arXiv subjects

Sinem Coleri

Publications and source records attributed to Sinem Coleri.

At least 19 recordsLinked to original sources

arXiv2026

FADE: A Flow-Based Approach for Multichannel Tail Estimation

Ultra-Reliable Low-Latency Communication (URLLC) is vulnerable to rare low-received-power events, and the spatial-diversity benefits of multiple receivers can be significantly reduced when they experience simultaneous deep fading. Multivariate Extreme Value Theory (MEVT) provides a principled framework for characterizing such joint tail behavior. However, conventional MEVT methods often rely on restrictive parametric assumptions or discrete representations of the dependence structure, which may not fully capture complex multivariate tail behavior. This paper proposes Flow-based Angular Density Estimation (FADE), a flow-based approach for characterizing the dependence between extreme events across receivers within the MEVT framework. FADE transforms multivariate extremes into a standard extreme-value representation and uses a flow-based density estimator to learn the dependence structure from the transformed data without imposing a predefined parametric form. The proposed framework is evaluated using experimentally collected data from a UAV communication system, in which the UAV serves as the transmitter and communicates with two ground receivers. FADE provides closer agreement with the empirical joint CDF, achieving reductions of up to 22.4% in MAE compared with the state-of-the-art Logistic and Maximum Empirical Likelihood (MEL) methods, while also improving distributional agreement and reducing absolute bias.

eess.SP↗

arXiv2026

Reliability- and Connectivity-Constrained Age-of-Information Optimization for UAV Swarm IoT Data Collection

Uncrewed aerial vehicle~(UAV) swarms provide a flexible platform for Internet of Things~(IoT) data collection by gathering delay-sensitive measurements from distributed sensor clusters and relaying them to a fusion center~(FC). Between successive updates, the FC estimates the current value of each monitored quantity; however, the estimation accuracy degrades as the last update ages. Such missions require jointly optimizing estimation accuracy, short-packet communication reliability, and swarm connectivity, yet existing approaches typically prioritize freshness while neglecting its impact on connectivity. This paper proposes a topology-coupled urgency~(TCU) scheduler that minimizes the FC's accumulated estimation error while incorporating the swarm's expected algebraic connectivity into the scheduling objective. The resulting connectivity reward encourages idle UAVs to reposition so as to preserve swarm connectivity. For each time slot, the resulting problem is a mixed-integer nonconvex program, which we solve by successive convex approximation. Specifically, the binary assignments are relaxed, while the connectivity reward is represented through a linear matrix inequality on the expected Laplacian. The finite-blocklength rate and the inter-UAV link reliability are linearized in the same convex subproblem, thereby preserving their coupling rather than separating them into alternating blocks. The integer assignments are subsequently recovered by Hungarian matching and verified against the original nonconvex constraints, while a deficit mechanism ensures long-term cluster coverage without requiring explicit long-horizon planning. In simulations comprising more than $19{,}000$ transmission attempts, all delivered updates satisfy the reliability target...

eess.SP↗

arXiv2026

Meta-Transfer Learning for mmWave Beam Alignment

Millimeter-wave (mmWave) beam alignment is critical for next-generation wireless systems, but existing approaches either update all parameters during adaptation or restrict updates to a subset of layers without adapting intermediate feature representations. We propose MTL-BA, a meta-transfer learning framework for multiple-input single-output (MISO) beam alignment that freezes a pre-trained convolutional backbone and meta-learns lightweight Scale-and-Shift (SS) adapters and a classifier head. Under an outdoor-to-indoor shift in DeepMIMO, MTL-BA achieves the highest Top-1 accuracy among the evaluated methods at 35 dB while updating $17\times$ fewer parameters than full fine-tuning and meta-training $6\times$ faster than MAML.

eess.SP↗

arXiv2026

Encoder-Sharing Hierarchical Federated Multi-Task Learning for VANETs

Most federated learning frameworks for vehicular ad hoc networks assume that all vehicles collaboratively train a single model for a common task. This assumption limits their applicability to practical vehicular environments, where vehicles may perform heterogeneous but related perception tasks with different output spaces. This paper proposes encoder-sharing hierarchical multi-task federated learning (EN-HMTFL), which integrates cluster-based hierarchical federated learning with a globally shared encoder and vehicle-local decoders. EN-HMTFL enables vehicles performing different tasks to collaboratively learn a transferable feature representation while preserving their task-specific models locally. Only the encoder is exchanged and aggregated through the hierarchy, whereas raw data and local decoder parameters remain at the vehicles. The proposed framework is evaluated on the MNIST and GTSRB datasets in different vehicular scenarios. Across the evaluated scenarios, EN-HMTFL improves accuracy by up to 24.0% relative to the compared representation-sharing benchmark. In scenarios where EN-HMTFL converges earlier, the reduction reaches up to 69 communication rounds (28.8%).

cs.LG↗

arXiv2026

Hierarchical Multi-Task Federated Learning in VANETs

Vehicular Ad hoc Networks (VANETs) increasingly rely on federated learning (FL) to enable collaborative intelligence without sharing raw sensory data. However, most existing vehicular FL frameworks assume that all vehicles train a single global model for a common task, which limits their applicability in practical vehicular environments where vehicles may perform heterogeneous learning tasks under non-independent and identically distributed (non-IID) data, intermittent connectivity, and high mobility. To address these challenges, this paper proposes an AutoEncoder-based Reliability-Optimized Hierarchical Multi-Task Federated Learning (AERO-HMTFL) framework for dynamic multi-hop clustered VANETs. The proposed framework introduces a tri-weighted clustering metric that jointly considers vehicular mobility, shared-model similarity, and task affinity to produce mobility-stable, semantically aligned clusters. Each vehicle employs a split-model architecture comprising a shared autoencoder-based representation module and multiple task-specific heads, with only the shared autoencoder parameters exchanged while the task heads remain local. To improve robustness, cluster heads perform reliability-aware aggregation based on historical validation performance and participation frequency, while the Evolved Packet Core (EPC) conducts global shared-autoencoder fusion across clusters. Extensive simulations demonstrate that, compared with the multi-task federated learning benchmarks, AERO-HMTFL achieves up to 13% higher sustained EPC-level accuracy, exhibits more stable learning dynamics, and reduces EPC-level packet transmissions by approximately 87-97%. Under short-range connectivity, it also requires approximately 13-29% fewer communication rounds to converge.

eess.SY↗

arXiv2026

From Ground to Sky: Architectures, Applications, and Challenges Shaping Low-Altitude Wireless Networks

In this article, we introduce a novel low-altitude wireless network (LAWN), which is a reconfigurable, three-dimensional (3D) layered architecture. In particular, the LAWN integrates connectivity, sensing, control, and computing across aerial and terrestrial nodes that enable seamless operation in complex, dynamic, and mission-critical environments. Different from the conventional aerial communication systems, LAWN's distinctive feature is its tight integration of functional planes in which multiple functionalities continually reshape themselves to operate safely and efficiently in the low-altitude sky. With the LAWN, we discuss several enabling technologies, such as integrated sensing and communication (ISAC), semantic communication, and fully-actuated control systems. Finally, we identify potential applications and key cross-layer challenges. This article offers a comprehensive roadmap for future research and development in the low-altitude airspace.

eess.SP↗

arXiv2026

AI-Based KPI Prediction Methods in Future 6G Networks: A Survey

The evolution from 5G to 5G-Advanced and the vision of 6G demand unprecedented levels of network performance, in which meeting stringent network Key Performance Indicators (KPIs), including capacity, latency, coverage, and reliability, is critical to supporting emerging applications such as autonomous driving, industrial automation, and immersive communications. Traditional reactive network management is insufficient in this context, driving the need for predictive, data-driven approaches. Machine Learning (ML) has emerged as a key enabler, enabling the forecasting of KPI trends from diverse data sources and thereby enabling proactive, AI-native automation in mobile networks. This survey provides the first comprehensive and systematic review of data-driven KPI prediction methods for future 6G networks. We introduce a multi-dimensional taxonomy that classifies prediction approaches by KPI type, data source, the network protocol stack at which the KPI is predicted, prediction horizon, model family, and prediction objective. Using this taxonomy, we analyze the state of the art across various KPIs, highlighting representative methods ranging from classical statistical models to deep learning and reinforcement learning. We further discuss enabling system aspects, including data collection and learning architectures, and examine deployment challenges, including data availability, scalability, privacy, and sustainability. Finally, we outline open research directions spanning new KPI definitions, probabilistic and explainable predictions. This survey aims to provide researchers and practitioners with a structured understanding of the KPI prediction landscape and a roadmap toward predictive network automation in future 6G systems.

eess.SY↗

arXiv2026

Resource-Efficient CSI Prediction: A Gated Fusion and Factorized Projection Approach

Accurate Channel State Information (CSI) prediction is essential for dynamic multiple-input multiple-output (MIMO) systems but remains computationally demanding. This letter proposes a resource-efficient predictor that combines a gated recurrent unit (GRU) encoder with Luong attention, a bottleneck gated fusion module, and a Dimension-wise Separable Linear Head (DSLH). The gated fusion module integrates local recurrent features with global attention context, while the DSLH reduces the cost of the output mapping. Evaluated on 3GPP TR 38.901-compliant channels, the proposed model achieves an average NMSE of -13.84 dB with 26% fewer parameters and approximately 2.3x higher inference throughput than a dimension-matched LinFormer baseline. The proposed model is best suited to LOS and mixed-condition scenarios, offering a practical accuracy-efficiency trade-off for short-horizon CSI prediction at moderate sequence lengths.

eess.SP↗

arXiv2026

EVT-Based Generative AI for Tail-Aware Channel Estimation

Ultra-reliable and low-latency communication (URLLC) will play a key role in fifth-generation (5G) and beyond networks, enabling mission-critical applications. Meeting the stringent URLLC requirements, characterized by extremely low packet error rates and minimal latency, calls for advanced statistical modeling to accurately capture rare events in wireless channels. Traditional methods, such as those that rely on large datasets and computationally intensive estimation techniques, often fail in real-time scenarios. In this paper, a novel framework is proposed to meet URLLC requirements through a synergistic integration of extreme value theory (EVT) with generative artificial intelligence (AI). EVT is used to model channel tail distributions, providing an accurate characterization of rare events. Concurrently, generative AI enables data augmentation and channel parameter estimation from limited samples. The integration of EVT with generative AI can thus help overcome the limitations of generative models in capturing extreme events during channel characterization. Using an experimental dataset collected from an automotive environment, it is demonstrated that this integration enhances data augmentation for extreme quantiles, while requiring fewer samples than traditional analytical EVT methods and generative baselines in online estimation of channel distribution.

eess.SP↗

arXiv2026

Large AI Model-Enabled Secure Communications in Low-Altitude Wireless Networks: Concepts, Perspectives and Case Study

Low-altitude wireless networks (LAWNs) have the potential to revolutionize communications by supporting a range of applications, including urban parcel delivery, aerial inspections and air taxis. However, compared with traditional wireless networks, LAWNs face unique security challenges due to low-altitude operations, frequent mobility and reliance on unlicensed spectrum, making it more vulnerable to some malicious attacks. In this paper, we investigate some large artificial intelligence model (LAM)-enabled solutions for secure communications in LAWNs. Specifically, we first explore the amplified security risks and important limitations of traditional AI methods in LAWNs. Then, we introduce the basic concepts of LAMs and delve into the role of LAMs in addressing these challenges. To demonstrate the practical benefits of LAMs for secure communications in LAWNs, we propose a novel LAM-based optimization framework that leverages large language models (LLMs) to generate enhanced state features on top of handcrafted representations, and to design intrinsic rewards accordingly, thereby improving reinforcement learning performance for secure communication tasks. Through a typical case study, simulation results validate the effectiveness of the proposed framework. Finally, we outline future directions for integrating LAMs into secure LAWN applications.

cs.NI↗

arXiv2025

SNR and Resource Adaptive Deep JSCC for Distributed IoT Image Classification

Sensor-based local inference at IoT devices faces severe computational limitations, often requiring data transmission over noisy wireless channels for server-side processing. To address this, split-network Deep Neural Network (DNN) based Joint Source-Channel Coding (JSCC) schemes are used to extract and transmit relevant features instead of raw data. However, most existing methods rely on fixed network splits and static configurations, lacking adaptability to varying computational budgets and channel conditions. In this paper, we propose a novel SNR- and computation-adaptive distributed CNN framework for wireless image classification across IoT devices and edge servers. We introduce a learning-assisted intelligent Genetic Algorithm (LAIGA) that efficiently explores the CNN hyperparameter space to optimize network configuration under given FLOPs constraints and given SNR. LAIGA intelligently discards the infeasible network configurations that exceed computational budget at IoT device. It also benefits from the Random Forests based learning assistance to avoid a thorough exploration of hyperparameter space and to induce application specific bias in candidate optimal configurations. Experimental results demonstrate that the proposed framework outperforms fixed-split architectures and existing SNR-adaptive methods, especially under low SNR and limited computational resources. We achieve a 10\% increase in classification accuracy as compared to existing JSCC based SNR-adaptive multilayer framework at an SNR as low as -10dB across a range of available computational budget (1M to 70M FLOPs) at IoT device.

eess.IV↗

arXiv2025

Scalable Wi-Fi RSS-Based Indoor Localization via Automatic Vision-Assisted Calibration

Wi-Fi-based positioning promises a scalable and privacy-preserving solution for location-based services in indoor environments such as malls, airports, and campuses. RSS-based methods are widely deployable as RSS data is available on all Wi-Fi-capable devices, but RSS is highly sensitive to multipath, channel variations, and receiver characteristics. While supervised learning methods offer improved robustness, they require large amounts of labeled data, which is often costly to obtain. We introduce a lightweight framework that solves this by automating high-resolution synchronized RSS-location data collection using a short, camera-assisted calibration phase. An overhead camera is calibrated only once with ArUco markers and then tracks a device collecting RSS data from broadcast packets of nearby access points across Wi-Fi channels. The resulting (x, y, RSS) dataset is used to automatically train mobile-deployable localization algorithms, avoiding the privacy concerns of continuous video monitoring. We quantify the accuracy limits of such vision-assisted RSS data collection under key factors such as tracking precision and label synchronization. Using the collected experimental data, we benchmark traditional and supervised learning approaches under varying signal conditions and device types, demonstrating improved accuracy and generalization, validating the utility of the proposed framework for practical use. All code, tools, and datasets are released as open source.

eess.SP↗

arXiv2025

Causal Beam Selection for Reliable Initial Access in AI-driven Beam Management

Efficient and reliable beam alignment is a critical requirement for mmWave multiple-input multiple-output (MIMO) systems, especially in 6G and beyond, where communication must be fast, adaptive, and resilient to real-world uncertainties. Existing deep learning (DL)-based beam alignment methods often neglect the underlying causal relationships between inputs and outputs, leading to limited interpretability, poor generalization, and unnecessary beam sweeping overhead. In this work, we propose a causally-aware DL framework that integrates causal discovery into beam management pipeline. Particularly, we propose a novel two-stage causal beam selection algorithm to identify a minimal set of relevant inputs for beam prediction. First, causal discovery learns a Bayesian graph capturing dependencies between received power inputs and the optimal beam. Then, this graph guides causal feature selection for the DL-based classifier. Simulation results reveal that the proposed causal beam selection matches the performance of conventional methods while drastically reducing input selection time by 94.4% and beam sweeping overhead by 59.4% by focusing only on causally relevant features.

cs.AI↗

arXiv2025

Reward-Augmented Reinforcement Learning for Continuous Control in Precision Autonomous Parking via Policy Optimization Methods

Autonomous parking (AP) represents a critical yet complex subset of intelligent vehicle automation, characterized by tight spatial constraints, frequent close-range obstacle interactions, and stringent safety margins. However, conventional rule-based and model-predictive methods often lack the adaptability and generalization needed to handle the nonlinear and environment-dependent complexities of AP. To address these limitations, we propose a reward-augmented learning framework for AP (RARLAP), that mitigates the inherent complexities of continuous-domain control by leveraging structured reward design to induce smooth and adaptable policy behavior, trained entirely within a high-fidelity Unity-based custom 3D simulation environment. We systematically design and assess three structured reward strategies: goal-only reward (GOR), dense proximity reward (DPR), and milestone-augmented reward (MAR), each integrated with both on-policy and off-policy optimization paradigms. Empirical evaluations demonstrate that the on-policy MAR achieves a 91\% success rate, yielding smoother trajectories and more robust behavior, while GOR and DPR fail to guide effective learning. Convergence and trajectory analyses demonstrate that the proposed framework enhances policy adaptability, accelerates training, and improves safety in continuous control. Overall, RARLAP establishes that reward augmentation effectively addresses complex autonomous parking challenges, enabling scalable and efficient policy optimization with both on- and off-policy methods. To support reproducibility, the code accompanying this paper is publicly available.

cs.RO↗

arXiv2025

Digital Twin-Assisted Explainable AI for Robust Beam Prediction in mmWave MIMO Systems

In line with the AI-native 6G vision, explainability and robustness are crucial for building trust and ensuring reliable performance in millimeter-wave (mmWave) systems. Efficient beam alignment is essential for initial access, but deep learning (DL) solutions face challenges, including high data collection overhead, hardware constraints, lack of explainability, and susceptibility to adversarial attacks. This paper proposes a robust and explainable DL-based beam alignment engine (BAE) for mmWave multiple-input multiple output (MIMO) systems. The BAE uses received signal strength indicator (RSSI) measurements from wide beams to predict the best narrow beam, reducing the overhead of exhaustive beam sweeping. To overcome the challenge of real-world data collection, this work leverages a site-specific digital twin (DT) to generate synthetic channel data closely resembling real-world environments. A model refinement via transfer learning is proposed to fine-tune the pre-trained model residing in the DT with minimal real-world data, effectively bridging mismatches between the digital replica and real-world environments. To reduce beam training overhead and enhance transparency, the framework uses deep Shapley additive explanations (SHAP) to rank input features by importance, prioritizing key spatial directions and minimizing beam sweeping. It also incorporates the Deep k-nearest neighbors (DkNN) algorithm, providing a credibility metric for detecting out-of-distribution inputs and ensuring robust, transparent decision-making. Experimental results show that the proposed framework reduces real-world data needs by 70%, beam training overhead by 62%, and improves outlier detection robustness by up to 8.5x, achieving near-optimal spectral efficiency and transparent decision making compared to traditional softmax based DL models.

cs.LG↗

arXiv2025

Safe Deep Reinforcement Learning for Resource Allocation with Peak Age of Information Violation Guarantees

In Wireless Networked Control Systems (WNCSs), control and communication systems must be co-designed due to their strong interdependence. This paper presents a novel optimization theory-based safe deep reinforcement learning (DRL) framework for ultra-reliable WNCSs, ensuring constraint satisfaction while optimizing performance, for the first time in the literature. The approach minimizes power consumption under key constraints, including Peak Age of Information (PAoI) violation probability, transmit power, and schedulability in the finite blocklength regime. PAoI violation probability is uniquely derived by combining stochastic maximum allowable transfer interval (MATI) and maximum allowable packet delay (MAD) constraints in a multi-sensor network. The framework consists of two stages: optimization theory and safe DRL. The first stage derives optimality conditions to establish mathematical relationships among variables, simplifying and decomposing the problem. The second stage employs a safe DRL model where a teacher-student framework guides the DRL agent (student). The control mechanism (teacher) evaluates compliance with system constraints and suggests the nearest feasible action when needed. Extensive simulations show that the proposed framework outperforms rule-based and other optimization theory based DRL benchmarks, achieving faster convergence, higher rewards, and greater stability.

eess.SP↗

arXiv2025

On the Performance of Unmanned Aerial Vehicles with MIMO VLC

This paper centers around a multiple-input-multiple-output (MIMO) visible light communication (VLC) system, where an unmanned aerial vehicle (UAV) benefits from a light emitting diode (LED) array to serve photo-diode (PD)-equipped users for illumination and communication simultaneously. Concerning the battery limitation of the UAV and considerable energy consumption of the LED array, a hybrid dimming control scheme is devised at the UAV that effectively controls the number of glared LEDs and thereby mitigates the overall energy consumption. To assess the performance of this system, a radio resource allocation problem is accordingly formulated for jointly optimizing the motion trajectory, transmit beamforming and LED selection at the UAV, assuming that channel state information (CSI) is partially available. By reformulating the optimization problem in Markov decision process (MDP) form, we propose a soft actor-critic (SAC) mechanism that captures the dynamics of the problem and optimizes its parameters. Additionally, regarding the high mobility of the UAV and thus remarkable rearrangement of the system, we enhance the trained SAC model by integrating a meta-learning strategy that enables more adaptation to system variations. By defining energy efficiency as a trade-off between the data rate and power consumption, simulations verify that upgrading a single-LED UAV by an array of 10 LEDs, exhibits 47% and 34% improvements in data rate and energy efficiency, albeit at the expense of 8% more power consumption.

eess.SP↗

arXiv2025

Secure Cluster-Based Hierarchical Federated Learning in Vehicular Networks

Hierarchical Federated Learning (HFL) has recently emerged as a promising solution for intelligent decision-making in vehicular networks, helping to address challenges such as limited communication resources, high vehicle mobility, and data heterogeneity. However, HFL remains vulnerable to adversarial and unreliable vehicles, whose misleading updates can significantly compromise the integrity and convergence of the global model. To address these challenges, we propose a novel defense framework that integrates dynamic vehicle selection with robust anomaly detection within a cluster-based HFL architecture, specifically designed to counter Gaussian noise and gradient ascent attacks. The framework performs a comprehensive reliability assessment for each vehicle by evaluating historical accuracy, contribution frequency, and anomaly records. Anomaly detection combines Z-score and cosine similarity analyses on model updates to identify both statistical outliers and directional deviations in model updates. To further refine detection, an adaptive thresholding mechanism is incorporated into the cosine similarity metric, dynamically adjusting the threshold based on the historical accuracy of each vehicle to enforce stricter standards for consistently high-performing vehicles. In addition, a weighted gradient averaging mechanism is implemented, which assigns higher weights to gradient updates from more trustworthy vehicles. To defend against coordinated attacks, a cross-cluster consistency check is applied to identify collaborative attacks in which multiple compromised clusters coordinate misleading updates. Together, these mechanisms form a multi-level defense strategy to filter out malicious contributions effectively. Simulation results show that the proposed algorithm significantly reduces convergence time compared to benchmark methods across both 1-hop and 3-hop topologies.

cs.CR↗