ArticlePDF Available

Abstract and Figures

Contagious disease pandemics present a significant threat worldwide in terms of both human health and economic damage. New diseases emerge annually and place enormous burdens on many countries. Additionally, using humans to handle pandemic situations increases the chances of disease spreading. Therefore, various technologies that do not directly involve humans should be employed to handle pandemic situations. The Internet of Drones (IoDT), artificial intelligence (AI), and blockchain are emerging technologies that have revolutionized the modern world. This paper presents a blockchain-based AIempowered pandemic situation supervision scheme in which a swarm of drones embedded with AI is engaged to autonomously monitor pandemic outbreaks, thereby keeping human involvement as low as possible. A use case based on a recent pandemic (i.e., COVID-19) is discussed. Two types of drone swarms are used to handle multiple tasks (e.g., checking face masks and imposing lockdowns). A lightweight blockchain is considered to handle situations in remote areas with poor network connectivity. Additionally, a two-phase lightweight security mechanism is adopted to validate the entities in the proposed scheme. A proof of concept is established using an experimental environment setup and dataset training. An analysis of the experimental results demonstrates the feasibility of the proposed scheme.
Content may be subject to copyright.
1536-1284/20/$25.00 © 2020 IEEE IEEE Wireless Communications • Accepted for Publication
1
AbstrAct
Contagious disease pandemics present a sig-
nificant threat worldwide in terms of both human
health and economic damage. New diseases
emerge annually and place enormous burdens
on many countries. Additionally, using humans to
handle pandemic situations increases the chances
of disease spreading. Therefore, various technolo-
gies that do not directly involve humans should be
employed to handle pandemic situations. The Inter-
net of Drones (IoDT), artificial intelligence (AI), and
blockchain are emerging technologies that have
revolutionized the modern world. This article pres-
ents a blockchain-based AI-empowered pandemic
situation supervision scheme in which a swarm of
drones embedded with AI is engaged to autono-
mously monitor pandemic outbreaks, thereby keep-
ing human involvement as low as possible. A use
case based on a recent pandemic (i.e., COVID-19)
is discussed. Two types of drone swarms are used
to handle multiple tasks (e.g., checking face masks
and imposing lockdowns). A lightweight blockchain
is considered to handle situations in remote areas
with poor network connectivity. Additionally, a two-
phase lightweight security mechanism is adopted
to validate the entities in the proposed scheme. A
proof of concept is established using an experimen-
tal environment setup and dataset training. An anal-
ysis of the experimental results demonstrates the
feasibility of the proposed scheme.
IntroductIon
Contagious disease pandemics are a glob-
al threat that affect not only human health but
also the economy. The world is constantly fac-
ing new diseases (e.g., COVID-19), which can
rapidly become a global threat [1]. Among the
contagious diseases, those that spread between
humans and from animals to humans are consid-
ered very dangerous. Handling pandemic situa-
tions in affected areas using human resources can
be extremely hazardous because the service pro-
viders face a high risk of infection. To minimize
risk, the combination of various technologies is
required to handle such situations.
Internet of Drone Things (IoDT) is an emerging
technology that has attracted significant attention
in both academia and industry. IoDT is a technol-
ogy that combines the Internet of Things, cloud/
edge computing, wireless communication, and so
on [2]. IoDT increases the quality of service (QoS)
by expanding the capabilities of data acquisition,
processing, and connectivity. It can perform crit-
ical missions (e.g., monitoring underground coal
mines) with higher accuracy than humans [3]. One
of the significant advantages of the IoDT is that it
improves the efficiency of performing missions in
remote areas that are dangerous for humans.
Artificial intelligence (AI) is another key tech-
nology that allows a robot, drone, or any machine
to think intelligently. AI and its sub-disciplines (e.g.,
machine learning) have revolutionized the world
of technology. AI covers a wide range of applica-
tions, such as autonomous vehicles, smart health-
care, and so on, and can enable the IoDT to act
intelligently. Based on these capabilities, the IoDT
combined with AI is a promising technology for
assisting in the monitoring of pandemic situations.
Blockchain is another prominent technology
that introduces trust into unknown environments
[4]. Blockchain is a distributed ledger that is shared
among the participants in a network, where each
participant holds a copy of the same ledger. No one
can alter the data once it is appended to the ledger.
Additionally, blockchain allows personal control over
data, meaning that different users can manage their
privacy settings. Furthermore, pairs of keys (i.e., pub-
lic keys) are used in the blockchain to manage user
identities to maintain pseudonymity [5]. In a pan-
demic situation, sensitive data (e.g., health data) are
collected from people that require both security and
privacy. Additionally, managing entities (e.g., identi-
ties) in the system requires seamless management.
Among recent works that have considered drones
for combating recent pandemics (e.g., COVID-19),
the authors of [6] presented a scheme in which data
were collected from wearable sensors on the bod-
ies of patients. They divided the affected area into
different zones to perform activities such as patient
identification and sanitization. However, they did not
address the security issues related to the data col-
lected by the system. The authors in [7] presented
a 6G-assisted and blockchain-supported unmanned
aerial vehicle (UAV)-swarm communication scheme
to address the COVID-19 pandemic situation. They
Anik Islam, Tariq Rahim, MD Masuduzzaman, and Soo Young Shin
A B-B
A I-E
C P S S
S U I  D 
ACCEPTED FROM OPEN CALL
The authors are with Kumoh National Institute of Technology. Soo Young Shin is the corresponding author.
Digital Object Identifier:
10.1109/MWC.001.2000429
This article has been accepted for inclusion in a future issue of this magazine. Content is final as presented, with the exception of pagination.
Authorized licensed use limited to: KUMOH NATIONAL INSTITUTE OF TECHNOLOGY. Downloaded on July 12,2021 at 00:35:39 UTC from IEEE Xplore. Restrictions apply.
IEEE Wireless Communications • Accepted for Publication 2
leveraged blockchain technology in their research,
and their primary concern was connectivity. How-
ever, they did not consider network scarcity in
remote areas in their scheme. Moreover, none of the
above-mentioned schemes performed experiments in
the real environment. After analyzing these previous
solutions, it is clear that a comprehensive scheme is
required that not only provides aid remotely, but also
provides security by keeping human intervention as
low as possible to reduce casualties.
This article presents an AI-empowered block-
chain-based supervision scheme in which the IoDT
is utilized to handle pandemic situations remotely
to enhance automation and reduce the risk of dis-
eases spreading in both urban and remote rural
areas, where network connectivity is scarce. The
main contributions of this article can be summa-
rized as follows:
A use case based on a recent pandemic (i.e.,
COVID-19) is discussed. Subsequently, a sys-
tem model is proposed to demonstrate the
applicability of the IoDT for addressing pan-
demic situations. The details of the proposed
scheme are then presented alongside a light-
weight blockchain and two-phase authentica-
tion mechanism.
• A discussion is presented to highlight the chal-
lenges related to opportunities for conducting
additional research in the future.
A proof of concept (PoC) is established to
demonstrate the feasibility of the proposed
scheme. A deep learning approach is present-
ed to determine whether individuals are wear-
ing a facemask. A detailed implementation with
dataset acquisition and performance evaluation
is presented in this article. Following the detec-
tion of subjects using AI-empowered activities,
real-time elevated body temperature (EBT) data
were collected using FLIR thermal cameras to
detect elevated skin temperature (EST). The
performance was measured based on preci-
sion, sensitivity, F1-score, F2-score, and dice-co-
efficient. An experimental environment was
established to demonstrate the performance
of the proposed scheme for drones after apply-
ing security mechanisms based on service exe-
cution times (i.e., authentication and security
tasks). A blockchain network was established
on top of a multichain containing 15 mining
nodes, and the performance was measured
based on the block transmission rate and ser-
vice execution time (i.e., block generation).
The remainder of this article is organized as fol-
lows. The following section presents a use case
containing a recent pandemic situation. We then
present an overview of the proposed system. Fol-
lowing that the detailed functionality of the pro-
posed scheme is presented. We then depict the
security challenges and protection mechanisms. A
discussion of the performance evaluation is then
presented. Following that we discuss the challeng-
es and opportunities for future research. Finally,
concluding remarks are drawn.
use cAse: covId-19
A disease known as coronavirus disease 2019
(termed as “COVID-19”) has recently spread world-
wide and has had a disastrous effect on human
health [8]. COVID-19 was first detected in Decem-
ber 2019 in China, and it continues to spread
worldwide. Johns Hopkins University’s COVID-19
dashboard has indexed more than 30 million con-
firmed cases from around the world, resulting in
1,647,108 deaths as of December 2020. COVID-
19 spreads between people in close contact, and
the culprits behind the spread are the droplets pro-
duced when sneezing, coughing, and talking. As
the droplets are relatively heavy, the disease has
been spreading by touching an infected surface
rather than traveling via air. Common symptoms
of COVID-19 include fatigue, fever, shortness of
breath, and so on [9]. Currently, there are no accu-
rate medicines available for directly treating COVID-
19. To avoid infection, specialists recommend
handwashing, maintaining physical distance, cover-
ing the face when coughing or sneezing, wearing
facemasks, and obeying quarantining rules [10].
overvIew of system ArchItecture
A drone-assisted pandemic situation supervision
scheme (termed as “BPD”) is proposed, in which
the users’ confidential data are stored in block-
chain and are retrieved from it whenever neces-
sary, as shown in Fig. 1. In the BPD, a multi-type
swarm of drones is considered. The primary com-
ponents of BPD can be summarized as follows.
Drone: In the BPD, two different types of
drones were used.
Surveillance Drone (SD): The primary tasks
of an SD involve checking the temperatures and
facemasks, calculating social distancing, performing
disinfection, imposing lockdowns, and spreading
awareness.
Bumblebee Drone (BD): A BD stays close to
users and assists them by performing various tasks.
The primary tasks performed by BDs include health
data collection, supplying emergency equipment,
collecting samples from patients, and delivering
products in lockdown areas.
Server: The BPD maintains a hierarchy which is
defined as follows.
Dew Server: Dew Computing (DC) is a new
paradigm that enables local computing considering
minimal network connectivity (i.e., offline) [11]. In
the BPD, the dew server is maintained by drones
and facilitates their computation capabilities. The
dew server contains collected data (e.g., health
data), user identities, training data for performing
surveillance, and so on.
Edge Server: Edge computing is a promising
technology that brings computational facilities at
the edge of the network to enhance QoS [12].
The edge server serves as a gateway allowing the
dew server to offload tasks and data without facing
latency or energy consumption issues.
Cloud Server: An edge server is connected to
the cloud through the Internet. The cloud server
acts as a miner.
Blockchain: In the proposed scheme, the BPD
considered a consortium blockchain network. The
main task of the blockchain is to provide secure
data management. BPD utilizes the following two
types of chains in the blockchain.
Light Chain: The light chain is only used by the
dew server. This chain contains limited spatio-tem-
poral data to assist drones in performing different
tasks (e.g., detecting citizens breaking rules).
Main Chain: The main chain holds all the data
related to citizens, ranging from basic information
to COVID-19-related data. Edge and cloud servers
Dew Computing is
a new paradigm that
enables local comput-
ing considering minimal
network connectivity
(i.e., offline). In the BPD,
the dew server is main-
tained by drones and
facilitates their compu-
tation capabilities. e
dew server contains
collected data (e.g.,
health data), user iden-
tities, training data for
performing surveillance,
and so on.
This article has been accepted for inclusion in a future issue of this magazine. Content is final as presented, with the exception of pagination.
Authorized licensed use limited to: KUMOH NATIONAL INSTITUTE OF TECHNOLOGY. Downloaded on July 12,2021 at 00:35:39 UTC from IEEE Xplore. Restrictions apply.
IEEE Wireless Communications • Accepted for Publication
3
hold the main chain and both work as miners in
the network. Therefore, each node holds a full
copy of the data.
In the initial phase, citizens register themselves
in the blockchain network by providing their basic
and biometric information. Additionally, citizens can
define the roles that can access their data. When
a pandemic occurs, authorities release drones in
the field. SDs roam the target area and inform
authorities and provide warnings to citizens for any
inconsistency. BDs are dedicated to assisting in dan-
gerous tasks, such as monitoring infected citizens,
by staying near them, and so on. In this manner, a
pandemic situation can be supervised by BPD.
drone-AssIsted blockchAIn-bAsed
PAndemIc sItuAtIon suPervIsIon
In this section, the functionality of the proposed
BPD system is described in detail. This discussion
is divided into several subsections.
outdoor ActIvIty hAndlIng
This section presents the major tasks performed
by the SDs. Prior to deploying SDs for surveil-
lance, authorities prepare a light chain for the
dew server maintained on the SDs. Every SD
is assigned to a zone, where zones are divided
based on geographic areas. The boundaries of
the zones form rectangular spaces defi ned by spa-
tial information (i.e., latitude and longitude). A
dataset is generated based on information from
people in each zone. This dataset includes both
basic and biometric information (i.e., facial data).
The details of the tasks are described as follows.
Face Mask Check: When SDs are deployed,
they continuously check for people roaming
outside. When an SD identifies a person, it first
checks if that person is wearing a facemask. If the
person is not wearing a mask, it warns the per-
son based on the relevant rules. BPD maintains a
threshold for the number of warnings Wth. After
surpassing Wth, a penalty is added to the block-
chain network for the detected person.
Temperature Check: When an SD detects a
person, after checking for a mask, it switches to
a thermal camera to estimate the temperature
of the target individual. A threshold temperature
value Tth represents abnormality. If the tempera-
ture is above Tth, then the SD notifi es authorities
with the basic information of the target individual.
If the SD cannot detect a person’s basic informa-
tion, then it shares spatial information with bio-
metric information (i.e., face data).
FIGURE 1. Blockchain-based IoDT assisted pandemic situation supervision scheme with the integration of AI.
Dew
Server
Blockchain
(Light Chain)
Disinfection
Imposing
Lockdown
Spreading
Awareness
Temperature
Check
Face mask
Check
Social
Distancing
Health Data
Collection
Emergency
Equipment
Supply
Sample
Collection
Delivery
Necessary
items
Edge Server
Blockchain
(Main Chain)
Edge Server
Blockchain
(Main Chain)
BS
BS
Ground Control Station
(GCS)
Edge Server
Blockchain
(Main Chain)
Cloud
Blockchain
(Light Chain)
Dew
Server
Dew
Server
Surveillance Drones
Surveillance Drones
Bumblebee Drones
Actions
Actions
Actions
Allotted Red Zones
Allotted Red Zones
Allotted Red Zones
Blockchain
(Main Chain)
Blockchain
(Light Chain)
hash (block n-1)
timestamp
nonce
data representation
nonce
data representation
Block n
Block Structure
hash (block n)
timestamp
nonce
data representation
nonce
data representation
Block n+1
Markle Root
Hash-01 Hash-23
Hash-0 Hash-1 Hash-3Hash-2
DATA-1 DATA-2 DATA-3
ID Sender Loc Data Datetime
2FF... 4FFB.. 20.6,84.2 B#36#H 1607501610
18D... 2E39.. 35.9,98.6 B#37#H 1607501632
DATA-0
This article has been accepted for inclusion in a future issue of this magazine. Content is final as presented, with the exception of pagination.
Authorized licensed use limited to: KUMOH NATIONAL INSTITUTE OF TECHNOLOGY. Downloaded on July 12,2021 at 00:35:39 UTC from IEEE Xplore. Restrictions apply.
IEEE Wireless Communications • Accepted for Publication 4
Social Distance Check: When an SD detects
more than one person in the same location, it
checks the distance between people. There is a
threshold value Dth representing a safe distance
(e.g., 1 m). If the target individuals do not maintain
Dth, then the SD warns them based on the relevant
rules. BPD maintains a threshold number of warn-
ings W’
th. After surpassing W’
th, a penalty is added to
the blockchain network for the detected individuals.
Lockdown Imposing: It is assumed that hand-
band devices are given to quarantined individuals
to monitor their movement and health status. Each
handband contains health sensors (e.g., tempera-
ture) and a global positioning system (GPS). When
a person is quarantined, a geofence is created at
their location. When an SD detects a person, it
can check their location based on GPS and match
their location to the allotted geofenced area. If any
inconsistencies are identified, the SD notifies the
authorities. Additionally, if lockdowns are imposed
on everyone, the SD checks if there are any peo-
ple roaming outside. If anyone is found, the SD first
attempts to identify the basic information of the tar-
get individuals based on their biometric data (i.e.,
face data). If a person hides their face, then a snap-
shot of the person is shared with the authorities
along with the corresponding spatial information.
Disinfection: As discussed previously, COVID-
19 spreads through droplets produced by cough-
ing, sneezing, or talking. As the droplets are
relatively heavy, they tend to remain on the ground
or other objects. Therefore, touching infected
areas can spread the disease, meaning disinfection
is essential. When an SD is deployed, it periodically
disinfects suspicious areas.
Spreading Awareness: Many new diseases (e.g.,
COVID-19) have become pandemics because there
are no vaccines available initially. Moreover, based
on the spread of false information, people tend to
get confused and panicked. Additionally, in rural
areas, people cannot receive enough information
because of the limited number of communication
channels, which accelerates the spread of diseases.
If accurate information can be shared from legiti-
mate sources, then the spread of the disease can be
controlled. Therefore, BPD also helps spread accu-
rate information using drones. In BPD, SDs continu-
ously spread information through speakers.
AssIstIng In PublIc servIces
This section presents the major tasks performed
by the BDs. Each task is described in the subsec-
tions below.
Health Data Collection: In BPD, body sensors are
provided to potentially infected individuals. These sen-
sors can directly share data from the wearer’s body
(e.g., body temperature) with the server. However,
people in remote areas typically face connectivity
issues. Additionally, communicating with the server
is highly energy-consuming. Therefore, BDs are used
to establish communication with sensors and peri-
odically collect patient health data. Before providing
body sensors to patients, a trust token Tq is gener-
ated so that a BD can easily establish secure com-
munications. Each person has a private key PR and
a corresponding public key PK. When handing out
sensors, corresponding location information PK, Tq,
latitude, longitude〉〉 is maintained in the blockchain.
Before collecting data, a secure channel is established
using the public key of the patient. Before establishing
the secure channel, an authentication and authoriza-
tion process is conducted containing a cuckoo filter
and digital signature algorithm to verify the sender.
If a sender fails to verify their identity, BD adds the
sender in a block list b after a threshold number of
attempts Ab. When senders reaches Ab, they can no
longer send data. After establishing a secure chan-
nel, a BD’s identity is validated using Tq. After valida-
tion is completed, the BD replaces the previous Tq
with the new Tq
new so that attackers cannot predict
Tq to perform cyberattacks (e.g., spoofing). Finally,
the data are shared between the patient and BD by
encrypting the data using Tq
new. After collecting data,
each drone shares these data to the nearest server. In
BPD, each server can act as a miner; data are mined
in a round-robin manner. Each miner has an equal
chance to mine. If miners try to mine outside their
turn, others can discard them by giving a vote. After
arrival in a server (e.g., edge server), the data is added
to a queue Qd. When given the chance, a miner
pulls data from Qd and proposes to other miners.
Other miners then check the validity of the proposal
alongside a timestamp that is added to the data. After
obtaining consent from other miners, data is added to
the network. If any changes are made, they have to
go through the same validation process. No chang-
es are allowed without the consent of other miners.
Thus, data are securely stored in the blockchain. The
structure of data is provided in Fig. 1.
Emergency Equipment Supply: Affected
patients sometimes require emergency equipment
(e.g., oxygen cylinders). However, having people
deliver such equipment can be dangerous due to
being contagious. When collecting and processing
health data, if any equipment is required, the BD
notifies the relevant authorities. The authorities can
then send the necessary equipment using the BDs.
Sample Collection: For COVID-19, not all types
of data can be collected through sensors (e.g., saliva
data). However, these data can be very important for
the analysis of the current status of patients. As these
samples cannot be collected using body sensors,
a manual collection process is required. However,
the use of people to collect samples from patients is
highly risky. To solve this problem, BPD uses BD to
collect samples from patients. BDs provide sample
collection kits to patients. After providing the sample,
the patient then attaches the kit to the BD.
Delivery of Daily Necessary Goods: During
a pandemic, lockdowns are imposed to slow the
spread of the disease by reducing contact between
individuals. During a lockdown, nobody can go
outside to purchase the necessary products. When
a user places an order online, a BD can assist the
user by delivering products to them.
securIty AnAlysIs
This section presents a security analysis of the pro-
posed BPD. The proposed BPD considers a threat
analysis model referred to as “STRIDE (Spoofing,
Tampering, Repudiation, Information Disclosure,
Denial of Service, Elevation of Privilege)” to analyze
potential threats and demonstrate the security feasibil-
ity against these threats. The discussion is as follows.
Spoofing (Intention: Falsify the Identity): The
proposed BPD adopts a digital signature scheme in
the data sharing process of sensors. It performs val-
idation before receiving data, which makes it tech-
nically challenging to transmit data with a forged
identity in the network.
Affected patients
sometimes require
emergency equipment
(e.g., oxygen cylinders).
However, having peo-
ple deliver such equip-
ment can be dangerous
due to being conta-
gious. When collecting
and processing health
data, if any equipment
is required, the BD
notifies the relevant
authorities. e author-
ities can then send the
necessary equipment
using the BDs.
This article has been accepted for inclusion in a future issue of this magazine. Content is final as presented, with the exception of pagination.
Authorized licensed use limited to: KUMOH NATIONAL INSTITUTE OF TECHNOLOGY. Downloaded on July 12,2021 at 00:35:39 UTC from IEEE Xplore. Restrictions apply.
IEEE Wireless Communications • Accepted for Publication
5
Tampering (Intention: Modify the Data): The
proposed BPD includes blockchain technology in
the system model to maintain data security. In BPD,
two chains (i.e., main and light chains) are utilized to
handle data. To maintain integrity, blockchain uses
a Markle tree and any changes in the data cause a
break in the chain of blocks that can be regenerated
with the consent of the miners. Thus, changes can
be detected, and actions can be taken accordingly.
Repudiation (Intention: Denial of Any Previ-
ous Activity): All the data is stored in blockchain
with the sender’s identity and signature. Because it
is immutable, nobody can change the information
after it has been added to the blockchain. Thus,
once any action is stored in the blockchain, it can-
not be denied.
Information Disclosure (Intention: Unau-
thorized Information Disclosure): In BPD, only
enrolled entities can enter the network and access
data. The identity of each entity is stored in the
blockchain, which helps to perform the two-phase
verification method (i.e., the combination of the
cuckoo filter and digital signature algorithm). Thus,
information is only available for valid entities.
Denial of Service (Intention: Service Unavail-
ability for Legitimate Users): Because BPD per-
forms a two-phase verification process, if any
entity fails to verify itself with a threshold number
of attempts, the BPD adds that entity into a block
list to prevent further communication. Thus, illegal
entities are filtered so that BPD can provide ser-
vices to valid entities without interruptions.
Elevation of Privilege (Intention: Unautho-
rized Access): In BPD, each entity’s identity is
stored in the blockchain. Moreover, each entity
can define roles that can access specific data while
registering the system. Before accessing any data,
BPD performs validation and verification based
on identity and roles. Thus, unauthorized access is
prevented in BPD.
PerformAnce evAluAtIon
This section discusses the environmental setup for
the experiments and the analysis of results from
these experiments.
envIronment setuP
A PoC was established to demonstrate the feasibil-
ity of the proposed BPD. In our experiments, one
DJI Mavic 2 Pro was used as the SD, equipped
FIGURE 2. Dataset training: a) network architecture of the default YOLOv3-tiny model; b) real-time train-
ing chart of the deep neural network.
Convolutionallayer
3*3*16
Convolutionallayer
3*3*32
Convolutionallayer
3*3*256
Convolutionallayer
3*3*64
Convolutionallayer
3*3*128
Input image
428*428
Convolutionallayer
3*3*512
Convolutionallayer
3*3*1024
YOLOv3Tiny
Architecture
Maxpooling
Maxpooling
Maxpooling
Maxpooling
Maxpooling
Maxpooling
Maxpooling
(a) (b)
TABLE 1.Network parameters used for YOLOv3-Tiny.
Network parameters Configuration values
Learning rate () 428 428
Optimizer Stochastic gradient descent (SGD)
Momentum 0.9
Batch size 32
Iterations (t) 5,000
In BPD, only enrolled
entities can enter the
network and access
data. e identity of
each entity is stored in
the blockchain, which
helps to perform the
two-phase verifica-
tion method (i.e., the
combination of the
cuckoo filter and digital
signature algorithm).
us, information is
only available for valid
entities.
This article has been accepted for inclusion in a future issue of this magazine. Content is final as presented, with the exception of pagination.
Authorized licensed use limited to: KUMOH NATIONAL INSTITUTE OF TECHNOLOGY. Downloaded on July 12,2021 at 00:35:39 UTC from IEEE Xplore. Restrictions apply.
IEEE Wireless Communications • Accepted for Publication 6
with a Jetson TX2 module. Two Parrot Bebop 2
were used as the BD and equipped with a Jetson
Nano module. We selected an FLIR thermal cam-
era for measuring the temperatures of individu-
als based on the EBT. The EST data collected by
the FLIR thermal camera were used to detect heat
radiation differences between surfaces with tem-
peratures ranging from 32°C to 42.5°C (89.6°F
to 108.5°F). Multichain (https://www.multichain.
com/) was used as a blockchain platform and 15
local computers were used to create a blockchain
network by operating as miners. Although Multi-
Chain supports the proof of work (PoW) as a con-
sensus algorithm, we ignored PoW by adjusting the
consensus parameter and validated it by applying
the round-robin algorithm. Elliptic-curve cryptog-
raphy (161 bit key) and the advanced encryption
standard (128 bit key) were used for asymmetric
and symmetric encryption, respectively.
dAtAset PrePArAtIon And trAInIng
A pre-trained “you only look once” (YOLO) model
(i.e., YOLOv3-Tiny) was used in our experiments
for performing deep learning (DL)-based mask
detection. Figure 2a presents the network archi-
tecture of the default YOLOv3-Tiny model, which
consists of seven convolutional layers and six max
pooling layers. An activation function such as a
rectified linear unit is used to avoid the gradient
vanishing problem, resulting in better sparsity [13,
14]. In this study, the coordinate error weight was
set to 5, and the network was trained using a data-
set acquired from the Kaggle (https://www.kaggle.
com/andrewmvd/face-mask-detection) containing
825 images with both Mask and No Mask class-
es. These two classes were considered for training
purposes, where 20.00 percent and 80.00 percent
of the data were used for testing and training,
respectively. Table 1 lists the network parameters
and configuration values used to train the model.
Figure 2b shows a real-time training stage for the
DL model implemented where the red line reflects
the mean average precision (mAP). The mAP is
a metric for localization and classification (object
detection) when dealing with DL models. It is the
average precision (AP) at each iteration, for exam-
ple, in Fig. 2b, after 1000 iterations the AP is 75
percent, and so on; the mAP is obtained after set-
ting a certain iteration. The blue line is the average
loss as a regression loss, showing the minimization
of the errors as a loss function. In particular, it is
the mean square error (MSE) as the average of the
squared difference between the predictions and
actual observations for the detection. A high mAP
and low average loss indicate that the model has
stable prediction and detection.
AnAlysIs
The detection results generated by the
YOLOv3-Tiny model for the Mask and No Mask
classes are presented in Fig. 3a. The results in Fig.
3a were generated using the best weights identi-
fied during the training phase.
Table 2 presents the detection performance for
the Mask and No Mask classes in terms of the pre-
cision, sensitivity, F1-score, F2-score, and dice-co-
efficient. In Table 2, it can be observed that a high
precision, F1-score, F2-score, and dice-coefficient
are achieved for both classes (i.e., Mask and No
Mask). Additionally, relatively low sensitivity values
reflect the robustness of the model.
Figure 3b presents the detection outputs gen-
erated by the thermal camera implementations
for both the Mask and No Mask classes. Figure 3c
presents a representative depiction of the imple-
mentation of social distancing measurement using
the Euclidean distance concept, where two people
in the Mask class are shown along with the com-
puted social distancing threshold.
Figure 4 presents experiments that were per-
formed using the security mechanisms. Figure
4a illustrates the authentication scheme that was
applied to both the SDs and BDs. In Fig. 4a, it
can be observed that the proposed scheme out-
performs previous authentication schemes (i.e.,
sequential search, bisection search, and bloom fil-
ter). Figure 4b presents the security actions that
were applied during communication. Both the SDs
and BDs utilize hybrid encryption (i.e., a combi-
nation of public and private encryption), result-
ing in rapid encryption and decryption. Figure 4c
presents the block transmission rate in the block-
chain network containing the blocks appended to
the main chain. In Fig. 4c, the block transmission
rate decreases with an increase in the number of
mining nodes because more time is required to
validate the blocks. Figure 4d presents the block
generation time (time required to obtain permis-
FIGURE 3. Experimental results obtained for outdoor activities: a) detection results generated by YOLOv3-ti-
ny model for Mask and No Mask; b) thermal images generated after detection of mask and no mask
showing human body temperature range; c) social distance checking including masks detection.
(a) (b) (c)
This article has been accepted for inclusion in a future issue of this magazine. Content is final as presented, with the exception of pagination.
Authorized licensed use limited to: KUMOH NATIONAL INSTITUTE OF TECHNOLOGY. Downloaded on July 12,2021 at 00:35:39 UTC from IEEE Xplore. Restrictions apply.
IEEE Wireless Communications • Accepted for Publication
7
sion to create a block). In Fig. 4d, larger packets
require more processing time with an increase in
the number of mining nodes because the waiting
time increases based on the accumulation of deci-
sions from additional mining nodes.
oPen chAllenges
This section presents the challenges and future
opportunities related to the proposed BPD.
Data Privacy: In the BPD, people share sensitive
information (e.g., health data) through a network.
This information is private and should not be exposed
to outsiders; therefore, a privacy scheme is required
to ensure the protection of such data. Moreover,
separate penalty management is necessary where
the citizens’ penalty information can be handled with
privacy and accuracy. The relevant information can
be accessed by different hierarchies of people (e.g.,
government works and service providers). Access
control is required for privacy management so that
users can determine who can access their informa-
tion. Moreover, AI can be adopted to enhance the
security and privacy of data that is collected from
people [15]. However, managing different levels of
access control is a very complicated task.
Battery Health: In the BPD, drones are cate-
gorized into two groups: SDs and BDs. Both SDs
and BDs perform a variety of tasks, as discussed in
the previous section. A large amount of energy is
required to execute these tasks. Additionally, not
all drones have sufficient battery power to provide
services for a long duration of time. Therefore, a
scheme for recharging drones or harvesting ener-
gy is required to improve the QoS.
Flight Management: To perform various tasks,
both SDs and BDs fly through the air. Additional-
ly, drones collect data and samples directly from
multiple patients. Therefore, proper flight planning
is required to avoid the collision of the drones.
Furthermore, an efficient trajectory planning algo-
rithm is required for drones to effectively collect
data and samples from patients.
Swarm Management: Employing swarms in mis-
sions can be beneficial in terms of improving QoS.
In a swarm, drones can distribute tasks among them-
selves to reduce the burden on each drone. Addi-
tionally, a swarm can cover a larger area compared
to a single drone. However, distributing swarms
poses another challenge, especially in densely pop-
ulated areas. The efficient distribution of swarms
can extend the service time and enhance QoS. A
scheme is required for allocating swarms in different
zones. In a swarm, frequent messaging is required to
maintain consistency between the drones that can
increase the network overhead. Therefore, a com-
pression algorithm for data packets and a schedul-
ing algorithm are required to reduce the network
overhead. Additionally, a medium access control
protocol for a swarm of drones is required to avoid
data collisions.
concludIng remArks
In this article, a blockchain-based IoDT-assisted pan-
demic situation supervision scheme was proposed
with incorporated AI technology. First, a use case of
the current global pandemic (i.e., COVID-19) was
discussed in detail. Subsequently, a system model
illustrating the applicability of the IoDT to such situa-
tions was presented. To handle various situations, a
combination of dew and edge computing were con-
sidered to extend the reach of the proposed system
in remote areas. The blockchain was divided into
two chains (i.e., main and light chains) to handle the
issue of network scarcity. Additionally, a lightweight
authentication scheme was developed to reduce the
burden on IoDT. An experimental environment was
established to demonstrate the effectiveness of the
proposed scheme. Further, a DL-based approach
was adopted to autonomously handle pandemic
situations. Research challenges were discussed, and
future directions that will be considered in the exten-
sions of this study were identified.
Acknowledgment
This work was supported by Priority Research
Centers Program through the National Research
Foundation of Korea (NRF) funded by the Min-
istry of Education, Science and Technology
(2018R1A6A1A03024003).
This research was supported by the MSIT (Min-
istry of Science and ICT), Korea, under the Grand
Information Technology Research Center support
program (IITP-2021-2020-0-01612) and super-
vised by the IITP (Institute for Information & com-
munications Technology Planning & Evaluation).
references
[1] S. Bekeschus et al., “Gas Plasma Technology — An Asset to
Healthcare During Viral Pandemics Such as the Covid-19
Crisis?” IEEE Trans. Radiation and Plasma Medical Sciences,
vol. 4, no. 4, 2020, pp. 391–99.
[2] A. Nayyar, B.-L. Nguyen, and N. G. Nguyen, “The Internet
of Drone Things (Iodt): Future Envision of Smart Drones,”
Proc. First Int’l. Conf. Sustainable Technologies for Compu-
tational Intelligence, A. K. Luhach, J. A. Kosa, R. C. Poonia,
X.-Z. Gao, and D. Singh, Eds. Singapore: Springer Singapore,
2020, pp. 563–80.
[3] A. Mukherjee, N. Dey, and D. De, “Edgedrone: Qos Aware
MQTT Middleware for Mobile Edge Computing in Oppor-
tunistic Internet of Drone Things,” Computer Commun., vol.
152, 2020, pp. 93–108.
[4] Y. Jiang, Y. Zhong, and X. Ge, “Smart Contract-Based Data
Commodity Transactions for Industrial Internet of Things,”
IEEE Access, vol. 7, 2019, pp. 180 856–66.
[5] S. Zheng et al., “Smart Contract-Based Spectrum Sharing
Transactions for Multi-Operators Wireless Communication
Networks,” IEEE Access, vol. 8, 2020, pp. 88 547–57.
[6] A. Kumar et al., “A Drone-Based Networked System and
Methods for Combating Coronavirus Disease (Covid-19)
Pandemic,” Future Generation Computer Systems, vol. 115,
2021, pp. 1–19.
[7] R. Gupta et al., “Blockchain-Envisioned Softwarized
Multi-Swarming UAVs to Tackle Covid-i9 Situations,” IEEE
Network, 2020, pp. 1–8.
[8] Q. Pham et al., “Artificial Intelligence (AI) and Big Data for
Coronavirus (Covid-19) Pandemic: A Survey on the State-of-
the-Arts,” IEEE Access, vol. 8, 2020, pp. 130 820–39.
[9] M. N. Islam and A. K. M. N. Islam, “A Systematic Review
of the Digital Interventions for Fighting Covid-19: The Ban-
gladesh Perspective,” IEEE Access, vol. 8, 2020, pp. 114
078–87.
TABLE 2. Performance results of the YOLOv3-Tiny
for the detection of face mask and no mask.
Performance metrics
Percentage values (%)
Mask No mask
Precision 95.18 94.82
Sensitivity 89.74 90 .14
F1-score 91.4 6 91.01
F2-score 91.0 3 92.66
Dice-coefficent 0.91 0.89
In a swarm, frequent
messaging is required
to maintain consistency
between the drones
that can increase the
network overhead.
erefore, a com-
pression algorithm for
data packets and a
scheduling algorithm
are required to reduce
the network overhead.
Additionally, a medium
access control protocol
for a swarm of drones
is required to avoid
data collisions.
This article has been accepted for inclusion in a future issue of this magazine. Content is final as presented, with the exception of pagination.
Authorized licensed use limited to: KUMOH NATIONAL INSTITUTE OF TECHNOLOGY. Downloaded on July 12,2021 at 00:35:39 UTC from IEEE Xplore. Restrictions apply.
IEEE Wireless Communications • Accepted for Publication 8
[10] J. Yawney and S. A. Gadsden, “A Study of the Covid-19
Impacts on the Canadian Population,” IEEE Access, vol. 8,
2020, pp. 128 240–49.
[11] P. P. Ray, “An Introduction to Dew Computing: Definition,
Concept and Implications,” IEEE Access, vol. 6, 2018, pp.
723–37.
[12] H. Lin et al., “A Survey on Computation Offloading Model-
ing for Edge Computing,” J. Network and Computer Applica-
tions, vol. 169, 2020, p. 102781.
[13] S. A. Hassan, T. Rahim, and S. Y. Shin, “Real-Time UAV
Detection Based on Deep Learning Network,” Proc. 2019
Int’l. Conf. Information and Commun. Technology Conver-
gence (ICTC), IEEE, 2019, pp. 630–32.
[14] T. Rahim, M. A. Usman, and S. Y. Shin, “A Survey on Contem-
porary Computer-Aided Tumor, Polyp, and Ulcer Detection
Methods in Wireless Capsule Endoscopy Imaging,” Computer-
ized Medical Imaging and Graphics, vol. 85, 2020, p. 101767.
[15] L. Xiao et al., “A Secure Mobile Crowdsensing Game with
Deep Reinforcement Learning,” IEEE Trans. Information
Forensics and Security, vol. 13, no. 1, 2018, pp. 35–47.
bIogrAPhIes
Anik islAm [M’21] has completed his Ph.D. degree in IT Con-
vergence Engineering from the Wireless and Emerging Network
System Laboratory (WENS Lab), at Kumoh National Institute
of Technology (KIT), South Korea. Currently, he is working as
a postdoctoral research fellow in the WENS Lab, at KIT, South
Korea. Earlier, he received his M.Sc. and B.Sc. both from Amer-
ican International University-Bangladesh. His major research
interests include blockchain, Internet of Things, unmanned vehi-
cles, Social Internet of Things, dew computing, edge computing,
and distributed system.
TAriq r Ahi m [S’20] completed his doctorate (Ph.D.) degree
majoring in IT convergence engineering in 2021 from WENS
Lab, Kumoh National Institute of Technology (KIT), South Korea.
Currently, he is working as a postdoctoral fellow and researcher
at the ICT-CRC, KIT, South Korea. His research interests mainly
include image processing, medical image analysis, deep learn-
ing, video processing, and quality of services of high frame rate
videos.
mD mAsu Duzz AmAn [S’20] is currently pursuing his Ph.D. in
IT convergence engineering from Wireless and Emerging Net-
work System Laboratory (WENS Lab), at Kumoh National Insti-
tute of Technology, Gumi, South Korea. Earlier, he received his
B.Sc. and M.Sc. degrees in computer science in 2013 and 2015,
both from American International University-Bangladesh. His
major research interests include blockchain, Internet of Things,
unmanned aerial vehicle, edge computing, deep learning, cryp-
tography, and network security.
soo Young s hin [M’07, SM’17] received his Ph.D. degree
in electrical engineering and computer science from Seoul
National University on 2006. He was with WiMAX Design Lab,
and Samsung Electronics, Suwon, South Korea from 2007 to
2010. He joined the School of Electronics, Kumoh National
Institute of Technology, Gumi, South Korea in 2010 as full-time
professor. He is currently an associate professor. He was a
post doc. researcher at the University of Washington, USA in
2007. In addition, he was a visiting scholar at the University of
the British Columbia, Canada in 2017. His research interests
include 5G/6G wireless communications and networks, signal
processing, Internet of Things, mixed reality, drone applica-
tions, and so on.
FIGURE 4. Experimental results performed in the IoDT and blockchain: a) service executing time for authenticating drones; b) service
executing time for executing security tasks in drones; c) block transmission rate over observed time; d) service executing time of
block for getting validated and getting added in the network.
(a) (b)
(c) (d)
This article has been accepted for inclusion in a future issue of this magazine. Content is final as presented, with the exception of pagination.
Authorized licensed use limited to: KUMOH NATIONAL INSTITUTE OF TECHNOLOGY. Downloaded on July 12,2021 at 00:35:39 UTC from IEEE Xplore. Restrictions apply.
... Previously, Bangladesh's economy relied solely on agriculture, but as time passed, new technology entered every aspect of the economy [7]. Various sectors use automation and control technologies, such as big data, blockchain, and IoT. ...
... Overall, the broad use of AI and BT have a bright possibility in Bangladesh, including ride-sharing, natural language processing (NLP) for Bengali, chatbots, hotel and ticket booking, real-time mapping, and more. Bangladesh will have a prosperous future if AI technologies are properly integrated since 34% of Bangladesh's youth are now interested in technology [7]. Before using AI technology, the Bangladeshi government needs to undertake considerable preparations. ...
... Furthermore, AI is a strategic asset for organizational performance and competitiveness in small and medium-sized businesses (SMEs) [7]. According to the study, adopting BT is accepting and using AI to provide services such as manufacturing, order reservation, and payment. ...
Article
Full-text available
This study investigates the variables affecting the adoption of blockchain technology (BT) among small and medium-sized enterprises (SMEs) with the application of artificial intelligence (AI) via the mediating lens of risk-taking behavior. As an initial sample, 150 owners/top managers from 150 SMEs (one informant from each) in Dhaka, Bangladesh, were chosen. A stratified random sample was employed for this cross-sectional study. Applying structural equation modeling, the combined influence of internal and external variables influencing the intention to adopt BT is explored. Results show that: (1) knowledge of artificial intelligence has a positive and significant effect on the adoption of blockchain technology; (2) the relevant advantage of artificial intelligence has a positive and significant effect on the adoption of blockchain technology; (3) perceived ease of use of artificial intelligence has a positive and significant effect on the adoption of blockchain technology ; (4) risk-taking behavior mediates the relationship between knowledge of artificial intelligence and adoption of blockchain technology; (5) risk-taking behavior does not mediate the relationship between relevant advantage and perceived ease of use of artificial intelligence with the adoption of blockchain technology. The current study is one of the few empirical investigations relating to SMEs using artificial intelligence and blockchain technologies for business operations. The study's limitations are the small sample size and use of a single informant. However, the findings on the adoption of blockchain technology have applications for boosting the competitiveness of SMEs. This study's originality stems from two factors: the novelty of blockchain technology and its potential to upend SMEs' conventional mode of operation. It highlights the need to consider the key variables affecting SMEs' adoption of blockchain technology with artificial intelligence.
... Since the battery capacity of the UAV is limited, it is critical to research how to reduce the UAV's energy consumption so that the wireless network's connection time may be extended. In some of the research works, the authors assumed that the UAV has sufficient energy for completing the given task for secure data collection [15,16] whereas in [17] reduce the energy usage of the communication by finding an optimized trajectory path using successive convex approximation technique for a mobile relay network [18]. In [19] the placement of the UAV optimization and performance analysis was studied to understand various characteristics of UAV enabled base station. ...
... The problem can be formulated as (16) c2 : u(0) = u I , u(T) = u F (17) c3 : E ET (h uav ) ≥E TH d 2 (18) The constraints for the problem are as follows: For simulation, E ET (h uav ) must be greater than the GN threshold energy (E TH ) multiplied by d 2 , which in turn is h 2 / sin 2 θ where θ is the elevation of the UAV (18). The velocity is assumed to be at the maximum (16) and u I and u F are the initial and final locations of the UAV to complete the mission (17). ...
... The problem can be formulated as (16) c2 : u(0) = u I , u(T) = u F (17) c3 : E ET (h uav ) ≥E TH d 2 (18) The constraints for the problem are as follows: For simulation, E ET (h uav ) must be greater than the GN threshold energy (E TH ) multiplied by d 2 , which in turn is h 2 / sin 2 θ where θ is the elevation of the UAV (18). The velocity is assumed to be at the maximum (16) and u I and u F are the initial and final locations of the UAV to complete the mission (17). The energy function problem will be quadratic equation and can be formulated as a linear quadratic equation and solved using linear quadratic regulator in MATLAB. ...
Article
Full-text available
The water distribution system has deployed several low-power IoT devices on an uneven surface where battery power is a major concern. Therefore, this paper focuses on using a UAV-enabled wireless powered communication network capable of directing energy to a target location and using it for communication, thereby reducing battery issues. In this paper, a static optimization was applied to find the initial height values using 3D clustering and beamforming method and dynamic optimization using extremum seeking method was applied to find the optimized height. The optimized height values were calculated and Travelling Salesman Problem (TSP) was applied to create the trajectory of the UAV. The overall energy consumption of the UAV was minimized by integrating dynamic optimization and dome packing method, which can find an optimal position and trajectory where the UAV will be hovering to direct energy and collect data. Moreover, we also minimized the total flight time of the UAV.
... MoT components IoT-IoS 5G-6G SLA Metaverse Blockchain NFT [6]- [10] • [11]- [21] • [4], [6], [8], [10], [13], [22] • • [1]- [3], [23], [24] • • [5], [25] • • • [4], [6], [8], [10], [13], [22] • • [26]- [34] • [35], [36] • • [37]- [41] • • • [7], [30], [31], [33], [42] • • [43]- [45] • [46], [47] • ...
... Initially, blockchain was perceived as the mechanism for storing financial data and as the intermediary for various financial transactions. However, now we witness the trend of shifting it toward other domains, including the IoT environment, such as for healthcare services with support of Internet of Skills [26], automated manufacturing processes [27], secure data aggregation [28], mixed reality content VOLUME 4, 2016 sharing [29], COVID pandemic monitoring [30], etc. ...
Article
Full-text available
The future of networking will be driven by the current emerging trends of combining the physical and virtual realities in cyberspace. Considering the ambient pandemic challenges, the role of virtual and augmented reality will definitely grow over time by transforming into the paradigm of the Metaverse of Things, where each person, thing or other entity will simultaneously exist within multiple synchronized realities. In this paper, we propose a novel framework for future metaverse applications composed of multiple synchronized data flows from multiple operators through multiple wearable devices and with different quality requirements. A new service quality model is proposed based on a customizable utility function for each individual data flow. The proposed approach is based on dynamic fine-grained data flow allocation and service selection using non-fungible tokens, which can be traded over the blockchain among users and operators in a decentralized mobile network environment.
... Among the recent pandemic handling scheme, [14] proposed a blockchain-based pandemic supervision scheme with the help of a drone and AI. A monkeypox detection using modified VGG16 is introduced in [15]. ...
... None of the aforementioned studies considered any privacy challenges. Moreover, only [14] considers security challenges in the scheme. A scheme is required where data can be collected securely during a pandemic without violating the privacy of the data owner. ...
Conference Paper
New diseases (e.g., monkeypox) are showing up and taking the form of a pandemic within a short time. Early detection can assist in reducing the spread. However, because of privacy-sensitive data, users do not share it continually. Thus, it becomes challenging to employ modern technologies (e.g., deep learning). Moreover, cyber threats encircle both communication and data. This paper introduces a blockchain-based data acquisition scheme during the pandemic in which federated learning (FL) is employed to assemble privacy-sensitive data as a form of the trained model instead of raw data. A secure training scheme is designed to mitigate cyber threats (e.g., man-in-the-middle-attack). An experimental environment is formulated based on a recent pandemic (i.e., monkeypox) to illustrate the feasibility of the proposed scheme.
... Blockchain as a Smart City Solution [5] Authentication and trust management [6,7] Healthcare [8] Waste management [9] IoT sensors [10][11][12][13][14] Drone applications for Smart City surveillance [14,15] Smart contracts [16] Online insurance [17] Legal and technical adoption issues for Smart City [18,19] Blockchain oracles problem [20][21][22][23] Blockchain consensus type overview [24][25][26][27][28][29][30][31] Security of data sent by oracles [32][33][34][35] Interplanetary File System for data storing [36][37][38] Smart City interoperability [39][40][41][42] Data consolidation and GDPR Thus, the contribution of this paper is a presentation of the whole topic of the digital transformation of a city and the peculiarities of possible application of blockchain in each instance. In doing so, it was beneficial to collaborate with the City of Osijek, with a goal to define the digitalization strategy document as the basis for later implementation. ...
... The tasks are completed efficiently, and predictions can be made using previous data, such as predicting the needs for exceptional situations that can dramatically change the future requirements and share these data with users. Drones can use geolocation data for city regions to identify the location of the supervised area and collected data [11], location of the emergency disaster, traffic jams, and safety violations [12,13]. Different internet platforms and companies like Google, Uber, Amazon, and Airbnb base their services on geolocation. ...
Article
Full-text available
With advances in Information and Communication Technologies (ICT) in convergence with blockchain technology, cities have been given the opportunity to improve their services, efficiently use resources, and, thus, become Smart Cities. The main properties of blockchain technology like decentralization, immutability, transparency, consensus, and robustness are qualities needed for Smart City. In this paper, we propose a digitalization strategy for the City of Osijek. Smart City digitalization strategy aims to solve problems of emerging urbanization, improve administration by reducing energy and water consumption, carbon emissions, pollution, and city waste management. To develop an information system based on blockchain technology, the administration structure and the current state of information systems are analyzed, and new solutions are presented.
... Integrated Technology Use Case [1] Internet of Mobile Things, Deep Neural Network Rapid testing, quick delivery of medical kits [9] Wireless Sensor Networks Sanitization, thermal image collection [20] YOLO-v3 Social distancing [21] Machine Learning Medical source distribution [22] Visual Sensing, DTL To monitor overcrowding in order to control COVID-19 spreads [118] Edge Computing Containment zone detection with offline data processing and computation [131] Could Virtual Reality Role in the rehabilitation after COVID-19 infection [136] IoT Spread reduction [137] Blockchain, 5G networks Vaccine distribution [138] Blockchain, 6G networks Mass surveillance [139] Internet of Things Sanitization [140] Blockchain, AI Pandemic supervision [141] Convolution Neural Network (CNN) Crowd density [142] Deep Learning Fast detection of medical face masks [143] YOLO-v3 Localization, navigation, people detection, crowd identification, and social distancing warning [144] Hybrid Reinforcement Learning Optimized path planning for UAV COVID-19 test kit delivery system [145] IoT Identifying COVID-19 patients for providing medical services using drones [146] 6G and Blockchain Proposes a generic scheme to integrate UAV, 6G, and BC for secured vaccine distribution [147] Machine Learning Crowd surveillance [148] AI, IoMT For monitoring and supplying COVID-19 patients [149] Radar Sensing Detection of respiratory disorders in COVID-19 patients [150] Blockchain Secure and QoS-aware drone delivery framework [151] Reinforcement Learning, Wireless Network COVID-19 tracing ...
Article
Full-text available
The COVID-19 pandemic, caused by a new coronavirus, has affected economic and social standards as governments and healthcare regulatory agencies throughout the world expressed worry and explored harsh preventative measures to counteract the disease's spread and intensity. Several academics and experts are primarily concerned with halting the continuous spread of the unique virus. Social separation, the closing of borders, the avoidance of big gatherings, contactless transit, and quarantine are important methods. Multiple nations employ autonomous, digital, wireless, and other promising technologies to tackle this coronary pneumonia. This research examines a number of potential technologies, including unmanned aerial vehicles (UAVs), artificial intelligence (AI), blockchain, deep learning (DL), the Internet of Things (IoT), edge computing, and virtual reality (VR), in an effort to mitigate the danger of COVID-19. Due to their ability to transport food and medical supplies to a specific location, UAVs are currently being utilized as an innovative method to combat this illness. This research intends to examine the possibilities of UAVs in the context of the COVID-19 pandemic from several angles. UAVs offer intriguing options for delivering medical supplies, spraying disinfectants, broadcasting communications, conducting surveillance, inspecting, and screening patients for infection. This article examines the use of drones in healthcare as well as the advantages and disadvantages of strict adoption. Finally, challenges , opportunities, and future work are discussed to assist in adopting drone technology to tackle COVID-19-like diseases.
... 18 Recently, a blockchain-based artificial intelligence approach has been developed to handle user confidentiality data during the pandemic. 19 Also, to avoid the network scarcity in the Internet of Drone Things (IoDT) devices, a federated learning (FL) approach based on blockchain technology is developed in Reference 20. Many researchers provided different solutions for data protection in the IoMT. ...
Article
Full-text available
Handling electronic health records from the Internet of Medical Things is one of the most challenging research areas as it consists of sensitive information, which targets attackers. Also, dealing with modern healthcare systems is highly complex and expensive, requiring much secured storage space. However, blockchain technology can mitigate these problems through improved health record management. The proposed work develops a scalable, lightweight framework based on blockchain technology to improve COVID‐19 data security, scalability and patient privacy. Initially, the COVID‐19 related data records are hashed using the enhanced Merkle tree data structure. The hashed values are encrypted by lattice based cryptography with a Homomorphic proxy re‐encryption scheme in which the input data are secured. After completing the encryption process, the blockchain uses inter planetary file system to store secured information. Finally, the Proof of Work concept is utilized to validate the security of the input COVID based data records. The proposed work's experimental setup is performed using the Python tool. The performance metrics like encryption time, re‐encryption time, decryption time, overall processing time, and latency prove the efficacy of the proposed schemes.
... The Internet of Drone Things (IDT) is an emerging technological innovation with the potential to revolutionize AI computing and big data analytics. Ref. [54] presented a novel approach to detecting contagious disease pandemics based on AI-enabled IDT infrastructure and blockchain technology. The proposed system captures real-time geolocated data from various sensors on each drone and creates a unified IDT database for combined computational processing, storage, and retrieval. ...
Article
Full-text available
Drones have attracted extensive attention for their environmental, civil, and military applications. Because of their low cost and flexibility in deployment, drones with communication capabilities are expected to play key important roles in Fifth Generation (5G), Sixth Generation (6G) mobile networks, and beyond. 6G and 5G are intended to be a full-coverage network capable of providing ubiquitous connections for space, air, ground, and underwater applications. Drones can provide airborne communication in a variety of cases, including as Aerial Base Stations (ABSs) for ground users, relays to link isolated nodes, and mobile users in wireless networks. However, variables such as the drone’s free-space propagation behavior at high altitudes and its exposure to antenna sidelobes can contribute to radio environment alterations. These differences may render existing mobility models and techniques as inefficient for connected drone applications. Therefore, drone connections may experience significant issues due to limited power, packet loss, high network congestion, and/or high movement speeds. More issues, such as frequent handovers, may emerge due to erroneous transmissions from limited coverage areas in drone networks. Therefore, the deployments of drones in future mobile networks, including 5G and 6G networks, will face a critical technical issue related to mobility and handover processes due to the main differences in drones’ characterizations. Therefore, drone networks require more efficient mobility and handover techniques to continuously maintain stable and reliable connection. More advanced mobility techniques and system reconfiguration are essential, in addition to an alternative framework to handle data transmission. This paper reviews numerous studies on handover management for connected drones in mobile communication networks. The work contributes to providing a more focused review of drone networks, mobility management for drones, and related works in the literature. The main challenges facing the implementation of connected drones are highlighted, especially those related to mobility management, in more detail. The analysis and discussion of this study indicates that, by adopting intelligent handover schemes that utilizing machine learning, deep learning, and automatic robust processes, the handover problems and related issues can be reduced significantly as compared to traditional techniques.
... By leveraging an IoD network architecture and the powerful capabilities of DL and Blockchain, a swarm of drones was used in [98] for autonomous monitoring of pandemics in urban and rural areas with insufficient wireless connectivity. In this regard, a lightweight authentication scheme that combines a cuckoo filter and a digital signature algorithm was proposed to avoid security attacks (i.e., spoofing, tampering, repudiation, information disclosure, DoS, and elevation of privilege). ...
Article
Full-text available
As the Internet of Things (IoT) ecosystem evolves, innovative applications with stringent demands with respect to latency will emerge. To handle computation-intensive tasks in a timely manner, data offloading to Mobile Edge Computing (MEC) servers has been suggested. On the other hand, prospective IoT networks are expected to include Unmanned Aerial Vehicles (UAVs) to enhance coverage and connectivity, while retaining reliable communication links with ground nodes in urban, suburban, and rural terrain. Nevertheless, the evolution of UAV-aided MEC-enabled IoT presupposes the mitigation of security threats through the implementation of efficient and robust countermeasures. As UAVs inherently have certain limitations in terms of energy, computational, and memory resources, designing lightweight security solutions is required. This paper provides an overview of the UAV-aided MEC-enabled IoT and a detailed presentation of use cases and application scenarios, where security is of utmost importance. Subsequently, up-to-date research works on security solutions for the UAV-aided MEC-enabled IoT are comprehensively presented. To this end, the adoption of information-theoretic techniques that ensure adequate Physical-Layer Security (PLS) is discussed along with sophisticated security approaches based on emerging technologies, such as Blockchain and Machine Learning (ML). In addition, research studies on software- and hardware-based methods for the identification and authentication of network nodes are presented. Finally, this paper provides future perspectives in this research domain, stimulating further work.
... It can well act as a high-altitude connections relay stage, any technology that conveys movable, steadfast link across various areas. ; ; Shin (2019a, 2019b); Islam et al (2021); Islam and Shin (2020) of our everyday lives, enabling us to execute activities that range from package shipping to dive into the water. Intended for IoT, they could adequately outfit to function as IoT gateways, storage, and transmission information from IoT devices situated in the hidden area to the legitimate user connected to the Internet over a cellular network. ...
Article
Full-text available
Evidence of the IoT is expanding the number of connected devices, including UAVs. UAVs overcome the flaws in the physical IoT infrastructure already in place. Low-altitude views are expected to be dominant swiftly in urban areas. In a short period of time, they are able to cover a large area and distribute goods and information around the globe. Additionally, how to provide a safe and secure UAV operation in high-level traffic circumstances is also a topic of investigation. When operating an UAV in a limited area, the IoLoUA system is used to maintain order. Additionally, it aids with node exploration. Basic principles that can be used to create new structural designs are analysed for both networks (IoLoUA). There has been an explanation of the IoLoUA strategy’s approach to implementation so far. Among the issues covered in this article are UAV-generated IoT data collection and delivery, security threats, and typical workflow approaches. This work presents a theoretical model of future design evolution.
Article
Full-text available
The very first infected novel coronavirus case (COVID-19) was found in Hubei, China in Dec. 2019. The COVID-19 pandemic has spread over 214 countries and areas in the world, and has significantly affected every aspect of our daily lives. At the time of writing this article, the numbers of infected cases and deaths still increase significantly and have no sign of a well-controlled situation, e.g., as of 13 July 2020, from a total number of around 13.1 million positive cases, 571, 527 deaths were reported in the world. Motivated by recent advances and applications of artificial intelligence (AI) and big data in various areas, this paper aims at emphasizing their importance in responding to the COVID-19 outbreak and preventing the severe effects of the COVID-19 pandemic. We firstly present an overview of AI and big data, then identify the applications aimed at fighting against COVID-19, next highlight challenges and issues associated with state-of-the-art solutions, and finally come up with recommendations for the communications to effectively control the COVID-19 situation. It is expected that this paper provides researchers and communities with new insights into the ways AI and big data improve the COVID-19 situation, and drives further studies in stopping the COVID-19 outbreak.
Article
Full-text available
With the recent outbreak of COVID-19, the reach and scale of COVID-19 cases is top of mind for everyone and many research groups are actively monitoring and exploring the potential spread. A positive consequence of past epidemics and pandemics is that there are sound epidemiological compartmental modelling approaches that can effectively model disease spread. With minor changes to the underlying dynamical system of equations, many different strategies and situations can be explored. In particular, one such strategy of social distancing is top of mind for many Canadians as our political leaders, local businesses, and fellow Canadians promote and adopt this approach with the hopes that it will effectively ‘flatten the curve’ and reduce or prevent further spread. In this paper, the baseline SIR model is introduced with its close counterpart, the SEIR model. Social distancing is modelled through the isolation of a subset of the susceptible population and comparative studies are performed considering a range in the proportion of individuals isolated. Robust and accurate numerical approximation techniques are used to simulate the pessimistic base case for which no preventative measures are taken and for various social distancing regimes. The results of social distancing are consolidated into two groups – those that flatten the curve and those that completely halt the disease spread. Mathematical formulations show that the turning point between these two regimes is when the effective reproductive rate, denoted Re, is equal to 1. Conclusions are made regarding the impacts and extent of the spread in relation to the severity of social distancing measures.
Article
Full-text available
The COVID-19 crisis profoundly disguised the vulnerability of human societies and health care systems in the situation of a pandemic. In many instances, it became evident that the quick and safe reduction of viral load and spread is the foremost principle in the successful management of such a pandemic. However, it became also clear that many of the established routines in healthcare are not always sufficient to cope with the increased demand for decontamination procedures of items, healthcare products, and even infected tissues. For the last 25 years, the use of gas plasma technology has sparked a tremendous amount of literature on its decontaminating properties, especially for heat-labile targets such as polymers and tissues, where chemical decontamination often is not appropriate. However, while the majority of earlier work focused on bacteria, only relatively few reports are available on the inactivation of viruses. We here aim to provide a perspective for the general audience of the chances and opportunities of gas plasma technology for supporting healthcare during viral pandemics such as the COVID-19 crisis. This includes possible real-world plasma applications, appropriate laboratory viral test systems, and critical points on the technical and safety requirements of gas plasmas for virus inactivation.
Preprint
Full-text available
Coronavirus disease (COVID-19) is an infectious disease caused by a newly discovered coronavirus. It is similar to influenza viruses and raises concerns through alarming levels of spread and severity resulting in an ongoing pandemic world-wide. Within five months (by May 2020), it infected 5.89 million persons world-wide and over 357 thousand have died. Drones or Unmanned Aerial Vehicles (UAVs) are very helpful in handling the COVID-19 pandemic. This work investigates the drone-based systems, COVID-19 pandemic situations, and proposes architecture for handling pandemic situations in different scenarios using real-time and simulation-based case studies. The proposed architecture uses wearable sensors to record the observations in Body Area Networks (BANs) in a push-pull data fetching mechanism. The proposed architecture is found to be useful in remote and highly congested pandemic areas where either the wireless or Internet connectivity is a major issue or chances of COVID-19 spreading are high. It collects and stores the substantial amount of data in a stipulated period and helps to take appropriate action as and when required. In real-time drone-based healthcare system implementation for COVID-19 operations, it is observed that a large area can be covered for sanitization, thermal image collection, patient identification etc. within a short period (2 KMs within 10 minutes approx.) through aerial route. In the simulation, the same statistics are observed with an addition of collision-resistant strategies working successfully for indoor and outdoor healthcare operations.
Article
Full-text available
The objective of this paper is to synthesize the digital interventions initiatives to fight against COVID-19 in Bangladesh and compare with other countries. In order to obtain our research objective, we conducted a systematic review of the online content. We first reviewed the digital interventions that have been used to fight against COVID-19 across the globe. We then reviewed the initiatives that have been taken place in Bangladesh. Thereafter, we present a comparative analysis between the initiatives taken in Bangladesh and the other countries. Our findings show that while Bangladesh is capable to take benefits of the digital intervention approaches, tighter cooperation between government and private organizations as well as universities would be needed to get the most benefits. Furthermore, the government needs to make sure that the privacy of its citizens are protected.
Article
Full-text available
Multiple-operators (multi-OPs) spectrum sharing mechanism can effectively improve the spectrum utilization in fifth-generation (5G) wireless communication networks. The secondary users are introduced to opportunistically access the licensed spectrum of idle operators (OPs). However, the identity privacy and data security issues raise great concerns about the secure spectrum sharing among multi-OPs. To address these challenges, a permissioned blockchain trust framework is proposed for the spectrum sharing in multi-OPs wireless communication networks in this paper. The Multi-OPs Spectrum Sharing (MOSS) smart contract is designed on the constructed permissioned blockchain to implement the spectrum trading among multi-OPs. Without the need of trustless spectrum broker, the MOSS smart contract enforces multi-OPs to share the spectrum truthfully and designs a punishment mechanism to punish malicious OPs. The MOSS smart contract is tested on the Remix integrated development environment (IDE) and the gas costs of MOSS smart contract is estimated. The performance analysis of the proposed permissioned blockchain trust framework demonstrates that the privacy, openness and fairness of the proposed solution are better than traditional spectrum allocation solutions.
Article
Full-text available
Internet of Things is a crucial research empire in the current era which enables a wide diversity of applications. One of the emerging classes of technology in recent age dominate the universe of IoT is the concept of the Internet of Drones Thing (IoDT). The following work fundamentally emphasizes the key concepts of the Internet of Drones architecture in the context of the Edge computing perspective. A state of the art “EdgeDrone” concept has been engineered where the standard message transfer strategy of IoT and the opportunistic Ad-Hoc network have been amalgamated. Parameters like message transfer latency, overhead ratio, message delivery chances under several QoS values and resource usage, energy performance for the protocol have been analyzed. A hardware testbed has been implemented with the JavaScript platform along with the simulation which has been executed after tuning the performance of the protocols. The result shows 30% improvement in average packet delivery for enhanced MQTT-SN and about 17% improvement for enhanced MQTT in comparing to standard strategy. The study also reveals the minimum value of the message delivery latency of 15.5 msec for enhanced MQTT-SN in QoS-1. In memory usage point of view, the result shows that the MQTT broker takes a maximum of 5.6 MB of memory during enhanced MQTT-SN takes to publish–subscribe operation which is significantly less. Another two major parameters which report the maximum message transfer bandwidth of 620 msg/sec for enhanced MQTT-SN at QoS 1 and about 1800 msg/sec for QoS 0 as well as the enhanced MQTT-SN within 802.15.4 interface ensures minimum energy consumption amongst all other strategies
Article
As a promising technology, edge computing extends computation, communication, and storage facilities toward the edge of a network. This new computing paradigm opens up new challenges, among which computation offloading is considered to be the most important one. Computation offloading enables end devices to offload computation tasks to edge servers and receive the results after the servers' execution of the tasks. In computation offloading, offloading modeling plays a crucial role in determining the overall edge computing performance. We present a comprehensive overview on the past development as well as the recent advances in research areas related to offloading modeling in edge computing. First, we present some important edge computing architectures and classify the previous works on computation offloading into different categories. Second, we discuss some basic models such as channel model, computation and communication model, and energy harvesting model that have been proposed in offloading modeling. Next, we elaborate on different offloading modeling methods which are based on (non-)convex optimization, Markov decision process, game theory, Lyapunov optimization, or machine learning. Finally, we highlight and discuss some research directions and challenges in the area of offloading modeling in edge computing.
Article
Wireless capsule endoscopy (WCE) is a process in which a patient swallows a camera-embedded pill-shaped device that passes through the gastrointestinal (GI) tract, captures and transmits images to an external receiver. WCE devices are considered as a replacement of conventional endoscopy methods which are usually painful and distressful for the patients. WCE devices produce over 60,000 images typically during their course of operation inside the GI tract. These images need to be examined by expert physicians who attempt to identify frames that contain inflammation / disease. It can be hectic for a physician to go through such a large number of frames, hence computer-aided detection methods are considered an efficient alternative. Various anomalies can take place in the GI tract of a human being but the most important and common ones and the aim of this survey are ulcers, polyps, and tumors. In this paper, we have presented a survey of contemporary computer-aided detection methods that take WCE images as input and classify those images in a diseased/abnormal or disease-free/ normal image. We have considered methods that detect tumors, polyps and ulcers, as these three diseases lie in the same category. Furthermore bleeding inside the GI tract may be the symptoms of these diseases; so an attempt is also made to enlighten the research work done for bleeding detection inside WCE. Several studies have been included with in-depth detail of their methodologies, findings, and conclusions. Also, we have attempted to classify these methods based on their technical aspects. This paper also includes a potential proposal for joint classification of aforementioned three diseases.
Article
With the spread of novel coronavirus, the global health concern has been increased as it has flattened the curve of mortality worldwide. To handle such a containment disease, multi-swarm Unmanned Aerial Vehicles (UAVs) with 5G can be used to reduce human intervention with major benefits of high bandwidth, ultra-low-latency, and reliability. Though multi-swarm UAVs sends a huge amount of data to ground stations with real-time connection density of 10^7 /km^2, which is a bottleneck on 5G networks and data security is another issue in sharing sensitive data. Motivated from these issues, in this article, we propose a blockchain-envisioned software multi-swarming UAVs communication scheme based on a 6G network with intelligent connectivity, Terahertz (THz) frequency bands, and virtualization of link and physical-level protocols. Softwarization makes the communication infrastructure flexible, agile, and easily configurable, and the potential of blockchain supports data security. Results show that the proposed scheme performs better in terms of processing delay, packet loss reduction, and throughput compared to exiting 4G/5G-based systems.