imaging professionals and helps to reduce the spread of
the virus. Furthermore, the computer-assisted AI-enabled automated classification and recommender
systems support the radiologists to make clinical judgments, i.e., infection identification, tracing,
projection with better accuracy, and efficiency [12].
The Reverse Transcription-Polymerase Chain Reaction (RT-PCR) test is typically used to measure
the amount of any particular type of RNA. This RT-PCR is being used for the COVID-19 infection
diagnosis [13]. However, the RT-PCR test has still some limitations. For example, as reported in [13],
this powerful test produces high specificity, but the sensitivity from the test is very low (for example,
as low as 59%). Therefore, the laboratory assessment suffers from inadequate sensitivity, which needs
to be improved to enhance the performance further and for wider adoption.
To solve the aforementioned problem related to the false positive diagnosis, the latest
AI-empowered tools and techniques need to contribute significantly toward building resiliency
IoT 2020, 1 511
against the COVID-19 pandemic. The success of the AI-enabled tools are not only limited as a prototype
these days, as a good number of commercial applications have also been introduced. Those applications
incorporate the strengths of powerful deep learning and intelligent techniques to help slow down the
spread and improved identification of the virus and thus exhibit technological competence against the
spread of the pandemic [12].
In [14], the authors describe a process where deep transfer learning was used with Generative
Adversarial Network (GAN) for COVID-19 recognition in X-ray images of a patient’s chest.
Ian Goodfellow introduced the Generative Adversarial Network (GAN) in 2014, which is a type of
deep learning algorithm. GAN prototypes are mainly comprised of two networks, generative and
discriminative network. The generator network is designed to generate new fake data instances,
which are similar to training data. The purpose of the discriminator is to differentiate between actual
data and fake data generated from a generator network. The generator network produces fake data to
evade the network, and the discriminator network identifies the difference between actual and fake
data and tries to prevent the evasion, which is the mission of the GAN models. The shortage of records
regarding COVID-19 such as chest X-rays images is the key motivation for considering this type of
model in [14]. The main idea of this GAN-based study is to gather all the available imaging data
and COVID-19 test results and then utilize the GAN network to create more datasets to assist in the
identification of the virus from the available X-rays scans with the maximum accuracy.
Another study [15] presents an early detection of COVID-19 using machine learning techniques,
where the detection procedure was employed on CT scans of an abdomen. The experienced radiologists
identified from CT scans that COVID-19 indicates dissimilar characteristics as compared to other viral
pneumonia. Hence, the medical specialists can identify the COVİD-19 infection in the initial stage.
For investigations regarding the identification of COVID-19, four dissimilar datasets were designed by
considering patches with dimensions as 64 × 64, 48 × 48, 32 × 32 and 16 × 16 from a number of 150 CT
scans. To improve the classification performance, a feature extraction process was applied to patches,
which utilized algorithms such as Grey Level Co-occurrence Matrix (GLCM), Local Directional Pattern
(LDP), Grey Level Run Length Matrix (GLRLM), Grey-Level Size Zone Matrix (GLSZM), and Discrete
Wavelet Transform (DWT). Support Vector Machines (SVM) were used to categorize the extracted
features. Ten-fold, 5-fold, and 2-fold cross-validations were applied throughout the categorization
process. Precision, accuracy, specificity, sensitivity, and F-score metrics were utilized to assess the
categorization performance. The best accuracies were achieved as 99.68% with 10-fold cross-validation
and the GLSZM feature extraction technique.
It is obvious that an initial identification of COVID-19 is essential to slow down the spread of
COVID-19 and avoid transmission by an early quarantine of victims as well as tracing and isolation
of close acquaintances. For patients diagnosed with COVID-19, the precise monitoring of disease
development is a vital element of disease administration. Medical imaging records such as chest X-ray
and CT scans play a significant part in confirming the positive identification of COVID-19 disease as
well as observing the evolution of the disease. These sorts of imaging data exhibit irregular distinctive
patterns that emerge right after the COVID-19 infection starts. These anomalies peaked during 6th to
11th day of the illness. The next most predominant pattern of lung conditions anomalies peaks during
the 12th to 17th day of the illness [16]. Computer-Aided Diagnosis (CAD) methods that integrate
X-ray and CT scan results with deep learning algorithms can help physicians as identification aids for
COVID-19 and assist further to provide a better understanding of the disease progression.
2.2. Patient Condition Monitoring Using Clinical Data

The patient’s condition can be monitored remotely by taking a patient’s status or clinical data
through the remote monitoring technology [7]. These technologies can link wirelessly to the networks
via WiFi, Bluetooth, or cellular connection. The same idea can be implemented for the monitoring
of infectious diseases such as COVID-19. This distant observing technique can be utilized to screen
persons exposed to COVID-19 as well as close acquaintances of the infected person. These technologies
IoT 2020, 1 512
can also be applied to prevent the exposure of medical professionals to the high-risk patient populations.
In principle, the same technological arrangements presently utilized by remote monitoring programs
can alsopersons
be utilizedexposed to COVID-19a temperature
to incorporate as well as close acquaintances
measurement of such
tool the infected person.
as a smart These
thermometer for
technologies
monitoring individualscan also
thatbeare
applied to prevent
suspected the exposure
of having of medical
COVID-19 [7]. professionals
AI and ML can to the high-risk
significantly help
patient populations. In principle, the same technological arrangements presently utilized by remote
to improve monitoring and identify abnormal patterns or behaviors. ML and AI-based advanced data
monitoring programs can also be utilized to incorporate a temperature measurement tool such as a
analyticssmart
andthermometer
signal processing can help to filter the data and identify the patterns.
for monitoring individuals that are suspected of having COVID-19 [7]. AI and
ML can significantly help to improve monitoring and identify abnormal patterns or behaviors. ML
2.3. Drug Development,
and Selection
AI-based advanced dataand Delivery
analytics and signal processing can help to filter the data and identify
In the
[17],patterns.
the authors use a drug–target interaction prototype titled as Molecule Transformer–
DrugTarget Interaction
2.3. Drug Development,(MT-DTI) that
Selectio,n anduses the deep learning method to identify drugs that are available
Delivery
in the market to react on viral proteins of SARS-COV-2. In another paper [18], the authors formulated
In [17], the authors use a drug–target interaction prototype titled as Molecule Transformer–
a modelDrugTarget
that uses machine learning technology to forecast the potential inhibitory synthetic antibodies
Interaction (MT-DTI) that uses the deep learning method to identify drugs that are
for SARS-COV-2
available in the market togathered
virus. They antibody
react on viral proteinssequences of theIn1933
of SARS-COV-2. virus
another and[18],
paper their
theclinical
authors patient
formulated a model that uses machine learning technology to forecast the potential inhibitoryreaction.
neutralization reaction and pre-trained a machine learning model to forecast the antibody
Utilizingsynthetic
graphicalantibodies for SARS-COV-2
representation withvirus. They gathered
different antibody sequences
ML techniques, of the 1933
the authors virus and
selected thousands
their clinical patient neutralization reaction and pre-trained a machine learning
of antibody sequences and found eight steady antibodies that hypothetically inhibit SARS-COV-2. model to forecast the
antibody reaction. Utilizing graphical representation with different ML techniques, the authors
The authors combined bioinformatics, structural biology, and Molecular Dynamics (MD) simulations
selected thousands of antibody sequences and found eight steady antibodies that hypothetically
to authenticate the constancy
inhibit SARS-COV-2. Theofauthors
the candidate
combined antibodies that can
bioinformatics, inhibitbiology,
structural the SARS-COV-2
and Molecular virus.
Dynamics (MD) simulations to authenticate the constancy of the candidate antibodies that can inhibit and it
Nowadays, we are observing rapid advancement in every aspect of science and technology,
thesame
is also the SARS-COV-2
scenario virus.
in the sector of biological science, where complex biological data such as DNA
structures and Nowadays,
proteinwe are observing
sequences arerapid
nowadvancement in every
available. With theaspect
helpofof science and technology,
machine and
learning techniques,
it is also the same scenario in the sector of biological science, where complex biological data such as
those available data can predict complex biological scenario to analyze the virus protein structure and
DNA structures and protein sequences are now available. With the help of machine learning
potentialtechniques,
antibodies. With proper and sufficient training data, a machine learning mechanism can be
those available data can predict complex biological scenario to analyze the virus protein
utilized structure
to createand relations between
potential the virus
antibodies. entity and
With proper and reaction
sufficient of its probable
training data, a antibody. A pre-trained
machine learning
ML toolmechanism
can predict can be utilized
potential to create relations
antibodies between
for a given the virus
protein entity of
sequence anda reaction of its than
virus faster probable
the human
immuneantibody.
system,Awhichpre-trained
can be ML tool useful
very can predict
whilepotential
combating antibodies for aany
against given protein sequence
pandemic such asofCOVID-19
a
and canvirus
savefaster
many than the in
lives human immune
a timely system, which can be very useful while combating against any
manner.
pandemic such as COVID-19 and can save many lives in a timely manner.
According to another study [4], in China, one approach that was utilized to overcome the medicine
According to another study [4], in China, one approach that was utilized to overcome the
deliverymedicine
concerns during
delivery the epidemic
concerns during thewas by employing
epidemic an IoT-based
was by employing service
an IoT-based platform
service platform(Figure 3
exhibits(Figure 3 exhibits the workflow). The platform created orders by automatically analyzing the
the workflow). The platform created orders by automatically analyzing the information from
information
historical records. from
Those historical
ordersrecords.
may be Those orders may
modified and be modified and
submitted by submitted by the pharmacists
the pharmacists and then sent to
and then
the medicine sent to thefrom
suppliers medicine
where suppliers from whereare
the medicines thedistributed
medicines arewithin
distributed within a specified
a specified time. This had
time. This had lessened the spread of the disease during medicine purchase and also saved resources
lessened the spread of the disease during medicine purchase and also saved resources and labor cost.
and labor cost.
(3) Automatically
IoT based service (1) Input data of
generated and placed
platform for previous sales
order based on forecast
drug delivery
(2) analysis done

on those data Hospital/
Drug
(4) Accept order and and forecast on (5) Download electronic Pharmacy/
manufacturer/
uploading e-invoice & medicine invoice and confirm drug store
supplier
packing list requirement order system
generated
(7) Acceptance of
product at warehouse/
(6) Delivery of products
drugstore/ hospital
electronic inventory
Figure 3. The Internet of Things (IoT)-based drug delivery system [4].
2.4. Virus Propagation Modeling and Prediction

The rapid spreading of the COVID-19 disease may be because of various reasons. One reason
is the lack of information transparency at the initial phase of this pandemic outbreak. Sharing the
IoT 2020, 1 513
pandemic-related information in a timely and precise way is tremendously vital for the anti-epidemic
reaction of the community. The transparency in information sharing could have minimized the spread
of this disease at the initial phase of the pandemic. Another reason is the unavailability of a proper
systematic diagnosis standard for this virus. The prompt development of testing systems for a novel
virus is very challenging. The symptoms of this virus are highly alike to symptoms of other less
dangerous flu, which worsens the accuracy of diagnosis. Finally, due to the absence of a proper
epidemic warning and prediction arrangement, we lost the chance to prohibit the spreading of this
disease at the early phase.
In the current SARS-COV-2 transmission situation, the epidemiological study is tremendously
essential for preventing the transmission by tracing the contagious trails and detecting the connection
chains contributing to the rapid spreading. However, the outbreak of the COVID-19 was boosted
up by the high movement of people during the most significant customary carnival of China,
which worsened the transmission of the virus and at the same time greatly amplified the challenges of
the epidemiological investigation [19]. It is vital to observe and predict the evolution of an epidemic
while making decision against this kind of health crisis. In this situation, the mathematical propagation
model has achieved more consideration and attention in terms of the epidemiological research.
The Susceptible–Infected–Removed (SIR) model is one of those mathematical propagation models.
The research on plague in the early 20th century introduced this SIR model. Remarkable development
has been made in the mathematical propagation model of epidemiological research since the middle
of the 20th century. At present, some important factors inducing the epidemic transmission were
incorporated in the classic SIR model, such as the model taking into consideration the maturation phase,
the SEIRS (Susceptible–Exposed–Infectious–Recovered–Susceptible) model taking into consideration
the age of people and the population exposed to an epidemic and the Susceptible–Infectious–Susceptible
(SIS) model including the birth and death of vulnerable patients. Some dynamical prototypes
were planned to consider only specific disease analysis. For instance, the dynamical models were
designed to simulate the spreading of human immunodeficiency virus (HIV), severe acute respiratory
syndrome (SARS), and Middle East Respiratory Syndrome (MERS). With the advancement of innovative
techniques, complex network theories and machine learning techniques were incorporated with the
mathematical propagation model, which generated an effective method of epidemic prediction.
The construction of the SIR prototype for an epidemic analysis requires defining a number
of vital parameters (such as the rate of infection and the rate of infection elimination) factually or
statistically. The SIR prototype has established a complex model enabling a more detailed classification
of individuals—for example, the exposed group and the protection group. As a matter of fact, the more
accurate the prototype, the more chances are there that it can make an accurate forecast. However,
for better accuracy, the model requires more realistic data to define additional factors. Alternately,
some effort has also been made for developing a simplified prototype. For instance, the renowned
logistic equation was used as the two sections “S-I” (Susceptible–Infectious) prototype, which can
be additionally incorporated for some procedures in the modeling of SARS. The aforementioned
studies demonstrate that the SIR-family prototypes can capture the base mechanism of the epidemic
transmission at diverse complex stages quite well.
In one study [19], the authors tried to represent an initial forecast of the COVID-19 epidemic
obtained from a basic SIR prototype. The justification of the obtained epidemiological information was
investigated initially to achieve a realistic approximation of the fundamental factor, such as the rate
of infection. Focusing on the rate of infection and the rate of disease elimination, a number of trials
were planned to simulate the transmission of SARS-COV-2 virus under diverse stages of anti-epidemic
measure and precautions. The forecasted infection intervals for the collective cases and the fading-out
time of the epidemic are presented. The outcomes of the study are supposed to deliver vital statistics
for crisis management against this COVID-19 pandemic.
IoT 2020, 1 514
2.5. Early Prediction or Detection of COVID-19 Syndromes

AI plays a significant role in identifying the collection of cases and forecasting the location where
this disease will spread in the future by gathering and scrutinizing all previous data related to this
outbreak. This technology can detect the disease characteristics and can predict its nature from the
obtained information through social media and other digital or paper media platforms, regarding the
possibilities of the contagion and potential nature of spreading. Additionally, it can predict the number
of infected cases and death in any specific area based on related data and information [20].
In [21], the authors present a machine learning analysis of the COVID-19 pandemic based on
the information of the initial phase of infection dynamics. The objective is to extract actionable
insights for the improved understanding of community health. These understandings include the
disease transmission probability, the rate at which mild infection transforms into a serious infection,
asymptomatic approximations for infections, and forecasts of new infections over time.
In a study [22], the authors demonstrate the Bayesian Convolutional Neural Networks (BCNN),
which is based on Monte-Carlo Dropout to determine the uncertainty in the methods of deep learning
techniques that are used to improve the performance of the detection process while investigating chest
X-ray reports of COVID-19 victims. They conclude that if the model is responsive about the system
uncertainty, this method will improve the performance hugely and can facilitate the medical sector
with a wider implementation of advanced technologies such as artificial intelligence.
In [23], the authors proposed a machine learning method-assisted SIR model to investigate
the COVID-19 epidemic in a practical scenario. In this effort, they utilize the traditional
Kermack–Mckendrick SIR prototype to describe the spreading pattern of the epidemic of COVID-19.
The SIR prototype can model how an infection is transmitted over a population. In the research,
they consider the total number of the population as a constant and classified them into different
categories for more accuracy.
In [24], the authors utilize an effective approach to identify potential therapeutic molecules that
combined machine learning technique and highly reliable docking simulation models. The researchers
initially apply the screening plan to two drug datasets to discover a number of therapeutic molecules
that have a strong bindness to the systems. The authors use the ML model to screen a huge number of
bio-particle datasets to create a list of possibly beneficial composites with high rank and order for more
confirmation. Overall, this effort will enhance the understanding of molecular treatment of COVID-19
and at the same time deliver an effective way of drug selection by merging high-performance machine
learning prototypes with high-fidelity models for speeding up the therapeutic treatment of the diseases.
A data-driven model trained with both data and first principles is proposed in [25]. The model can
quickly be re-trained any time when new data become available.
2.6. Protecting Healthcare Workers

Most researchers have identified that artificial intelligence has brought an exemplary change in the
medical sector and there might be value in the use of AI to the present COVID-19 epidemic, for instance,
in forecasting the place of the next occurrence. As David Heymann (Assistant Director, WHO) headed
the global response to SARS, he clarifies some vital factors that are essential for an effective public
health response to an occurrence of a novel contamination. These factors include a consideration of
transmissibility and vulnerable groups; forming the natural history of contamination, comprising
the development period and death rate; recognizing and characterizing the underlying reasons; and,
in some cases, epidemiological modeling to propose effective prevention and control measures [26].
These data can be gathered from those employed at epidemic locations virtually linked with the
WHO. This approach functioned for SARS and is, again, a major source of information for COVID-19,
as discussed by David Heymann. Finally, this information can be utilized to train and introduce the AI
application for its dedicated task. The role of the healthcare professionals is important. They are not
only helping to collect the COVID data but also helping the vulnerable patients in person, risking their
own life. AI and ML can help identify the risk and also help automate a number of functionalities.
important. They are not only helping to collect the COVID data but also helping the vulnerable
patients
IoT 2020, in
1 person, risking their own life. AI and ML can help identify the risk and also help automate 515
a number of functionalities. Reflecting on a swiftly rising fear in the present epidemic that concerns
the contamination of medical staff, Kuan Chen, founder of Infervision, points out that the AI
Reflecting on
application a swiftly
can assist rising fear in the
in protecting present
the epidemic
healthcare that concerns
professionals the Similarly,
[26]. contamination of medical
researchers and
staff, Kuan Chen, founder of Infervision, points out that the AI application can assist in
vendors are trying to utilize AI-enabled medical devices to reduce direct contact during SARS-COV-protecting
2 the healthcare professionals [26]. Similarly, researchers and vendors are trying to utilize AI-enabled
virus diagnosis and treatment.
medical devices to reduce direct contact during SARS-COV-2 virus diagnosis and treatment.
2.7. AI-Enabled Self-Testing Framework
2.7. AI-Enabled Self-Testing Framework
An
AnAI-enabled self-testingframework
AI-enabled self-testing framework is shown
is shown in Figure
in Figure 4. The4.framework
The framework
has threehas three
major major
phases.
phases. At the initial phase, the patient-side sensor devices will collect the specimen supplied
At the initial phase, the patient-side sensor devices will collect the specimen supplied by the patient. by the
patient.
Based onBased on the samples
the samples collectedcollected by the sensors,
by the sensors, AI and ML-based
AI and ML-based analytics analytics willfor
will be used be further
used for
further processing. Decisions can be made locally in an edge node or could be
processing. Decisions can be made locally in an edge node or could be in the cloud when compared in the cloud when
compared with data
with historical historical data if necessary.
if necessary. Finally,
Finally, based on thebased on the patients
test results, test results,
willpatients willvia
be notified bemobile
notified
via mobile phone. To communicate among the peers, the blockchain-based framework
phone. To communicate among the peers, the blockchain-based framework could be very helpful. could be very
helpful. As results
As the test the test
areresults are very
very sensitive sensitive
and and require
require better security better security
and privacy and privacy
protection, protection,
blockchain may
blockchain may serve
serve that purpose. thatapurpose.
Being Being
distributed ledgera distributed
technology, ledger technology, the
the blockchain-based blockchain-based
framework can be
framework can be
connected with connected
local with local
and international and international
databases, databases,
while the AI-based while the AI-based
decision-making process decision-
helps
making
patientsprocess helps patients
with self-diagnosis with self-diagnosis [27].
[27].
Figure 4. Artificial intelligence (AI)-enabled self-testing framework, adopted from [27].

Figure 4. Artificial intelligence (AI)-enabled self-testing framework, adopted from [27].
Table
Table11 summarizes
summarizes the
the articles and projects
articles and projects related
related to
tothe
theAI
AIapplications
applicationstoward
towardimproved
improved
resiliency against the COVID-19 pandemic.
resiliency against the COVID-19 pandemic.
IoT 2020, 1 516
Table 1. Summary of the research contributions considering artificial intelligence (AI) to

mitigate COVID-19.
Paper/Project Name Reference No. Domain Contribution

Madurai Elavarasan, R. and Pugazhendhi, Review of potential technologies
R. (2020). Restructured society and such as AI, ML, and IoT in the
Drug development, selection,
environment: A review on potential [4] healthcare sector for forecast of the
and delivery
technological strategies to control the epidemic, disease investigation,
COVID-19 pandemic. medicine delivery, etc.
Review of outbreak response
Alwashmi, M. F. (2020). The Use of Digital
Patient condition monitoring management and analysis system
Health in the Detection and Management [7]
using clinical data and remote monitoring
of COVID-19.
technology for infected victims.
Shi, F., Wang, J., Shi, J., Wu, Z., Wang, Q.,
Review of integration of artificial
Tang, Z., Shen, D. (2020). Review of
Medical Imaging for intelligence in imaging for
Artificial Intelligence Techniques in [12]
COVID-19 patients detection, diagnostics, and tracing
Imaging Data Acquisition, Segmentation
the spread of the epidemic.
and Diagnosis for COVID-19.
Meng Li. Review: Chest CT features and Review of COVID-19 disease
Medical Imaging for
their role in COVID-19. Radiology of [13] detection by imaging tools such as
COVID-19 patients
Infectious Diseases, www.sciencedirect.com CT scans.
Mohamed Loey, Florentin Smarandache Describes a deep learning process
and Nour Eldeen M. Khalifa. Within the that used Generative Adversarial
Medical Imaging for
Lack of Chest COVID-19 X-ray Dataset: A [14] Network (GAN) for COVID-19
COVID-19 patients
Novel Detection Model Based on GAN and investigation in chest X-ray
Deep Transfer Learning. images of patients.
Mucahid Barstugan, Umut Ozkaya, Saban Describes the implementation of
Ozturk. “Coronavirus (COVID-19) Medical Imaging for the machine learning technique in
[15]
Classification using CT Images by Machine COVID-19 patients the process of COVID-19
Learning Methods”. disease detection.
Sara Hosseinzadeh Kassania, Peyman
Hosseinzadeh Kassasnib, Michal J.
Reviews the implementation of
Wesolowskic, Kevin A. Schneidera, Ralph
Medical Imaging for machine learning methods to
Deters. “Automatic Detection of [16]
COVID-19 patients identify COVID-19 disease in
Coronavirus Disease (COVID-19) in X-ray
medical images.
and CT Images: A Machine Learning
Based Approach”.
Beck, B. R., Shin, B., Choi, Y., Park, S., and
Implementation of a deep learning
Kang, K. (2020). Predicting commercially
method to identify potential
available antiviral drugs that may act on the Drug development, selection,
[17] medicine against COVID-19
novel coronavirus (SARS-CoV-2) through a and delivery
disease among commercially
drug–target interaction deep
available medicine.
learning model.
Rishikesh Magar, Prakarsh Yadav and Amir Application of artificial
Barati Farimani. “Potential Neutralizing Drug development, selection, intelligence to forecast potential
[18]
Antibodies Discovered for Novel Corona and delivery antibodies against
Virus Using Machine Learning.” SARS-COV-2 virus.
Zhong, L., Mu, L., Li, J., Wang, J., Yin, Z.,
and Liu, D. (2020). Early Prediction of the Describes early prediction of
Virus propagation modeling
2019 Novel Coronavirus Outbreak in the [19] COVID-19 epidemic based on SIR
and prediction
Mainland China based on a Simple epidemic prediction model.
Mathematical Model.
Review of the application of
Vaishya, R., Javaid, M., Khan, I. H., and
Early prediction or detection artificial intelligence technologies
Haleem, A. (2020). Artificial Intelligence [20]
of COVID-19 syndromes in prediction of
(AI) applications for COVID-19 pandemic.
COVID-19 spreading.
Present implementation of
Malik Magdon-Ismail. “Machine Learning
Early prediction or detection machine learning analysis on
the Phenomenology of COVID-19 From [21]
of COVID-19 syndromes COVID-19 epidemical statistics to
Early Infection Dynamics”.
forecast disease transmission.
Demonstration of Monte-Carlo
Biraja Ghoshal and Allan Tucker. Dropweight-based Bayesian
“Estimating Uncertainty and Early prediction or detection Convolutional Neural Networks
[22]
Interpretability in Deep Learning for of COVID-19 syndromes method to improve the
Coronavirus (COVID-19) Detection”. performance of COVID-19
detection process.
Babacar Mbaye Ndiaye, Lena Tendeng,
Proposes an SIR model supported
Diaraf Seck. “Analysis of the COVID-19 Early prediction or detection
[23] by machine learning to investigate
pandemic by SIR model and machine of COVID-19 syndromes
the epidemic in the real world.
learning techniques for forecasting”.
IoT 2020, 1 517
Table 1. Cont.

Rohit Batra, Henry Chan, Ganesh Kamath,
Rampi Ramprasad, Mathew J. Cherukara, Proposes the utilization of a
and Subramanian Sankaranarayanan. Early prediction or detection machine learning and docking
[24]
“Screening of Therapeutic Agents for of COVID-19 syndromes simulation model to identify
COVID-19 using Machine Learning and therapeutic molecules.
Ensemble Docking Simulations”.
Proposes a data-driven model that
Luca Magri and Nguyen Anh Khoa Doan.
Early prediction or detection is trained with both data and first
“First-principles machine learning [25]
of COVID-19 syndromes principles on an epidemiological
modelling of COVID-19”.
model.
Becky McCall. “COVID-19 and artificial Review of artificial intelligence
intelligence: protecting health-care workers [26] Protecting healthcare workers application in protecting
and curbing the spread”. healthcare professionals.
3. Social and Information Science-Related Applications Using AI and ML

On social perspectives, AI has been used in numerous regions of epidemiological exploration
modeling, including predicting the number of cases to develop different public policy choices as per
the requirement and identifying the regions with different stages and different degrees of severity of
the pandemic. Another interesting application of AI is measuring the social distancing, which will
play a vital role while encountering this epidemic.
3.1. Forecast the COVID-19 Statistics

As we already discussed in the above section, an AI and ML-driven system can forecast the number
of COVID-19-infected persons, which can help developing public policies to achieve protection against
the pandemic. In [28], the authors demonstrate a new and well-timed approach that combines disease
approximations from systematic prototypes with digital traces via interpretable machine-learning
procedures to consistently predict COVID-19 activity in Chinese provinces in real time. That technique
successfully produces precise and constant predictions 2 days earlier. The model utilizes information
from the official medical records, internet search related to COVID-19, and daily forecast from the
Global Epidemic and Mobility (GLEAM) model. The proposed machine-learning technique uses a
bunching method that allows the manipulation of a three-dimensional figure of COVID-19 activity
through the region of China, and a data augmentation procedure to deal with the inadequate amount
of available past disease activity reports along with patterns of evolving epidemics. This prototype’s
ability to predict disease spread outperforms a number of standard prototypes in most of the provinces
of China and could be readily applied to other geographical locations that are currently infected with
the epidemic to assist the authorities in strategy development.
3.2. Identify Influential Service Providers

Recognizing the greatest influential providers in a medical sector is a vital stage for optimizing the
utilization of accessible healthcare resources and confirming the more efficient distribution of matched
healthcare services while building resilience against pandemics such as COVID-19. In [29], the authors
offered a privacy-preserving network-based technique for detecting influential providers inside the
medical sector. Initially, the authors assembled a provider-networking system by engaging the openly
accessible data on the locations and categories of healthcare service providers. Next, the authors rank
the nodes in the generated provider-networking system on the basis of the nodal influence metrics.
Then, the authors assessed the influence of those top-ranked nodes in the provider-networking system
by comparing network indicators and identified the most influential provider.
3.3. Measuring Social Distancing

The COVID-19 pandemic has quickly spread around the world and triggered changing guidelines
to maintain physical distancing for slowing down the spread of the infection. In [30], the authors
IoT 2020, 1 518
demonstrate a novel hybrid machine learning prototype, SIRNET (named after the foundational
epidemiological model SIR), for predicting the transmission of the COVID-19 epidemic that combines
with the epidemiological prototypes. The authors utilized the characterization of spatiotemporal
cell-phone movement information, along with population density and other local data points.
In that work, trial outcomes from SIRNET are considered to create initial boundaries on such
localized movement that enable disease containment over time. The prototype can support studying
non-pharmacological mitigation techniques that minimize corresponding cases and develop control
mechanisms for a prolonged period of time.
SIRNET is a hybrid between machine learning methods, physical science, and epidemic modeling.
The epidemic modeling generates significant variables from a physical perspective that adds a
spontaneous understanding of how the prototype can be used for forecasting disease trends. In addition,
machine learning methods offer an instrument for interpreting variables—for example, movement,
non-pharmacological mitigation techniques, and population demographics—into variables that
influence a pandemic prototype. It also allows us to determine connections between real-world trends
on the spread of COVID-19, as well as the influence of underlying scenarios such as relaxing social
distancing rules.
3.4. Data Sharing and Hosting

Nowadays, it is a common practice to share news regarding an ongoing incident in social media
by the majority of the users. From the beginning of the COVID-19 pandemic, people have utilized
social media to interchange different types of data about the disease at an increasing volume. To build
resilience against this pandemic, only related and appropriate data are valuable for the community and
administration. Hence, it is essential to classify the categories of data and to analyze the way it is being
broadcast on social media so that proper data-sharing policies can be applied. This article in [31] utilizes
Weibo data and natural language processing techniques to categorize seven types of COVID-19-related
situational information. The results provide data-driven insights into information. The conclusion of
this study also indicates that different strategies should be used while publishing different types of
circumstantial news or information. These carefully chosen publishing strategies can also help the
authorities control the huge amount of information regarding the COVID-19 situation. Additionally,
this can help the researchers construct information-based emergency and crisis response plans.
3.5. AI Governance
The wide adoption of AI has impacted our socio-economic life, and therefore, it has a significant
influence on government policy and decision making. In this regard, article [32] described the
detailed effects of computerized decision support mechanisms on community services and the
growing potentials for administrations to become an indispensable part of the digital community.
The government authorities can compare the suitability of the prospective technologies while controlling
and perhaps avoiding undesirable effects. This is highly important in the present situation of the
COVID-19 epidemic where artificial intelligence and the supporting governing structure of the
information network have become strategic concerns, as a large number of inventions are based on big
data acquisition from smart appliances and the real-time availability of data and services.
The utilization of computerized decision-making systems in the public sector has certain values
and requirements that it offers to deliver. This type of computerized system is important in the current
situation of the COVID-19 pandemic, as the authorities are developing applications or tools that can
monitor human mobility in an effort to reduce the probabilities of spreading.
For most of the artificial intelligence-based applications used in the public sector, the goal is
to increase the efficiency and value of services, which is not completely addressed in the case of
many other technology-agnostic services of the public sector. Moreover, it is beneficial to measure the
appropriateness of the existing performance measurement tools and determine the way they can be
further developed in the future, particularly if the condition after crisis does not bring us to “normality”
IoT 2020, 1 519
and rather forces us collectively to alter our lifestyles and brings challenges to our regular social life
and if the preventive actions are necessary to anticipate new challenges.
3.6. Raising Social Awareness

It is a great challenge to control the fast-growing “Infodemic” in the present situation of the
COVID-19 pandemic. This involves enabling social awareness and a sensible behavior model in
order to avoid and minimize occurrences such as the present pandemic. Thus, there is an ongoing
effort to raise social awareness by providing up-to-date information and minimize the threat of false
information. In [33], the authors exhibit an AI-enabled Infodemic Management solution WashKaro that
utilizes natural language processing (NLP) methods, machine learning, and m-Health to reach out to
the community, where audio-visual content used is translated in native languages. WashKaro provides
reliable sources of data with regular bulletins, which is supplemented with a Bluetooth-based Contact
Tracer, WHO directive-based Symptom Self-Assessment tool, and human-authenticated information
delivered in native language.
To build resilience against the pandemic of COVID-19, it has become fundamentally essential to
broadcast precise and well-timed data regarding the epidemic. As a result of the widespread internet
connectivity and smart appliances usage, social sensing is developing as a dynamic sensing prototype
to gather live opinions from online users. In another paper [34], the researchers demostrate CovidSens,
the idea of social-sensing-oriented threat warning arrangements to inform the general public regarding
the COVID-19 epidemic. The CovidSens idea is inspired by two of the latest observations: (i) people
share their health status and COVID-19 experience actively on social media, and (ii) news agencies and
official channels regarding COVID-19 news and warnings are relatively slower than the people’s activity
on social media regarding the pandemic. They anticipate an extraordinary prospect to leverage the
posts created by the social media users to form a live analytics platform for collecting and broadcasting
crucial data regarding the COVID-19 spreading. Precisely, the idea of CovidSens tries to answer the
following questions: How to track the spread of COVID-19? How to filter reliable data regarding the
disease with the existence of prevalent rumors and misrepresentation in social media? How to notify
the general public about the up-to-date status of the spread timely and efficiently and prepare them
for the circumstances? In the article, the authors demonstrate the roles of CovidSens and find the
impending challenges in the implementation of dependable social-sensing-oriented threat notification
systems. The authors suggest that the methods introduced by numerous disciplines (for instance,
machine learning, estimation theory, constrained optimization) can be effective in addressing the
challenges. Table 2 summarizes the articles related to the AI applications in social/information sciences
for managing the pandemic.
Table 2. Summary of the research contributions considering AI for social science applications.

Dianbo Liuy, Leonardo Clementey,
Canelle Poiriery, Xiyu Ding, Matteo
Chinazzi, Jessica T Davis, Alessandro Demonstrates the application of
Vespignani, Mauricio Santillana. “A machine learning methods to
Forecasting the
machine learning methodology for [28] forecast COVID-19 transmission
COVID-19 statistics
real-time forecasting of the 2019–2020 based on internet data, news, and
COVID-19 outbreak using Internet epidemical forecast model.
searches, news alerts, and estimates
from mechanistic models”.
Qi, X., Mei, G., Cuomo, S., and Xiao, L.
Proposes a network-based privacy
(2020). A network-based method with
Identify influential preserving model to detect the
privacy-preserving for identifying [29]
service provider influential service provider of the
influential providers in large
medical sector.
healthcare service systems.
IoT 2020, 1 520
Table 2. Cont.

Nicholas Soures, David Chambers,
Zachariah Carmichael, Anurag
Demonstration of a unique
Daram, Dimpy P. Shah, Kal Clark,
machine learning model
Lloyd Potter, Dhireesha Kudithipudi.
[30] Measuring social distancing “SIRNET” to predict COVID-19
“SIRNET: Understanding Social
spreading with the help of an
Distancing Measures with Hybrid
epidemiological model, SIR.
Neural Network Model for COVID-19
Infectious Spread”.
Li, L. et al. (2020). Characterizing the
Demonstrates methods to
Propagation of Situational
categorize data and information
Information in Social Media During [31] Data sharing and hosting
shared in social media related
COVID-19 Epidemic: A Case Study
to COVID-19.
on Weibo.
Kuziemski, M. and Misuraca, G.
(2020). AI governance in the public Describes the influence of artificial
sector: Three tales from the frontiers [32] AI governance intelligence on government policy
of automated decision-making in and decision making.
democratic settings.
Rohan Pandey, Vaibhav Gautam,
Chirag Jain, Priyanka Syal, Himanshu
Sharma, Kanav Bhagat, Ridam Pal,
Lovedeep Singh Dhingra, Arushi, Demonstrates a social awareness
Lajjaben Patel, Mudit Agarwal, app “WashKaro" based on
Samprati Agrawal, Manan Arora, [33] Raising social awareness artificial intelligence where
Bhavika Rana, Ponnurangam audio-visual content used is
Kumaraguru, Tavpritesh Sethi. “A translated in native languages.
Machine Learning Application for
Raising WASH Awareness in the
Times of COVID-19 Pandemic”.
Md Tahmid Rashid, Dong Wang. Demonstrates a COVID-19 risk
“CovidSens: A Vision on Reliable alerting system that is based on
[34] Raising social awareness
Social Sensing based Risk Alerting sensing information about the
Systems for COVID-19 Spread”. epidemic on social media.
4. IoT Applications during COVID-19

With the advancement of information and communication technologies, IoT-based techniques have
sparked a growing interest among healthcare applications developers. Undoubtedly, IoT applications
emerge as a highly viable option for COVID-19 pandemic management. IoT technologies can be
utilized for tracing the COVID-19 infection spread pattern, diagnosing COVID-19 patients, providing
telemedicine services, and integrating these applications to wearables. In the following subsections,
different IoT applications for COVID-19 disease management are outlined.
4.1. Existing Contact Tracing Mechanisms

IoT-based contact tracing applications have evolved as an effective solution for managing
COVID-19 across different countries and regions [35–39]. The contact tracing mechanism requires
citizens with COVID-19 to disclose their contact list to a trusted party such as public health officers.
Then, based on the location of the tested citizen, other people who have been at the same location
or had interactions with the person infected with COVID-19 are requested to take actions such as
self-quarantine or testing [40]. Enabling IoT technologies for contact tracing can improve the efficiency
in terms of automated processing, quick response, and most importantly, the privacy of the infected
person [40]. There are a number of IoT-based contact tracing solutions proposed for the COVID-19
pandemic, as outlined in the following section.
Trace Together: This app has been released by the Singapore government for mobile applications
in March 2020. The app uses Bluetooth technology to exchange randomly generated time-varying
tokens among nearby phones as well as with the central server [41]. Upon installation of the app,
a pseudonym will be generated and associated with the user ID or phone number. Then, the central
server generates encrypted random tokens for each user, which the user broadcasts at pre-defined time
intervals [42]. A person identified as COVID-19 positive will be requested to provide information of
IoT 2020, 1 521
tokens received by his/her phone, which the government can decrypt and relate with phone numbers
and identities [41].
Decentralized Privacy-Preserving Proximity Tracing (DP3T): This decentralized solution is
proposed by the Pan-European Privacy-Preserving Proximity Tracing project team [43], which prompts
individual users to generate daily random keys and broadcast ephemeral identifiers in random order.
The users store all identifiers along with their proximities in the device database. If a user is detected
as COVID-positive, the central health authority will request the user’s secret key for the first day
when the user became infected. Then, the secret key is then broadcast to all users, who can compute
ephemeral identifiers for that specific day and subsequent days. As a result, other users can check if
they were in close proximity of the user tested as COVID-19 positive for the past few days [42].
Efficient Privacy-Preserving Contact Tracing (EPIC): In this solution, the user devices exchange
Bluetooth messages with nearby user devices and the server [44]. When the server has information on
the infected users, it offers data-matching services only to users who are interested to know if they
have shared the same location with the infected person. For this, the interested user sends timestamp
messages to the server using homomorphic encryption, and the server reports back with the overlapped
timestamps from the infected user. Then, the interested user sends the matched timestamps to the
server, which computes the distance between the interested user and user infected with COVID-19 and
forwards the information [42].
Contact Categorization: The solution utilizes contact categories rather than locations for infection
spread detection. The user devices store a list of contacts based on the received Bluetooth messages.
The developed application matches this list with the list of people infected with the virus, as obtained
from the health authority. When a match is found, the application categorizes the contact based on the
duration for which the non-infected user has been in contact with the user infected with COVID-19.
The categorization helps the health authority prioritize testing when the infection spreading level is
very high. Based on the signal strength, the proximity of the infected and non-infected users can also
be obtained similar to the other approaches [45].
Privacy-Sensitive Protocols and Mechanisms for Mobile Contact Tracing (PACT): The solution
enables users to generate pseudorandom IDs and broadcast to nearby users. Each user stores the
received ID and time stamp. The users infected with COVID-19 upload the IDs and time stamps to the
server, and the server adds the information to the list of users tested as COVID-positive. Any user can
download this list and extract the IDs as well as time stamps to match with its local storage and find
out if the user is in close proximity of the user infected with COVID-19. The solution allows for a time
delay before the ID, and time stamps are added to the public list to prevent replay attacks. In addition,
it uses a predetermined schedule of updating seeds for a pseudorandom generator [40].
4.2. IoT for COVID-19 Diagnosis

IoT technologies can improve the pace, accuracy, and efficiency of the COVID-19 diagnosis and
treatment process [46]. The authors in [47] have integrated a COVID-19 Intelligent Diagnosis and
Treatment Assistant Program into a cloud-based application. The application utilizes electronic medical
records and machine learning techniques for automated diagnosis. It can assist the health authority
by information collection from patients, managing coordination as well as enabling self-diagnosis.
The application is based on fifth-generation (5G) technologies, incorporating the high bandwidth and
higher communication efficiencies of such networks. It allows better coordination between diagnosis
and treatment through WeChat and establishes a common platform for doctors, medical scientists,
and health workers [48].
4.3. IoT for Telemedicine Services during COVID-19

To prevent the spread of the disease, adequate healthcare must be provided remotely to patients
infected with COVID-19 [49–52]. Many health authorities are focusing on developing chatbots for
automated screening of the disease and schedule follow-ups [53]. Robotic telemedicine carts (such as
IoT 2020, 1 522
Vici InTouch) can be used for the remote monitoring of patients in quarantine without the physical
presence of the health workers. A number of hospitals in the USA monitor patients in intensive care
units through the use of bidirectional audio and video communications [51].
4.4. IoT-Enabled Wearable Technologies for Predicting COVID-19

The advancement of IoT-enabled wearables has promoted a number of mobile applications
for monitoring physiological parameters such as heart rate, temperature, and sleep cycles [51].
These devices or sensors can be used and integrated with machine learning technologies to predict
the different phases of COVID-19 infection. The automated monitoring of temperature and blood
oxygen levels can generate alarms to prioritize attention from hospital staff. There has been a number
of studies such as Digital Engagement and Tracking for Early Control and Treatment or Tempredict
through the use of data from Fitbit or Apple Watch to match the heart rate and activity pattern with
that reported from the patients infected with COVID-19 [51].
4.5. Drone and UAV to Fight the Pandemic

The contagious nature of COVID-19 will compel a majority of the health-monitoring activities
to take place remotely, causing significant stress on the existing Wi-Fi connections. Thus, alternative
communication technologies such as Long Range Wide Area Network (LoRaWAN) have received
significant focus. For example, unmanned aerial vehicles (UAVs) have been proposed to improve the
information exchange reliability between LoRA devices attached to the infected users and the base
station. The approach makes use of the distributed topology control algorithm to update the UAV
topology based on the movement of the LoRA end devices, which improves the packet reception rate
at the base station [54].
Similarly, drone technologies and robotics can be significantly useful for resolving many different
technological challenges arising from the pandemic [4]. Given that many people will have to stay
in quarantine for a long time period irrespective of their infection status, there can be a number of
applications where drones can be useful such as drone-based food delivery, the automated delivery
of parcels [55], as well as providing assistance with the handling of clinical microbiology samples.
Drones can also help with the delivery of life-saving medicines in remote hospitals [56]. Robots can
be used in hospitals and other premises to remind users about social distancing and the use of
masks/gloves. They can also be trained for facial emotion recognition to identify health workers
in stress who need further attention [4]. Table 3 outlines the aforementioned applications of IoT in
managing COVID-19 pandemic.
Table 3. Summary of the research contributions in IoT for COVID-19 applications.

Madurai Elavarasan, R., and Pugazhendhi, Reviews the potential technologies
R. (2020). Restructured society and Drone and UAV to achieve such as AI, ML and IoT in
environment: A review on potential [4] protection against healthcare sector for forecast of
technological strategies to control the the pandemic epidemic, disease investigation,
COVID-19 pandemic. medicine delivery, etc.
Justin Chan, Dean Foster, Shyam Gollakota,
Eric Horvitz†, Joseph Jaeger, Sham Kakade,
Tadayoshi Kohno, John Langford, Jonathan Implementation of IoT technology
Existing contact
Larson, Sudheesh Singanamalla, Jacob [40] to improve the efficiency of
tracing mechanisms
Sunshine, Stefano Tessaro. “PACT: contact tracing.
Privacy-Sensitive Protocols And
Mechanisms for Mobile Contact Tracing”.
Hyunghoon Cho, Daphne Ippolito, Yun
Demonstration of IoT-enabled
William Yu. “Contact Tracing Mobile Apps Contact tracing using
[41] mobile app for contact tracing
for COVID-19: Privacy Considerations and TraceTogether
of COVID-19.
Related Trade-offs”.
IoT 2020, 1 523
Table 3. Cont.

Qiang Tang. “Privacy-Preserving Contact Discussion on privacy preserving
Efficient privacy-preserving
Tracing: current solutions and [42] contact tracing solution and
contact tracing
open questions”. their challenges.
Prof. Carmela Troncoso et al., Demonstration of a decentralized
“Decentralized Privacy-Preserving [43] Contact tracing using DP3T privacy preserving proximity
Proximity Tracing”. tracing solution.
Thamer Altuwaiyan, Mohammad Hadian,
Demonstration of a privacy
and Xiaohui Liang. “EPIC: Efficient Efficient privacy-preserving
[44] preserving contact tracing solution
Privacy-preserving Contact Tracing for contact tracing
using Bluetooth technology.
Infection Detection”.
Christoph, Michael and Daniel Günther. Demonstration of contact
Contact categorization for
“Tracing Contacts to Control the [45] categorization based on
contact tracing
COVID-19 Pandemic”. Bluetooth messages.
Bai, L., Yang, D., Wang, X., Tong, L., Zhu, X.,
Implementation of cloud-based
Bai, C., and Powell, C. A. (2020). Chinese
IoT enabled applications for
experts’ consensus on the Internet of [47] IoT for COVID-19 diagnosis
diagnostics and treatment
Things-aided diagnosis and treatment of
of COVID-19.
coronavirus disease 2019.
Application of WeChat app for
Christian Montag, Benjamin Becker and
better coordination between
Chunmei Gan. “The Multipurpose
[48] IoT for COVID-19 diagnosis diagnosis and treatment of
Application WeChat: A Review on
COVID-19 for doctors, medical
Recent Research”.
scientists, and health workers.
Kapoor, A., Guha, S., Kanti Das, M.,
IoT for telemedicine services Demonstration of IoT-enabled
Goswami, K. C., and Yadav, R. (2020).
during COVID-19, IoT-enabled remote and wearable monitoring
Digital Healthcare: The only solution for [51]
wearable technologies for solution for the
better healthcare during
predicting COVID-19 COVID-19 epidemic.
COVID-19 pandemic?
Saraereh, O. A., Alsaraira, A., Khan, I., and Application of Long Range Wide
Uthansakul, P. (2020). Performance Drone and UAV to fight the Area Network (LoRaWAN)
[54]
Evaluation of UAV-Enabled LoRa Networks pandemic technology for remote monitoring
for Disaster Management Applications. of COVID-19 epidemic activity.
5. Potential Risk of Intelligent Techniques

Although AI, ML, and IoT technologies have a huge potential to improve as well as automate the
COVID tracing, management, and associated healthcare applications, the risks of their implementation
cannot be overlooked. This section discusses the potential vulnerabilities and implications of the
incorrect decisions made by AI, ML, and IoT technologies.
5.1. Potential Risks of AI and ML

AI and ML are data-driven techniques where the decisions are made based on the model developed
completely from data or information. There is a saying: “garbage in, garbage out”. Now, any decision
made based on the AI and ML will be biased if the input data is wrong or falsified. During COVID-19,
information management has been highlighted as a critical challenge, as there is lots of wrong and false
information propagating in the media. Therefore, policy decisions, as well as patient monitoring and
diagnosis, could be biased or wrongly conducted because of the wrong input. Therefore, a significant
amount of risk is associated during the automation of the AI and ML-based systems [57]. GAN,
based on a class of deep learning and machine learning class, can create new images or datasets with
the same statistics as the training dataset. As a result, GAN can create images that never existed before.
Consequently, an adversary can use this learning model to generate fake CT scan data or other medical
imaging data and images. Mirsky et al. show that a stealthy attack can fool the radiologists with a
high success rate, e.g., cancer injection has a success rate of 99.2%, while cancer removal has 95.8%
when radiologists have no prior knowledge about the attack [57,58].
IoT 2020, 1 524
5.2. Potential Risks of IoT

The existing IoT applications certainly have some limitations in terms of privacy and security.
The contact tracing methods currently used by different countries pose significant challenges in terms
of security risks. For example, the mechanism used in TraceTogether requires a high level of trust to be
placed upon government officials, as they can identify sensitive information of persons infected with
COVID-19. Thus, the TraceTogether app cannot offer privacy preserving solutions for the infected group,
although in general, it can keep information secured from third parties [38]. The decentralized solution
in DP3T can bring new types of privacy attacks in the scenario, including backend impersonation,
false report, replay attack, and relay attack [59]. Data breaches in healthcare systems can massively
impact the treatment process and patient well-being, which have emerged as a serious problem in
modern healthcare systems with increasing hacking attacks [60]. IoT-based applications can enhance
this vulnerability a lot more due to their dependence on data extracted from connected networks.
Not every age group in the society will have the same level of technology readiness, which poses
additional challenges in the adoption of IoT-based applications in healthcare, as identified in a survey
from older/senior citizens [61].
5.3. Enhancing the Privacy and Security of AI and IoT Techniques

Since privacy and security are the key challenges of AI and IoT techniques, given the sensitivity
of the revealed information and associated implications, it is highly important to ensure appropriate
measures for preserving privacy and security in the AI and IoT applications. In general, these measures
need to achieve privacy from the “trusted” authority, attackers as well as other users of the app.
For COVID-19 contact tracing applications, polling can be a mechanism to protect the privacy of the
users infected with COVID-19 from the non-infected users, where non-infected users can poll the health
authority regularly to check if they have been in close contact with an infected user. Privacy from the
health authority can be achieved using private messaging systems [62] and private set intersection
protocols [63]. However, these protocols can be computationally expensive, so a trade-off needs to be
designed between security and computational efficiency [41]. The integrity of the COVID-positive
reports can be enhanced by including verification keys that combine a memo to the report through
cryptography. The memo can list a summary of users’ symptoms as well as certificates from third-party
health services [40].
The incorporation of innovative technologies to secure information sharing during a pandemic
such as COVID-19 can be highly effective. In this regard, appropriate standardization methods
for new communication and network protocols are required for their seamless integration in
healthcare systems [64]. Since IoT applications enable widespread access to system monitoring
data, new data-driven security techniques can be developed to build predictive ML models to detect
IoT attacks [65]. For secured information sharing among multiple entities in the healthcare sector,
distributed ledger technologies and blockchain can ensure the information integrity without involving
a third party, which allows privacy-preserving solutions for smart healthcare systems [66].
6. Conclusions
In this paper, a range of medical sector applications such as drug delivery and infection detection
based on AI and ML techniques have been elaborated. Moreover, AI and ML applications for
forecasting disease trends and developing social awareness programs have been outlined. In addition,
the recent advancements in IoT for tracing and reporting patients infected with COVID-19, as well
as the potential applications in automated monitoring through wearables technologies have been
reviewed. The applications of blockchain technologies for decentralized decision making in healthcare
systems during COVID-19 scenarios have been outlined. Security and privacy aspects of the AI, ML,
and IoT technologies have also been elaborated, along with their impact on the critical policy-making
IoT 2020, 1 525
operations. Future studies will be performed to extend the findings for developing new algorithms for
IoT-aided COVID-19 health-monitoring applications.
Author Contributions: Conceptualization, A.A. and A.M.T.O.; methodology, S.N.I.; software, A.N.M.; validation,
S.M.A.A.A., and S.N.I.; formal analysis, S.M.A.A.A.; investigation, A.A. and A.N.M.; resources, A.M.T.O.;
data curation, S.M.A.A.A; writing—original draft preparation, S.M.A.A.A. and S.N.I.; writing—review and editing,
A.A.; visualization, A.A.A. and S.N.I.; supervision, A.N.M.; project administration, A.M.T.O.; All authors have
read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Conflicts of Interest: The authors declare no conflict of interest.
References
1. Timeline: WHO’s COVID-19 Response. Available online: https://www.who.int/emergencies/diseases/novel-
coronavirus-2019/interactive-timeline?gclid=CjwKCAiA2O39BRBjEiwApB2Ikh-fQFKjiYNKczrHGfW-
VpPVYkuNEh6d53pNhA8fEM1WYjtAfpaSERoC0lkQAvD_BwE#event-115 (accessed on 24 August 2020).
2. WHO Coronavirus Disease (COVID-19) Dashboard. Available online: https://covid19.who.int/ (accessed on
24 August 2020).
3. COVID-19 Coronavirus Pandemic, Worldometer. Available online: https://www.worldometers.info/
coronavirus/ (accessed on 24 August 2020).
4. Elavarasan, R.M.; Pugazhendhi, R. Restructured society and environment: A review on potential technological
strategies to control the COVID-19 pandemic. Sci. Total Environ. 2020, 725, 138858. [CrossRef]
5. Bullock, J.; Luccioni, A.; Hoffmann Pham, K.; Lam, C.S.N.; Luengo-Oroz, M. Mapping the landscape of
Artificial Intelligence applications against COVID-19. arXiv 2020, arXiv:2003.11336.
6. COVID-19 Open Research Dataset (CORD-19). Semantic Scholar. Published 2020. Available online:
https://pages.semanticscholar.org/coronavirus-research (accessed on 30 March 2020).
7. Alwashmi, M.F. The Use of Digital Health in the Detection and Management of COVID-19. Int. J. Environ.
Res. Public Health 2020, 17, 2906. [CrossRef]
8. One Healthcare Cloud: Many Imaging Solutions, Cimar. Available online: www.cimar.co.uk (accessed on
25 November 2020).
9. Hare, S.; Rodrigues, J.; Jacob, J.; Edey, A.; Devaraj, A.; Johnstone, A.; McStay, R.; Nair, A.; Robinson, G.
A UK-wide British Society of Thoracic Imaging COVID-19 imaging repository and database: Design, rationale
and implications for education and research. Clin. Radiol. 2020, 75, 326–328. [CrossRef]
10. Shobha, G.; Rangaswamy, S. Chapter 8—Machine Learning. In Handbook of Statistics; Elsevier: Amsterdam,
The Netherlands, 2018; Volume 38, pp. 197–228.
11. Bogoch, I.I.; Watts, A.; Thomas-Bachli, A.; Huber, C.; Kraemer, M.U.G.; Khan, K. Pneumonia of unknown
aetiology in Wuhan, China: Potential for international spread via commercial air travel. J. Travel Med. 2020,
27, 1–3. [CrossRef]
12. Shi, F.; Wang, J.; Shi, J.; Wu, Z.; Wang, Q.; Tang, Z.; He, K.; Shi, Y.; Shen, D. Review of Artificial Intelligence
Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19. IEEE Rev. Biomed. Eng.
2020, 1. [CrossRef]
13. Meng, L. Review: Chest CT Features and Their Role in COVID-19. Radiology of Infectious Diseases.
Available online: www.sciencedirect.com (accessed on 30 March 2020).
14. Loey, M.; Smarandache, F.M.; Khalifa, N.E. Within the Lack of Chest COVID-19 X-ray Dataset: A Novel
Detection Model Based on GAN and Deep Transfer Learning. Symmetry 2020, 12, 651. [CrossRef]
15. Öztürk, Ş.; Özkaya, U.; Barstuğan, M. Classification of Coronavirus (COVID-19) from X-ray and CT images
using shrunken features. Int. J. Imaging Syst. Technol. 2020. [CrossRef] [PubMed]
16. Kassania, S.H.; Kassasnib, P.H.; Wesolowskic, M.J.; Schneider, K.A.; Deters, R. Automatic Detection of
Coronavirus Disease (COVID-19) in X-ray and CT Images: A Machine Learning Based Approach. arXiv
2020, arXiv:2004.10641.
17. Beck, B.R.; Shin, B.; Choi, Y.; Park, S.; Kang, K. Predicting commercially available antiviral drugs that
may act on the novel coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model.
Comput. Struct. Biotechnol. J. 2020, 18, 784–790. [CrossRef] [PubMed]
IoT 2020, 1 526
18. Magar, R.; Yadav, P.; Farimani, A.B. Potential Neutralizing Antibodies Discovered for Novel Corona Virus
Using Machine Learning. arXiv 2020, arXiv:2003.08447.
19. Zhong, L.; Mu, L.; Li, J.; Wang, J.; Yin, Z.; Liu, D. Early Prediction of the 2019 Novel Coronavirus Outbreak in
the Mainland China Based on Simple Mathematical Model. IEEE Access 2020, 8, 51761–51769. [CrossRef]
[PubMed]
20. Vaishya, R.; Javaid, M.; Khan, I.H.; Haleem, A. Artificial Intelligence (AI) applications for COVID-19
pandemic. Diabetes Metab. Syndr. Clin. Res. Rev. 2020, 14, 337–339. [CrossRef] [PubMed]
21. Magdon-Ismail, M. Machine Learning the Phenomenology of COVID-19 From Early Infection Dynamics.
arXiv 2020, arXiv:2003.07602.
22. Ghoshal, B.; Tucker, A. Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus
(COVID-19) Detection. arXiv 2020, arXiv:2003.10769v3.
23. Ndiaye, B.M.; Tendeng, L.; Seck, D. Analysis of the COVID-19 pandemic by SIR model and machine learning
technics for forecasting. arXiv 2020, arXiv:2004.01574v1.
24. Batra, R.; Chan, H.; Kamath, G.; Ramprasad, R.; Cherukara, M.J.; Sankaranarayanan, S. Screening of
Therapeutic Agents for COVID-19 using Machine Learning and Ensemble Docking Simulations. arXiv 2020,
arXiv:2004.03766v1.
25. Magri, L.; Khoa Doan, N.A. First-principles machine learning modelling of COVID-19. arXiv 2020,
arXiv:2004.09478v1.
26. McCall, B. COVID-19 and artificial intelligence: Protecting health-care workers and curbing the spread.
Lancet Digit. Health 2020, 2, e166–e167. [CrossRef]
27. Mashamba-Thompson, T.P.; Crayton, E.D. Blockchain and Artificial Intelligence Technology for Novel
Coronavirus Disease 2019 Self-Testing. Diagnostics 2020, 10, 198. [CrossRef]
28. Liu, D.; Clemente, L.; Poirier, C.; Ding, X.; Chinazzi, M.; Davis, J.T.; Vespignani, A.; Santillana, M. A machine
learning methodology for real-time forecasting of the 2019–2020 COVID-19 outbreak using Internet searches,
news alerts, and estimates from mechanistic models. arXiv 2020, arXiv:2004.04019v1.
29. Qi, X.; Mei, G.; Cuomo, S.; Xiao, L. A network-based method with privacy-preserving for identifying
influential providers in large healthcare service systems. Futur. Gener. Comput. Syst. 2020, 109, 293–305.
[CrossRef] [PubMed]
30. Soures, N.; Chambers, D.; Carmichael, Z.; Daram, A.; Shah, D.P.; Clark, K.; Potter, L.; Kudithipudi, D.
SIRNET: Understanding Social Distancing Measures with Hybrid Neural Network Model for COVID-19
Infectious Spread. arXiv 2020, arXiv:2004.10376v1.
31. Li, L.; Zhang, Q.; Wang, X.; Zhang, J.J.; Wang, T.; Gao, T.-L.; Duan, W.; Tsoi, K.K.-F.; Wang, F.-Y.
Characterizing the Propagation of Situational Information in Social Media During COVID-19 Epidemic:
A Case Study on Weibo. IEEE Trans. Comput. Soc. Syst. 2020, 7, 556–562. [CrossRef]
32. Kuziemski, M.; Misuraca, G. AI governance in the public sector: Three tales from the frontiers of automated
decision-making in democratic settings. Telecommun. Policy 2020, 44, 101976. [CrossRef]
33. Pandey, R.; Gautam, V.; Jain, C.; Syal, P.; Sharma, H.; Bhagat, K.; Pal, R.; Dhingra, L.S.; Arushi; Patel, L.;
et al. A Machine Learning Application for Raising WASH Awareness in the Times of COVID-19 Pandemic.
arXiv 2020, arXiv:2003.07074.
34. Rashid, M.T.; Wang, D. CovidSens: A Vision on Reliable Social Sensing based Risk Alerting Systems for
COVID-19 Spread. arXiv 2020, arXiv:2004.04565v1.
35. Bell, J.; Butler, D.; Hicks, C.; Crowcroft, J. TraceSecure: Towards Privacy Preserving Contact Tracing.
arXiv 2020, arXiv:2004.04059v1.
36. Roomp, K.; Oliver, N. ACDC-Tracing: Towards Anonymous Citizen-Driven Contact Tracing. arXiv 2020,
arXiv:2004.07463.
37. Lorch, L.; Trouleau, W.; Tsirtsis, S.; Szanto, A.; Schölkopf, B.; Gomez-Rodriguez, M. A Spatiotemporal
Epidemic Model to Quantify the Effects of Contact Tracing, Testing, and Containment. arXiv 2020,
arXiv:2004.07641v1.
38. Venkateswaran, J.; Damani, O. Effectiveness of Testing, Tracing, Social Distancing and Hygiene in Tackling
Covid-19 in India: A System Dynamics Model. arXiv 2020, arXiv:2004.08859.
39. Kim, H.; Paul, A. Contact Tracing: A game of big numbers in the time of COVID-19. arXiv 2020,
arXiv:2004.10762v1. [CrossRef]
IoT 2020, 1 527
40. Chan, J.; Foster, D.; Gollakota, S.; Horvitz, E.; Jaeger, J.; Kakade, S.; Kohno, T.; Langford, J.; Larson, J.;
Singanamalla, S.; et al. PACT:Privacy-Sensitive Protocols And Mechanisms for Mobile Contact Tracing.
arXiv 2020, arXiv:2004.03544v3.
41. Cho, H.; Ippolito, D.; Yu, Y.W. Contact Tracing Mobile Apps for COVID-19:Privacy Considerations and
Related Trade-offs. arXiv 2020, arXiv:2003.11511v2.
42. Tang, Q. Privacy-Preserving Contact Tracing: Current solutions and open questions. arXiv 2020,
arXiv:2004.06818v2.
43. Troncoso, C.; Payer, M.; Hubaux, J.-P.; Salathé, M.; Larus, J.; Bugnion, E.; Lueks, W.; Stadler, T.; Pyrgelis, A.;
Antonioli, D.; et al. Decentralized Privacy-Preserving Proximity Tracing. arXiv 2020, arXiv:2005.12273.
44. Altuwaiyan, T.; Hadian, M.; Liang, X. EPIC: Efficient Privacy-Preserving Contact Tracing for Infection
Detection. In Proceedings of the 2018 IEEE International Conference on Communications (ICC), Kansas City,
MO, USA, 24–28 May 2018.
45. Michael, C.; Günther, D. Tracing Contactsto Control the COVID-19 Pandemic. arXiv 2020, arXiv:2004.00517v1.
46. Rahman, S.; Peeri, N.C.; Shrestha, N.; Zaki, R.; Haque, U.; Ab Hamid, S.H. Defending against the
Novel Coronavirus (COVID-19) outbreak: How can the Internet of Things (IoT) help to save the world?
Health Policy Technol. 2020, 9, 136–138. [CrossRef]
47. Bai, L.; Yang, D.; Wang, X.; Tong, L.; Zhu, X.; Zhong, N.; Bai, C.; Powell, C.A.; Chen, R.; Zhou, J.; et al.
Chinese experts’ consensus on the Internet of Things-aided diagnosis and treatment of coronavirus disease
2019 (COVID-19). Clin. eHealth 2020, 3, 7–15. [CrossRef]
48. Montag, C.; Becker, B.; Gan, C. The Multipurpose Application WeChat: A Review on Recent Research.
Front. Psychol. 2018, 9, 2247. [CrossRef]
49. Yang, T.; Gentile, M.; Shen, C.-F.; Cheng, C. Combining Point-of-Care Diagnostics and Internet of Medical
Things (IoMT) to Combat the COVID-19 Pandemic. Diagnostics 2020, 10, 224. [CrossRef] [PubMed]
50. Torous, J.; Keshavan, M. COVID-19, mobile health and serious mental illness. Schizophr. Res. 2020, 218, 36–37.
[CrossRef] [PubMed]
51. Kapoor, A.; Guha, S.; Das, M.; Goswami, K.C.; Yadav, R. Digital healthcare: The only solution for better
healthcare during COVID-19 pandemic? Indian Hear. J. 2020, 72, 61–64. [CrossRef] [PubMed]
52. Ying, W.; Qian, Y.; Kun, Z. Drugs supply and pharmaceutical care management practices at a designated
hospital during the COVID-19 epidemic. Res. Soc. Adm. Pharm. 2020. [CrossRef] [PubMed]
53. Gupta, M.; Abdelsalam, M.; Mittal, S. Enabling and Enforcing Social Distancing Measures using Smart City
and ITS Infrastructures:A COVID-19 Use Case. arXiv 2020, arXiv:2004.09246v1.
54. Saraereh, O.A.; Alsaraira, A.; Khan, I.; Uthansakul, P. Performance Evaluation of UAV-Enabled LoRa
Networks for Disaster Management Applications. Sensors 2020, 20, 2396. [CrossRef] [PubMed]
55. Kellermann, R.; Biehle, T.; Fischer, L. Drones for parcel and passenger transportation: A literature review.
Transp. Res. Interdiscip. Perspect. 2020, 4. [CrossRef]
56. Mesar, T.; Lessig, A.; King, D.R. Use of Drone Technology for Delivery of Medical Supplies During Prolonged
Field Care. J. Spéc. Oper. Med. 2018, 18, 34–35.
57. Chu, L.C.; Anandkumar, A.; Shin, H.C.; Fishman, E.K. The Potential Dangers of Artificial Intelligence for
Radiology and Radiologists. J. Am. Coll. Radiol. 2020, 17, 1309–1311. [CrossRef]
58. Mirsky, Y.; Mahler, T.; Shelef, I.; Elovici, Y. CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep
Learning. In Proceedings of the 28th USENIX Security Symposium, Santa Clara, CA, USA, 14–16 August 2019;
pp. 461–478.
59. Vaudenay, S. Analysis of DP3T Between Scylla and Charybdis. Available online: https://infoscience.epfl.ch/
record/277808/files/dp3t-ana.pdf (accessed on 10 July 2020).
60. Seh, A.H.; Zarour, M.; Alenezi, M.; Sarkar, A.K.; Alenezi, M.; Kumar, R.; Agrawal, A. Healthcare Data
Breaches: Insights and Implications. Healthcare 2020, 8, 133. [CrossRef]
61. Wang, S.; Bolling, K.; Mao, W.; Reichstadt, J.; Jeste, D.; Kim, H.-C.; Nebeker, C. Technology to Support Aging
in Place: Older Adults’ Perspectives. Healthcare 2019, 7, 60. [CrossRef] [PubMed]
62. Van den Hooff, J.; Lazar, D.; Zaharia, M.; Zeldovich, N. Vuvuzela: Scalable private messaging resistant to
traffic analysis. In Proceedings of the 25th Symposium on Operating Systems Principles (SOSP ‘15); Association for
Computing Machinery: New York, NY, USA, 2015; pp. 137–152.
63. Freedman, M.J.; Nissim, K.; Pinkas, B. Efficient Private Matching and Set Intersection. Lecture Notes
Comput. Sci. 2004, 1–19. [CrossRef]
IoT 2020, 1 528
64. Allam, Z.; Jones, D.S. On the Coronavirus (COVID-19) Outbreak and the Smart City Network: Universal Data
Sharing Standards Coupled with Artificial Intelligence (AI) to Benefit Urban Health Monitoring and
Management. Healthcare 2020, 8, 46. [CrossRef] [PubMed]
65. Wheelus, C.; Zhu, X. IoT Network Security: Threats, Risks, and a Data-Driven Defense Framework. IoT 2020,
1, 259–285. [CrossRef]
66. Liu, H.; Crespo, R.G.; Martínez, O.S. Enhancing Privacy and Data Security across Healthcare Applications
Using Blockchain and Distributed Ledger Concepts. Healthcare 2020, 8, 243. [CrossRef]
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional
affiliations.
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).

Building Resilience Against Covid-19 Pandemic Using Artificial Intelligence, Machine Learning, and Iot: A Survey of Recent Progress

Uploaded by

Copyright:

Available Formats

Building Resilience Against Covid-19 Pandemic Using Artificial Intelligence, Machine Learning, and Iot: A Survey of Recent Progress

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Building Resilience Against Covid-19 Pandemic Using Artificial Intelligence, Machine Learning, and Iot: A Survey of Recent Progress

Uploaded by

Copyright:

Available Formats

IoT

Keywords: COVID-19; coronavirus; machine learning; artificial intelligence; Internet of Things

IoT 2020, 1, 506–528; doi:10.3390/iot1020028 www.mdpi.com/journal/iot

(a) Cumulative Confirmed Case (b) Cumulative death toll

Cumulative death toll

IoT 2020, 1, FOR PEER REVIEW 3

Organization and Contents of the Paper

2. Application of AI and ML for the Medical Sector

2.1. Medical Imaging for COVID-19 Patients

2.2. Patient Condition Monitoring Using Clinical Data

(2) analysis done

Figure 3. The Internet of Things (IoT)-based drug delivery system [4].

2.4. Virus Propagation Modeling and Prediction

2.5. Early Prediction or Detection of COVID-19 Syndromes

2.6. Protecting Healthcare Workers

Figure 4. Artificial intelligence (AI)-enabled self-testing framework, adopted from [27].

Table 1. Summary of the research contributions considering artificial intelligence (AI) to

Paper/Project Name Reference No. Domain Contribution

Paper/Project Name Reference No. Domain Contribution

3. Social and Information Science-Related Applications Using AI and ML

3.1. Forecast the COVID-19 Statistics

3.2. Identify Influential Service Providers

3.3. Measuring Social Distancing

3.4. Data Sharing and Hosting

3.6. Raising Social Awareness

Paper/Project Name Reference No. Domain Contribution

Paper/Project Name Reference No. Domain Contribution

4. IoT Applications during COVID-19

4.1. Existing Contact Tracing Mechanisms

4.2. IoT for COVID-19 Diagnosis

4.3. IoT for Telemedicine Services during COVID-19

4.4. IoT-Enabled Wearable Technologies for Predicting COVID-19

4.5. Drone and UAV to Fight the Pandemic

Table 3. Summary of the research contributions in IoT for COVID-19 applications.

Paper/Project Name Reference No. Domain Contribution

Paper/Project Name Reference No. Domain Contribution

5. Potential Risk of Intelligent Techniques

5.1. Potential Risks of AI and ML

5.2. Potential Risks of IoT

5.3. Enhancing the Privacy and Security of AI and IoT Techniques

You might also like