ArticlePDF Available

Formalizing and securing relationships on multi-task metric learning for IoT-based smart cities

Authors:
B I Savelyev
B I Savelyev
B I Savelyev
  • This person is not on ResearchGate, or hasn't claimed this research yet.
S V Solodov
S V Solodov
S V Solodov
  • This person is not on ResearchGate, or hasn't claimed this research yet.
D V Tropin
D V Tropin
D V Tropin
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Download full-text PDF
Read full-text
Download citation

Abstract

The use of modern information and communication technologies is an essential condition for the formation of the transport infrastructure of a smart city. Scientific and methodological approaches are developed to effectively monitor the transport infrastructure of a smart city based on multi-channel metric learning in the Internet of Things. The proposed solutions provide invariance to the type and nature of the movement of objects. The principles of technical implementation of the proposed method are substantiated using the characteristics of unmanned aerial vehicles of a smart city. Adaptive automatic switching of transport infrastructure monitoring channels is implemented in the form of a neural network analyzer software.
Available via license: CC BY 3.0
Content may be subject to copyright.
Journal of Physics: Conference Series
PAPER • OPEN ACCESS
Formalizing and securing relationships on multi-task metric learning for
IoT-based smart cities
To cite this article: B I Savelyev et al 2021 J. Phys.: Conf. Ser. 2094 032062
View the article online for updates and enhancements.
This content was downloaded from IP address 62.241.57.173 on 30/11/2021 at 06:03
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution
of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Published under licence by IOP Publishing Ltd
APITECH III 2021
Journal of Physics: Conference Series 2094 (2021) 032062
IOP Publishing
doi:10.1088/1742-6596/2094/3/032062
1
Formalizing and securing relationships on multi-task metric
learning for IoT-based smart cities
B I Savelyev, S V Solodov1 and D V Tropin
Federal Center of Theoretical and Applied Sociology of Russian Academy of
Sciences, 24/35, Krzhizhanovsky Street, Moscow, 117218, Russia
1 E-mail: solodovsvl@mai.ru
Abstract. The use of modern information and communication technologies is an essential
condition for the formation of the transport infrastructure of a smart city. Scientific and
methodological approaches are developed to effectively monitor the transport infrastructure of a
smart city based on multi-channel metric learning in the Internet of Things. The proposed
solutions provide invariance to the type and nature of the movement of objects. The principles
of technical implementation of the proposed method are substantiated using the characteristics
of unmanned aerial vehicles of a smart city. Adaptive automatic switching of transport
infrastructure monitoring channels is implemented in the form of a neural network analyzer
software.
1. Introduction
The Internet of Things (IoT) is the interconnection of physical devices, vehicles, buildings and other
items provided with electronics, software, sensors that allow these objects to collect and exchange data.
The Internet of Things allows devices to be discovered or monitored remotely through existing network
infrastructure, creating opportunities for direct integration of the physical world into a computer system,
resulting in increased efficiency, accuracy, and economic benefits. When the Internet of Things is
complemented by sensors and actuators, this technology becomes the basis for more general cyber-
physical systems that also encompass smart city technologies such as smart grids, smart homes and
smart transportation. Each item is uniquely identified through its embedded computing system, but is
capable of interacting with the existing infrastructure of the Internet.
The Internet of Things is especially relevant for the development of transport infrastructure, since it
provides systems for collecting and processing information in an automatic mode in order to increase
the efficiency, reliability, sustainability and economy of the distribution of traffic flows. At the same
time, it is necessary to achieve high reliability and accuracy of the analysis, under adverse weather
conditions and the presence of interference of natural and artificial origin. The main technical means of
solving telecommunication problems are radar means of a smart city. However, there are significant
limitations to the effectiveness of existing radar facilities of a smart city based on direct electromagnetic
contact with transport infrastructure objects [1, 2]:
• one-channel;
• insufficient range of action;
• operability only for moving infrastructure objects of the smart city.
APITECH III 2021
Journal of Physics: Conference Series 2094 (2021) 032062
IOP Publishing
doi:10.1088/1742-6596/2094/3/032062
2
Ground-based radar means of a smart city, based on the tangent method for determining the location
of transport objects [3, 4], providing targeted multichannel, have insufficient range due to energy
constraints. Removing the restrictions of the radio horizon is provided by means of monitoring devices
of the Internet of things [5]. However, the existing telecommunication schemes for transmitting
information are characterized by a significant time delay, which is unacceptable for highly dynamic
transport systems of a smart city.
Therefore, it is relevant to search for methods and ways to ensure high-precision monitoring of the
infrastructure of a smart city at the maximum ranges of the Internet of Things devices with a
simultaneous increase in the target multichannel in the range of all possibilities of its effective
application. At the same time, the use of the potential information capabilities of observation channels
of various parts of the spectrum of electromagnetic waves [6] by means of their constructive and
functional integration becomes of fundamental importance.
2. Radio engineering and telecommunication systems of a smart city
Modern information technologies cover all spheres of city life. Under their influence, there is a radical
change in all processes in the city management system, they automate management processes, contribute
to the effective development of management decisions, and make management more transparent. IoT
technologies are increasingly being used in smart city telecommunication systems. They are a
prerequisite for the development of smart cities. Together with the benefits from their use, the threat of
their misuse for analyzing the transport infrastructure of a smart city increases.
In the ranges of the spectrum of electromagnetic waves used to analyze the transport infrastructure
of a smart city, the limiting range of detection, measurement of coordinates and recognition of objects
is determined by the line-of-sight range. In a radar channel, even in the presence of direct optical contact
with objects of the transport infrastructure of a smart city, the maximum range of its observation is
determined by the effective scattering surface.
Known methods of increasing the radio horizon when observing ground objects of a smart city are
based on the use of telecommunication systems for transceiver devices [7, 8]. However, the application
of this approach significantly increases the complexity and technical characteristics of the structure and,
as a consequence, the cost of such systems. On the other hand, there are known ways to remove
restrictions on the radio horizon through the use of unmanned aerial vehicles within a smart city [9].
However, the isolation of the aperture parts of the telecommunication channels does not allow realizing
the potential possibilities of monitoring infrastructure objects in a dynamically changing environment
over the entire depth of range.
In [10, 11], it is shown that the integration of observation channels of different parts of the spectrum
of electromagnetic waves within the framework of a general information-measuring system is a
powerful tool for increasing the reliability and accuracy of remote monitoring of transport objects of a
smart city. In [12, 13], algorithms for multispectral information processing were obtained, taking into
account the synchronization of partial spectral channels at different stages of observation of
infrastructure objects (identification, estimation of coordinates, recognition). In [14, 15], a methodology
was developed and options for constructive integration of partial spectral observation channels were
considered to ensure mutually consistent work in space and time. However, the dependence of the
potential capabilities of partial spectral channels in the optical range, which is associated with the state
of the surface layer of the atmosphere (rain, dust and smoke obstacles, time of day), limits the range of
their effective use when installing equipment on ground infrastructure facilities of a smart city, while
the channels radio bands are practically devoid of this drawback.
3. Multitasking IoT metric learning
The main scientific and technical idea of the proposed approach to improve the efficiency of monitoring
the infrastructure of smart cities based on the Internet of Things is to expand the range, target
multichannel and remove restrictions on the nature and parameters of movement of transport
infrastructure objects. It is proposed to use a combination of the advantages of high-potential
APITECH III 2021
Journal of Physics: Conference Series 2094 (2021) 032062
IOP Publishing
doi:10.1088/1742-6596/2094/3/032062
3
multichannel radio engineering systems and multitasking metric learning of IoT devices installed on
unmanned aerial vehicles within an integrated complex. At the same time, the practical implementation
is based on the constructive and functional integration of various technical solutions [16, 17]. The
practical implementation of the method includes:
• the use of one or more spatial observation channels, which are formed by a phased antenna array
in normal mode for multitasking metric training of unmanned aerial vehicles of a smart city;
• placement on an unmanned aerial vehicle of multispectral equipment for monitoring transport
infrastructure objects of a smart city.
If multispectral monitoring equipment is placed on board an unmanned aerial vehicle, it is necessary
to use special algorithms for solving location problems of identifying, evaluating coordinates and
recognizing transport infrastructure objects. When integrating partial channels at the level of a smart
city decision support system, it is proposed to use the following functionality as an optimality principle:
( )
1
2
2
1
N
ii
i
F f f a
+
=

=−


, (1)
where
1
( , , )
i i iN
a a a=
is the vector of partial decisions, if
1
i
a=
is the decision on the presence of a
signal, made by the
i
th channel of the Internet of Things; otherwise, the decision about the absence of a
signal is made by the
i
th channel of the Internet of Things;
is the weighting factor characterizing the
information contribution of the
i
th partial Internet of Things channel in identifying the observed object,
and
f+
is the maximum value of the weighting factor.
The weighting factor is of a probabilistic nature:
(1 )
ln (1 )
TF
ii
iFT
ii
PP
fPP

−
=
−

, (2)
where
T
i
P
is the probability of correct detection in the
i
th partial Internet of Things channel;
F
i
P
is the
probability of false detection in the
i
th partial IoT channel.
In case the multitasking metric learning consists of three channels: optical, infrared, radar. Then, the
optimal value of the objective function (1) will be achieved in the case:
• favorable weather conditions
10a=
;
• meteorological precipitation
20a=
;
• night period
30a=
.
These ratios reflect the fact that at small distances corresponding to the flight altitudes of unmanned
aerial vehicles, the observation channels of ground objects can be differentiated in terms of efficiency
with the subsequent disconnection of ineffective ones. It should be noted that the proposed methodology
applies to algorithms for estimating coordinates and recognizing objects in the transport infrastructure
of a smart city.
Adaptive automatic switching of observation channels is implemented in the form of software for a
neural network analyzer of smart city infrastructure. The analyzer uses information from controllers that
collect and process information.
Processor means are used as controllers. The amount of memory and data is determined by the type
of controller. Microcontrollers were used to create prototypes of such sensors. Microcontrollers were
programmed using the functions of the C and C ++ languages in the PlatformIO environment. In addition
APITECH III 2021
Journal of Physics: Conference Series 2094 (2021) 032062
IOP Publishing
doi:10.1088/1742-6596/2094/3/032062
4
to using traditional compilation tools, the PlatformIO project provides an integrated development
environment (IDE) [18]. The PlatformIO IDE has a built-in library that provides access to many simple
I / O routines.
4. Conclusion
The digitalization of the transport sector is a global trend that creates new conditions for the functioning
of human society. IoT technologies are not only the main feature of a smart city, but are also aimed at
improving the quality of life of the population, increasing the efficiency and availability of city services,
increasing the level of safety and environmental protection, and developing the socio-economic system
of the city. The developed scientific and methodological approaches to assessing coordinates and
recognizing objects of the transport infrastructure of a smart city allow ensuring the reliability and safety
of urban systems and the efficiency of resource use.
At the same time, the transition to the smart city model is limited by the lack of a technical base for
creating IoT information technology platforms. A roadmap for the digital transformation of the national
economy has not been developed. Therefore, the main obstacles to the digital transformation of cities
are the underdevelopment of technological solutions in the field of standardization of new technologies
and work with big data. Modeling the functioning of the transport infrastructure of smart cities, in
particular the collection and use of big data for this purpose, is of great interest for further scientific
research.
Acknowledgments
The article is prepared with the financial support of the Russian Science Foundation, project № 19-78-
10035.
References
[1] Amico G, Szopik K and Ioppolo G 2021 Sustainable Cities and Society 69 102801
[2] Zhao P, Lu C and Markham A 2021 Ad Hoc Networks 116 102475
[3] Hoang L, Kim M and Kong S 2019 IEEE Transactions on Signal Processing 67 3516-30
[4] Ma B, Zhu W and Huang Q 2021 Journal of Applied Geophysics 190 104342
[5] Tong Z, Gao J and Yuan D 2020 Construction and Building Materials 258 120371
[6] Sagnard F, Norgeot C and Lebental B 2016 Measurement 88 318-30
[7] Deng T, Zhang K and Shen Z 2021 Journal of Management Science and Engineering 6 125-34
[8] Lai W, Derobert X and Annan P 2017 NDT & E International 96 58-78
[9] Mohamed N, Jaroodi J and Mohammed F 2018 Technological Forecasting and Social Change
153 119293
[10] Qadir Z, Ullah F and Turjman F 2021 Computer Communications 168 114-35
[11] Khan N, Jhanjhi N and Nayyar A 2020 Computer Communications 157 434-43
[12] Outay F, Mengash H and Adnan M 2020 Transportation Research Part A: Policy and Practice
141 116-29
[13] Alsamhi S, Afghah F and Guizani M 2021 Ad Hoc Networks 117 102505
[14] Ge C, Ma G and Liu Z 2020 Journal of Systems Architecture 107 101728
[15] Ullah Z, Turjman F and Gagliardi R 2020 Computer Networks 182 107478
[16] Kumari A, Gupta R and Tanwar S 2021 Computer Communications 172 102-18
[17] Alsamhi S, Afghah F and Guizani M 2021 Ad Hoc Networks 117 102505
[18] Camprodon G, Gonzalez O and Bizzotto A 2019 HardwareX 6 100070
... The second part of the problem is the lack of a general understanding of the model of such an architecture and, in particular, some generalized unified representation of its components and their structural and functional relationships. Thus, in order to implement such large-scale projects as the digital transformation of industrial enterprises, the issues of developing competent graphical models of the future structural and functional architectures of an integrated digital enterprise management system play significant roles due to the peculiarities of the formulation of initial requirements [24][25][26][27], namely: ...
... The complexity of formalization, and in some cases a complete lack of understanding of the final functional and non-functional requirements for a digital enterprise as a single system [3,[4][5][6][7]19,[24][25][26]; The second part of the problem is the lack of a general understanding of the model of such an architecture and, in particular, some generalized unified representation of its components and their structural and functional relationships. Thus, in order to implement such large-scale projects as the digital transformation of industrial enterprises, the issues of developing competent graphical models of the future structural and functional architectures of an integrated digital enterprise management system play significant roles due to the peculiarities of the formulation of initial requirements [24][25][26][27], namely: ...
... The complexity of formalization, and in some cases a complete lack of understanding of the final functional and non-functional requirements for a digital enterprise as a single system [3,[4][5][6][7]19,[24][25][26]; The second part of the problem is the lack of a general understanding of the model of such an architecture and, in particular, some generalized unified representation of its components and their structural and functional relationships. Thus, in order to implement such large-scale projects as the digital transformation of industrial enterprises, the issues of developing competent graphical models of the future structural and functional architectures of an integrated digital enterprise management system play significant roles due to the peculiarities of the formulation of initial requirements [24][25][26][27], namely: ...
Models and Methods of Designing Data-Centric Microservice Architectures of Digital Enterprises
Article
Full-text available
  • Jan 2023
The article is devoted to methods and models of designing systems for the digital transformation of industrial enterprises within the framework of the Industry 4.0 concept. The purpose of this work is to formalize a new notation for graphical modeling of the architecture of complex large-scale systems with data-centric microservice architectures and to present a variant of the reference model of such an architecture for creating an autonomously functioning industrial enterprise. The paper provides a list and justification for the use of functional components of a data-centric microservice architecture based on the analysis of modern approaches to building systems and the authors’ own results obtained during the implementation of a number of projects. The problems of using traditional graphical modeling notations to represent a data-centric microservice architecture are considered. Examples of designing a model of such an architecture for a mining enterprise are given.
View
... Современные технологии позволяют использовать алгоритмы компьютерного зрения для раннего обнаружения огня, что может существенно снизить ущерб от пожаров, обеспечивая быстрое и точное реагирование. В последние годы значительные усилия исследователей были направлены на разработку и улучшение алгоритмов машинного обучения [1,2], способных эффективно классифицировать изображения по наличию на них огня. Наиболее перспективными в этом направлении являются сверточные нейронные сети (CNN), которые показали выдающиеся результаты в задачах компьютерного зрения благодаря своей способности извлекать сложные признаки из изображений [3]. ...
Методы глубокого обучения для обнаружения огня
Article
Full-text available
  • May 2024
В данной работе проводится сравнение эффективности двух различных подходов к распознаванию огня на изображениях: использование архитектуры сверточной нейронной сети ResNet50 и применение модели FireNet. Подробно рассматриваются архитектуры обеих моделей, их особенности и принципы работы. Исследование демонстрирует, как выбор архитектуры нейросети может влиять на качество решения задачи классификации изображений. Анализ преимуществ и недостатков каждого подхода предоставляет важные данные для разработки и оптимизации систем обнаружения огня.
View
A Systematic Review of the Digital Twin City: The New Pattern of Urban Governance Towards Smart City
Article
Full-text available
  • Jan 2021
Many countries and governments consider smart cities as solutions to global warming, population growth and resource depletion. Numerous challenges arise on the way to a smart city. Digital twins, along with the internet of things (IoT), the fifth-generation wireless systems (5G), blockchain, collaborative computing, simulation and artificial intelligence (AI) technologies, offer great potential in the transformation of current urban governance paradigm toward smart city. In this paper, the concept of digital twin city (DTC) was proposed. The characteristics, key technologies and application scenarios of a digital twin city is elaborated. Further, we discuss the theories, research directions and framework towards digital twin city.
View
Imaging shallow fault structures by three-dimensional reverse time migration of ground penetration radar data
Article
  • Apr 2021
  • J APPL GEOPHYS
Ground penetrating radar (GPR) is an effective technology for investigating shallow underground structures using high-frequency electromagnetic waves. Migration is necessary to interpret GPR data because it resolves the true structure from distorted and blurry time-domain profiles. Wave-equation-based reverse time migration (RTM) can provide higher-resolution and more reliable results compared to ray-based migration methods. We have developed a three-dimensional RTM approach based on the finite-difference time-domain algorithm and applied it to field GPR data collected in the northern segment of the Huangzhuang-Gaoliying fault in suburban Beijing. Migrated images clearly show the subsurface structures, with clear indications of underground reflectors in agreement with geological cross-sections proposed in previous studies. Our results demonstrate that GPR is a convenient, non-destructive, and reliable technique that provides a new comprehensive approach to image subsurface conditions, thus allowing effective monitoring of active faults in urban areas.
View
Green Internet of Things using UAVs in B5G Networks: A Review of Applications and Strategies
Article
  • Apr 2021
  • AD HOC NETW
Smart drone has emerged as a promising advanced technology that potentially enhances cities' life quality and smartness dramatically and increases overall economic efficiency. Drones fly autonomously in space to support human activities and are associated with different civilian society applications such as agriculture, communication, transportation, disaster management, public safety, healthcare, and environmental preservation. A smart world is conceived of intelligent things that can automatically and collaboratively improve smart cities' smartness. Therefore, the Internet of Things (IoT) is required to ensure collaboration between the vast multitude of things efficiently anywhere in the real world and in real-time. However, many IoT devices consume a significant amount of energy when transmitting the collected data from surrounding environments. Due to a drone's capability to fly closer to IoT, drone technology plays a vital role in greening IoT by transmitting collected data to achieve a sustainable, reliable, eco-friendly world. This survey presents an overview of the techniques and strategies proposed recently to achieve green IoT using drones in edge intelligence infrastructure for a reliable and sustainable smart world. This survey is different from other works in terms of concept, focus, and discussion.
View
Human tracking and identification through a millimeter wave radar
Article
  • Mar 2021
  • AD HOC NETW
The key to offering personalised services in smart spaces is knowing where a particular person is with a high degree of accuracy. Visual tracking is one such solution, but concerns arise around the potential leakage of raw video information and many people are not comfortable accepting cameras in their homes or workplaces. We propose a human tracking and identification system (mID) based on millimeter wave radar which has a high tracking accuracy, without being visually compromising. Using a low-cost, commercial, off-the-shelf radar, we first obtain sparse point clouds and form temporally associated trajectories. With the aid of a deep recurrent network, we identify individual users and show how to detect intruders. We evaluate and demonstrate our system, showing median position errors of 0.16 m, identification accuracy of 89% and intruder detection accuracy of 73% for 12 insiders. By increasing observation time from 2 s to 7 s, identification accuracy rises to 99%.
View
Amalgamation of Blockchain and IoT for Smart Cities underlying 6G Communication: A Comprehensive Review
Article
  • Mar 2021
  • COMPUT COMMUN
Nowadays, increasing urbanization has necessitated the social, environmental, and economic development of cities to enhance the Quality of Life (QoL) significantly and introduces the ``Smart City" concept. It integrates Information and Communication Tools (ICT), Internet of Things (IoT), and other technologies to resolve urban challenges. The key goal is to make the most acceptable use of available resources and technologies to develop smart cities. An IoT-enabled application plays a crucial role here, but it has various security, privacy, latency, and reliability issues with a single-point-of-failure problem. The evolving technology blockchain can handle the aforementioned security and privacy issues and provide high-quality services due to several features like transparency, trust-free, decentralization, immutability, and others. The 6G communication network takes care of latency and reliability issues in the smart city with their unique characteristics such as latency (10−100μs10-100 \mu s) and reliability (99.99999\%). Motivated by these facts, in this paper, we presented a comprehensive review for blockchain technology and IoT together functional to smart cities. First, state-of-art-the works and contextual information are introduced. Then, we proposed a blockchain-based decentralized architecture for IoT-integrated smart cities covering different application perspectives, such as smart grid, Intelligent Transportation System (ITS), and healthcare 5.0 underlying 6G communication networks. Next, we describe the challenges of the proposed architecture respective to each application, as mentioned above. Finally, we collated the open research issues and future direction to efficiently integrate blockchain into IoT-envisioned smart cities.
View
Addressing disasters in smart cities through UAVs path planning and 5G communications: A systematic review
Article
  • Jan 2021
  • COMPUT COMMUN
UAVs are increasingly incorporated in a wide range of domains such as disaster management and rescue missions. UAV path planning deals with finding the most optimal or shortest path for UAVs such that minimum energy and resources are utilized. This paper examines the path planning algorithms for UAVs through a literature survey conducted on 139 systematically retrieved articles published in the last decade that are narrowed down to 36 highly relevant articles. As retrieved from the shortlisted articles, the path planning algorithms include RRT, Artificial Potential, Voronoi, D-Star, A-Star, Dijkstra, MILP, Neural Network, Ant Colony Optimization, and Particle Swarm Optimization that are classified into four main types: Model-based, Conventional, Learning-based, and Cell-based. Most of the disaster-related articles are focused on the post-disaster phase only and use conventional and learning-based algorithms with applications to localize victims and optimize paths. Regarding the UAV communication network (UAVCN), the key challenges are communication issues, resource allocation, UAV deployment, defining UAV trajectory, and content security. UAV path planning’s key barriers are path optimization, path completeness, optimality, efficiency, and achieving robustness. Accordingly, a holistic IoT-powered UAV-based smart city management system has been recommended in the current study where all the smart city key components are integrated to address disasters like floods, earthquakes, and bush fire. The proposed holistic system can help prepare for disasters and mitigate them as soon as these arise and help enhance the smart city governance.
View
The stochastic container relocation problem with flexible service policies
Article
  • Sep 2020
  • TRANSPORT RES B-METH
This paper investigates the Stochastic Container Relocation Problem in which a flexible service policy is adopted in the import container retrieval process. The flexible policy allows the terminal operators to determine the container retrieval sequence to some extent, which provides more opportunity for reducing the number of relocations and the truck waiting times. A more general probabilistic model that captures customers’ arrival preference is presented to describe the randomness for external truck arrivals within their appointed time windows. Being a multi-stage stochastic sequential decision-making problem, it is first formulated into a stochastic dynamic programming (SDP) model to minimize the expected number of relocations. Then, the SDP model is extended considering a secondary objective representing the truck waiting times. Tree search-based algorithms are adapted to solve the two models to their optimality. Heuristic algorithms are designed to seek high-quality solutions efficiently for larger problems. A discrete-event simulation model is developed to evaluate the optimal solutions and the heuristic solutions respectively on two performance metrics. Extensive computational experiments are performed based on instances from literature to verify the effectiveness of the proposed models and algorithms.
View
Advances of deep learning applications in ground-penetrating radar: A survey
Article
  • Oct 2020
  • CONSTR BUILD MATER
Deep learning has achieved state-of-the-art performance on signal and image processing. Due to the remarkable success, it has been applied in more challenging tasks, such as ground-penetrating radar (GPR) testing in civil engineering. This paper reviews methods involving deep leaning and GPR for civil engineering inspection and provides a classification based on the data types that they exploit. Based on the results of a comparison study, we conclude that methods using A-scan data slightly surpass the models using B- and C-scan data, though C-scan data is maybe the most promising in the further thanks to its complete space information. Two current limitations of deep learning exploiting GPR are its dependence on big data and overconfident decision-making. Therefore, benchmark GPR data sets and cautious deep learning are required.
View
Smart traffic monitoring system using Unmanned Aerial Vehicles (UAVs)
Article
  • May 2020
  • COMPUT COMMUN
Road traffic accidents are one of the leading causes of deaths and injuries in the word resulting in the not only loss of precious human lives but also affect the economic resources. According to the World Health Organization (WHO), over 1.35 million people are killed, and over 50 million are injured due to road accidents throughout the world. Unfortunately, as compared to other developing countries with the same ratio of vehicle possession, in Saudi Arabia, the fatalities and injuries are much higher. Every year around 7000-9000 people die, and over 39000 serious injuries occur in road accidents. There is at least one accident happens every minute in Saudi Arabia. To decrease the road traffic accidents, fatalities, and injuries caused by them, the Saudi Ministry of Interior came up with new rules, regulations, and hefty fines. Also, they introduced a new traffic system called the SAHER system. Still, due to the static nature and other limitations of the system, the drivers found loopholes and ways to deceive the system to avoid the fines and not being caught by the system. The most common violation includes excess speed, abrupt deceleration, and distracted driving. In this paper, we propose a smart traffic surveillance system based on Unmanned Aerial Vehicle (UAV) using 5G technology. This traffic monitoring system covers the existing limitations of the SAHER system deployed in KSA. By overcoming the existing limitations and loopholes of the SAHER system, it is observed that the number of accidents and fatalities can be decreased. The projected results show that those violations when to overcome, the number of accidents per year falls to 299,317 leading to 4,868 deaths and 33,199 injuries for 1st year, and in the next five years the number of deaths and will be decreased to 3,745 and injuries to 16,600 based on the current data available. We aim the system will further reduce the number of accidents and fatalities and injuries caused by it.
View
A Semi-autonomous Distributed Blockchain-based Framework for UAVs System
Article
  • Aug 2020
  • J SYST ARCHITECT
The impact of the Internet of Things (IoT) to our daily life has become bigger than ever, which can be witnessed from smart homes, smart transportation, and smart personal care. With widespread applications of UAVs in IoT contexts such as delivery and military, protecting communications between UAVs and ground control system is needed so as to resist potential vulnerabilities and optimize the coordination between distributed UAVs. In this work, to secure communications during data acquisition and transmission, as well as diminish the probability of attacking by malicious manipulated UAVs, we propose a distributed UAVs scheme harnessing blockchain technology whose network has similar topology to IoT along with cloud server. Instead of directly using the typical blockchain technique which requires expensive computation and high bandwidth overhead, we propose a novel, secure, and lightweight blockchain architecture which mitigates the computation and storage overhead while retaining its privacy and security benefits. Moreover, multiples types of transactions are defined to describe various data access and a novel reputation-based consensus protocol is designed to ensure the reliability of the decentralized network. Finally, performance evaluation demonstrates our blockchain-based distributed scheme is secure and efficient.
View