ICT Express最新文献

This paper offers an in-depth exploration of semantic communications, focusing on its integral role in wireless networks. We dissect its foundational architecture and the key elements that enable seamless AI integration. Our research categorizes semantic communications into various multimedia and task types, evaluating their applicability in both single and multitasking environments. We also investigate resource allocation and goal-oriented strategies, supported by empirical case studies. The paper concludes by spotlighting emerging trends, including AI, IoT, and 5G beyond. It identifies pressing challenges such as standardization, security, and efficiency. Our work provides a holistic understanding of contemporary semantic communications paradigms.

Recent developments in the fields of communications, smart transportation systems and computer systems have significantly expanded the potential for intelligent solutions in the domains of traffic safety, convenience and efficiency. The utilization of Artificial Intelligence (AI) is presently prevalent across diverse sectors of application due to its significant capacity to augment conventional data-driven methodologies. In the domain of Vehicular Ad hoc NETworks (VANETs), data is regularly gathered from several sources. The collected data serves multiple goals, such as facilitating efficient routing, enhancing driver awareness, forecasting mobility patterns to prevent potential risks, and ultimately enhancing passenger comfort, safety and overall road experience. Internet of thing (IoT) can be a good solution fro many issues that of VANETs. In order to make a complete system of VANETs communications are very essential like 5G and 6G. This study provides a detailed examination of AI, IoT and 5G/6G methodologies currently being investigated by multiple research endeavors in the field of VANETs. The merits and demerits of the AI-based methodologies suggested for the VANET domain have been analyzed with the using of IoT and 5G/6G. In conclusion, forthcoming research prospects in the field of VANETs are ascertained.

Digital twins (DTs) are an emerging digitalization technology with a huge impact on today’s innovations in both industry and research. DTs can significantly enhance our society and quality of life through the virtualization of a real-world physical system, providing greater insights about their operations and assets, as well as enhancing their resilience through real-time monitoring and proactive maintenance. DTs also pose significant security risks, as intellectual property is encoded and more accessible, as well as their continued synchronization to their physical counterparts. The rapid proliferation and dynamism of cyber threats in today’s digital environments motivate the development of automated and intelligent cyber solutions. Today’s industrial transformation relies heavily on artificial intelligence (AI), including machine learning (ML) and data-driven technologies that allow machines to perform tasks such as self-monitoring, investigation, diagnosis, future prediction, and decision-making intelligently. However, to effectively employ AI-based models in the context of cybersecurity, human-understandable explanations, and their trustworthiness, are significant factors when making decisions in real-world scenarios. This article provides an extensive study of explainable AI (XAI) based cybersecurity modeling through a taxonomy of AI and XAI methods that can assist security analysts and professionals in comprehending system functions, identifying potential threats and anomalies, and ultimately addressing them in DT environments in an intelligent manner. We discuss how these methods can play a key role in solving contemporary cybersecurity issues in various real-world applications. We conclude this paper by identifying crucial challenges and avenues for further research, as well as directions on how professionals and researchers might approach and model future-generation cybersecurity in this emerging field.

Online video services are responsible for a large amount of global data traffic, which is why wireless video caching has become a major focus in order to deal with the increasing amount of data. While conventional caching methods have been successful in reducing file transmission latency and data traffic on the core network, there is still a lot of potential to improve wireless caching for streaming users’ satisfaction, especially as video streaming technology continues to improve. To improve caching, it is important to consider the distinct characteristics of a video file, video encoding, dynamic video streaming, and even 3D video services such as virtual reality (VR) and augmented reality (AR). This paper investigates the distinct video features that can be used to design video caching policies. Additionally, recent studies on wireless video caching and delivery are surveyed, with a focus on four key characteristics: (1) partitioning a video file, (2) encoding a video file into multiple quality versions, (3) recognizing that video file popularity is dynamic and heterogeneous, and (4) understanding that video recommendation affects a series of user requests.

In this paper, we introduce new codes for the private information retrieval (PIR). The conventional Tian-Sun-Chen (TSC) scheme achieves PIR capacity under the perfect privacy conditions with the minimum message length. Based on the TSC scheme, weakly PIR (WPIR) schemes have been developed to benefit download costs by relaxing privacy. We show that the proposed scheme has lower download cost than the TSC scheme in the weak privacy setting. While our scheme is not capacity-achieving under perfect privacy, it has smaller message sizes compared with the TSC scheme.

To address the accuracy degradation as well as prolonged convergence time due to the inherent data heterogeneity among end-devices in federated learning (FL), we introduce the joint batch size and weighted aggregation adjustment problem, which is non-convex problem. To adjust optimal hyperparameters, we develop deep reinforcement learning (DRL) to empower a mechanism known as Batch size and Weighted aggregation Adjustment (BWA). Experimental evaluation demonstrates that BWA not only outperforms methods optimized solely from either a local training or server perspective but also achieves higher accuracy, with an increase of up to 5.53% compared to FedAvg, and additionally accelerates convergence speeds.

To effectively manage the escalating traffic, attention is drawn to the coexistence mechanism of cellular and Wi-Fi networks which offload the cellular traffic from the licensed band to the unlicensed band. For the coexistence of 5G new radio-unlicensed and Wi-Fi, we tackle the energy efficiency maximization problem by sequentially determining the duty cycle and transmit power through the use of distributed deep Q-network (DQN) techniques. When utilizing the existing unlicensed band, the proposed method minimizes the impact on Wi-Fi networks while achieving optimal energy efficiency. Simulations validate the superior energy efficiency of the proposed coexistence mechanism over various benchmark methods.

Mobile learning allows for an interactive way of learning through devices like smartphones. However, current methods usually rely on pre-set situations and struggle to recognize new contexts when they come up during testing. To solve this, we suggest the Open-set Learning Context Recognition Model (OLCRM). This model uses data extracted from smartphone sensors to identify whether a learning context is known or unknown. It also uses a Dual Discriminator Generative Adversarial Network (DDGAN) to create high-quality fake examples, which helps improve the accuracy of recognizing contexts. Experimental results demonstrate the effectiveness of OLCRM in open-set learning context recognition problems.

This paper presents field experiment results that illustrate the impact of cross-link interference on the cell search procedure in a 5G time division duplex system. We initially show how cross-link interference affects to the cell search procedure from an analytic aspect. An example of an experimental result provided in this paper shows how the user equipment wrongly estimates the symbol timing offset due to cross-link interference. Furthermore, we propose a modified cell search algorithm which is robust against the strong influence of cross-link interference. The proposed modification efficiently suppresses the effects of cross-link interference by applying selective energy normalization to the correlation process. The experimental results show that the modified algorithm can accurately estimate the symbol timing offset with a negligible increment in computation time.

Digital credentials represent digital versions of physical credentials. They are the cornerstone of digital identity on the Internet. In order to enhance privacy, different authors implement selective disclosure in digital credentials, allowing users to disclose only the claims or attributes they want. This paper gives an overview of the most influential articles for selective disclosure, a chronology of the evolution of the methods, and a list of strategies and approaches to the problem. We identify the categories of approaches and their advantages and disadvantages. In addition, we recognize research gaps and open challenges and provide potential future directions.