Role of Artiﬁcial Intelligence of Things (AIoT) in Covid-19 Pandemic: A

Brief Survey

Venkatesh K. Pappakrishnan

, R. Mythili

, V. Kavitha

and N. Parthiban

Palo Alto Networks, CA, U.S.A.

Department of Computer Science and Engineering,

SRM Institute of Science and Technology, Kattankulathur, Tamilnadu, India

Keywords:

AIoT, Healthcare 4.0, COVID-19, IoT, AI, Smart Healthcare.

Abstract:

Digital twins, Internet of Things (IoT) and Artiﬁcial Intelligence (AI), plays a proactive role in numerous

ways during a pandemic such as COVID-19 by allowing us to make informed decisions using real-time data.

According to World Health Organization (WHO), COVID-19 is an infectious disease caused by Severe Acute

Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) that predominantly spreads through body ﬂuids, leading

to a mild-to-severe respiratory illness. Considering the global health crisis due to COVID-19 and novelty of

the SARS-CoV-2 virus due diligence is required in vaccine preparation and human trials. At the early stages

of the pandemic, due to lack of complete knowledge on the virus, there are two main objectives: (1) treat

patients as effectively as possible and (2) control the spread of the disease. IoT devices in healthcare empower

the healthcare industry in identifying potential carriers of COVID-19 and quarantine. Even though IoT plays

a major role in healthcare 4.0, decision making capabilities are limited due to the type of the algorithms and

decision making paradigms used. Using AI, we will be able to identify critical medical conditions earlier

and take necessary steps. Artiﬁcial Intelligence of Things (AIoT) implementation has the potential to greatly

reduce the mortality rate allowing us in early identiﬁcation of high-risk patients, monitoring the spread of the

disease, methods to limit the spread, predict mortality risk by analyzing patient’s health history, remote or

in-home treatments to reduce hospital occupancy, and other techniques to signiﬁcantly control the spread and

treat the patients effectively.

1 INTRODUCTION

Artiﬁcial Intelligence (AI) has gained a lot of trac-

tion recently and has been widely adopted and rev-

olutionizing various ﬁelds including healthcare, re-

tail, banking, ﬁnancial services, marketing, travel,

real estate, logistics, and food technology (Hall and

Pesenti, 2017). Internet of Things (IoT) is a group

of interconnected devices that are programmed to

act individually or collectively with the knowledge

gained through all the interconnected devices (Ini-

tiative et al., 2015). IoT devices typically contain

sensors to collect useful data, processor and mem-

ory units, internet capability, and part of a network

of millions of similar devices (Atzori et al., 2010).

The collected data are either processed locally using

edge computing which can efﬁciently handle a small

amount of data within a limited bandwidth which pro-

vides us enhanced security mechanisms (local), low-

latency, and faster responsiveness or using fog com-

puting. The fog computing is a decentralized archi-

tecture where the computing is performed at the fog

node which is located within the LAN providing the

same advantages as edge computing in terms of data

security and latency. The intelligence still remains

close to the source of the data. However, when heavy

data processing and computation is required due to

the volume and velocity of the data, then cloud com-

puting is the best alternative which comes at the cost

of high latency, high cost, and possible data secu-

rity issues (Armbrust et al., 2010). Recently, more

focus is given to edge computing especially for IoT

applications due to high responsiveness, improved

performance, and better data security compared to

fog and cloud computing architectures (Hassan et al.,

2018). AIoT (Artiﬁcial Intelligence of Things) is

the combination of AI’s computational power and

IoT’s collective interoperability that pushes the limits

on the intelligence of smart devices by empowering

them to perform highly challenging tasks which are

Pappakrishnan, V., Mythili, R., Kavitha, V. and Parthiban, N.

Role of Artiﬁcial Intelligence of Things (AIoT) in Covid-19 Pandemic: A Brief Survey.

DOI: 10.5220/0010461502290236

In Proceedings of the 6th International Conference on Internet of Things, Big Data and Security (IoTBDS 2021), pages 229-236

ISBN: 978-989-758-504-3

229

technically impossible with current IoT architectures

(Ghosh et al., 2018; Poniszewska-Maranda and Kacz-

marek, 2015; Gonz

alez Garc

ıa et al., 2019). AIoT has

been widely adopted in different sectors such as retail,

healthcare, automobile, home appliances, etc (Ghosh

et al., 2018).

Industrial revolution 4.0 (I4.0) is the integration

of technologies from different sectors such as IoT,

AI, Big Data, 5G, etc (Lampropoulos et al., 2019).

There are four major components in I4.0: Cyber

Physical System (CPS), IoT, resource availability, and

cognitive computing. Information and Communica-

tion Technology (ICT) is the integration of infor-

mation through telecommunication and the compo-

nents in the ICT are computing, communications, and

entertainment that helps in exchange of information

through digital electronic media. Health-CPS is des-

ignated for patient-centric healthcare applications and

services which is based on cloud computing and big

data analytics (Zhang et al., 2015). Healthcare 4.0 is

an integral component of Industry 4.0 where differ-

ent domains of the industries are integrated through

personalization and virtualization. It revolves around

the idea of how a centralised health care system such

as hospitals, provide a decentralized patient-friendly

health care services using innovative research ﬁelds of

computer science such as IoT, AI, big data, robotics

and so on (Javaid and Haleem, 2019; Javaid and

Haleem, 2018; Ekstrand et al., 2018).

Figure 1: Components of Healthcare 4.0 (H4.0).

Figure 1 shows different components in H4.0

which are borrowed from I4.0 with applications tai-

lored to the healthcare industry. As everyone is con-

nected through digital technologies, ICT helps in im-

proving healthcare for individuals and larger com-

munities (Thilakarathne et al., 2020). ICT monitors

and controls every component in the system includ-

ing hardware such as sensors and actuators. All the

components should follow a predetermined procedure

and require constant monitoring and periodic mainte-

nance.

In H4.0, patients’ data are continuously collected

using various sensors and stored in a cloud infras-

tructure for data analysis and predictive modeling. In

IoT based health care systems, sensors connected to

micro-controllers (eg. arduino) and integrated chips

(eg. raspberry pi) monitor health statistics and vi-

tal parameters such as body temperature, pulse rate,

respiratory rate, blood glucose level, and ECG (Ku-

mar et al., 2017). For effective communication, wire-

less technologies currently used in IoT are: (1) wide

area cellular technologies such as GSM, LTE and 5G,

(2) short range technologies such as ZigBee, Z-wave,

WiFi and Bluetooth, and (3) low power technologies

such as LoRa and Sigfox are used (Qadir et al., 2018).

This paper is organised as follows: In section 2

we discuss the pandemic evolution and the challenges

faced. In section 3 we present existing work related

to AI and IoT in the ﬁeld of healthcare. In section 4

we discuss the technologies currently available for di-

agnosis and monitoring of patients. In section 5 we

discuss the process ﬂow of telemedicine using AIoT,

remote health monitoring, and telematics. This is fol-

lowed by applications and beneﬁts of AIoT during

pandemics. In section 6 we brieﬂy discuss the secu-

rity challenges of personal health data and ﬁnally in

section 7 we summarize all the important ﬁndings.

2 PANDEMIC OVERVIEW AND

CHALLENGES

Infectious diseases are classiﬁed into endemic, epi-

demic, and pandemic based on geographic spread and

scale of the people infected. A pandemic is usu-

ally triggered by a zoonotic transmission of pathogens

from animals to humans (Belay et al., 2017). This is

due to the fact that human’s immune system are not

evolved to ﬁght pathogens from other species, espe-

cially the ones that are from uncommon environmen-

tal conditions known to humans.

The following are the common challenges faced

during a pandemic (Madhav et al., 2017):

• Lack of preparedness after the initial outbreak

as the developing countries have limited ﬁnancial

and technical resources.

• Shortage in essential medical necessities such as

gloves, masks, syringes, etc. Unavailability of an-

tiviral agents and vaccines.

• Insufﬁcient number of healthcare workers and

lack of training in specialized areas for effective

control of the infection in the early stages.

• Economic downfall including short-term ﬁscal

shocks and longer-term negative impact to the

economic growth.

IoTBDS 2021 - 6th International Conference on Internet of Things, Big Data and Security

230

• Slowdown in social and economic growth due to

pandemic mitigation plans from every country.

• High morbidity and mortality rates due to poor

public health resources and population density

(Oshitani et al., 2008).

Figure 2: (a) Total deaths and (b) mortality in per-

centage across different continents (data source: https://

ourworldindata.org/coronavirus-data).

Mortality rate and total deaths of the COVID pa-

tients are continuously tracked and periodically pub-

lished for the public by various organizations and uni-

versities including WHO and John Hopkins Univer-

sity. Europe has been critically affected in terms of

total deaths followed by N. America and other con-

tinents (Figure 2 (a)) and in terms of mortality rate,

which considers only infected patients, S. America

has been severely affected with over 3% mortality rate

(Figure 2 (b)).

Figure 3: Impact of pandemics (death count)

during different time periods (data sources:

https://www.worldometers.info/coronavirus/, https:

//en.wikipedia.org/wiki/List of epidemics).

Figure 3 depicts the death count during each pan-

demic that are known to us. One of the recent pan-

demics that has been making a signiﬁcant impact is

HIV/AIDS with over 35M deaths and this is mainly

due to the nature of the virus itself and lack of tech-

nological advancements to predict and control the

spread during that period. The COVID-19 has al-

ready claimed over 1.27M lives across the world as of

Nov 2020 (Organization et al., 2020) and continues to

climb. Recent technological advancements allows us

to accelerate the research and development of the vac-

cine for SARS-CoV-2 compared to the technologies

we had during HIV/AIDS outbreak. According to the

WHO, there are currently more than 60 COVID-19

vaccine candidates in clinical development and over

170 in pre-clinical development.

For COVID-19 two types of vaccines are de-

veloped by three major pharmaceutical companies:

Pﬁzer-BioNTech COVID-19 Vaccine (pﬁzer, BioN-

Tech) (Tanne, 2020), Moderna COVID-19 Vaccine

(Morderna) (Cohen, 2020), and Serum Institute of In-

dia (Covishield ChAdOx1 nCoV19). The vaccines

show promising results based on initial human tri-

als and released to public. However, the side effects

and the effectiveness of the vaccine still needs fur-

ther study. Although, various hospitals are pioneer-

ing in smart healthcare and forge ahead for better and

advanced treatments, there still prevails various chal-

lenges in this sector (Zhu, 2019; Gastaldi and Corso,

2012).

3 RELATED WORK

Pardeshi et al., explains the process remote moni-

toring of patients remotely, data storage techniques,

data processing, and data transmission methods along

with the hardware and the software required for the

successful monitoring of the patients (Pardeshi et al.,

2017). Remote monitoring system is used for keeping

track of non-critical patients from their home with-

out the need for hospital occupancy. Islam et al., dis-

cusses the advances imposed in the IoT industry and

various industrial implementations of healthcare solu-

tions along with a detailed explanation of a collabora-

tive security model to address the security issues (Is-

lam et al., 2015). Rodrigues et al., discusses products,

services, and features of IoHT technology (Rodrigues

et al., 2018). Smart clothing based health care system

has been introduced as Wearable 2.0 to support bed-

ridden patients with accurate monitoring of health

statistics (Chen et al., 2017). To improve the energy

efﬁciency of the IoT devices, ARM micro controllers

are used for collecting real-time data. Pang et al.,

discusses the advancement in automation, biomedi-

cal industry, and health analytics and identiﬁes the

research gap and industrial demands to set direction

on future research (Pang et al., 2018). Assisted liv-

ing for the elderly people can be achieved using AIoT;

Genni an intelligent IoT application designed as a per-

sonal assistant using wearable technology for moni-

toring vital signs such as heart rate, blood pressure,

sleep hours, etc., and integrate them in a distributed

data management framework for demonstrating data

interoperability and data accessibility (Serrano et al.,

2018). In spite of strong security measures to protect

Role of Artiﬁcial Intelligence of Things (AIoT) in Covid-19 Pandemic: A Brief Survey

231

patients medical e-records, security breaches may still

occur due to various unique techniques followed by

the hackers. The security challenges include privacy

and conﬁdentiality of the patients data. According to

Ermakova et al., due to the privacy concerns, patients

are still skeptical and less likely to prefer cloud envi-

ronments for storing their medical records (Ermakova

et al., 2013; Kuo et al., 2014). AIoT is currently used

for cardiac disease detection and analysis of electro-

cardiogram (ECG) signals. Convolution Neural Net-

work (CNNs) are used for arrhythmia classiﬁcation

(Lin et al., 2019).

4 DIAGNOSIS AND

MONITORING OF COVID-19

PATIENTS

According to the WHO, the most common symp-

toms of COVID-19 are fever, dry cough and tired-

ness and the less common symptoms are aches and

pains, sore throat, diarrhoea, conjunctivitis, headache,

etc. Severe symptoms include difﬁculty in breath-

ing, chest pain, loss of speech or movement (Chamola

et al., 2020). For effective identiﬁcation, the diag-

nosis needs to be scaled up to test millions of po-

tential patients with symptoms which is critical dur-

ing a pandemic. For scaling up, the challenges in-

clude availability of the medical kits, trained health

care workers, and health care facility. IoT would

tackle the challenge by integrating the medical de-

vices with the in-built sensors, algorithms and mo-

bile health applications. AI, virtual healthcare man-

agement, and telemedicine reduces the manual inter-

ventions in considerable way thereby protect the front

line workers. The image sensing such as CT scans

and X-ray detect and classiﬁes the abnormalities ob-

served. This intelligent classiﬁcation will enhance the

automation process, less intervention of the physician

with the patients. The performance of analytics helps

in monitoring the spread of COVID-19. The com-

plexity in handling the applications has been reduced

and the technology is easy to adapt. Although there

are several challenges, AI and IoT would help us op-

timize logistics of medical kits and required equip-

ment to reduce shortage during critical times, improve

the accuracy of the diagnosis, efﬁcient and effective

data collection required for gain better understand-

ing of the disease and in developing accurate algo-

rithms or models. There are sensors that help us in

pure data collection and others that allow us to con-

tinuously monitor the patients for taking necessary

actions. Here we have listed sensors and devices in

the table 1 that are known to be quite helpful so far

in the early detection of COVID-19 symptoms and

monitoring of affected patients. The contact trac-

ing applications developed by various countries are

COVIDSafe (Australia), Stopp Corona (Austria), e-

Tabib (Azerbaijan), Corona Tracer BD (Bangladesh),

CoronApp (Colombia), Smittestop (Denmark), Stop-

Covid (France), Corona-Warn-App (Germany), Aar-

ogya Setu app (India), and HaMagen (Israel).

5 AIoT FOR COVID-19

AIoT holds a tremendous potential in addressing

the limitations of IoT in H4.0. A typical process

of AIoT system involves three main components:

telemedicine, remote data gathering, and algorithm.

The telemedicine segment includes both the sensors

for recording data or monitoring health of patients

and the actuators to act physically based on the signal

either from health care practitioner (semi-automated

system) or the algorithm directly (fully-automated

system). The collected data is pre-processed and

stored in distributed storage system and the data can

be processed in batch mode or streaming mode for

model building and prediction. During every batch or

cycle, the data collected is used for predicting the next

behavior. The algorithm could be re-trained periodi-

cally like every 3-6 months using last n days of data

or the entire data set.

5.1 Contact Tracing and Tracking

Contact tracking is the process of monitoring a person

who has been exposed to the disease in-order to alert

his contacts to curtail the transmission of the disease

(Thayyil et al., 2020). The contact tracing and track-

ing API have been developed by Google and Apple

and they provide a GUI platform for building trac-

ing apps using which a user can participate in digi-

tal contact-tracing. For instance, if two people meet

for ﬁve minutes or more, an identiﬁer is exchanged

between their phones via Bluetooth. Later, if one of

them is tested positive for COVID–19, an alert noti-

ﬁcation is send to the other person’s phone who has

come in contact with him. Privacy is preserved as

user’s location and other details are not shared. Trac-

ing and tracking of patients and their health statistics

is discussed in detail in (Nazirun et al., 2017).

IoTBDS 2021 - 6th International Conference on Internet of Things, Big Data and Security

232

Table 1: Types of Sensors.

SENSOR MEASURES / MONITORS COMPANY

Temperature Body temperature Analog devices, Mitsumi, Melexis

Pressure Blood pressure Sensata Technologies, IFM Efector,

Keller America

Airﬂow Breathing rate HydraCheck, RCM Industries, Inc.,

ERDCO Engineering Corporation

Oxygen Oxygen level Honeywell, Unimed, Cubic

Electrocardiogram Heart rate NeuroSky, Eko Devices, Inc. , Cognionics

Accelerometers Movement of body First Sensor Inc., Baumer Group, Colibrys SA

Biosensors Level of cholesterol InnovoGENE Biosciences, Biodot, Aryballe

5.2 Telehealth, Remote Health

Monitoring, and Telematics

With ever increasing number of COVID-19 patients

across the globe, automation of healthcare workers’

duties will be of great deeds (Alwashmi, 2020). This

would reduce medical expenditures and in-facility

congestion. Remote Patient Monitoring (RPM), also

called home-care telehealth, allows patients to per-

form a routine check up, send real-time data to the

medical practitioner, and receive medicines through

home delivery (Avitall et al., 2001). RPM technol-

ogy with the introduction of biosensors makes health

care accessible to remote areas requiring timely ac-

tion. The WHO describes the synergy of telehealth

and telemedicine as telematics, a term for information

technology based health care activities. Telemedicine

Figure 4: Remote Health monitoring.

involves distance learning component wherein con-

sultation of the case management can also be per-

formed between the physicians at different geolo-

cations. The prescription and drug management is

also enhanced by tracking and delivering drugs to

the concerned client and to analyze the side effects

of the same, if any (Organization et al., 2019). In

telemedicine although the doctors can check the ex-

ternal features for diagnosis, however there are still

challenges that exist including checking of the heart

beat, blood pressure, etc. In this scenario, wearables

play a vital role to monitor heart rate and blood pres-

sure and abnormalities could be diagnosed in earlier

stages. The factors inﬂuencing the telemedicine de-

ployment are the installation space, network availabil-

ity, proper management of sensors and wearables, and

proper adherence to the health care polices and digi-

tal infrastructure. The incident rate for COVID-19 is

increasing exponentially; in such a scenario reverse

quarantine would be the best possible monitoring sys-

tem in near future (Raveendran and Jayadevan, 2020).

Figure 4 shows remote health monitoring system that

collects the medical health data using the sensors and

actuators from one place and transmit it to the cloud

infrastructure and can be used for decision making

and analytics to the physicians or healthcare providers

for medical assessment or medicine recommenda-

tions. Here is a list of telemedicine apps developed by

companies worldwide: Mﬁne (Novocura Tech), eSan-

jeevaniOPD (C-DAC, India), Practo (Practo), Doc-

Clocker (Fast Pathway), and CMED Health (CMED).

5.3 AI and IoT Applications in

Pandemic and beyond

• Early Warning System: BlueDot, an AI based

company detected and notiﬁed to its users an out-

break of pneumonia cases (Wuhan, China) as dig-

ital smoke signal even before it was ofﬁcially de-

clared by WHO. The AI VFusion platform by Vi-

vace Health Solutions is reliable in identifying

Acute Respiratory Distress Syndrome (ARDS).

• Tracking the Spread of Virus: AI-based

Healthmaps integrate data sources from Google

and other social media platforms. The data are

then sent to epidemiologist for the detection of

early sign of a possible outbreak. Healthmaps in

the Boston Children’s Hospital ﬁrst recognizes the

kind of pneumonia attacking a group of people.

• Contact Tracing: Geo-location data are used to

identify people coming in close contact with each

other and notify them directing to isolate them-

Role of Artiﬁcial Intelligence of Things (AIoT) in Covid-19 Pandemic: A Brief Survey

233

selves if one of them is infected.

• Prediction of Virus Protein Structure: Deep-

Mind, a company developed a method to predict

the virus protein structures using AlphaFold AI

system (Alimadadi et al., 2020). They have re-

leased AlphaFold, a deep learning library that use

neural networks for predicting how the proteins

that make organisms crinkle or curve on the basis

of their genome. This predicts the receptor shape

in the cells of the living being. By learning its

shape drug development becomes easier.

• Early Detection and Diagnosis: AI and digital-

imaging are used together with the COVID-19 de-

tection neural network (COVNet) algorithm to de-

tect positive cases using the chest computed To-

mography (CT) images (Li and Xia, 2020). XG-

Boost machine learning based model to predict

survival rates of the COVID-19 affected patients

using blood samples data.

• Robots: Robots are deployed to respond to imme-

diate needs in hospitals such as delivery of food,

medications and equipment, to cleanse and ster-

ilise tools, and to aid medical practitioners. Asi-

mov Robotics, a robotic service provider com-

pany based in India, assist patients with their

needs to minimize the risk of health-care work-

ers. UVD Robots, emit powerful UV light that

can disinfect surfaces (Chamola et al., 2020).

• Drones: Drones are deployed for crowd surveil-

lance and to avoid gathering of people in large

groups. In India, drones are used to monitor

body temperature using an array of infrared (IR)

sensors and supply commodities, medical kits,

food supplies, and collect samples from people

for COVID-19 diagnosis (Anggraeni et al., ; Mo-

hammed et al., 2020).

5.4 Advantages of AIoT during a

Pandemic

AI allows us to minimize the workforce required to

achieve a task which is critical during a pandemic.

Chatbots, a NLP based AI application, is vital in

spreading general awareness to the public. Viola-

tion of rules in areas with restricted movements can

be monitored efﬁciently using unarmed aerial vehi-

cles (UAV), real-time monitoring using closed cir-

cuit television (CCTV) reduces the incident rate of

COVID-19. Medical fraternities are moving towards

e-learning to abridge the gap in medical workforce

(Jecker et al., 2020; Tang et al., 2020). ML algo-

rithms, a subset of AI system helps in the following

ways to handle such pandemics:

• Screening of Individuals: Using CNNs people

with illness, sweating, and discoloration can be

detected using thermal scanning face cameras.

Wearable rings are used at the University of Cali-

fornia to track health statistics of people.

• Chatbots for Diagnostic: Chatbots can be pro-

grammed to feed patients with a questionnaire

about their symptoms as a part of self triage,

hence reducing the risk of infection to other

health-care workers.

• Risk Prediction: Health risk of a patient can be

determined using various factors such as age, gen-

eral hygiene, and social interactions.

• Bio Medical Knowledge Graphs: Using NLP,

entities of drugs and proteins are connected to-

gether as structured graphs. Similarly, customised

BenevolentAI knowledge graph is used to ﬁnd

the connection between COVID-19 and Barici-

tinib (Richardson et al., 2020).

6 SECURITY CHALLENGES OF

DATA

Health records are continuously monitored and

recorded using telemonitoring facilities, there exists a

potential security threat (Singh et al., 2020). Tamper-

ing of data, unauthorized access of personal informa-

tion of the patients, sensitive and conﬁdential infor-

mation breach, Distributed Denial of Service (DDoS)

are possible as the records are most likely placed in a

centralized server. A poorly conﬁgured central server

in terms of network security, all the sensitive content

could be compromised and data would be leaked. To

limit the security threats, it is important to highest

privileges to only few individuals who are qualiﬁed

to handle. By limiting the number people with broad

privileges we could greater reduce the chances of be-

ing hacked (Tarouco et al., 2012). According to Anas-

tasios Arampatzis, most of the healthcare threats are

done using hidden HTTPS and Domain Name Server

(DNS) tunnels, ransomware, and BOTNET. Neces-

sary privacy policies need to be adhered to protect

against unauthorized access to health records. Tele-

health sector must be provided with enhanced authen-

tication, authorization and accountability (Williams

and McCauley, 2016). Data integration and consis-

tency is an another major challenge. A proper envi-

ronment has to be provided in-order to integrate large

sets of data and to make them readily available for

accessing and analyzing at any given point of time.

According to TrapX report, some hospitals are prone

IoTBDS 2021 - 6th International Conference on Internet of Things, Big Data and Security

234

to medical device hijacking which is also called med-

jacking. A different scenario includes radiology im-

age storage system connected to the main server gets

compromised and the sensitive contents are leaked. In

another scenario attackers could use a vulnerability in

drug pumps to control the hospital’s network.

7 SUMMARY

Healthcare 4.0 integrated with AI would greater help

in lowering the mortality rate during a pandemic such

as COVID-19. We speciﬁcally discussed the role of

IoT with various sensors to monitor health remotely

and how AI would further improve the capabilities

in terms of accurate detection of the disease, trac-

ing and tracking of infected/potential patients, etc.,

allowing us to proactively handle the situation. The

need for digital intervention in healthcare and sup-

porting structures has also been discussed along with

the security challenges in protecting patients medical

records. Finally, we have proposed ideas and listed

relevant works on AIoT in healthcare and how it could

be used to improve the current healthcare system even

beyond 4.0.

REFERENCES

Alimadadi, A., Aryal, S., Manandhar, I., Munroe, P. B., Joe,

B., and Cheng, X. (2020). Artiﬁcial intelligence and

machine learning to ﬁght covid-19.

Alwashmi, M. F. (2020). The use of digital health in

the detection and management of covid-19. Interna-

tional Journal of Environmental Research and Public

Health, 17(8):2906.

Anggraeni, S., Maulidina, A., Dewi, M. W., Rahmadianti,

S., Rizky, Y. P. C., Arinalhaq, Z. F., Usdiyana, D.,

Nandiyanto, A. B. D., and Al-Obaidi, A. S. M. The

deployment of drones in sending drugs and patient

blood samples covid-19. Indonesian Journal of Sci-

ence and Technology, 5(2):18–25.

Armbrust, M., Fox, A., Grifﬁth, R., Joseph, A., Katz, R.,

Konwinski, A., Lee, G., Patterson, D., Rabkin, A.,

Stoica, I., and Zaharia, M. (2010). A view of cloud

computing. Commun. ACM, 53:50–58.

Atzori, L., Iera, A., and Morabito, G. (2010). The internet of

things: A survey. Computer networks, 54(15):2787–

2805.

Avitall, B., Peterson, B., Kletch, J., Griswold, E. B., and

Moran, P. (2001). Remote health monitoring system.

US Patent 6,171,237.

Belay, E. D., Kile, J. C., Hall, A. J., Barton-Behravesh,

C., Parsons, M. B., Salyer, S., and Walke, H.

(2017). Zoonotic disease programs for enhancing

global health security. Emerging infectious diseases,

23(Suppl 1):S65.

Chamola, V., Hassija, V., Gupta, V., and Guizani, M.

(2020). A comprehensive review of the covid-19 pan-

demic and the role of iot, drones, ai, blockchain, and

5g in managing its impact. IEEE Access, 8:90225–

90265.

Chen, M., Ma, Y., Li, Y., Wu, D., Zhang, Y., and Youn, C.-

H. (2017). Wearable 2.0: Enabling human-cloud in-

tegration in next generation healthcare systems. IEEE

Communications Magazine, 55(1):54–61.

Cohen, J. (2020). Vaccine designers take ﬁrst shots at covid-

19.

Ekstrand, C., Jamal, A., Nguyen, R., Kudryk, A., Mann,

J., and Mendez, I. (2018). Immersive and interac-

tive virtual reality to improve learning and retention

of neuroanatomy in medical students: a randomized

controlled study. CMAJ open, 6(1):E103.

Ermakova, T., Fabian, B., and Zarnekow, R. (2013). Se-

curity and privacy system requirements for adopting

cloud computing in healthcare data sharing scenarios.

Gastaldi, L. and Corso, M. (2012). Smart healthcare digi-

talization: Using ict to effectively balance exploration

and exploitation within hospitals. International Jour-

nal of Engineering Business Management, 4(Godi

ste

2012):4–9.

Ghosh, A., Chakraborty, D., and Law, A. (2018). Artiﬁcial

intelligence in internet of things. CAAI Transactions

on Intelligence Technology, 3(4):208–218.

Gonz

alez Garc

ıa, C., N

nez Vald

ez, E. R., Garc

ıa D

ıaz,

V., Pelayo Garc

ıa-Bustelo, B. C., and Cueva Lovelle,

J. M. (2019). A review of artiﬁcial intelligence in the

internet of things. International Journal of Interactive

Multimedia and Artiﬁcial Intelligence.

Hall, W. and Pesenti, J. (2017). Growing the artiﬁcial in-

telligence industry in the uk. Department for Digital,

Culture, Media & Sport and Department for Business,

Energy & Industrial Strategy. Part of the Industrial

Strategy UK and the Commonwealth.

Hassan, N., Gillani, S., Ahmed, E., Yaqoob, I., and Imran,

M. (2018). The role of edge computing in internet of

things. IEEE communications magazine, 56(11):110–

115.

Initiative, I. I. et al. (2015). Towards a deﬁnition of the

internet of things (iot)(revision-1).

Islam, S. R., Kwak, D., Kabir, M. H., Hossain, M., and

Kwak, K.-S. (2015). The internet of things for health

care: a comprehensive survey. IEEE access, 3:678–

708.

Javaid, M. and Haleem, A. (2018). Additive manufactur-

ing applications in medical cases: A literature based

review. Alexandria Journal of Medicine, 54(4):411–

422.

Javaid, M. and Haleem, A. (2019). Industry 4.0 applications

in medical ﬁeld: a brief review. Current Medicine

Research and Practice, 9(3):102–109.

Jecker, N. S., Wightman, A. G., and Diekema, D. S. (2020).

Prioritizing frontline workers during the covid-19

pandemic. The American Journal of Bioethics, pages

1–5.

Kumar, S. P., Samson, V. R. R., Sai, U. B., Rao, P. M., and

Eswar, K. K. (2017). Smart health monitoring system

Role of Artiﬁcial Intelligence of Things (AIoT) in Covid-19 Pandemic: A Brief Survey

235

of patient through iot. In 2017 international confer-

ence on I-SMAC (IoT in social, mobile, analytics and

cloud)(I-SMAC), pages 551–556. IEEE.

Kuo, K.-M., Ma, C.-C., and Alexander, J. W. (2014). How

do patients respond to violation of their information

privacy? Health Information Management Journal,

43(2):23–33.

Lampropoulos, G., Siakas, K., and Anastasiadis, T. (2019).

Internet of things in the context of industry 4.0: An

overview. International Journal of Entrepreneurial

Knowledge, 7(1):4–19.

Li, Y. and Xia, L. (2020). Coronavirus disease 2019 (covid-

19): role of chest ct in diagnosis and management.

American Journal of Roentgenology, 214(6):1280–

1286.

Lin, Y.-J., Chuang, C.-W., Yen, C.-Y., Huang, S.-H., Huang,

P.-W., Chen, J.-Y., and Lee, S.-Y. (2019). Artiﬁcial

intelligence of things wearable system for cardiac dis-

ease detection. In 2019 IEEE International Confer-

ence on Artiﬁcial Intelligence Circuits and Systems

(AICAS), pages 67–70. IEEE.

Madhav, N., Oppenheim, B., Gallivan, M., Mulembakani,

P., Rubin, E., and Wolfe, N. (2017). Pandemics: risks,

impacts, and mitigation.

Mohammed, M., Hazairin, N. A., Al-Zubaidi, S., AK, S.,

Mustapha, S., and Yusuf, E. (2020). Toward a novel

design for coronavirus detection and diagnosis system

using iot based drone technology. International Jour-

nal of Psychosocial Rehabilitation, 24(7):2287–2295.

Nazirun, N. N. N., Shakhih, M. F. M., Ren, P. C., Zaini,

M. A. A., Nordin, N., Empaling, S., Amran, D. I., and

Supriyanto, E. (2017). User acceptance analysis of

hospital asset management system. In 2017 Interna-

tional Conference on Robotics, Automation and Sci-

ences (ICORAS), pages 1–5. IEEE.

Organization, W. H. et al. (2019). Who guideline: recom-

mendations on digital interventions for health system

strengthening: web supplement 2: summary of ﬁnd-

ings and grade tables. Technical report, World Health

Organization.

Organization, W. H. et al. (2020). Covid-19 weekly epi-

demiological update, 24 november 2020.

Oshitani, H., Kamigaki, T., and Suzuki, A. (2008). Major

issues and challenges of inﬂuenza pandemic prepared-

ness in developing countries. Emerging infectious dis-

eases, 14(6):875.

Pang, Z., Yang, G., Khedri, R., and Zhang, Y.-T. (2018).

Introduction to the special section: convergence of

automation technology, biomedical engineering, and

health informatics toward the healthcare 4.0. IEEE

Reviews in Biomedical Engineering, 11:249–259.

Pardeshi, V., Sagar, S., Murmurwar, S., and Hage, P.

(2017). Health monitoring systems using iot and rasp-

berry pi—a review. In 2017 international conference

on innovative mechanisms for industry applications

(ICIMIA), pages 134–137. IEEE.

Poniszewska-Maranda, A. and Kaczmarek, D. (2015). Se-

lected methods of artiﬁcial intelligence for internet of

things conception. In 2015 Federated Conference on

Computer Science and Information Systems (FedC-

SIS), pages 1343–1348. IEEE.

Qadir, Q. M., Rashid, T. A., Al-Salihi, N. K., Ismael, B.,

Kist, A. A., and Zhang, Z. (2018). Low power wide

area networks: a survey of enabling technologies, ap-

plications and interoperability needs. IEEE Access,

6:77454–77473.

Raveendran, A. and Jayadevan, R. (2020). Reverse quaran-

tine and covid-19. Diabetes & Metabolic Syndrome:

Clinical Research & Reviews, 14(5):1323–1325.

Richardson, P., Grifﬁn, I., Tucker, C., Smith, D., Oechsle,

O., Phelan, A., and Stebbing, J. (2020). Baricitinib

as potential treatment for 2019-ncov acute respiratory

disease. Lancet (London, England), 395(10223):e30.

Rodrigues, J. J., Segundo, D. B. D. R., Junqueira, H. A.,

Sabino, M. H., Prince, R. M., Al-Muhtadi, J., and

De Albuquerque, V. H. C. (2018). Enabling tech-

nologies for the internet of health things. Ieee Access,

6:13129–13141.

Serrano, M., Dang, H. N., and Nguyen, H. M. Q. (2018).

Recent advances on artiﬁcial intelligence and internet

of things convergence for human-centric applications:

internet of things science. In Proceedings of the 8th

International Conference on the Internet of Things,

pages 1–5.

Singh, R. P., Javaid, M., Haleem, A., and Suman, R. (2020).

Internet of things (iot) applications to ﬁght against

covid-19 pandemic. Diabetes & Metabolic Syndrome:

Clinical Research & Reviews.

Tang, Y.-W., Schmitz, J. E., Persing, D. H., and Stratton,

C. W. (2020). Laboratory diagnosis of covid-19: cur-

rent issues and challenges. Journal of clinical micro-

biology, 58(6).

Tanne, J. H. (2020). Covid-19: Fda panel votes to approve

pﬁzer biontech vaccine.

Tarouco, L. M. R., Bertholdo, L. M., Granville, L. Z., Ar-

biza, L. M. R., Carbone, F., Marotta, M., and De San-

tanna, J. J. C. (2012). Internet of things in healthcare:

Interoperatibility and security issues. In 2012 IEEE

international conference on communications (ICC),

pages 6121–6125. IEEE.

Thayyil, J., Kuniyil, V., and Cherumanalil, J. M. (2020).

Covid-19: digital contact tracing technologies and

ethical challenges. International Journal of Commu-

nity Medicine and Public Health, 7(7):2854.

Thilakarathne, N. N., Kagita, M. K., Gadekallu, T. R., and

Maddikunta, P. K. R. (2020). The adoption of ict pow-

ered healthcare technologies towards managing global

pandemics. arXiv preprint arXiv:2009.05716.

Williams, P. A. and McCauley, V. (2016). Always con-

nected: The security challenges of the healthcare in-

ternet of things. In 2016 IEEE 3rd World Forum on

Internet of Things (WF-IoT), pages 30–35. IEEE.

Zhang, Y., Qiu, M., Tsai, C.-W., Hassan, M. M., and

Alamri, A. (2015). Health-cps: Healthcare cyber-

physical system assisted by cloud and big data. IEEE

Systems Journal, 11(1):88–95.

Zhu, X. (2019). Case vi: Children’s hospital of shanghai: A

pioneer in smart healthcare. In Emerging Champions

in the Digital Economy, pages 195–210. Springer.

IoTBDS 2021 - 6th International Conference on Internet of Things, Big Data and Security

236