scholarly journals DeepBrain: Experimental Evaluation of Cloud-Based Computation Offloading and Edge Computing in the Internet-of-Drones for Deep Learning Applications

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5240
Author(s):  
Anis Koubaa ◽  
Adel Ammar ◽  
Mahmoud Alahdab ◽  
Anas Kanhouch ◽  
Ahmad Taher Azar
Keyword(s):  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Smart Cities ◽  
Transportation Systems ◽  
Edge Computing ◽  
Aerial Images ◽  
Computation Offloading ◽  
The Internet ◽  
Real Time Processing ◽  
Computing Approach

Unmanned Aerial Vehicles (UAVs) have been very effective in collecting aerial images data for various Internet-of-Things (IoT)/smart cities applications such as search and rescue, surveillance, vehicle detection, counting, intelligent transportation systems, to name a few. However, the real-time processing of collected data on edge in the context of the Internet-of-Drones remains an open challenge because UAVs have limited energy capabilities, while computer vision techniquesconsume excessive energy and require abundant resources. This fact is even more critical when deep learning algorithms, such as convolutional neural networks (CNNs), are used for classification and detection. In this paper, we first propose a system architecture of computation offloading for Internet-connected drones. Then, we conduct a comprehensive experimental study to evaluate the performance in terms of energy, bandwidth, and delay of the cloud computation offloading approach versus the edge computing approach of deep learning applications in the context of UAVs. In particular, we investigate the tradeoff between the communication cost and the computation of the two candidate approaches experimentally. The main results demonstrate that the computation offloading approach allows us to provide much higher throughput (i.e., frames per second) as compared to the edge computing approach, despite the larger communication delays.

scholarly journals An Advanced Deep Learning Approach for Multi-Object Counting in Urban Vehicular Environments

2021 ◽  
Vol 13 (12) ◽  
pp. 306
Author(s):  
Ahmed Dirir ◽  
Henry Ignatious ◽  
Hesham Elsayed ◽  
Manzoor Khan ◽  
Mohammed Adib ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Smart Cities ◽  
Weather Conditions ◽  
Research Area ◽  
Transportation Systems ◽  
Detection Accuracy ◽  
Adverse Weather ◽  
Object Counting ◽  
The Impact

Object counting is an active research area that gained more attention in the past few years. In smart cities, vehicle counting plays a crucial role in urban planning and management of the Intelligent Transportation Systems (ITS). Several approaches have been proposed in the literature to address this problem. However, the resulting detection accuracy is still not adequate. This paper proposes an efficient approach that uses deep learning concepts and correlation filters for multi-object counting and tracking. The performance of the proposed system is evaluated using a dataset consisting of 16 videos with different features to examine the impact of object density, image quality, angle of view, and speed of motion towards system accuracy. Performance evaluation exhibits promising results in normal traffic scenarios and adverse weather conditions. Moreover, the proposed approach outperforms the performance of two recent approaches from the literature.

scholarly journals Blockchain for the Internet of Vehicles: A Decentralized IoT Solution for Vehicles Communication Using Ethereum

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 3928 ◽  
Author(s):  
Rateb Jabbar ◽  
Mohamed Kharbeche ◽  
Khalifa Al-Khalifa ◽  
Moez Krichen ◽  
Kamel Barkaoui
Keyword(s):  
Intelligent Transportation Systems ◽  
Secure Communication ◽  
Data Exchange ◽  
Smart Cities ◽  
Transportation Systems ◽  
Smart Devices ◽  
The Internet ◽  
Internet Of Vehicles ◽  
Computing Platform ◽  
Blockchain Technology

The concept of smart cities has become prominent in modern metropolises due to the emergence of embedded and connected smart devices, systems, and technologies. They have enabled the connection of every “thing” to the Internet. Therefore, in the upcoming era of the Internet of Things, the Internet of Vehicles (IoV) will play a crucial role in newly developed smart cities. The IoV has the potential to solve various traffic and road safety problems effectively in order to prevent fatal crashes. However, a particular challenge in the IoV, especially in Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communications, is to ensure fast, secure transmission and accurate recording of the data. In order to overcome these challenges, this work is adapting Blockchain technology for real time application (RTA) to solve Vehicle-to-Everything (V2X) communications problems. Therefore, the main novelty of this paper is to develop a Blockchain-based IoT system in order to establish secure communication and create an entirely decentralized cloud computing platform. Moreover, the authors qualitatively tested the performance and resilience of the proposed system against common security attacks. Computational tests showed that the proposed solution solved the main challenges of Vehicle-to-X (V2X) communications such as security, centralization, and lack of privacy. In addition, it guaranteed an easy data exchange between different actors of intelligent transportation systems.

scholarly journals Edge Computing and IoT Analytics for Agile Optimization in Intelligent Transportation Systems

Energies ◽  
2021 ◽  
Vol 14 (19) ◽  
pp. 6309
Author(s):  
Mohammad Peyman ◽  
Pedro J. Copado ◽  
Rafael D. Tordecilla ◽  
Leandro do C. Martins ◽  
Fatos Xhafa ◽  
...  
Keyword(s):  
Intelligent Transportation Systems ◽  
Smart Cities ◽  
Intelligent Transportation ◽  
Transportation System ◽  
Transportation Systems ◽  
Edge Computing ◽  
Analytical Models ◽  
Current Status ◽  
Ride Sharing ◽  
The City

With the emergence of fog and edge computing, new possibilities arise regarding the data-driven management of citizens’ mobility in smart cities. Internet of Things (IoT) analytics refers to the use of these technologies, data, and analytical models to describe the current status of the city traffic, to predict its evolution over the coming hours, and to make decisions that increase the efficiency of the transportation system. It involves many challenges such as how to deal and manage real and huge amounts of data, and improving security, privacy, scalability, reliability, and quality of services in the cloud and vehicular network. In this paper, we review the state of the art of IoT in intelligent transportation systems (ITS), identify challenges posed by cloud, fog, and edge computing in ITS, and develop a methodology based on agile optimization algorithms for solving a dynamic ride-sharing problem (DRSP) in the context of edge/fog computing.These algorithms allow us to process, in real time, the data gathered from IoT systems in order to optimize automatic decisions in the city transportation system, including: optimizing the vehicle routing, recommending customized transportation modes to the citizens, generating efficient ride-sharing and car-sharing strategies, create optimal charging station for electric vehicles and different services within urban and interurban areas. A numerical example considering a DRSP is provided, in which the potential of employing edge/fog computing, open data, and agile algorithms is illustrated.

scholarly journals Routing and Mobility Management in the Internet of Things

2020 ◽  
Author(s):  
Bruno Pereira Santos ◽  
Luiz Filipe Menezes Vieira ◽  
Antonio Alfredo Ferreira Loureiro
Keyword(s):  
Internet Of Things ◽  
Mobility Management ◽  
Intelligent Transportation Systems ◽  
Computer Network ◽  
Smart Cities ◽  
Transportation Systems ◽  
The Internet ◽  
Research Areas ◽  
New Research ◽  
The Impact

This Ph.D. Thesis proposes new techniques for routing and mobility management for Internet of Things (IoT). In the future IoT, everyday mobile objects will probably be connected to the Internet. Currently, static IoT's devices have already been connected, but handle mobile devices suitably still being an open issue in IoT context. Then, solutions for routing mobility detection, handover, and mobility management are proposed through an algorithm that integrates Machine Learning (ML) and mobility metrics to figure out devices' mobility events, which we named Dribble. Also, an IPv6 hierarchical routing protocol named Mobile Matrix to boost efficient (memory and fault tolerance) end-to-end connectivity over mobility scenarios. The Thesis contributions are supported by numerous peer-reviewed publications in national and international conferences and journals included in ISI-JCR. Also, the applicability of this Thesis is evident by showing that our results overcome state-of-the-art in static and mobile scenarios, as well as, the impact of the proposed solutions is a step forward in at least two new research areas so-called Internet of Mobile Things (IoMT) and Social IoT, where devices move around and do social ties respectively. Moreover, during the Ph.D. degree, the author has contributed to different computer network fields rather than routing by publishing in areas like social networks, smart cities, intelligent transportation systems, software-defined networks, and parallel computing.

scholarly journals A NOVEL DEEP LEARNING BASED METHOD FOR DETECTION AND COUNTING OF VEHICLES IN URBAN TRAFFIC SURVEILLANCE SYSTEMS

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 793-800
Author(s):  
J. J. Majin ◽  
Y. M. Valencia ◽  
M. E. Stivanello ◽  
M. R. Stemmer ◽  
J. D. Salazar
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Management Strategies ◽  
Transportation Systems ◽  
Urban Traffic ◽  
Surveillance Systems ◽  
Real Time Processing ◽  
Detection Model

Abstract. In intelligent transportation systems (ITS), it is essential to obtain reliable statistics of the vehicular flow in order to create urban traffic management strategies. These systems have benefited from the increase in computational resources and the improvement of image processing methods, especially in object detection based on deep learning. This paper proposes a method for vehicle counting composed of three stages: object detection, tracking and trajectory processing. In order to select the detection model with the best trade-off between accuracy and speed, the following one-stage detection models were compared: SSD512, CenterNet, Efficiedet-D0 and YOLO family models (v2, v3 and v4). Experimental results conducted on the benchmark dataset show that the best rates among the detection models were obtained using YOLOv4 with mAP = 87% and a processing speed of 18 FPS. On the other hand, the accuracy obtained in the proposed counting method was 94% with a real-time processing rate lower than 1.9.

scholarly journals Authentication-Based Secure Data Dissemination Protocol and Framework for 5G-Enabled VANET

2020 ◽  
Vol 12 (4) ◽  
pp. 63
Author(s):  
Nishu Gupta ◽  
Ravikanti Manaswini ◽  
Bongaram Saikrishna ◽  
Francisco Silva ◽  
Ariel Teles
Keyword(s):  
Automobile Industry ◽  
Intelligent Transportation Systems ◽  
Data Dissemination ◽  
Smart Cities ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
The Internet ◽  
Vehicular Communication ◽  
Security Attacks ◽  
Architecture Model

The amalgamation of Vehicular Ad hoc Network (VANET) with the Internet of Things (IoT) leads to the concept of the Internet of Vehicles (IoV). IoV forms a solid backbone for Intelligent Transportation Systems (ITS), which paves the way for technologies that better explain about traffic efficiency and their management applications. IoV architecture is seen as a big player in different areas such as the automobile industry, research organizations, smart cities and intelligent transportation for various commercial and scientific applications. However, as VANET is vulnerable to various types of security attacks, the IoV structure should ensure security and efficient performance for vehicular communications. To address these issues, in this article, an authentication-based protocol (A-MAC) for smart vehicular communication is proposed along with a novel framework towards an IoV architecture model. The scheme requires hash operations and uses cryptographic concepts to transfer messages between vehicles to maintain the required security. Performance evaluation helps analyzing its strength in withstanding various types of security attacks. Simulation results demonstrate that A-MAC outshines other protocols in terms of communication cost, execution time, storage cost, and overhead.

scholarly journals Cooperation and radio silence strategy in Mix Zone to Protect Location Privacy of Vehicle in VANET

2021 ◽  
Vol 28 (1) ◽  
pp. 31-39
Author(s):  
Izdihar Shaleesh ◽  
Akram Almohammedi ◽  
Naji Mohammad ◽  
Ali Ahmad ◽  
Vladimir Shepelev
Keyword(s):  
Intelligent Transportation Systems ◽  
Traffic Accidents ◽  
Location Privacy ◽  
Smart Cities ◽  
Transportation Systems ◽  
High Rate ◽  
The Internet ◽  
Vehicular Communication ◽  
Internet Of Vehicles ◽  
The Internet Of Things

With increase in the population, the number of registered vehicles has dramatically increased over all the world, and this leads to a high rate of traffic accidents on the roads. Therefore, in order to prevent such accidents, an Intelligent Transportation Systems (ITSs) is needed to be installed to notify drivers of obstacles in advance. Recently, the Internet of things (IoT) evolves the vehicular communications and covers this technology under the Internet of vehicles (IoV) application. IoV is a new field for the automotive industry and a significant part of the smart cities. However, protecting the privacy of vehicle's location is the most challenging subject in the vehicular communication, as because it threatens the personal life of drivers. This paper provides cooperation and radio silence strategy in mix zone (CRSMZ) to protect location privacy of vehicle in IoV. The strategy implements either cooperation or radio silence depending on the speed of the vehicle while it is in mix _zone. The simulation results show that CRSMZ is an efficient strategy to protect location information of vehicle drivers. CRSMZ outperforms the existing strategies in terms of mean of the number tracker confusion, continuous tracking period and max of the entropy.

scholarly journals Applications of Deep Learning Techniques for Pedestrian Detection in Smart Environments: A Comprehensive Study

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Fen He ◽  
Paria Karami Olia ◽  
Rozita Jamili Oskouei ◽  
Morteza Hosseini ◽  
Zhihao Peng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Smart Cities ◽  
Pedestrian Detection ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Main Challenge ◽  
Learning Techniques ◽  
The World ◽  
Self Driving Cars

Intelligent transportation systems have been very well received by car companies, people, and governments around the world. The main challenge in the world of smart and self-driving cars is to identify obstacles, especially pedestrians, and take action to prevent collisions with them. Many studies in this field have been done by various researchers, but there are still many errors in the accurate detection of pedestrians in self-made cars made by different car companies, so in the research in this study, we focused on the use of deep learning techniques to identify pedestrians for the development of intelligent transportation systems and self-driving cars and pedestrian identification in smart cities, and then some of the most common deep learning techniques used by various researchers were reviewed. Finally, in this research, the challenges in each field are discovered, which can be very useful for students who are looking for an idea to do their dissertations and research in the field of smart transportation and smart cities.

Sign in / Sign up

Export Citation Format

Share Document