Intelligent Technologies for Internet of Vehicles

The IoT concept comes from products that go from the refrigerator to the washing machine, even smart sensors and smart devices that can be connected and regulated by mobile devices. In this sense, as the automotive industry continues to accelerate towards connected cars, more Internet of Vehicles (IoV) solutions, which technology would be similar to the IoT that is already known, but focused on connectivity in vehicles. Thus, the IoV is the possibility for vehicles to connect and exchange information, it is the possibility that vehicles communicate with each other automatically, consisting of a subarea of IoT applied to automobiles. Through IoT technology and mobile technology, people have the feeling of being connected all the time, and through IoV, this possibility is transformed into reality in solution integrated into data, device, and operations management through the implementation of secure and unified network access considering mass data collection and analysis. Representing the innumerable possibility of services can be explored with data and with Information Technology fully integrated with Automation Technology. Besides, IoV is an ecosystem that has an extensive field of intelligent transport systems, with a variety of traffic control solutions, transport management, emergency telecommunications cluster, secure, efficient, and ubiquitous wireless connections. Therefore, this chapter has the mission and objective of providing an updated overview of IoV, it is worth mentioning the novelty of this manuscript is in dealing with the approach to the theme focusing on the role of this technology in modern perspectives, categorizing and synthesizing the potential of the technique.

With the deployment of 5th Generation networks, characterized by a wider bandwidth and an increased computational capability, is now possible to develop more complex services that requires low latency, such as applications for public safety based on artificial intelligence. To this aim, it has been studied a possible use of the so-called Multi-access Edge Computing (MEC) enabled by 5G that reduces the latency thanks to computational resources located closer to the user. This allows to deploy an application that recognizes the formation of traffic queues on the highway through the analysis of video streams, to be used in the context of smart mobility. In order to do so, it is needed to detect the travelling vehicles and to track their movement to understand when a traffic jam is occurring. For the implementation, the Convolutional Neural Network (CNN) paradigm has been leveraged for the detection of the vehicles. Among the several alternatives compared, it has been chosen the third version of You Only Look Once (YOLO) for its trade-off between accuracy and real-time computation. Then, the detections tracked through the Simple Online and Realtime Tracking (SORT) algorithm are exploited to identify the direction of the traffic flows and then to calculate when the vehicles are slowing down or stopping, by either measuring the number of stationary vehicles or the travelling time of the vehicles within a region of interest. The service has been developed with the objective of being employed through the parallel computation offered by 5G MEC servers equipped with modern GPUs, in order to obtain real-time performances.

This chapter presents the Internet of Vehicles (IoV) concept, technologies and applications used to realise intelligent functions, optimise vehicle performance, control, and decision-making for future electric, connected, autonomous, and shared (ECAS) vehicles mobility scenarios. The concept addresses the convergence of the edge intelligence embedded in the vehicles based on Artificial Intelligence (AI) technologies with the cooperative, collaborative intelligence distributed into the Internet of Things (IoT) devices and edge computing infrastructure federated with the hierarchical cognitive processes and analytics in physical, network, infrastructure, and data spaces. IoV integrates and links the ECAS vehicles’ domains with the intra-vehicle networks, vehicle-to-everything (V2X) networks, the processing and cognitive functions provided by federated platforms using the intelligent edge and cloud computing infrastructure. The cognitive transformation of vehicles and the integration of immersive technologies, i.e., virtual reality (VR) and augmented reality (AR) combined with intelligent connectivity, IoT, Distributed Ledger Technologies (DLTs), digital twins (DTs), data, knowledge, security/privacy requirements and learning platforms provide the technological foundation of IoV allowing for entirely new services, applications, and user experiences. The paper advances the latest architectural concepts for ECAS vehicles. It proposes an IoV 3D multi-layered architecture that combines AI, edge computing and connectivity as part of the functional layers while integrating the system properties and trustworthiness properties into the overall architecture to provide efficient new mobility applications and services. The proposed system of systems concept for IoV applications allows for distributed intelligent functions to be embedded into the edge and cloud infrastructure for ECAS vehicles to provide a computing, processing, and intelligent connectivity continuum for IoV applications and services.

Internet of things (IoTs) has been emerging significantly in recent years and has its impact on different industries, one of such is the automotive industry. In automotive industry, Internet of Vehicles (IoVs) gain considerable attention as it is one of the important constituents of IoTs. There are different scenarios with different network requirements to be considered in IoVs. For instance, safety messages require low latency network, while on the other hand, infotainment services demand high bandwidth network. For such various requirements, the network should be able to allocate appropriate resources to accomplish the desired service. One of the promising technologies that is leveraged to fulfil such goal is Network Slicing. With network slicing, the underlying infrastructure is divided into multiple slices each equipped with required resources to meet specific need. To slice the network, the infrastructure should be controllable in a way that allow a central unit to guide the slicing process. For this purpose, Software-defined Networking (SDN) is utilised to decouple the control plane from the data plane, allowing a separate unit to take control. In this chapter, we discuss vehicular SDN slicing and how to boost it with intelligent capabilities using recent advances in machine and deep learning.

In the Internet of Vehicles (IoV), the Internet of Things (IoT) is integrated with Vehicular Ad hoc NETworks (VANET). This enables gathering, processing and sharing of lots of information (regarding vehicles, roads and their surroundings) through the Internet and hence, helps in making intelligent decisions. On the other hand, Software Defined Networking (SDN) has the capability of designing a flexible programmable IoV network that can foster innovation and reduce complexity. Applying SDN in IoV will be useful, as SDN enabled IoV devices can be controlled seamlessly from an external server (called a controller) which can be located in the cloud and may have computational resources to run resource-intensive algorithms, making intelligent decisions. This chapter provides an introduction about SDN, describes the benefits of integrating SDN in IoV and reports the recent advances. It also presents an Artificial Intelligence (AI) based architecture and open challenges. Finally, the chapter presents an automatic configuration method with which SDN can be deployed automatically in IoV without any manual configuration. The experiments are performed on a publicly available European testbed using an emulator for wireless SDN networks. Experiments are conducted for automatic configuration of SDN in IoV network’s topologies and for data collection in SDN enabled IoV. The results show the effectiveness of the proposed automatic configuration method. Furthermore, AI-assisted intelligent decisions supported by SDN enabled IoV are introduced. The challenges and solutions presented in this chapter may have a huge impact on the speed at which IoV infrastructure can efficiently evolve with market evolution.

Recently, there was much interest in Technology which has emerged greatly to the development of smart cars. Internet of Vehicle (IoV) enables vehicles to communicate with public networks and interact with surrounding environment. It also enables vehicles to exchange information in addition to collect information about other vehicles and roads. However, actual applications of smart IoV systems face many challenges. These challenges are related to different problematic issues like big data connection with IoV, cloud network, data processing, and efficient communication between a large amount of different vehicles types, in addition to optimum decision data processing on or off board. Intelligence of the huge amount of data that can be processed to reduce road congestion and improve traffic management, as well as ensuring road safety is an important issue in future IoV trends.

Artificial Intelligence (AI) technology with Machine Learning (ML) mechanisms offers smart solutions that can improve IoV network efficiency. For example, decision for data processing at various layers i.e. on-board units (OBUs), Fog level or cloud level are one of the problems which need ML algorithms. Other critical issues that can be resolved by ML mechanisms are time, energy, rapid topology of IoV, optimization quality of experience (QoE) and channel modeling. These issues need to be optimized. This chapter provides theoretical fundamentals for ML models, algorithms in IoV applications and future directions.

Internet of vehicles (IoV) has become an important revolution of intelligent transportation system (ITS). It became an emerging research area as the need for it has increased tremendously. With a great number of applications available, in addition to the intention to improve the quality of life and quality of services, the application of artificial intelligence (AI) techniques would dramatically enhance the performance of the IoV overall system. This chapter will discuss deep learning networks as a type of machine learning use in IoV with influence of Neural Networks (NN), where great amounts of unlabeled data are processed, classified and clustered. Deep learning network approaches i.e., Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Deep Reinforcement Learning (DRL), classification, clustering, and predictive analysis (regression) will briefly discussed in this chapter, in addition to review its ability to obtain better performing IoV applications.

Reducing vehicle energy demand has been the subject of academic research for several years. Distributing energy equally and efficiently among vehicle wheels addresses challenges that may have an impact on energy consumption. Therefore, this chapter aims to contribute through the proposal of a novel system by integrating smart panels. The effects of road’s change of gradient and anomalies motivate us to work on more torque at the wheel joints that demand more energy procurement. Though the supply affects all the wheels equally, which interprets for the engine as more consumption. We approach the emerging issue by developing a V2SP (Vehicle to Smart-Panel) system in fluid dynamics. Based on fundamental mathematics equations of fluid flow from Navier–Stokes, we implement an algorithm that could run in real-time on the grid that will be integrated on panels and interact accordingly with a vehicle’s operational system. The objective is the distribution of the appropriate energy among wheels based on their needs.

Internet-of-vehicle (IoV) is a heterogeneous environment involving information exchange between system components such as road infrastructure devices, vehicular embedded sensors and other vehicular elements. In IoV network, devices communications and data exchange need to be secure, efficient and transparent to achieve the platform’s goals. Blockchain technology is proved to provide decentralization, immutability, security and transparency properties due to the features of its distributed ledger. In this chapter, we introduce the integration of blockchain technology into IoV networks to support the essential data exchange and storage requirements such as decentralizing, security and transparency. We describe blockchain terminologies and how blockchain can be adopted in IoV environments. Then, we explain blockchain support for IoV data sharing. Besides, blockchain support for IoV trust and verification is also clarified. We also explore the most popular blockchain-based IoV applications the researchers have developed.

Vehicle guidance systems are considered key to improve capacity and safety of transport systems. Information and communication technologies enable both vehicle speeds and distances to be optimized without being limited to human reaction times. As the major two competing topological approaches for communication networks, viz. ad-hoc and cellular networks, exhibit specific advantages and disadvantages in different applications, there is still no standardized solution in the offing. Established encryption methods have either proven to be insecure or lack real-time capabilities when used in distributed automation systems, where the only proven secure concept for encryption – perfect security – has not been employed so far due to practical shortcomings. Meeting existing standards, a communication architecture for vehicle guidance systems allowing for perfectly secure encryption and observing real-time requirements for wireless communication is presented. Its core components are a central instance authenticating all participants, generating and distributing the required keys as well as a transmission infrastructure based on relay stations. Different sensitivity analyses show that one-time pad cryptography can keep up with or even outperform the AES in the presented use case. The keys required for a sufficiently long operating time can be stored on common storage media.

With the rapid development of smart transportation, autonomous vehicles (AVs) are becoming one of the most anticipating means of transport. However, as the complexity of autonomous vehicles is increasing, it is intuitive that it would bring along with more possible attacks and higher potential risks. For example, by tampering the in-car sensors or hacking into any of the electronic control units (ECUs) in the vehicle, it could severely affect the driving performance or even cause life-threatening situations to users. Moreover, since AVs will also be the Internet of Vehicles (IoVs) that connect to the vehicular network in the future, the network security of the intra-vehicular and inter-vehicular links should also be carefully studied. To identify and mitigate the security risks involved in AV holistically, in this chapter, we provide a comprehensive taxonomy for attack surfaces and countermeasures for defense. Specifically, four different attack surfaces are defined, namely ECUs, sensors, intra-vehicular links, and inter-vehicular links. For each of the attack surfaces, various common attack vectors are discussed in detail. Subsequently, we also provide a survey of the latest major existing work for defending the attacks on each surface. We hope this chapter can be a guide for the general public to understand the security aspect of AVs, as well as to encourage future researchers to improve the security in AVs.

This chapter will tackle one of the most important disadvantages that will take place in the Vehicular Ad Hoc Network during a crisis scenario. Vehicular Ad Hoc Network which is abbreviated as VANET is a variation of Mobile Ad Hoc Network (MANET). VANET routing protocols are a wide research area due to their different classifications with the pros and cons of each. This chapter will summarize the five VANET routing protocols categories. The common criteria among those five-routing protocols are the requirement of infrastructure which is also known as a road-side unit (RSU) or base station (BS). The role of the RSU is to provide an internet connection. Packets will be uploaded to the RSU which will, in turn, be uploaded to the internet thus making them available for future download. In a crisis scenario, one or more RSU might be disconnected from the internet which will result in a disconnected network. The disconnected network will lead to the failure of packet upload and time out leading to loss. This chapter will propose a protocol to ensure a successful packet delivery with a disconnected RSU from the internet. The network is considered as a set of sensors that periodically upload data to the RSU which in turn uploads them to the internet. The sensors might be those of Wireless Sensor Network (WSN) or onboard sensors. The proposed protocol will take into consideration that vehicles are assumed to be capable of short-range wireless communication and hence can collect data from a nearby RSU. The main target of the proposed protocol is to ensure a successful data transfer during the time a certain vehicle known as the carrier vehicle is within the communication range of a road-side unit. A simulation carried in MATLAB studied the different effects of network parameters on the successful data transfer from the disconnected RSU to the carrier vehicle.

Vehicular Delay Tolerant Network (VDTN) routing is referred to the hybridization of Delay Tolerant Networks (DTNs) with VANETs which mobilizes both knowledge-based and geography-based forwarding techniques. Numerous shortage are stated in existing VDTN routing protocols in both modes exposes such as the inaccurate location information and uncontrolled congestion due to bundles flooding. In this paper, we introduce a hybrid VDTN routing strategy combining a swarm-inspired algorithm, namely the Firefly Algorithm (FA) to enhance the decision-making of finding better next Store-Carry-and-Forward (SCF) relay vehicle in accordance with the use of geographical forwarding for better localization of closer nodes to the destination. Thus, the flooding of bundles is controlled by the movement of fireflies in early routing stages, then a reliable geographic routing is followed to better track closer SCF vehicles toward bundle’s destination. We implement our approach using the Opportunistic Network Environment (ONE) simulator and compare it with few common DTN routers, namely Spray-and-Wait (SnW), ProPHET and Epidemic (ER) routers; the simulation results shows superior balance between average delivery delays and delivery probability with a reasonable overheads ratio and flooding levels.

Delay-Tolerant Networks (DTNs) are networks where there are no permanent end-to-end connections, that is, they have a variable topology, with frequent partitions in the connections. Given the dynamic characteristics of these networks, routing protocols can take advantage of dynamic information, such as the node’s location, to route messages. Geolocation-based routing protocols choose the node that moves closer to the location of the message destination as the message carrier. However, such protocols suffer from obsolete location information due to node mobility and network partitions. In this chapter and conversely to the state-of-the-art, an epidemic-based decentralized localization system (i.e., DTN-Locate) and a hybrid location-based routing (i.e., SnLocate) are proposed. The former is used for disseminating node’s localization information meanwhile the latter to create and route multiple copies of a message, using geographic mechanisms to disseminate them. Besides, a novel distributed contention mechanism is also proposed. The performance evaluation shows that the SnLocate protocol has a higher delivery rate and lower latency than other geographic and non-geographic routing protocols considered.

This chapter presents the results of a narrative literature review study of acceptability of new assistive and information technology, including Internet of Things (IoT) technologies and artificial intelligence, by older adults (65 or older). The study followed a careful search strategy in specific databases and was based on inclusion/exclusion criteria and keywords. The search strategy resulted in 28 articles, which reflected the research aim, and were reviewed on the basis of an interpretive approach and critically appraised in accordance with the ‘critical assessment skills programme’ guidelines. This study is an important contribution to scholarship because, unlike other literature reviews, it explored both assistive and information technology and looked for overarching reasons why older adults may accept new technology. The results showed that older adults accept technology when they have a good sense of control over the devices and their lives, the technology is useful, has characteristics which are not threatening, and other compromising factors such as financial cost, restricting health conditions and inappropriate physical environment are not present. Based on these findings, we propose the N-ACT principles whereby technology developers should consider users’ Needs, Adjustable technology and personalised service, users’ Control over technology and their lives and Trust in technology.

This chapter presents the procedure and results of piloting vINCI, a new ambient assisted technology. vINCI aims to enhance older adults’ active life and quality of living by measuring end-users’ physical, psychological and social state and providing them with information and feedback about any necessary corrective measures they need to take. To achieve this, vINCI has been based on a microservices architecture and integrated IoT (Internet of Things) monitoring technologies and artificial intelligence. The interconnected devices which are capturing end-users’ biopsychosocial state are tablets (the vINCI app), smart insoles and smart watches. In order to ensure that end-users would accept and use such set of technologies, this study employed a mixed research methodology to understand any acceptability factors. The results indicated that clarity of instructions, comfort of technology, ease to use, usefulness, and a sense of safety, control, familiarity and normalisation were very important features of vINCI, which could cause participants to accept and use such technology. The study highlights the importance of a mixed research method for gauging acceptability in order to ensure that the end-users’ experience with new technology during pilots is fully captured and understood.