Search

Machine learning (ML) models have become increasingly popular in the field of path loss prediction. Their performance depends profoundly on the data they use as their input. The work at hand proposes and evaluates new input features for urban propagation. These features were obtained via image processing tools. Moreover, we propose a new two-level ensemble model using the concept of stacked generalization. The proposed model is based on seven different basic ML models. To the best of the authors knowledge, this is the first time that a two-level ensemble method is applied to a modeling problem in electromagnetics. The results demonstrate that the new input features, coupled with the new ensemble, provide improved prediction performance. [ABSTRACT FROM AUTHOR]

In this paper, the problem of joint power allocation and user association is studied for non-orthogonal multiple access (NOMA) downlink networks with multiple base stations (BSs). We consider that users are grouped into orthogonal clusters to allocate into different physical resource blocks (PRBs). The problem is formulated using two different utility functions. The first is the maximization of the weighted sum rate and the other is the maximization of the minimum achievable user rate. We apply two different evolutionary algorithms in order to solve this problem. Namely, the recently introduced Salp Swarm Algorithm (SSA) and the popular Particle Swarm Optimization (PSO). The simulation results show that the above-described problem can be effectively solved by both algorithms. SSA is more efficient in average than PSO. The effect of increasing the number of user is also studied. In this case the problem becomes more difficult to solve, which indicates that more network resources are required. [ABSTRACT FROM AUTHOR]

In body-centric communications, energy efficiency is a critical performance metric, while the achievable data rate is not of primary concern. In this paper we present a novel modulation scheme, which can be efficiently used in body-centric terahertz (THz) nanonetworks. The proposed scheme is a combination of the time-spread On-Off keying (TS–OOK) and the pulse position modulation (PPM) and presents lower energy consumption, compared to other existing methods as TS–OOK, at a minor cost to the data rate. Furthermore, another important aspect is that the proposed modulation scheme can be effectively used to mitigate the impact of the specific kind of noise in THz body-centric communications, thus leading to better error performance. Finally, we present analytical and simulation results in order to compare the new scheme with the existing TS–OOK. [ABSTRACT FROM AUTHOR]

Chaos-related applications are abundant in the literature, and span the fields of secure communications, encryption, optimization, and surveillance. Such applications take advantage of the unpredictability of chaotic systems as an alternative to using true random processes. The chaotic systems used, though, must showcase the statistical characteristics suitable for each application. This may often be hard to achieve, as the design of maps with tunable statistical properties is not a trivial task. Motivated by this, the present study explores the task of constructing maps, where the statistical measures like the mean value can be appropriately controlled by tuning the map's parameters. For this, a family of piecewise maps is considered, with three control parameters that affect the endpoint interpolations. Numerous examples are given, and the maps are studied through a collection of numerical simulations. The maps can indeed achieve a range of values for their statistical mean. Such maps may find extensive use in relevant chaos-based applications. To showcase this, the problem of chaotic path surveillance is considered as a potential application of the designed maps. Here, an autonomous agent follows a predefined trajectory but maneuvers around it in order to imbue unpredictability to potential hostile observers. The trajectory inherits the randomness of the chaotic map used as a seed, which results in chaotic motion patterns. Simulations are performed for the designed strategy. [ABSTRACT FROM AUTHOR]

The implementation of smart networks has made great progress due to the development of the Internet of Things (IoT). LoRa is one of the most prominent technologies in the Internet of Things industry, primarily due to its ability to achieve long-distance transmission while consuming less power. In this work, we modeled different environments and assessed the performances of networks by observing the effects of various factors and network parameters. The path loss model, the deployment area size, the transmission power, the spreading factor, the number of nodes and gateways, and the antenna gain have a significant effect on the main performance metrics such as the energy consumption and the data extraction rate of a LoRa network. In order to examine these parameters, we performed simulations in OMNeT++ using the open source framework FLoRa. The scenarios which were investigated in this work include the simulation of rural and urban environments and a parking area model. The results indicate that the optimization of the key parameters could have a huge impact on the deployment of smart networks. [ABSTRACT FROM AUTHOR]

Fifth generation (5G) and beyond 5G (B5G) wireless communications will provide services under different promising usage scenarios and applications including enhanced mobile broadband (eMBB), high-reliability low-latency communications (HRLLC), and massive machine type communications (mMTC) with stringent performance attributes such as higher system capacity, low latency, high reliability, greater spectral efficiency, as well as enabling massive internet of Things (mIoT) for a fully connected, intelligent digital world. Antennas are vital components in wireless systems that directly affect their performance. Novel and innovative solutions in antenna design are required for reliable performance and to reduce complexities and difficulties in system integration across a diverse range of devices and platforms. [ABSTRACT FROM AUTHOR]

The fifth generation (5G) of telecommunications networks is currently commercially deployed. One of their core enabling technologies is cellular Massive Multiple-Input-Multiple-Output (M-MIMO) systems. However, future wireless networks are expected to serve a very large number of devices and the current MIMO networks are not scalable, highlighting the need for novel solutions. At this moment, Cell-free Massive MIMO (CF M-MIMO) technology seems to be the most promising idea in this direction. Despite their appealing characteristics, CF M-MIMO systems face their own challenges, such as power allocation and channel estimation. Deep Learning (DL) has been successfully employed to a wide range of problems in many different research areas, including wireless communications. In this paper, a review of the state-of-the-art DL methods applied to CF M-MIMO communications systems is provided. In addition, the basic characteristics of Cell-free networks are introduced, along with the presentation of the most commonly used DL models. Finally, future research directions are highlighted. [ABSTRACT FROM AUTHOR]

Abstract: This paper reviews the state of the art in the area of enhancing eGovernment interoperability by using common models and/or ontologies. This area has currently become a very active research field. We identify and present a significant number (>40) of relevant efforts. These initiatives are grouped into categories based on the owner, scope and modelling perspective of each project. We then focus on the cases that build generic and universal eGovernment representations and models. We analyse, evaluate and rate them using an additional set of criteria. We end up with conclusions and possible directions for the exploitation and usage of these models. [Copyright &y& Elsevier]

The design of thinned planar microstrip arrays under specific constraints concerning the impedance-matching condition of the array elements and the radiation pattern is presented. The radiation characteristics of the structure are extracted by applying the method-of- moments. The array design is based on a novel optimization method, which is a modified version of the boolean particle swarm optimization that employs velocity mutation (BPSO-vm). Apart from the optimization of the array geometry, the proposed method is applicable to other discrete-variable optimization problems. Moreover, the planar array design is coped with by means of other techniques, namely, a binary coded Genetic Algorithm, the binary Particle Swarm Optimization, and the Boolean PSO. The comparison of the above methods and the BPSO-vm shows the efficiency of the proposed technique. [ABSTRACT FROM AUTHOR]

Automatic generation of medical reports can provide diagnostic assistance to doctors and reduce their workload. To improve the quality of the generated medical reports, injecting auxiliary information through knowledge graphs or templates into the model is widely adopted in previous methods. However, they suffer from two problems: 1) The injected external information is limited in amount and difficult to adequately meet the information needs of medical report generation in content. 2) The injected external information increases the complexity of model and is hard to be reasonably integrated into the generation process of medical reports. Therefore, we propose an Information Calibrated Transformer (ICT) to address the above issues. First, we design a Precursor-information Enhancement Module (PEM), which can effectively extract numerous inter-intra report features from the datasets as the auxiliary information without external injection. And the auxiliary information can be dynamically updated with the training process. Secondly, a combination mode, which consists of PEM and our proposed Information Calibration Attention Module (ICA), is designed and embedded into ICT. In this method, the auxiliary information extracted from PEM is flexibly injected into ICT and the increment of model parameters is small. The comprehensive evaluations validate that the ICT is not only superior to previous methods in the X-Ray datasets, IU-X-Ray and MIMIC-CXR, but also successfully be extended to a CT COVID-19 dataset COV-CTR.

Modern Healthcare cyberphysical systems have begun to rely more and more on distributed AI leveraging the power of Federated Learning (FL). Its ability to train Machine Learning (ML) and Deep Learning (DL) models for the wide variety of medical fields, while at the same time fortifying the privacy of the sensitive information that are present in the medical sector, makes the FL technology a necessary tool in modern health and medical systems. Unfortunately, due to the polymorphy of distributed data and the shortcomings of distributed learning, the local training of Federated models sometimes proves inadequate and thus negatively imposes the federated learning optimization process and in extend in the subsequent performance of the rest Federated models. Badly trained models can cause dire implications in the healthcare field due to their critical nature. This work strives to solve this problem by applying a post-processing pipeline to models used by FL. In particular, the proposed work ranks the model by finding how fair they are by discovering and inspecting micro-Manifolds that cluster each neural model's latent knowledge. The produced work applies a completely unsupervised both model and data agnostic methodology that can be leveraged for general model fairness discovery. The proposed methodology is tested against a variety of benchmark DL architectures and in the FL environment, showing an average 8.75% increase in Federated model accuracy in comparison with similar work.

A challenging problem in millimeter wave (mmWave) communications for the fifth generation of cellular communications and beyond (5G/B5G) is the beam selection problem. This is due to severe attenuation and penetration losses that are inherent in the mmWave band. Thus, the beam selection problem for mmWave links in a vehicular scenario can be solved as an exhaustive search among all candidate beam pairs. However, this approach cannot be assuredly completed within short contact times. On the other hand, machine learning (ML) has the potential to significantly advance 5G/B5G technology, as evidenced by the growing complexity of constructing cellular networks. In this work, we perform a comparative study of using different ML methods to solve the beam selection problem. We use a common dataset for this scenario found in the literature. We increase the accuracy of these results by approximately 30%. Moreover, we extend the given dataset by producing additional synthetic data. We apply ensemble learning techniques and obtain results with about 94% accuracy. The novelty of our work lies in the fact that we improve the existing dataset by adding more synthetic data and by designing a custom ensemble learning method for the problem at hand.