Papers

The practical deployment of Audio-Visual Speech Recognition (AVSR) systems is fundamentally challenged by significant performance degradation in real-world environments, characterized by unpredictable acoustic noise and visual interference. This dissertation posits that a systematic, hierarchical approach is essential to overcome these challenges, achieving the robust scalability at the representation, architecture, and system levels. At the representation level, we investigate methods for building a unified model that learns audio-visual features inherently robust to diverse real-world corruptions, thereby enabling generalization to new environments without specialized modules. To address architectural scalability, we explore how to efficiently expand model capacity while ensuring the adaptive and reliable use of multimodal inputs, developing a framework that intelligently allocates computational resources based on the input characteristics. Finally, at the system level, we present methods to expand the system's functionality through modular integration with large-scale foundation models, leveraging their powerful cognitive and generative capabilities to maximize final recognition accuracy. By systematically providing solutions at each of these three levels, this dissertation aims to build a next-generation, robust, and scalable AVSR system with high reliability in real-world applications.

Rotatable intelligent reflecting surfaces (IRSs) introduce a new degree of freedom (DoF) for shaping wireless propagation by adaptively adjusting the orientation of IRSs. This paper considers an angle-dependent reflection model in a wireless communication system aided by two rotatable IRSs. Specifically, we study the joint design of the base station transmit beamforming, as well as the cooperative passive beamforming and orientation of the two IRSs, to maximize the received signal-to-noise ratio (SNR). Under the light-of-sight (LoS) channels, we first develop a particle swarm optimization (PSO) based method to determine the IRS rotation and derive an optimal rotation in a closed-form expression for a two-dimensional IRS deployment. Then, we extend the design to the general Rician fading channels by proposing an efficient alternating optimization and PSO (AO-PSO) algorithm. Numerical results validate the substantial gains achieved by the IRS rotation over fixed-IRS schemes and also demonstrate the superior performance of the double rotatable IRSs over a single rotatable IRS given a sufficient total number of IRS elements.

We present a novel neural RGB-D Simultaneous Localization And Mapping (SLAM) system that learns an implicit map of the scene in real time. For the first time, we explore the use of Scene Coordinate Regression (SCR) as the core implicit map representation in a neural SLAM pipeline, a paradigm that trains a lightweight network to directly map 2D image features to 3D global coordinates. SCR networks provide efficient, low-memory 3D map representations, enable extremely fast relocalization, and inherently preserve privacy, making them particularly suitable for neural implicit SLAM. Our system is the first one to achieve strict real-time in neural implicit RGB-D SLAM by relying on a SCR-based representation. We introduce a novel SCR architecture specifically tailored for this purpose and detail the critical design choices required to integrate SCR into a live SLAM pipeline. The resulting framework is simple yet flexible, seamlessly supporting both sparse and dense features, and operates reliably in dynamic environments without special adaptation. We evaluate our approach on established synthetic and real-world benchmarks, demonstrating competitive performance against the state of the art. Project Page: https://github.com/ialzugaray/ace-slam

In cognitive Internet of Things (CIoT) networks, efficient spectrum sharing is essential to address increasing wireless demands. This paper presents a novel deep reinforcement learning (DRL)-based approach for joint cooperative caching and spectrum access coordination in CIoT networks, enabling the CIoT agents to collaborate with primary users (PUs) by caching PU content and serving their requests, fostering mutual benefits. The proposed DRL framework jointly optimizes caching policy and spectrum access under challenging conditions. Unlike traditional cognitive radio (CR) methods, where CIoT agents vacate the spectrum for PUs, or relaying techniques, which merely support spectrum sharing, caching brings data closer to the edge, reducing latency by minimizing retrieval distance. Simulations demonstrate that our approach outperforms others in lowering latency, increasing CIoT and PU cache hit rates, and enhancing network throughput. This approach redefines spectrum sharing, offering a fresh perspective on CIoT network design and illustrating the potential of DRL-guided caching to highlight the benefits of collaboration over dynamic spectrum access scenarios, elevating CIoT performance under constrained resources.

Semantic communication systems often use end-to-end neural networks to map input data into continuous symbols. These symbols, which are essentially neural network features, have fixed dimensions and often exhibit heavy-tailed distributions. However, the mechanism behind this distributional shape remains underexplored due to the end-to-end nature of encoder training, hindering systematic analysis and design. In this paper, we propose a parametric model for semantic symbol distributions. We model end-to-end training as inducing two coupled pressures on the symbol distribution: a source pressure that favors power allocation minimizing the average description cost, and a channel pressure that favors distributions with higher channel utilization. Under surrogate objectives that capture these effects, we obtain a Student's t-distribution as a model for the semantic symbols. Experiments on image-based semantic systems show that the model closely predicts how the shape parameter varies with (i) explicit symbol rate control and (ii) dataset entropy variability. Furthermore, enforcing a target symbol distribution via regularization (e.g., a Gaussian prior) improves training convergence, which is consistent with our hypothesis.

In this paper, we address the challenge of dynamic spectrum access in a cognitive Internet of Things (CIoT) network where a secondary user (SU) operates under both energy constraints and adversarial interference from a smart jammer. The SU coexists with primary users (PUs) and must ensure that its transmissions do not exceed a predefined interference threshold on licensed channels. At each time slot, the SU must jointly determine whether to transmit or harvest energy, which channel to access, and the appropriate transmit power while satisfying energy and interference constraints. Meanwhile, a smart jammer actively selects a channel to disrupt, aiming to degrade the SU's communication performance. This setting presents a significant challenge due to its multi-level decision structure and hybrid action space, which combines both discrete and continuous decisions. To tackle this, we propose a novel Hierarchical Deep Deterministic Policy Gradient (H-DDPG) framework that decomposes the decision-making process into three levels: the high-level policy determines the mode (transmit or harvest), the mid-level policy selects the channel, and the low-level actor outputs a continuous power level. Concurrently, the jammer is modeled as a reinforcement learning agent that learns an adaptive channel jamming strategy using a discrete variant of DDPG. Simulation results show that our H-DDPG approach outperforms conventional flat reinforcement learning baselines.

As agriculture faces increasing pressure from water scarcity, especially in regions like Tunisia, innovative, resource-efficient solutions are urgently needed. This work explores the integration of indoor vertical hydroponics with Machine Learning (ML) techniques to optimize basil yield while saving water. This research develops a prediction system that uses different ML models and assesses their performance. The models were systematically trained and tested using data collected from IoT sensors of various environmental parameters like CO2, light. The experimental setup features 21 basil crops and uses Raspberry Pi and Arduino. 10k data points were collected and used to train and evaluate three ML models: Linear Regression (LR), Long Short-Term Memory (LSTM), and Deep Neural Networks (DNN). The comparative analysis of the performance of each model revealed that, while LSTM showed high predictive capability and accuracy of 99%, its execution time was 10 times longer than LR and its RAM usage was about 3 times higher than DNN's when simulated on a standard CPU environment. Conversely, the DNN model had an accuracy rate of 98%. This proves an efficient balance between computational speed and prediction quality, which makes this model well-suited for real-life deployment. Moreover, LR excelled in fast processing of basic prediction with an execution time of 11 seconds. This makes the LR model more suitable for low-complexity or resource-limited applications. These performance trade-offs highlight the potential of DNN-based solutions for building responsive, high-accuracy decision-support systems tailored to agricultural environments, making it suitable for future edge-device deployment.

In this letter, we investigate the fundamental limits of localization in fluid antenna systems (FAS) utilizing a Fisher-information-theoretic framework. We develop a unified model to quantify the localization information extractable from time-of-arrival (ToA) and angle-of-arrival (AoA) measurements, explicitly capturing the synthetic aperture effects induced by FAS. Closed-form expressions are derived for the equivalent Fisher information matrix (EFIM) and the corresponding positioning error bound (PEB) in both user-side and base-station (BS)-side FAS configurations. Also, we propose optimal port-selection strategies based on greedy algorithms and convex relaxation to maximize the information gain under a constrained number of activated ports. Numerical results demonstrate that the proposed port-selection schemes can substantially tighten the PEB compared with random activation, thereby confirming the strong potential of FAS to enable high-precision localization. These results offer analytical insights and practical design guidelines for FAS-aided positioning in future-generation wireless networks

Controlling stochastic systems with unknown dynamics and under complex specifications is specially challenging in safety-critical settings, where performance guarantees are essential. We propose a data-driven policy synthesis framework that yields formal performance guarantees for such systems using conditional mean embeddings (CMEs) and uncertain Markov decision processes (UMDPs). From trajectory data, we learn the system's transition kernel as a CME, then construct a finite-state UMDP abstraction whose transition uncertainties capture learning and discretization errors. Next, we generate a policy with formal performance bounds through robust dynamic programming. We demonstrate and empirically validate our method through a temperature regulation benchmark.

Dynamical decoupling seeks to mitigate phase decoherence in qubits by applying a carefully designed sequence of effectively instantaneous electromagnetic pulses. Although analytic solutions exist for pulse timings that are optimal under specific noise regimes, identifying the optimal timings for a realistic noise spectrum remains challenging. We propose a reinforcement learning (RL)-based method for designing pulse sequences on qubits. Our novel action set enables the RL agent to efficiently navigate this inherently non-convex optimization landscape. The action set, derived from Thompson's group $F$, is applicable to a broad class of sequential decision problems whose states can be represented as bounded sequences. We demonstrate that our RL agent can learn pulse sequences that minimize dephasing without requiring explicit knowledge of the underlying noise spectrum. This work opens the possibility for real-time learning of optimal dynamical decoupling sequences on qubits which are dephasing-limited. The model-free nature of our algorithm suggests that the agent may ultimately learn optimal pulse sequences even in the presence of unmodeled physical effects, such as pulse errors or non-Gaussian noise.

This thesis presents a fundamental rethink of electricity market design at the wholesale and balancing layers. Rather than treating markets as static spot clearing mechanisms, it reframes them as a continuously online, event driven dynamical control system: a two sided marketplace operating directly on grid physics. Existing energy only, capacity augmented, and zonal market designs are shown to admit no shock robust Nash equilibrium under realistic uncertainty, instead relying on price caps, uplift, and regulatory intervention to preserve solvency and security. In response, the thesis develops a holarchic Automatic Market Maker (AMM) in which prices are bounded, exogenous control signals derived from physical tightness rather than emergent equilibrium outcomes. The AMM generalises nodal and zonal pricing through nested scarcity layers, from node to cluster to zone to region to system, such that participant facing prices inherit from the tightest binding constraint. Nodal and zonal pricing therefore emerge as special cases of a unified scarcity propagation rule. Beyond pricing, the AMM functions as a scarcity aware control system and a digitally enforceable rulebook for fair access and proportional allocation under shortage. Fuel costs are recovered through pay as bid energy dispatch consistent with merit order, while non fuel operating and capital costs are allocated according to adequacy, flexibility, and locational contribution. Large scale simulations demonstrate bounded input bounded output stability, controllable procurement costs, zero structural waste, and improved distributional outcomes. The architecture is climate aligned and policy configurable, but requires a managed transition and new operational tools for system operators and market participants.

Restoring hand function requires simultaneous and proportional control (SPC) of multiple degrees of freedom (DoFs). This study evaluated the multichannel linear descriptors-based block field method (MLD-BFM) against conventional feature extraction approaches for continuous decoding of five finger-joint DoFs using high-density surface electromyography (HD sEMG). Twenty-one healthy participants performed dynamic sinusoidal finger movements while HD sEMG signals were recorded from the proximal forearm. MLD-BFM extracted spatial descriptors including effective field strength ($\Sigma$), field-strength variation rate ($\Phi$), and spatial complexity ($\Omega$). Performance was optimized (block size: $2\times2$; window: 0.15,s) and compared with conventional time-domain features, root mean square (RMS) and mean absolute value plus waveform length (MAV-WL), as well as dimensionality reduction methods (PCA and NMF), using multi-output regression models. MLD-BFM achieved the highest mean variance-weighted coefficient of determination ($\mathrm{R}^2_\mathrm{vw}$) across all models, with the multilayer perceptron yielding the best result ($86.68 \pm 0.33 \%$). However, the improvement was not statistically significant relative to time-domain features, suggesting that dense multichannel recordings already encode spatial information through amplitude-based descriptors. MLD-BFM significantly outperformed dimensionality reduction approaches, indicating that preserving the spatial resolution of HD sEMG is critical for accurate multi-DoF finger movement regression.

This paper proposes a Safe Online Control-Informed Learning framework for safety-critical autonomous systems. The framework unifies optimal control, parameter estimation, and safety constraints into an online learning process. It employs an extended Kalman filter to incrementally update system parameters in real time, enabling robust and data-efficient adaptation under uncertainty. A softplus barrier function enforces constraint satisfaction during learning and control while eliminating the dependence on high-quality initial guesses. Theoretical analysis establishes convergence and safety guarantees, and the framework's effectiveness is demonstrated on cart-pole and robot-arm systems.

This paper presents a pipeline stage resolved timing characterization of a 32-bit RISC V processor implemented on a 20 nm FPGA and a 7 nm FinFET ASIC platform. A unified analysis framework is introduced that decomposes timing paths into logic, routing, and clocking components and maps them to well-defined pipeline stage transitions. This approach enables systematic comparison of timing behavior across heterogeneous implementation technologies at a microarchitectural level. Using static timing analysis and statistical characterization, the study shows that although both implementations exhibit dominant critical paths in the EX to MEM pipeline transition, their underlying timing mechanisms differ fundamentally. FPGA timing is dominated by routing parasitics and placement dependent variability, resulting in wide slack distributions and sensitivity to routing topology. In contrast, ASIC timing is governed primarily by combinational logic depth and predictable parametric variation across process, voltage, and temperature corners, yielding narrow and stable timing distributions. The results provide quantitative insight into the structural origins of timing divergence between programmable and custom fabrics and demonstrate the effectiveness of pipeline stage resolved analysis for identifying platform specific bottlenecks. Based on these findings, the paper derives design implications for achieving predictable timing closure in processor architectures targeting both FPGA and ASIC implementations.

This paper proposes a U-Net-based autoencoder framework for mitigating interference in communication signals corrupted by noise and diverse interference sources. The approach targets scenarios involving both signal-plus-noise and signal-plus-interference-plus-noise mixtures, including sinusoidal interferers, LFM chirps, QPSK interferers with different sampling rates, and modulated interference such as QAM. The U-Net architecture leverages multiscale feature extraction and skip connections to preserve fine-grained temporal structure while suppressing interference components. Performance is evaluated using bit error rate and compared against conventional cancellation methods. Results show that the proposed method consistently outperforms traditional techniques in low- and mid-SIR regimes, while remaining competitive at high SIRs. Additional experiments examine the autoencoder's behavior under model mismatch conditions such as carrier offset and colored noise. The study demonstrates that multiscale neural architectures provide a flexible and effective platform for interference mitigation across a wide range of interference types.

Autonomous driving requires reliable collision avoidance in dynamic environments. Nonlinear Model Predictive Controllers (NMPCs) are suitable for this task, but struggle in time-critical scenarios requiring high frequency. To meet this demand, optimization problems are often simplified via linearization, narrowing the horizon window, or reduced temporal nodes, each compromising accuracy or reliability. This work presents the first general convex obstacle avoidance formulation, enabled by a novel approach to integrating logic. This facilitates the incorporation of an obstacle avoidance formulation into convex MPC schemes, enabling a convex optimization framework with substantially improved computational efficiency relative to conventional nonconvex methods. A key property of the formulation is that obstacle avoidance remains effective even when obstacles lie outside the prediction horizon, allowing shorter horizons for real-time deployment. In scenarios where nonconvex formulations are unavoidable, the proposed method meets or exceeds the performance of representative nonconvex alternatives. The method is evaluated in autonomous vehicle applications, where system dynamics are highly nonlinear.

We consider a computation offloading system where jobs are processed sequentially at a local server followed by a higher-capacity cloud server. The system offers two service modes, differing in how the processing is split between the servers. Our goal is to design an optimal policy for assigning jobs to service modes and partitioning server resources in order to minimize delay. We begin by characterizing the system's stability region and establishing design principles for service modes that maximize throughput. For any given job assignment strategy, we derive the optimal resource partitioning and present a closed-form expression for the resulting delay. Moreover, we establish that the delay-optimal assignment policy exhibits a distinct breakaway structure: at low system loads, it is optimal to route all jobs through a single service mode, whereas beyond a critical load threshold, jobs must be assigned across both modes. We conclude by validating these theoretical insights through numerical evaluation.

The forward problem in electrocardiology, computing body surface potentials from cardiac electrical activity, is traditionally solved using physics-based models such as the bidomain or monodomain equations. While accurate, these approaches are computationally expensive, limiting their use in real-time and large-scale clinical applications. We propose a proof-of-concept deep learning (DL) framework as an efficient surrogate for forward solvers. The model adopts a time-dependent, attention-based sequence-to-sequence architecture to predict electrocardiogram (ECG) signals from cardiac voltage propagation maps. A hybrid loss combining Huber loss with a spectral entropy term was introduced to preserve both temporal and frequency-domain fidelity. Using 2D tissue simulations incorporating healthy, fibrotic, and gap junction-remodelled conditions, the model achieved high accuracy (mean $R^2 = 0.99 \pm 0.01$). Ablation studies confirmed the contributions of convolutional encoders, time-aware attention, and spectral entropy loss. These findings highlight DL as a scalable, cost-effective alternative to physics-based solvers, with potential for clinical and digital twin applications.

Monitoring contact pressure in hospital beds is essential for preventing pressure ulcers and enabling real-time patient assessment. Current methods can predict pressure maps but often lack physical plausibility, limiting clinical reliability. This work proposes a framework that enhances plausibility via Informed Latent Space (ILS) and Weight Optimization Loss (WOL) with conditional generative modeling to produce high-fidelity, physically consistent pressure estimates. This study also applies diffusion based conditional Brownian Bridge Diffusion Model (BBDM) and proposes training strategy for its latent counterpart Latent Brownian Bridge Diffusion Model (LBBDM) tailored for pressure synthesis in lying postures. Experiment results shows proposed method improves physical plausibility and performance over baselines: BBDM with ILS delivers highly detailed maps at higher computational cost and large inference time, whereas LBBDM provides faster inference with competitive performance. Overall, the approach supports non-invasive, vision-based, real-time patient monitoring in clinical environments.

Satellite data of atmospheric pollutants are often available only at coarse spatial resolution, limiting their applicability in local-scale environmental analysis and decision-making. Spatial downscaling methods aim to transform the coarse satellite data into high-resolution fields. In this work, two widely used deep learning architectures, the super-resolution deep residual network (SRDRN) and the encoder-decoder-based UNet, are considered for spatial downscaling of tropospheric ozone. Both methods are extended with a lightweight temporal module, which encodes observation time using either sinusoidal or radial basis function (RBF) encoding, and fuses the temporal features with the spatial representations in the networks. The proposed time-aware extensions are evaluated against their baseline counterparts in a case study on ozone downscaling over Italy. The results suggest that, while only slightly increasing computational complexity, the temporal modules significantly improve downscaling performance and convergence speed.

Terahertz inter-satellite links (THz-ISL) offer unprecedented bandwidth for future space networks but face fundamental constraints from onboard power and thermal budgets. This paper establishes theoretical performance limits for MIMO Integrated Sensing and Communication (ISAC) systems under per-element constant-envelope (CE) transmission constraints. We demonstrate that hardware distortions – specifically power amplifier nonlinearity, ADC quantization, and oscillator phase noise – impose a capacity ceiling that cannot be overcome by increasing transmit power. A unified link budget framework integrates wideband beam squint, aperture pointing errors, and colored noise sources through a spectral consistency principle that ensures residual phase noise is counted exactly once across communication and sensing analyses. The sensing bounds are derived via the Whittle-Fisher Information Matrix under a Constant Acceleration kinematic model with jerk noise, yielding closed-form scaling laws: residual phase noise variance scales as $\alpha^{-1}$ while dynamic state-estimation error (DSE) variance scales as $\alpha^{-5}$ with pilot overhead $\alpha$. Numerical results show divergent MIMO scaling: sensing precision improves with array size ($\mathrm{RMSE} \propto 1/\sqrt{N_t N_r}$), while the critical SNR exhibits scale invariance regarding array size, implying that the distortion-limited transition point stabilizes regardless of the array scale. The steep $\alpha^{-5}$ DSE scaling creates an operationally infeasible region at $\alpha < \alpha^* \approx 0.16$, where $\alpha^* = (C_{\mathrm{DSE}}/C_{\mathrm{PN}})^{1/4}$ – a constraint-driven threshold under the adopted baseline for LEO operation. These findings provide design guidelines for hardware-efficient THz-ISL constellations.

Federated learning (FL) enables a privacy-preserving training paradigm for audio classification but is highly sensitive to client heterogeneity and poisoning attacks, where adversarially compromised clients can bias the global model and hinder the performance of audio classifiers. To mitigate the effects of model poisoning for audio signal classification, we present REVERB-FL, a lightweight, server-side defense that couples a small reserve set (approximately 5%) with pre- and post-aggregation retraining and adversarial training. After each local training round, the server refines the global model on the reserve set with either clean or additional adversarially perturbed data, thereby counteracting non-IID drift and mitigating potential model poisoning without adding substantial client-side cost or altering the aggregation process. We theoretically demonstrate the feasibility of our framework, showing faster convergence and a reduced steady-state error relative to baseline federated averaging. We validate our framework on two open-source audio classification datasets with varying IID and Dirichlet non-IID partitions and demonstrate that REVERB-FL mitigates global model poisoning under multiple designs of local data poisoning.

Digital/Analog converters based on sigma-delta modulation are simple and unexpensive circuits featuring a signal bandwidth limited by speed constraints. Multi-bit modulators allow balancing complexity and speed by reducing the clock frequency and increasing the number of levels in the quantizer. In this case, the multi-bit digital to analog block (DAC) can reduce the performance of the entire system. Data Weighted Averaging (DWA) methods have been proposed to reduce the vulnerability to DAC errors at the cost of spurious tones in the signal band. This work analyzes the tone producing mechanism and proposes a modification of the DWA to remove spurious tones.

Bidding flexibility in day-ahead and intraday auctions would enable decentralized flexible resources, such as electric vehicles and heat pumps, to efficiently align their consumption with the intermittent generation of renewable energy. However, because these resources are individually too small to participate in those auctions directly, an aggregator (e.g., a utility) must act on their behalf. This requires aggregating many decentralized resources, which is a computationally challenging task. In this paper, we propose a computationally efficient and highly accurate method that is readily applicable to European day-ahead and intraday auctions. Distinct from existing methods, we aggregate only economically relevant power profiles, identified through price forecasts. The resulting flexibility is then conveyed to the market operator via exclusive groups of block bids. We evaluate our method for a utility serving the Swiss town of Losone, where flexibility from multiple heat pumps distributed across the grid must be aggregated and bid in the Swiss day-ahead auction. Results show that our method aggregates accurately, achieving 98% of the theoretically possible cost savings. This aggregation accuracy remains stable even as the number of heat pumps increases, while computation time grows only linearly, demonstrating strong scalability.

Ever since R.D.Middlebrook proposed the state space averaging notion. The small signal model has been widely used as a design tool to tune control parameters. As Moore's law is continuing and the AI chip's high demand for power consumption and dynamic response, the control bandwidth needs to be boosted. However, the average model has two basic assumptions: the low-frequency assumption, the small ripple assumption. In high-bandwidth design, these two assumptions are violated. In order to solve this, various methods have been proposed. This paper gives a comprehensive overview of the existing small signal model for PWM converters from the following perspectives: 1. model fidelity, 2. analytical tractability. 3. complexity of the derivation process and result 4.generality.

In many signal processing applications, including communications, sonar, radar, and localization, a fundamental problem is the detection of a signal of interest in background noise, known as signal detection [1] [2]. A simple version of this problem is the detection of a signal of interest with unknown parameters in Additive White Gaussian Noise (AWGN). When the parameters defining the signal are not known, an optimal detector (in the Neyman-Pearson sense) does not exist. An upper bound on the performance of any detector is the matched filter, which implies perfect sample by sample knowledge of the signal of interest. In recent years Deep Neural Networks (DNNs) have proven to be very effective at hypothesis testing problems such as object detection and image classification. This paper examines the application of DNN-based approaches to the signal detection problem at the raw I/Q level and compares them to statistically based approaches as well as the Matched Filter. These methods aim to maximize the Probability of Detection Pd while maintaining a constant Probability of False Alarm PF A. Two Machine Learning (ML) algorithms are trained and assessed on this signal detection problem, across three signal of interest models. A model was also trained on a unified dataset and assessed across all signals of interest.

Building on the previous work on interference mitigation, this paper introduces a modular recommender system that automatically selects the most effective interference mitigation strategy based on the interference characteristics present in the received signal. The system integrates three key stages: an SPS classifier module, a SIR predictor, and a bank of specialized U-Net autoencoders designed for different interference conditions. The classification block identifies the parameters required for cancellation. The recommender then directs the signal to the appropriate mitigation model, optionally incorporating SIR-based decisions for scenarios where successive interference cancellation may be advantageous. Experiments conducted across diverse SIR levels and modulation environments show that the recommender strategy improves robustness and reduces BER compared to using any single mitigation method alone. The results demonstrate the potential of adaptive, model-selective architectures to enhance interference resilience in dynamic communication environments.

Purpose: To develop DarkSPARC, a retrospective, training-free, self-calibrated spectral reconstruction method that converts routine bright-blood 3D left atrial (LA) late gadolinium enhancement (LGE) MRI into a dark-blood image, and to quantify its impact on LA scar-pool CNR, SNR, effective CNR (eCNR), and scar quantification accuracy. Methods: DarkSPARC embeds bright-blood LA LGE into a calibrator-conditioned (N+1)-dimensional spectral domain and reconstructs a dark-blood-like image using scan-specific spectral landmarks. A scan-specific 3D numerical phantom framework was built from LAScarQS post-ablation LGE by cloning remote myocardium into the LA wall and imposing controlled scar burden. Five baseline cases spanning the 5th-95th percentiles of native scar-pool CNR, each with multiple scar burdens and 10 CNR degradation levels, yielded 200 phantoms. For every phantom, LA scar-pool CNR, SNR, eCNR, and Scar% were measured on bright-blood and DarkSPARC images. In vivo performance was evaluated in 60 public post-ablation scans of atrial fibrillation patients. Results: In scan-specific phantoms, DarkSPARC increased LA scar-pool CNR, SNR, and eCNR over bright-blood in all 200 experiments, with DarkSPARC/bright-blood ratios up to about 30-fold for CNR and about 6-fold for SNR in the lowest-CNR conditions. At 70% CNR degradation, bright-blood underestimated ground-truth LA Scar% by -37% to -54%, whereas DarkSPARC reduced bias to about -3% to -5%. In vivo, DarkSPARC similarly improved metrics: median scar-pool CNR, SNR, and eCNR increased from 20.0 to 135.9 (6.8x), 70.6 to 200.6 (2.8x), and 0.22 to 0.75 (3.4x), respectively (all p<0.001), and LA Scar% increased from 3.9% to 9.75%. Conclusion: DarkSPARC is a self-calibrated, training-free reconstruction that yields dark-blood 3D LA LGE, boosting CNR/SNR/eCNR and stabilizing reliable scar quantification without extra scans.

This paper investigates the performance of networked control systems subject to multiplicative routing transformations that alter measurement pathways without directly injecting signals. Such transformations, arising from faults or adversarial actions, modify the feedback structure and can degrade performance while remaining stealthy. An $H_2$-norm framework is proposed to quantify the impact of these transformations by evaluating the ratio between the steady-state energies of performance and residual outputs. Equivalent linear matrix inequality (LMI) formulations are derived for computational assessment, and analytical upper bounds are established to estimate the worst-case degradation. The results provide structural insight into how routing manipulations influence closed-loop behavior and reveal conditions for stealthy multiplicative attacks.

The large-scale deployment of renewable energy sources, particularly offshore wind, requires large-scale transmission grid expansion projects to transmit the produced low-carbon power to the main demand centers. However, the planning and design of such complex projects currently lack a transparent and systematic process that system operators can follow when considering such investments in their grids. This paper identifies and classifies the main technical design constraints and considerations relevant to the planning of transmission grid expansion projects, and more specifically, electrical energy hubs. Seven key areas of interest are identified, namely network integration, HVDC technologies, costs (CAPEX, OPEX, and space requirements), electricity market design, future proofness and modular expandability, reliability-availability-maintainability, and sustainability. Each area of interest is analyzed in terms of its technical and operational relevance, with technical design constraints and considerations derived from such analysis. In addition, a hierarchical classification of the identified constraints and considerations (and therefore areas of interest) is introduced, distinguishing them between three criticality classes, namely hard constraints, main drivers, and key considerations. The dependencies between the different areas are discussed, too. Therefore, this work provides system operators and policymakers with a structured basis to support a transparent planning methodology with clear decision hierarchies for investments in transmission grid expansion projects.