ICT Express最新文献

By considering the limited energy of Internet of Things (IoT) devices. We take the resource allocation to guarantee the stringent Quality of Service (QoS) depending on the joint optimization of power control and finite blocklength of channel. To achieve large volumes of arrival rates, we propose Adversarial Training based Generative Adversarial Networks (AT-GANs), which utilize a significant number of extreme events to provide high reliability and adjust real data in real-time. Simulation results show that Deep-Reinforcement Learning (Deep-RL) for AT-GAN could eliminate the transient training time. As a result, the AT-GAN keeps the reliability higher than 99.9999%.

In this paper, we propose a novel federated learning framework named FedHM that aims to address the challenge of training models on heterogeneous devices with varying architectures. Our approach enables the collaborative training of diverse local models by sharing a fully convolutional network (FCN) architecture that effectively extracts the local-to-global representations. By leveraging the weights with respect to this abstraction as common information across different DNN architectures, FedHM achieves efficient federated learning with minimal computational and communication overhead. We compare FedHM with three federated learning frameworks using two datasets for image classification tasks. Our results show that FedHM achieves high accuracy with considerably lower computational and communication costs compared to the other frameworks.

Aerial Computing, utilizing unmanned aerial vehicles (UAVs), has emerged as a promising solution to enhance mobile cloud computing (MCC) infrastructure for the Internet of Things (IoT). The continuous generation of vast amounts of data by IoT devices requires efficient processing and monitoring for timely decision-making. However, wireless connections between IoT devices and remote servers can be unreliable, resulting in data loss. UAVs, with their increasing processing power and autonomy, can act as bridges between IoT devices and remote servers such as edge or cloud computing. In that context, this paper proposes a continuous time Markov chain (CTMC) models for an aerial computing system to evaluate system dependability metrics including availability and reliability. Sensitivity analysis is conducted to provide extended CTMC models with improved system availability. The proposed advanced model reduces downtime by 62 h compared to the baseline model, showcasing the potential of UAVs in enhancing the availability and reliability of MCC infrastructures. The use of UAVs and MCC in aerial computing is believed to be a win–win solution for cost-effective and energy-saving communication and computation services in various environments.

In this paper, we study covert communications strategies in a compress-and-forward (CF) relay system. Along with a public message to a destination node via a CF relay, a source node attempts to transmit a covert message while evading the surveillance of the CF relay. We identify the optimal power distribution between the public and covert messages and the optimal amount of compression that maximize the covert rate subject to the minimum detection error probability requirement. Our provided solutions also reveal that both the power distribution and the achievable covert rate are identical to that of an equivalent amplify-and-forward (AF) relay system if an adequate quantization codebook with the optimal compression is employed. The numerical results verify the effectiveness of the optimal solutions and confirm our analyses.

In this study, we explore the potential of leveraging machine learning techniques, specifically auto-encoders (AE), for the decoding of linear block codes. Our findings suggest that this approach can outperform the conventional ordered statistics decoding (OSD) method, especially in a Rayleigh fading channel environment. We have rigorously trained the AE under both additive white Gaussian noise and Rayleigh fading channel conditions to ensure robustness in its performance. The output of the AE is combined with the received vector in a suitable manner to perform OSD. Through our experiments, we demonstrate that this proposed decoding approach yields better results than the conventional OSD method in Rayleigh fading channel when we used (23,12) Golay code.

The metaverse promises to revolutionize the internet by introducing a new era of three-dimensional objects. The advancements in artificial intelligence and immersive technologies have made the metaverse a trending topic in various industries, including manufacturing. This study aims to provide a comprehensive understanding of the metaverse, its underlying technologies, and the current trends shaping its development. By delving into the concept and potential applications of the metaverse in manufacturing, we seek to uncover its transformative benefits for the industry. Through an exploration of existing use cases, we aim to highlight the practical implications of the metaverse. Recognizing the need for further research, this study also addresses the limitations, privacy concerns, and security implications associated with the metaverse. By examining these aspects, we hope to motivate further investigation and contribute to the ongoing discourse surrounding this emerging paradigm.

A novel channel estimation method based on deep learning algorithm is proposed for large-scale IoT networks. We consider asymmetric backscatter communication system to maintain low-power at sensor nodes. In order to obtain channel data, we design denoising autoencoder which consists of encoder with Feedforward Neural Network (FNN) and decoder with Convolutional Neural Network (CNN). Finally, the channel estimation error is minimized, while the pilots are optimized. Especially, we adopt beamforming technique that relies only on cascaded channel data to reduce complexity in multi-sensor system. It is shown that the accuracy is slightly degraded while the complexity is greatly reduced.

Like numerous new websites created globally every day on the web, new spaces are constantly produced in the metaverse and interconnected to each other through the Internet. The continuous expansion of the metaverse space requires a search system that supports efficiently navigating and retrieving globally distributed spaces. Current metaverse search systems are limited to text-based retrieval within local platforms, and web search systems have critical limitations to apply to the metaverse. In this study, we propose an architecture for a metaverse search system that overcomes these limitations, enabling global space search across the distributed metaverse. We analyze the gaps between the web and the metaverse, identify challenges and technologies in developing a metaverse search system, and explore potential applications from different user perspectives. This study sets the foundation for a seamless browsing experience in the metaverse, enabling users to navigate three-dimensional spaces easily and freely, similar to surfing the traditional web.

Cyber threats increasingly target mission-critical systems in the military and private sectors. CMIA has emerged to mitigate such cyber threats and assure the resilience of critical missions. Existing approaches merely provide partial, manual analysis methods to support CMIA and lack the ability to provide optimal defense measures. In this paper, we propose a novel CMIA framework enabling a streamlined, automated CMIA procedure, based on the Bayesian Stackelburg game. Unlike conventional approaches, our framework provides the most probable cyber threat and the optimal defense, i.e., countermeasures against the cyber threat in a given mission environment, securing the resilience of mission-critical systems.

Note that 40% of the world’s population, $i.e.,$ three billion people, live within 100 km of the ocean or seashore surfaces. To explore and experience marine life, human activities in ocean-based environments are increasing day-by-day. To make human activities safer and stronger, highly efficient and reliable wireless communication is crucial for conveying any unnatural things that occur in oceans. Exploring the vast environment is difficult because of its rapidly changing characteristics, which creates various levels of skip-zone, resulting in the loss of information. A re-configurable intelligent surface (RIS)-assisted optical link is employed to mitigate the effects of skip-zones and enable high-speed and efficient communication links. In addition to this, it is also necessary to convey information to the coastal line through a RIS-assisted free-space optical (FSO) link. In this study, we propose a RIS-assisted dual-hop underwater wireless optical communication (UWOC)-FSO communication system. For the proposed RIS-based dual-hop UWOC-FSO system, closed-form expressions for the outage probability (OP), bit error rate (BER) for coherent and non-coherent type binary phase-shift keying, binary frequency shift keying modulation schemes are derived and results are corroborated with the Monte-Carlo simulations and asymptotic analysis.