arXiv subjects

Marko Beko

Publications and source records attributed to Marko Beko.

8 recordsLinked to original sources

arXiv2025

Visual Event Detection over AI-Edge LEO Satellites with AoI Awareness

Non terrestrial networks (NTNs), particularly low Earth orbit (LEO) satellite systems, play a vital role in supporting future mission critical applications such as disaster relief. Recent advances in artificial intelligence (AI)-native communications enable LEO satellites to act as intelligent edge nodes capable of on board learning and task oriented inference. However, the limited link budget, coupled with severe path loss and fading, significantly constrains reliable downlink transmission. This paper proposes a deep joint source-channel coding (DJSCC)-based downlink scheme for AI-native LEO networks, optimized for goal-oriented visual inference. In the DJSCC approach, only semantically meaningful features are extracted and transmitted, whereas conventional separate source-channel coding (SSCC) transmits the original image data. To evaluate information freshness and visual event detection performance, this work introduces the age of misclassified information (AoMI) metric and a threshold based AoI analysis that measures the proportion of users meeting application specific timeliness requirements. Simulation results show that the proposed DJSCC scheme provides higher inference accuracy, lower average AoMI, and greater threshold compliance than the conventional SSCC baseline, enabling semantic communication in AI native LEO satellite networks for 6G and beyond.

cs.IT↗

arXiv2025

Reinforcing Localization Credibility Through Convex Optimization

This work proposes a novel approach to reinforce localization security in wireless networks in the presence of malicious nodes that are able to manipulate (spoof) radio measurements. It substitutes the original measurement model by another one containing an auxiliary variance dilation parameter that disguises corrupted radio links into ones with large noise variances. This allows for relaxing the non-convex maximum likelihood estimator (MLE) into a semidefinite programming (SDP) problem by applying convex-concave programming (CCP) procedure. The proposed SDP solution simultaneously outputs target location and attacker detection estimates, eliminating the need for further application of sophisticated detectors. Numerical results corroborate excellent performance of the proposed method in terms of localization accuracy and show that its detection rates are highly competitive with the state of the art.

eess.SP↗

arXiv2025

Voting Scheme to Strengthen Localization Security in Randomly Deployed Wireless Sensor Networks

This work aspires to provide a trustworthy solution for target localization in adverse environments, where malicious nodes, capable of manipulating distance measurements (i.e., performing spoofing attacks), are present, thus hindering accurate localization. Besides localization, its other goal is to identify (detect) which of the nodes participating in the process are malicious. This problem becomes extremely important with the forthcoming expansion of IoT and smart cities applications, that depend on accurate localization, and the presence of malicious attackers can represent serious security threats if not taken into consideration. This is the case with most existing localization systems which makes them highly vulnerable to spoofing attacks. In addition, existing methods that are intended for adversarial settings consider very specific settings or require additional knowledge about the system model, making them only partially secure. Therefore, this work proposes a novel voting scheme based on clustering and weighted central mass to securely solve the localization problem and detect attackers. The proposed solution has two main phases: 1) Choosing a cluster of suitable points of interest by taking advantage of the problem geometry to assigning votes in order to localize the target, and 2) Attacker detection by exploiting the location estimate and basic statistics. The proposed method is assessed in terms of localization accuracy, success in attacker detection, and computational complexity in different settings. Computer simulations and real-world experiments corroborate the effectiveness of the proposed scheme compared to state-of-the-art methods, showing that it can accomplish an error reduction of $30~\%$ and is capable of achieving almost perfect attacker detection rate when the ratio between attacker intensity and noise standard deviation is significant.

eess.SP↗

arXiv2024

Performance Analysis of UAV-Assisted RF-UOWC Systems

This paper introduces a relay-assisted solution for downlink communications in a mixed system of Radio Frequency (RF) and Underwater Optical Wireless Communications (UOWC) technologies. During the initial downlink phase, data transmission occurs via RF link between hovering Unmanned Aerial Vehicle (UAV) and the floating buoys at the water surface. As fixed buoy acts as amplify-and-forward relays, the second UOWC link represents downlink signal transmission from the floating buoy to the underwater device. Best relay selection is adopted, meaning that only the buoy with the best estimated RF-based UAV-buoy channel will perform signal transmission to an underwater device. Analytical expression for the outage probability is derived and utilized to examine the system's performance behaviour for various UOWC and RF channel conditions.

eess.SY↗

arXiv2024

A Closed-form Solution for Weight Optimization in Fully-connected Feed-forward Neural Networks

This work addresses weight optimization problem for fully-connected feed-forward neural networks. Unlike existing approaches that are based on back-propagation (BP) and chain rule gradient-based optimization (which implies iterative execution, potentially burdensome and time-consuming in some cases), the proposed approach offers the solution for weight optimization in closed-form by means of least squares (LS) methodology. In the case where the input-to-output mapping is injective, the new approach optimizes the weights in a back-propagating fashion in a single iteration by jointly optimizing a set of weights in each layer for each neuron. In the case where the input-to-output mapping is not injective (e.g., in classification problems), the proposed solution is easily adapted to obtain its final solution in a few iterations. An important advantage over the existing solutions is that these computations (for all neurons in a layer) are independent from each other; thus, they can be carried out in parallel to optimize all weights in a given layer simultaneously. Furthermore, its running time is deterministic in the sense that one can obtain the exact number of computations necessary to optimize the weights in all network layers (per iteration, in the case of non-injective mapping). Our simulation and empirical results show that the proposed scheme, BPLS, works well and is competitive with existing ones in terms of accuracy, but significantly surpasses them in terms of running time. To summarize, the new method is straightforward to implement, is competitive and computationally more efficient than the existing ones, and is well-tailored for parallel implementation.

cs.LG↗

arXiv2023

Two-Tier UAV-based Low Power Wide Area Networks: A Testbed and Experimentation Study

In this paper, we propose, design, deploy and demonstrate a two-tier Low Power Wide Area Network (LP WAN) system based on Unmanned Aerial Vehicle (UAV) base stations suitable for dynamic deployment in deep rural environments. The proposed UAV-based LP WAN network augments the existing macro-cellular LP WAN network (Tier 1) with an additional layer of mobile base stations (Tier 2) based also on LP WAN technology. Mobile Tier 2 LP WAN base stations provide connectivity to static or mobile LP WAN user equipment deployed in the areas without direct Tier 1 LP WAN network coverage. The proposed two-tier LP WAN network scenario is suitable for various agricultural, forestry and environmental applications such as livestock or wild animal monitoring. In this experimental work, we report the prototype that was successfully deployed and used in a real-world deep rural environment without Tier 1 LP WAN network coverage.

cs.NI↗

arXiv2021

Distributed Value Function Approximation for Collaborative Multi-Agent Reinforcement Learning

In this paper we propose several novel distributed gradient-based temporal difference algorithms for multi-agent off-policy learning of linear approximation of the value function in Markov decision processes with strict information structure constraints, limiting inter-agent communications to small neighborhoods. The algorithms are composed of: 1) local parameter updates based on single-agent off-policy gradient temporal difference learning algorithms, including eligibility traces with state dependent parameters, and 2) linear stochastic time varying consensus schemes, represented by directed graphs. The proposed algorithms differ by their form, definition of eligibility traces, selection of time scales and the way of incorporating consensus iterations. The main contribution of the paper is a convergence analysis based on the general properties of the underlying Feller-Markov processes and the stochastic time varying consensus model. We prove, under general assumptions, that the parameter estimates generated by all the proposed algorithms weakly converge to the corresponding ordinary differential equations (ODE) with precisely defined invariant sets. It is demonstrated how the adopted methodology can be applied to temporal-difference algorithms under weaker information structure constraints. The variance reduction effect of the proposed algorithms is demonstrated by formulating and analyzing an asymptotic stochastic differential equation. Specific guidelines for communication network design are provided. The algorithms' superior properties are illustrated by characteristic simulation results.

cs.LG↗

arXiv2020

Towards Secure Localization in Randomly Deployed Wireless Networks

Being able to accurately locate wireless devices, while guaranteeing high-level of security against spoofing attacks, benefits all participants in the localization chain (e.g., end users, network operators, and location service providers). On the one hand, most of existing localization systems are designed for innocuous environments, where no malicious adversaries are present. This makes them highly susceptible to security threats coming from interferers, attacks or even unintentional errors (malfunctions) and thus, practically futile in hostile settings. On the other hand, existing secure localization solutions make certain (favorable) assumptions regarding the network topology (e.g., that the target device lies within a convex hull formed by reference points), which restrict their applicability. Therefore, this work addresses the problem of target localization in randomly deployed wireless networks in the presence of malicious attackers, whose goal is to manipulate (spoof) the estimation process and disable accurate localization. We propose a low-complex solution based on clustering and weighted central mass to detect attackers, using only the bare minimum of reference points, after which we solve the localization problem by a bisection procedure. The proposed method is studied from both localization accuracy and success in attacker detection point of views, where closed-form expressions for upper and lower bounds on the probability of attacker detection are derived. Its performance is validated through computer simulations, which corroborate the effectiveness of the proposed scheme, outperforming the state-of-the-art methods.

eess.SP↗