The Internet of Vehicles (IoV) represents a significant advancement in intelligent transportation systems (ITS), enabling real-time data exchange between vehicles and infrastructure to enhance road safety, traffic efficiency, and user experiences. Vehicular edge computing (VEC) has emerged as a critical enabler, offering localized data processing and facilitating data trading among vehicles and edge servers. While data trading enhances system efficiency by enabling seamless information exchange among vehicles and infrastructure, it also introduces significant challenges in preserving user privacy, protecting against malicious tracking, and managing energy consumption effectively. To tackle these challenges, we propose a novel Energy-Efficient Pseudonym Management with Dueling Deep Q-Network (E2PM-DDQN) framework for VEC-enabled IoV, aiming to enhance the balance between privacy protection and energy efficiency during data trading. By deploying an RL agent at VEC servers, our approach dynamically manages pseudonym updates during data trading, improving the trade-off between privacy and energy consumption. Simulation results in a VEC-enabled IoV environment confirm that our proposed E2PM-DDQN framework achieves higher privacy entropy than state-of-the-art approach, enables higher rewards than baseline strategies, and ensures lower energy consumption. These results highlight how a reinforcement learning (RL) approach outperforms non-RL methods.

The evolution of vehicular networks from vehicular ad-hoc networks (VANETs) to Internet of Vehicles (IoVs) has played a pivotal role in the intelligent transportation system (ITS). However, these networks are increasingly vulnerable to security, privacy, and trust (SPT) threats due to various emerging attacks. In response, Reinforcement Learning (RL) has emerged as a promising technique for strengthening vehicular network security. This paper provides a comprehensive exploration of the SPT challenges within vehicular networks and presents RL as a promising solution for enhancing SPT provisioning. First, we provide a tutorial on vehicular networks and integrated concepts, and the overview of RL concepts and different types of RL. Then, we conduct a detailed analysis of existing RL-based solutions, categorizing them within two novel taxonomies: one based on the specific SPT focused area and the other on the specific RL methods employed. We conclude by discussing key lessons learnt, current open challenges, and potential future directions in this rapidly evolving field.

The fairness of Artificial Intelligence (AI) has gained tremendous attention within the criminal justice system in recent years, mainly when predicting the risk of recidivism. The primary reason is attributed to evidence of bias towards demographic groups when deploying these AI systems. Many proposed fairness-improving techniques applied at each of the three phases of the fairness pipelines, pre-processing, in-processing and post-processing phases, are often ineffective in mitigating the bias and attaining high predictive accuracy. This paper proposes a novel approach by integrating existing fairness-improving techniques: Reweighing, Adversarial Learning, Disparate Impact Remover, Exponential Gradient Reduction, Reject Option-based Classification, and Equalized Odds optimization across the three fairness pipelines simultaneously. We evaluate the effect of combining these fairness-improving techniques on enhancing fairness and attaining accuracy. In addition, this study uses multi- and bi-objective optimization techniques to provide and to make well-informed decisions when predicting the risk of recidivism. Our analysis found that one of the most effective combinations (i.e., disparate impact remover, adversarial learning, and equalized odds optimization) demonstrates a substantial enhancement and balances achievement in fairness through various metrics without a notable compromise in accuracy.

In smart cities, graph embedding technologies, Graph Neural Networks (GNNs), and related variants are extensively employed to address predictive tasks within complex urban networks, such as traffic management, the Internet of Things (IoT), and public safety. These implementations frequently require processing substantial personal information and topological details in graph formats, thereby raising significant privacy concerns. Mitigating these concerns necessitates an in-depth analysis of existing privacy preservation techniques integrated with GNNs in the specific context of smart cities. To this end, this paper provides a comprehensive systematic review of current applications of privacy-aware GNNs in smart cities. Our research commenced with a methodical literature search that identified 14 pertinent papers and summarized prevalent privacy preservation mechanisms, including federated learning, differential privacy, homomorphic encryption, adversarial learning, and user-trust-based approaches. Subsequent analysis examined how the integration of these technologies with GNNs enhances privacy security and model utility in smart city applications. Further, we proposed an analytical framework for privacy-aware GNNs across the machine learning lifecycle, assessing the challenges of current integration from a practical viewpoint. The paper concluded by suggesting potential directions for future research.

Permissioned distributed ledgers (PDLs) provide security and trust for Internet of Vehicles (IoV) applications, but face scalability issues due to resource-intensive consensus mechanisms. To address this, we propose a novel hybrid consensus network (HCN) architecture that leverages the computational capabilities of parked connected autonomous vehicles (CAVs) through a multi-layer vehicular edge computing (VEC) framework. The HCN is designed following guidelines outlined by the European Telecommunications Standards Institute (ETSI) regarding the structuring of PDLs. It aims to improve the performance, reliability and scalability of PDL-based IoV networks while maintaining their security and trust guarantees.

Vehicular edge computing (VEC) empowers real-time applications in the autonomous vehicle (AV) domain by positioning edge servers closer to AVs. This proximity reduces latency and energy consumption for task processing. However, effectively managing the offloading of these tasks and allocating resources across dynamic vehicular environments poses significant challenges. Centralized strategies face scalability hurdles, while decentralized approaches often lack cooperative and co-ordinated mechanisms. To tackle these limitations, this paper introduces a novel decentralized framework for optimizing task management and network resource utilization in dynamic vehicular settings. This framework is equipped with a multi-agent deep reinforcement learning algorithm (MADRL) that makes intelligent task offloading decisions. The proposed algorithm considers the diverse computing capabilities of network entities and enhances energy efficiency without compromising latency or task completion rates. The simulation-based performance assessment demonstrates the effectiveness of this framework in reducing energy consumption and improving task completion rates in comparison to existing algorithms.

The development of the Internet of Vehicles (IoV) and autonomous vehicles plays a significant role in intelligent transportation systems (ITS) that are empowered by vehicular networks. However, the dynamic nature of these networks presents challenges that need to be addressed. Reinforcement learning (RL) has emerged as an effective technique for strengthening vehicular networks. The use of standard single-agent RL and deep reinforcement learning (DRL) has recently been demonstrated to enable each network entity as a decision-making agent to adapt to unknown environments by learning an optimal decision-making policy. However, in the complex and dynamic environments of vehicular networks, the limitations of single-agent approaches become apparent. Multi-agent reinforcement learning (MARL) offers a compelling alternative, enabling net-work entities to learn their optimal policies by observing the environment as well as the policies of other network entities. Due to this, MARL has recently been used to solve various problems in IoV by improving its learning efficiency. In this paper, we review the applications of MARL in IoV networks. Following the review, four main application areas for MARL in IoV were identified, namely: resource management, task offloading, trust management, and privacy preservation. Furthermore, the MARL-based approaches in IoV were classified into three main categories: fully centralized, fully decentralized, and centralized training with decentralized execution (CTDE) depending on the MARL architecture employed. Finally, we discuss the challenges, open issues, and future directions related to the applications of MARL in the IoV.

Artificial Intelligence (AI) is applied in almost every public sector because of its positive impacts. However, AI’s ethical aspects and trustworthiness constitute a significant uproar and concern among different AI stakeholders due to AI’s adverse effect on users when the AI system lacks cautionary measures. AI is used in the criminal justice system for predicting recidivism risk. However, AI’s negative impact translates into bias and high incarceration towards a group of defendants in a population assessed for recidivism risk. This paper focuses on fairness as a requirement of a trustworthy AI framework previously proposed to ascertain the appropriate application of AI systems in predicting recidivism. This paper aims to raise awareness about the fairness of AI models and stimulate further research and deployment of efficient and effective exploitation of fair and trustworthy AI models in the criminal justice system when predicting recidivism. Fairness has been a significant concern for criminal justice system stakeholders and has received considerable attention with more theoretical and practical studies than other trustworthy AI requirements. Hence, this paper reviews state-of-the-art fairness, outlines valuable findings, and proposes future directions to achieve fair AI systems for predicting recidivism risk. In addition, this paper ensures mapping existing technical works in the literature to the fairness pipeline corresponding to the criminal justice system’s AI development phases.

Vehicle-to-everything communication (V2X) has recently attracted considerable attention in 5G and beyond 5G due to its potential benefits, including increased capacity, spectral efficiency, and delay reduction, as well as the ability to provide new services associated with intelligent transportation. Several modes of communication can be used for V2X communications, namely sidelink mode, cellular uplink/downlink mode, and combined modes of communication which enable vehicles to communicate directly with each other. The challenge, however, is to select the appropriate operating mode in accordance with the requirements of V2X services. To minimize the overall latency of the V2X communications links, we propose a novel latency-aware mode coordination (LAMOC) algorithm that constructs an association graph of the vehicular network’s elements and finds the feasible path that minimizes total latency. The proposed solution is assessed using a simulation-based analysis. Simulation results have demonstrated that the proposed solution improves network performance in terms of reliability and latency in various scenarios.

Vehicular Ad-Hoc Networks (VANETs) are very promising in the context of intelligent transportation systems. VANETs are vulnerable to various types of attacks, including black hole and gray hole attacks, which can disrupt or intercept communication and compromise the security and reliability of the network. To address this issue, we propose a method for detecting and preventing malicious vehicles activity in VANETs by utilizing a trustworthy routing technique based on Q-learning (QL-TRT). Our approach, which is formulated based on the Markov Decision Process, allows the vehicle to choose the best neighbor for routing and avoid malicious neighbors. To evaluate the trustworthiness and reliability of the links between pairs of vehicles, we consider factors such as packet forwarding ratios, energy consumption, and expected transmission time. Q-learning is used to learn the trust value of links and select the most trusted route from source to destination. The evaluation results demonstrate the effectiveness of QL-TRT in detecting black hole and gray hole attacks, while ensuring the communication performance in VANETs.

Contact tracing apps used in tracing and mitigating the spread of COVID-19 have sparked discussions and controversies worldwide. The major concerns in relation to these apps are around privacy. Ireland was in general praised for the design of its COVID tracker app, and the transparency through which privacy issues were addressed. However, the ”voice” of the Irish public was not really heard or analysed. This study aimed to analyse the Irish public sentiment towards privacy and COVID tracker app. For this purpose we have conducted sentiment analysis on Twitter data collected from public Twitter accounts from Republic of Ireland. We collected COVID-19 related tweets generated in Ireland over a period of time from January 1, 2020 up to December 31, 2020 in order to perform sentiment analysis on this data set. Moreover, the study performed sentiment analysis on the feedback received from a national survey on privacy conducted in Republic of Ireland. The findings of the study reveal a significant criticism towards the app that relate to privacy concerns, but other aspects of the app as well. The findings also reveal some positive attitude towards the fight against COVID-19, but these are not necessarily related to the technological solutions employed for this purpose. The findings of the study contributed to the formulation of useful recommendations communicated to the relevant Irish actors.

Contact tracing apps used in tracing and mitigating the spread of COVID-19 have sparked discussions and controversies worldwide with major concerns around privacy. COVID Tracker app used in the Republic of Ireland was praised in general for the way it addressed privacy and was used as baseline for other contact tracing apps worldwide. The success of the app is dependent on the general public uptake, hence their voice and attitude is the one that really matters. This paper focuses on developing a survey and the methods aiming to examine the attitudes toward privacy during COVID-19 of the general public in the Republic of Ireland and their impact on the uptake of the COVID tracker app. Various privacy models are used and health belief model as well in this purpose. A pilot study with 286 participants show a change in attitude towards privacy during COVID-19 pandemic, with more people willing to share their data in the interest of saving lives. However, privacy attitudes are shown to have impacted the adoption of the app in Ireland.

The General Data Protection Regulation (GDPR) is a prescriptive legislation in the European Union (EU) for privacy and data protection that applies to every organisation within the EU and any organisation outside the EU if they offer goods or services to EU citizens. The enforcement of GDPR created a big challenge for organisations which were required to create new professional figures, system, policies, procedures and standards, budget for new investments, and to set up a project plan or catalogue specific to the GDPR. This paper focuses on the GDPR 'right to be forgotten' and the specific implementation challenges it poses. The research study used two surveys to collect data from both organisations and users. The results show that while organisations are struggling with GDPR and right to be forgotten, there are also positive aspects about its implementation that translate into improved data privacy. The findings related to the users show that they are in general happy with the legislation.

Teachers are facing many difficulties when trying to improve the motivation, engagement, and learning outcomes of students in Science, Technology, Engineering, and Mathematics (STEM) subjects. Game-based learning helps the students learn in an immersive and engaging environment, attracting them more towards STEM education. This paper introduces a new interactive educational 3D video game called Final Frontier, designed for primary school children. The proposed game design methodology is described and an analysis of a research study conducted in Ireland that investigated learner experience through a survey is presented. Results show that: (1) 92.5% of students have confirmed that the video game helped them to understand better the characteristics of the planets from the Solar system, and (2) 92.6% of students enjoyed the game and appreciated different game features, including the combination between fun and learning aspects which exists in the game.

In recent years, the emerging immersive technologies (e.g. Virtual/Augmented Reality, multisensorial media) bring brand-new multi-dimensional effects such as 3D vision, immersion, vibration, smell, airflow, etc. to gaming, video entertainment and other aspects of human life. This paper reports results from an European Horizon 2020 research project on the impact of multisensoral media (mulsemedia) on educational learner experience. A mulsemedia-enhanced test-bed was developed to perform delivery of video content enhanced with haptic, olfaction and airflow effects. The results of the quality rating and questionnaires show significant improvements in terms of mulsemedia-enhanced teaching.

Cycling, as a very attractive green form of transportation, is also one of the most sustainable. Electric bicycles, the most popular electric vehicles, subscribe to this type of transportation, being highly environmentally friendly. They have several advantages when compared to traditional bicycles, but also a weak point in terms of long battery (re)charging duration. Consequently power-saving solutions for electric bicycles are of high research interest. In this context, this paper proposes a novel energy-efficient weather-aware route planner (eWARPE) for electric bicycles. The solution makes use of the weather information in order to recommend the optimal departure time that allows the cyclist to avoid the adverse weather conditions and to maximize the energy savings of the electric bicycle. Note that the departure time is in a user-configurable time interval. The departure time can be recommended for a preferred route introduced by the user or for a route built in eWARPE based on user input. The proposed solution was validated through numerical analysis. Moreover, a survey was conducted in order to assess the impact of the adverse weather conditions on cyclists and to measure how the cyclists will benefit from the proposed solution.

Vehicular ad-hoc networks (VANETs) are considered to have an enormous potential in enhancing road traffic safety and traffic efficiency. Socio-economic challenges, network scalability and stability are identified among the main challenges in VANETs. In response to these challenges, this paper proposes a novel user-oriented Fuzzy Logic-based k-hop distributed clustering scheme for VANETs that takes into consideration the vehicle passenger preferences. The novelty element introduced is the employment of Fuzzy Logic as a prominent player in the clustering scheme. To the best knowledge of the authors, there are no Fuzzy Logic-based clustering algorithms designed for VANETs. Simulation-based testing demonstrate how the proposed solution increases the stability of vehicular networks, lifetime and stability of cluster heads compared to both the classic Lowest ID algorithm and an utility function-based clustering scheme previously proposed by the same authors.

Information provided in real-time via Vehicular Ad-hoc Networks is of great value in any kind of traffic systems. Bandwidth issues arise in this type of networks due to the potential large number of nodes. Data aggregation addresses these issues avoiding the dissemination of similar messages in the network. The lack of flexibility in the similarity criteria, security issues and the need of standardization were mentioned among the challenges of data aggregation schemes. Fuzzy Logic, very efficient in real-time systems, has been lately employed in data aggregation schemes. This paper analyzes various solutions for using Fuzzy Logic in data aggregation schemes and their mode of addressing the underlined challenges. The analysis conducted concludes that making use of Fuzzy Logic in data aggregation schemes is suitable to solving some of their issues and has great benefits in the development process of traffic systems that relies on these schemes.