In this paper, we examine the machine learning (ML) approach for wireless signal strength analysis, which can be further used for device localization. In the indoor environment, we acquired a set of received signal strength indicators (RSSI). Further, collected RSSI values were used to train ML algorithms: Linear Regression, Random Forest Regressor and Decision Tree Classifier and Logistic Regression Classifier. We compare different ML approaches and algorithms such as regression, classification and clustering in order to establish a baseline for further work on device localization. The ML approach offers quick insight for analysis and results without the need to address the theory of electromagnetic wave propagation in detail.

This paper analyzes the performance of an amplify-and-forward (AF) relay system with Rayleigh fading on the source-relay (S-R) link and Nakagami- $m$ fading on the relay-destination (R-D) link. System performance is evaluated through outage probability $(\boldsymbol{P}_{\text {out }})$ based on the signal-tointerference ratio (SIR). The analysis considers the effects of the receiver threshold $\left(\boldsymbol{\gamma}_{\mathbf{t h}}\right)$, the Nakagami fading parameter $\boldsymbol{m}$, and the number of relays N. Results show that increasing the number of relays and higher values of $\boldsymbol{m}$ significantly improve system reliability and reduce outage probability. Numerical and graphical results confirm the analytical analysis and provide guidelines for AF relay network optimization. Additionally, the study investigates locally deployable Generative AI (GenAI) for agentic network design and management, demonstrating reduced execution time and operational effort while maintaining high accuracy.

In this paper, the performance of dual-hop relay transmission in modern wireless communication systems is analyzed by considering two fundamental relaying techniques, namely, Amplify-and-Forward (AF) and Decode-and-Forward (DF). The propagation conditions on the source–relay (S-R) and relay–destination (R-D) links are modeled using the κ-μ statistical distribution, which effectively captures the fading characteristics in both line-of-sight (LoS) and non-line-of-sight (NLoS) environments. The analysis focuses on key performance metrics, including the outage probability (Pout) and average bit error probability (Pe), for Binary Phase Shift Keying (BPSK) and Quadrature Phase Shift Keying (QPSK) modulation schemes, assuming transmission via a single relay without a direct S–D link. Closed-form expressions for the considered metrics are derived based on the κ-μ model and verified by numerical evaluation. In addition to classical analytical modeling, a Generative Artificial Intelligence (GenAI)-enabled workflow is incorporated as a supportive tool in order to aid in automated analysis, the interpretation of the results in the context of network management under varying channel and system parameters based on the Pout and Pe calculations with the aim to tackle the underlying complexity and cognitive load of infrastructure adaptation and re-configuration operations. The combined analytical and GenAI-assisted approach provides valuable insights for the optimization, design, and continuous evolution of robust relay-based architectures in next-generation wireless networks.

This paper analyzes the outage probability ($\boldsymbol{P}_{\text {out }}$) as a key reliability metric for wireless systems under Hoyt fading and co-channel interference (CCI). A receiver with Selection Combining (SC) selects the best of $\boldsymbol{L}$ independent branches based on signal quality. The Hoyt fading model, as a generalization of Rayleigh fading, enables accurate modeling of non-line-of-sight (NLoS) environments. Closed-form expressions for $\boldsymbol{P}_{\text {out }}$ are derived to evaluate the effects of channel parameters, number of branches, and interference. In the second part, we propose an agentic AI-based workflow for network management, leveraging the previously derived outage probability expression and associated channel parameters for the presented case study.

This paper investigates the performance of a maximal ratio combining (MRC) receiver with L diversity branches operating over a k-mu fading channel, which is a generalized fading model suitable for various wireless environments. An exact closed-form expression for the channel capacity (CC) is derived based on the signal-to-noise ratio (SNR) at the output of the MRC receiver. Furthermore, the impact of various link-level and system-level parameters on the channel capacity is analyzed through detailed graphical simulations. The presented results provide valuable insights into the design and optimization of wireless communication systems operating over k-mu fading channels. Finally, we also introduce Large Language Model (LLM) based approach to electromagnetic radiation (EMR) estimation, leveraging the previously calculated values of channel capacity among other factors.

This paper presents a novel approach to analyzing Bluetooth signals using deep learning with neural networks. Due to their complex properties, Bluetooth signals require advanced methods for analysis. Thes neural network model predicts the mean and standard deviation of these signals, utilizing fully connected layers and Tanh and Softmax activation functions. Model performance is evaluated with metrics such as MAE, MSE, RMSE, and R-squared. The research demonstrates that neural networks can accurately extract statistical features from Bluetooth signals, contributing to improvements in wireless communication by optimizing signal analysis and error detection.

In this paper, a micro-MRC receiver with L branches operating in a correlated gamma-shadowed eta-mu fading channel is considered. For such a system, the channel capacity (CC) is determined based on the maximum signal-to-noise ratio (SNR) at the L branches at the input of the MRC receiver. The results are presented graphically to illustrate the impact of different system parameters on performance and the improvements that result from the advantages of combined diversity. Additionally, we introduce the application of Large Language Models (LLMs) to make network experimentation more practical, using the previously presented expression as a case study. Moreover, a Vision Language Model (VLM) aided method aiming to make model-driven network design and experimentation more convenient is introduced and evaluated for the previously considered case study

The topic of this study is uplink non-orthogonal multiple access (NOMA) systems. The Fisher-Snedecor (F) distribution is used to model composite wireless channels that exhibit fading and shadowing phenomena concurrently. The issue of matching users with nearby channel gains in NOMA clusters is overcome by proposing a deep hybrid pairing strategy. Based on the idea of maximizing the total data rate, the power allocation coefficients for clustered users are calculated. Simulation results demonstrate the effectiveness of the suggested deep hybrid approach for user pairing.

The Low Earth Orbit (LEO) small satellites are extensively used for global connectivity to enable services in underpopulated, remote or underdeveloped areas. Their inherent broadcast nature exposes LEO–terrestrial communication links to severe security threats, which always reveal new challenges. The secrecy performance of the satellite-to-ground user link in the presence of a ground eavesdropper is studied in this paper. We observe both scenarios of the eavesdropper’s channel state information (CSI) being known or unknown to the satellite. Throughout the analysis, we consider that locations of the intended and unauthorized user are both arbitrary in the satellite’s footprint. On the other hand, we analyze the case when the user is in the center of the satellite’s central beam. In order to achieve realistic physical layer security features of the system, the satellite channels are assumed to undergo Gamma-shadowed Ricean fading, where both line-of-site and scattering components are influenced by shadowing effect. In addition, some practical effects, such as satellite multi-beam pattern and free space loss, are considered in the analysis. Capitalizing on the aforementioned scenarios, we derive the novel analytical expressions for the average secrecy capacity, secrecy outage probability, probability of non-zero secrecy capacity, and probability of intercept events in the form of Meijer’s G functions. In addition, novel asymptotic expressions are derived from previously mentioned metrics. Numerical results are presented to illustrate the effects of beam radius, satellite altitude, receivers’ position, as well as the interplay of the fading or/and shadowing impacts over main and wiretap channels on the system security. Analytical results are confirmed by Monte Carlo simulations.

This paper analyses the sequential and parallel execution of Simpson's Rule in Java for numerical integration, focusing on time analysis, speedup, efficiency, and overhead. Using multi-core processors, we examine performance improvements for computing the Fresnel integral. The implementation is evaluated based on execution time, hardware configuration, software setup, and accuracy relative to the threshold value. Results show that parallel execution significantly reduces computation time and improves optimally configured accuracy. We also discuss the trade-offs of parallelism, such as overhead and diminishing returns, and its implications for high-performance computing in Java..

The aim of this paper is to estimate the error probability in coherent detection of multilevel phase-shift keying (MPSK) signals transmitted through a channel in which the multipath fading and shadowing are present simultaneously together with thermal noise. To describe this type of fading, we use a Fisher-Snedecor model that was proposed relatively recently. For this fading model, using the Fourier series, we first represent the probability density function (PDF) of the composite signal phase. We present expressions for the coefficients in the Fourier series, that were previously derived by ourselves. We examine the convergence of this series for different numerical values of the channel parameters. Next, we present the expression for estimating the error probability in MPSK signal detection. Based on this, we examine the influence of multipath fading severity and the shadowing spread on the numerical values of the error probability for different number of phase levels. The obtained results enable a further evaluation of the performance of differentially coded signals, as well as an evaluation of the influence of the phase noise both on the error probability and the mutual information in the channel with this type of fading.

For the purpose of free-space optics (FSO) channel simulation, we adapt a previously proposed method for generation of stochastic signal samples. By using this method, we generate signal samples that have a given probability density function, as well as a desired autocorrelation function. We use another unrelated method based on stochastic differential equations to generate the stochastic signal samples of the same FSO channel. We compare these two methods based on the resulting probability density functions and autocorrelations. The results are significant for determining important FSO system performance parameters such as error probability, level-crossing rate and average fade duration. The importance of the results is significant specifically in channels where error correction codes are used.

Channel modeling is a first step towards the successful projecting of any wireless communication system. Hence, in this paper, we analyze the performance at the output of a multi-branch selection combining (SC) diversity receiver in a wireless environment that has been distracted by fading and co-channel interference (CCI), whereby the fading is modelled by newer Beaulieu-Xie (BX) distribution, and the CCI is modelled by the κ-µ distribution. The BX distribution provides the ability to include in consideration any number of line-of-sight (LOS) useful signal components and non-LOS (NLOS) useful signal components. This distribution contains characteristics of some other fading models thanks to its flexible fading parameters, which also applies to the κ-µ distribution. We derived here the expressions for the probability density function (PDF) and cumulative distribution function (CDF) for the output signal-to-co-channel interference ratio (SIR). After that, other performances are obtained, namely: outage probability (Pout), channel capacity (CC), moment-generating function (MGF), average bit error probability (ABEP), level crossing rate (LCR), and average fade duration (AFD). Numerical results are presented in several graphs versus the SIR for different values of fading and CCI parameters, as well as the number of input branches in the SC receiver. Then, the impact of parameters on all performance is checked. From our numerical results, it is possible to directly obtain the performance for all derived and displayed quantities for cases of previously known distributions of fading and CCI by inserting the appropriate parameter values. In the second part of the paper, a workflow for automated network experimentation relying on the synergy of Large Language Models (LLMs) and model-driven engineering (MDE) is presented, while the previously derived expressions are used for evaluation. Due to the aforementioned, the biggest value of the obtained results is the applicability to the cases of a large number of other distributions for fading and CCI by replacing the corresponding parameters in the formulas for the respective performances.

In this paper, we study an uplink power-domain non-orthogonal multiple access (PD-NOMA) system, in which 2K+1 users are served. The user clustering process based on High-High/High-Low algorithm precedes the utilization of the data-rate based power allocation algorithm. Channels are characterized by Fisher-Snedecor composite fading model interpreted as model with a high level of generality. The influence of different fading/shadowing channel conditions, number of users and their positions is portrayed through the numerical results of data sum rate of the studied PD-NOMA system.

In this paper, a model of a wireless SC receiver with $\boldsymbol{L}$ input branches is considered, which is used to reduce the effects of short fading and co-channel interference (CCI) on system performance. The useful signal at the receiver has an $\boldsymbol{\alpha}-\boldsymbol{\mu}$ distribution, while the Interfering Signal (CCI) has Weibull characteristics. In this paper, closed-form expressions for the channel capacity (CC) of the signal-to-interference ratio (SIR) system at the outputs of SC with $\boldsymbol{L}$ branches are presented. We also propose a workflow for network experimentation, planning that combines the strengths of large language models (LLMs) and model-driven engineering (MDE), incorporating previously derived expressions into the evaluation process.

The paper presents the design of two dispersive filters (also called phasers) dedicated to Analog Signal Processing (ASP) applications. Possible ASP applications targeted for these filters are also proposed: analog pulse compression radar, analog chirp Fourier transformer and frequency discriminator. In the past decades, dispersive filters for ASP have been implemented with Surface Acoustic Wave (SAW) filters, having a reduced bandwidth leading to a poor resolution in the applications. Consequently, designing these filters with a larger bandwidth is a significant progress and this is what is proposed in this work. The design of the two filters is described step-by-step: the mathematical method employed to optimize the parameters of the filters, the calculation of theoretical values of components and the selected real values of components of the shelves for the PCB. The two measured filters, composed of 2 passive cells, have negative slope and positive slope group delay characteristics: the first filter has a group delay downslope of -1 ns/GHz for the considered bandwidth [700MHz - 1.9GHz], and the second has a group delay upslope of 1.25ns/GHz for the considered bandwidth [500MHz-1.3GHz].

In this paper, particular study of security of ground-to-unmanned aerial vehicle (UAV) communication link, on physical layer, in the presence of a ground eavesdropper is given. We characterize the UAV as data collector, which is distributed randomly in a horizontal plane of certain cylindrical region, while a ground user that sends data up to UAV, is located in the centre of cylinder's base. Furthermore, we assume that the eavesdropper is randomly located within a circle which defines the base of the cylindrical region. The main (user-to-UAV) channel is characterized as severely corrupted by the path loss effect, while the wiretap (source-to-eavesdropper) channel is subjected to Fisher-Snedecor fading. Under aforementioned system/channel scenario, the probability of intercept events is investigated. In more details, throughout numerical results, the impact of the predefined cylinder's height and its base's radius, as well as the impact of the fading depth and shadowing severity of the ground wiretap channel, on the intercept probability, is analysed. Related concluding remarks are also given.

In this work, we determine the physical layer security (PLS) metrics for ground-to-unmanned aerial vehicle (UAV) link in the presence of a suspicious UAV, which intends to overhear confidential transmission. The ground node sends data up to the UAV, which is positioned exactly above the transmitter and is able to spot an aerial eavesdropper according to the predefined horizontal and/or vertical guard distance. However, the attacker tries to intercept the channel transmission outside of marked zone. The main and wiretap channel are both assumed to be subjected to Fisher-Snedecor fading process. Under such system/channel scenario, the average secrecy capacity, lower bound of secrecy outage probability, intercept probability and non-zero secrecy capacity are characterized in terms of mathematical tractable forms. In addition, numerical and simulation results are presented to verify the correctness of theoretical ones. The impact of different positions of UAVs (their heights and mutual distances) and various conditions over channels on the secrecy transmission is analysed and discussed in details. The proposed PLS scenario can be utilized in Internet of Things environments, with UAV as a data collector, to enhance the security of energy-aware or disaster-stricken transmissions. All obtained results can be helpful in prediction of positioning UAV to achive low probability of interception of confidential communication.