Presented is an algorithm to synthesize the optimal infinite-horizon LQR feedback controller for continuous-time systems. The algorithm does not require knowledge of the system dynamics but instead uses only a finite-length sampling of arbitrary input-output data. The algorithm is based on a constrained optimization problem that enforces a necessary condition on the dynamics of the optimal value function along any trajectory. In addition to calculating the standard LQR gain matrix, a feedforward gain can be found to implement a reference tracking controller. This paper presents a theoretical justification for the method and shows several examples, including a validation test on a real scale aircraft.

Reconfigurable intelligent surfaces (RIS) are conventionally implemented as two-dimensional (2D) electromagnetic (EM) structures to steer incident waves toward desired reflection angles. This approach limits the reflection to a single hemisphere, and the beam-scanning range is relatively small. In this work, a novel three-dimensional (3D) RIS concept is proposed, where beam-scanning can be realized not only through reflection from the illuminated surface but also through controlled transmission toward adjacent surfaces, enabling near blind-spot-free coverage in the full 3D spatial domain. A cube-based 3D-RIS design operating at millimeter-wave (mm-Wave) frequencies and consisting of six interconnected RIS surfaces is presented. Each surface integrates reconfigurable receiving and reflecting arrays with orthogonal polarizations to ensure intrinsic EM isolation, while a reconfigurable feeding network supports dynamic operation. A subarray-based synthesis approach with binary amplitude gating and predefined phase offsets is developed through a unified theoretical model. This model, validated through full-wave simulations, enables efficient beam switching through a shared aperture. Based on this framework, an 8 x 12 element surface comprising six 4 x 4 subarrays is designed, with each surface covering an angular range from -30 deg to +30 deg. The experimental prototype has been characterized in the 24 to 30 GHz band, and the results demonstrate a gain enhancement of 14.7 dB for reflection, while 14.1 dB is achieved for transmission to the neighboring surface. Finally, wireless communication trials using the Pluto software-defined radio platform combined with frequency up/down converters confirm improved constellation quality and a 6-7 dB improvement in error vector magnitude (EVM) for both reflection and neighboring surface transmission scenarios.

This work investigates near-field focusing using a three-dimensional (3D) large intelligent surface (LIS) across frequencies and polarizations. Specifically, the LIS elements are distributed in 3D space within a long corridor, rather than being confined to a single planar aperture, and the focal point is located at a prescribed position in the radiating near field. By formulating optimization problems under both local and global power constraints, we obtain the corresponding optima. For continuous apertures, the optimal current magnitude distribution matches time-reversal (TR) solution under the global constraint and conjugate-phase (CP) solution when the local constraint dominates. When both constraints are active, the solution assigns larger excitation magnitudes to elements closer to the illumination field. This behavior remains invariant with respect to frequency and polarization for a fixed-size LIS. These findings are consistent to the more practical case of using discretized apertures in the form of Hertzian dipole arrays, studied using both analytical results and full-wave simulation. In addition, with the CP method, specific polarizations lead to identical transverse and longitudinal resolution, in contrast, under the TR method, these quantities can differ across polarizations.

Nonlinear system identification (NL-SI) has proven to be effective in obtaining accurate models for highly complex systems. Recent encoder-based methods for artificial neural network state-space (ANN-SS) models have shown state-of-the-art performance with improved computational efficiency, where the encoder is used to estimate the initial state allowing for batch optimisation methods. To address the lack of interpretability of these black-box ANN models, model augmentation approaches can be used. These combine prior available baseline models with the ANN learning components, resulting in faster convergence and more interpretable models. The combination of the encoder-based method with model augmentation has shown potential. Thus far, however, the encoder has still been treated as a black-box function in the overall estimation process, while additional information in the form of the baseline model is available to predict the model state from past input-output data. In this paper, we propose novel encoder initialisation approaches based on the available baseline model, resulting in improved noise robustness and faster convergence compared to black-box initialisation. The performance of these initialisation methods is demonstrated on a mass-spring-damper system.

Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications. However, the massive parameter scale and computational demands of LAIMs pose significant challenges for resource-limited embodied agents. To address this issue, we investigate quantization-aware collaborative inference (co-inference) for embodied AI systems. First, we develop a tractable approximation for quantization-induced inference distortion. Based on this approximation, we derive lower and upper bounds on the quantization rate-inference distortion function, characterizing its dependence on LAIM statistics, including the quantization bit-width. Next, we formulate a joint quantization bit-width and computation frequency design problem under delay and energy constraints, aiming to minimize the distortion upper bound while ensuring tightness through the corresponding lower bound. Extensive evaluations validate the proposed distortion approximation, the derived rate-distortion bounds, and the effectiveness of the proposed joint design. Particularly, simulations and real-world testbed experiments demonstrate the effectiveness of the proposed joint design in balancing inference quality, latency, and energy consumption in edge embodied AI systems.

State-space models (SSM) are common in signal processing, where Kalman smoothing (KS) methods are state-of-the-art. However, traditional KS techniques lack expressivity as they do not incorporate spatial prior information. Recently, [1] proposed an ADMM algorithm that handles the state-space fidelity term with KS while regularizing the object via a sparsity-based prior with proximity operators. Plug-and-Play (PnP) methods are a popular type of iterative algorithms that replace proximal operators encoding prior knowledge with powerful denoisers such as deep neural networks. These methods are widely used in image processing, achieving state-of-the-art results. In this work, we build on the KS-ADMM method, combining it with deep learning to achieve higher expressivity. We propose a PnP algorithm based on KS-ADMM iterations, efficiently handling the SSM through KS, while enabling the use of powerful denoising networks. Simulations on a 2D+t imaging problem show that the proposed PnP-KS-ADMM algorithm improves the computational efficiency over standard PnP-ADMM for large numbers of timesteps.

The spherical nature of the wavefronts exhibited in the near-field of antenna arrays enables advanced beamforming capabilities, such as beampointing and beamnulling. In this paper, we exploit these properties to design a near-field beam pattern under a low exposure region constraint. We address the continuous region constraint through spatial discretization, which results in a large number of constraints that lead to prohibitive computational complexity. We propose a novel low-complexity algorithm that enables a computationally tractable beam pattern design. It uses a low-dimensional subspace representation of the low exposure region based on a singular value decomposition. Our approach achieves low complexity while providing a power received at a target user close to the optimal achievable power, yet with uniform power mitigation over the low exposure region.

This paper investigates systematic selection of optimal grid points for grid-based Linear Parameter-Varying (LPV) and robust controller synthesis. In both settings, the objective is to identify a set of local models such that the controller synthesized for these local models will satisfy global stability and performance requirements for the entire system. Here, local models correspond to evaluations of the LPV or uncertain plant at fixed values of the scheduling signal or realizations of the uncertainty set, respectively. Then, Bayesian optimization is employed to discover the most informative points that govern the closed-loop performance of the designed LPV or robust controller for the complete system until no significant further performance increase or a user specified limit is reached. Furthermore, when local model evaluations are computationally demanding or difficult to obtain, the proposed method is capable to minimize the number of evaluations and adjust the overall computational cost to the available budget. Lastly, the capabilities of the proposed method in automatically obtaining a sufficiently informative grid set are demonstrated on three case-studies: a robust controller design for an unbalanced disk, a multi-objective robust attitude controller design for a satellite with uncertain parameters and two flexible rotating solar arrays, and an LPV controller design for a robotic arm.

Deep Neural Networks (DNNs) often struggle to suppress noise at low signal-to-noise ratios (SNRs). This paper addresses speech enhancement in scenarios dominated by harmonic noise and proposes a framework that integrates cyclostationarity-aware preprocessing with lightweight DNN-based denoising. A cyclic minimum power distortionless response (cMPDR) spectral beamformer is used as a preprocessing block. It exploits the spectral correlations of cyclostationary noise to suppress harmonic components prior to learning-based enhancement and does not require modifications to the DNN architecture. The proposed pipeline is evaluated in a single-channel setting using two DNN architectures: a simple and lightweight convolutional recurrent neural network (CRNN), and a state-of-the-art model, namely ultra-low complexity network (ULCNet). Experiments on synthetic data and real-world recordings dominated by rotating machinery noise demonstrate consistent improvements over end-to-end DNN baselines, particularly at low SNRs. Remarkably, a parameter-efficient CRNN with cMPDR preprocessing surpasses the performance of the larger ULCNet operating on raw or Wiener-filtered inputs. These results indicate that explicitly incorporating cyclostationarity as a signal prior is more effective than increasing model capacity alone for suppressing harmonic interference.

Non-line-of-sight sensing of human activities in complex environments is enabled by multiple-input multiple-output through-the-wall radar (TWR). However, the distinctiveness of micro-Doppler signature between similar indoor human activities such as gun carrying and normal walking is minimal, while the large scale of input images required for effective identification utilizing time-frequency spectrograms creates challenges for model training and inference efficiency. To address this issue, the Chebyshev-time map is proposed in this paper, which is a method characterizing micro-Doppler signature using polynomial orders. The parametric kinematic models for human motion and the TWR echo model are first established. Then, a time-frequency feature representation method based on orthogonal Chebyshev polynomial decomposition is proposed. The kinematic envelopes of the torso and limbs are extracted, and the time-frequency spectrum slices are mapped into a robust Chebyshev-time coefficient space, preserving the multi-order morphological detail information of time-frequency spectrum. Numerical simulations and experiments are conducted to verify the effectiveness of the proposed method, which demonstrates the capability to characterize armed and unarmed indoor human activities while effectively compressing the scale of the time-frequency spectrum to achieve a balance between recognition accuracy and input data dimensions. The open-source code of this paper can be found in: https://github.com/JoeyBGOfficial/Represent-Micro-Doppler-Signature-in-Orders.

We investigate reconfigurable intelligent surfaces (RISs) for the task of position and velocity estimation in non-LOS (NLOS) indoor scenarios, using a snapshot based multi-step estimation algorithm. We evaluate a compound RIS structure prototype composed of four RIS tiles with 1-bit phase control per RIS unit cell. Numerical simulation results taking the antenna patterns into account are presented for an 3 m x 3 m area of interest. We demonstrate that the initial grid search step using the far field assumption is not robust enough for small distances to the RIS center and propose a more robust algorithm. Furthermore, we show that the effect of the antenna pattern causes an increased position and velocity error. Our modified three-step algorithm achieves a position error of 7 mm and a velocity error of 0.12 m/s at a distance of 2 m to the RIS center under a realistic numerical propagation model.

The demand for high-precision indoor localization has grown significantly with the rise of smart environments, industrial automation, and location-aware applications. While massive Multiple-Input and Multiple-Output (MIMO) systems enable millimeter-level accuracy by leveraging rich Channel State Information (CSI), most existing solutions are optimized for static environments, where users or devices remain fixed during data collection and inference. Real-world applications, however, often require real-time localization in changing environments, where rapid movement, unpredictable blockages, and dynamic channel conditions pose significant challenges. To address these challenges, we introduce two data augmentation techniques designed to resemble blocked antennas, enhancing the generalizability of localization models to dynamic scenarios. Additionally, we enhance an existing Deep Learning (DL) model by incorporating attention modules, improving its ability to focus on relevant channel features and antennas. We train our model on data from a static scenario, augmented with the proposed techniques, and evaluate it on a dataset collected in changing scenarios. We investigate the performance enhancements achieved by the data augmentation techniques and the Attention modules, and observe a localization accuracy improvement from a mean error of 286 mm, when trained without Attention and without data augmentations, to 66 mm, when trained with Attention and data augmentation. This shows that high localization accuracy can be maintained in changing environments, even without training data from those scenarios.

Next-generation wireless networks at upper mid-band and millimeter-wave frequencies require accurate site-specific deterministic channel propagation prediction. Wireless ray tracing (RT) provides site-specific predictions but demands high-fidelity three-dimensional (3D) environment models with material properties. Manual 3D model reconstruction achieves high accuracy but requires weeks of expert effort, creating scalability bottlenecks for large environment reconstruction. Traditional vision-based 3D reconstruction methods lack RT compatibility due to geometrically defective meshes and missing material properties. This paper presents Holistic Reconstruction with Automated Material Assignment (HoRAMA) for wireless propagation prediction using NYURay. HoRAMA generates RT-compatible 3D models from RGB video readily captured using a smartphone or low-cost portable camera, by integrating MASt3R-SLAM dense point cloud generation with vision language model-assisted material assignment. The HoRAMA 3D reconstruction method is verified by comparing NYURay RT predictions, using both manually created and HoRAMA-generated 3D models, against field measurements at 6.75 GHz and 16.95 GHz across 12 TX-RX locations in a 700 square meter factory. HoRAMA ray tracing predictions achieve a 2.28 dB RMSE for matched multipath component (MPC) power predictions, comparable to the manually created 3D model baseline (2.18 dB), while reducing 3D reconstruction time from two months to 16 hours. HoRAMA enables scalable wireless digital twin creation for RT network planning, infrastructure deployment, and beam management in 5G/6G systems, as well as eventual real-time implementation at the edge.

Cardiac magnetic resonance imaging (CMR) offers detailed evaluation of cardiac structure and function, but its limited accessibility restricts use to selected patient populations. In contrast, the electrocardiogram (ECG) is ubiquitous and inexpensive, and provides rich information on cardiac electrical activity and rhythm, yet offers limited insight into underlying cardiac structure and mechanical function. To address this, we introduce a contrastive learning framework that improves the extraction of clinically relevant cardiac phenotypes from ECG by learning from paired ECG-CMR data. Our approach aligns ECG representations with 3D CMR volumes at end-diastole (ED) and end-systole (ES), with a dual-phase contrastive loss to anchor each ECG jointly with both cardiac phases in a shared latent space. Unlike prior methods limited to 2D CMR representations with or without a temporal component, our framework models 3D anatomy at both ED and ES phases as distinct latent representations, enabling flexible disentanglement of structural and functional cardiac properties. Using over 34,000 ECG-CMR pairs from the UK Biobank, we demonstrate improved extraction of image-derived phenotypes from ECG, particularly for functional parameters ($\uparrow$ 9.2\%), while improvements in clinical outcome prediction remained modest ($\uparrow$ 0.7\%). This strategy could enable scalable and cost-effective extraction of image-derived traits from ECG. The code for this research is publicly available.

Task-Oriented Source Coding (TOSC) has emerged as a paradigm for efficient visual data communication in machine-centric inference systems, where bitrate, latency, and task performance must be jointly optimized under resource constraints. While recent works have proposed rate-distortion bounds for coding for machines, these results often rely on strong assumptions on task identifiability and neglect the impact of deployed task models. In this work, we revisit the fundamental limits of single-TOSC through the lens of indirect rate-distortion theory. We highlight the conditions under which existing rate-distortion bounds are achievable and show their limitations in realistic settings. We then introduce task model-aware rate-distortion bounds that account for task model suboptimality and architectural constraints. Experiments on standard classification benchmarks confirm that current learned TOSC schemes operate far from these limits, highlighting transmitter-side complexity as a key bottleneck.

Cell-free massive multi-input multi-output (MIMO) promises uniform high performance across the network, but also brings a high energy cost due to joint transmission from distributed radio units (RUs) and centralized processing in the cloud. Leveraging the resource-sharing capabilities of Open Radio Access Network (O-RAN), we propose EARL, an energy-aware adaptive antenna control framework based on reinforcement learning. EARL dynamically configures antenna elements in RUs to minimize radio, optical fronthaul, and cloud processing power consumption while meeting user spectral efficiency demands. Numerical results show power savings of up to 81% and 50% over full-on and heuristic baselines, respectively. The RL-based approach operates within 220 ms, satisfying O-RAN's near-real-time limit, and a greedy refinement further halves power consumption at a 2 s runtime.

The success of surveillance applications involving small unmanned aerial vehicles (UAVs) depends on how long the limited on-board power would persist. To cope with this challenge, alternative renewable sources of lift are sought. One promising solution is to extract energy from rising masses of buoyant air. This paper proposes a local-global behavioral management and decision-making approach for the autonomous deployment of soaring-capable UAVs. The cooperative UAVs are modeled as non-deterministic finite state-based rational agents. In addition to a mission planning module for assigning tasks and issuing dynamic navigation waypoints for a new path planning scheme, in which the concepts of visibility and prediction are applied to avoid the collisions. Moreover, a delayed learning and tuning strategy is employed optimize the gains of the path tracking controller. Rigorous comparative analyses carried out with three benchmarking baselines and 15 evolutionary algorithms highlight the adequacy of the proposed approach for maintaining the surveillance persistency (staying aloft for longer periods without landing) and maximizing the detection of targets (two times better than non-cooperative and semi-cooperative approaches) with less power consumption (almost 6% of battery consumed in six hours).

Existing medical imaging datasets for abdominal CT often lack three-dimensional annotations, multi-organ coverage, or precise lesion-to-organ associations, hindering robust representation learning and clinical applications. To address this gap, we introduce 3DLAND, a large-scale benchmark dataset comprising over 6,000 contrast-enhanced CT volumes with over 20,000 high-fidelity 3D lesion annotations linked to seven abdominal organs: liver, kidneys, pancreas, spleen, stomach, and gallbladder. Our streamlined three-phase pipeline integrates automated spatial reasoning, prompt-optimized 2D segmentation, and memory-guided 3D propagation, validated by expert radiologists with surface dice scores exceeding 0.75. By providing diverse lesion types and patient demographics, 3DLAND enables scalable evaluation of anomaly detection, localization, and cross-organ transfer learning for medical AI. Our dataset establishes a new benchmark for evaluating organ-aware 3D segmentation models, paving the way for advancements in healthcare-oriented AI. To facilitate reproducibility and further research, the 3DLAND dataset and implementation code are publicly available at https://mehrn79.github.io/3DLAND.

In this paper, we investigate the performance of RIS-aided orthogonal time frequency space (OTFS) and orthogonal frequency division multiplexing (OFDM) systems in the presence of oscillator phase noise. OFDM is known to be sensitive to phase noise, which could limit the potential gains promised by RIS systems. OTFS, on the other hand, is a compelling potential waveform for RIS-aided systems in the presence of phase noise due to it's resilience to time-varying channels. However, the effect of phase noise on OTFS has not been fully analyzed in the literature as of yet. Additionally, no existing works in the literature consider the effect of phase noise on an RIS-aided OTFS system. Hence, we propose a joint RIS channel and phase noise estimation technique using a Wiener filtering approach. Our proposed method exploits the statistical nature of both the phase noise and the Doppler spread channel in a setup with RIS. Our numerical analysis demonstrates the significant gain of RIS-aided OTFS offers compared to RIS-aided OFDM in the presence in the presence of phase noise. Additionally, our results demonstrate the superiority of our proposed estimation technique, with gains of up to 3~dB in terms of bit error rate (BER), over existing methods in the literature.

Channel State Information (CSI) provides a detailed description of the wireless channel and has been widely adopted for Wi-Fi sensing, particularly for high-precision indoor positioning. However, complete CSI is rarely available in real-world deployments due to hardware constraints and the high communication overhead required for feedback. Moreover, existing positioning models lack mechanisms to detect when users move outside their trained regions, leading to unreliable estimates in dynamic environments. In this paper, we present FPNet, a unified deep learning framework that jointly addresses channel feedback compression, accurate indoor positioning, and robust anomaly detection (AD). FPNet leverages the beamforming feedback matrix (BFM), a compressed CSI representation natively supported by IEEE 802.11ac/ax/be protocols, to minimize feedback overhead while preserving critical positioning features. To enhance reliability, we integrate ADBlock, a lightweight AD module trained on normal BFM samples, which identifies out-of-distribution scenarios when users exit predefined spatial regions. Experimental results using standard 2.4 GHz Wi-Fi hardware show that FPNet achieves positioning accuracy above 97% with only 100 feedback bits, boosts net throughput by up to 22.92%, and attains AD accuracy over 99% with a false alarm rate below 1.5%. These results demonstrate FPNet's ability to deliver efficient, accurate, and reliable indoor positioning on commodity Wi-Fi devices.

While ex-ante screening and static price caps are global standards for mitigating price volatility, Singapore's electricity market employs a unique dual-defense mechanism integrating vesting contracts (VC) with a temporary price cap (TPC). Using high-frequency data from 2021 to 2024, this paper evaluates this mechanism and yields three primary findings. First, a structural trade-off exists within the VC framework: while VC quantity (VCQ) suppresses average prices, it paradoxically exacerbates instability via liquidity squeezes. Conversely, VC price (VCP) functions as a tail-risk anchor, dominating at extreme quantiles where VCQ efficacy wanes. Second, a structural break around the 2023 reform reveals a fundamental re-mapping of price dynamics; the previously positive pass-through from offer ratios to clearing prices was largely neutralized post-reform. Furthermore, diagnostics near the TPC threshold show no systematic evidence of strategic bid shading, confirming the TPC's operational integrity. Third, the dual-defense mechanism exhibits a critical synergy that resolves the volatility trade-off. The TPC reverses the volatility penalty of high VCQ, shifting the elasticity of conditional volatility from a destabilizing 0.636 to a stabilizing -0.213. This synergy enables the framework to enhance tail-risk control while eliminating liquidity-related stability costs. We conclude that this dual-defense mechanism successfully decouples price suppression from liquidity risks, thereby maximizing market stability.

Intense bandwidth depletion within consumer and constrained networks has the potential to undermine the stability of real-time video conferencing: encoder rate management becomes saturated, packet loss escalates, frame rates deteriorate, and end-to-end latency significantly increases. This work delineates an adaptive conferencing system that integrates WebRTC media delivery with a supplementary audio-driven talking-head reconstruction pathway and telemetry-driven mode regulation. The system consists of a WebSocket signaling service, an optional SFU for multi-party transmission, a browser client capable of real-time WebRTC statistics extraction and CSV telemetry export, and an AI REST service that processes a reference face image and recorded audio to produce a synthesized MP4; the browser can substitute its outbound camera track with the synthesized stream with a median bandwidth of 32.80 kbps. The solution incorporates a bandwidth-mode switching strategy and a client-side mode-state logger.

Reconfigurable intelligent surfaces (RISs) are envisioned as a key enabler for next-generation wireless networks, offering programmable control over propagation environments. While extensive research focuses on planar RIS architectures, practical deployments often involve non-planar surfaces, such as structural columns or curved facades, where standard planar beamforming models fail. Moreover, existing analytical solutions for curved RISs are often restricted to specific, pre-defined array manifold geometries. To address this limitation, this paper proposes a novel deep learning (DL) framework for optimizing the phase shifts of non-planar RISs. We first introduce a low-dimensional parametric model to capture arbitrary surface curvature effectively. Based on this, we design a neural network (NN) that utilizes a sparse set of received power measurements to estimate the surface geometry and derive the optimal phase configuration. Simulation results demonstrate that the proposed algorithm converges fast and significantly outperforms conventional planar beamforming designs, validating its robustness against arbitrary surface curvature. We also analyze the impact of the measurement location error on the algorithm's performance.

Lung cancer remains one of the most common and deadliest forms of cancer worldwide. The likelihood of successful treatment depends strongly on the stage at which the disease is diagnosed. Therefore, early detection of lung cancer represents a critical medical challenge. However, this task poses significant difficulties for thoracic radiologists due to the large number of studies to review, the presence of multiple nodules within the lungs, and the small size of many nodules, which complicates visual assessment. Consequently, the development of automated systems that incorporate highly accurate and computationally efficient lung nodule detection and classification modules is essential. This study introduces three methodological improvements for lung nodule classification: (1) an advanced CT scan cropping strategy that focuses the model on the target nodule while reducing computational cost; (2) target filtering techniques for removing noisy labels; (3) novel augmentation methods to improve model robustness. The integration of these techniques enables the development of a robust classification subsystem within a comprehensive Clinical Decision Support System for lung cancer detection, capable of operating across diverse acquisition protocols, scanner types, and upstream models (segmentation or detection). The multiclass model achieved a Macro ROC AUC of 0.9176 and a Macro F1-score of 0.7658, while the binary model reached a Binary ROC AUC of 0.9383 and a Binary F1-score of 0.8668 on the LIDC-IDRI dataset. These results outperform several previously reported approaches and demonstrate state-of-the-art performance for this task.

Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose Lamer-SSL, a parameter-efficient framework that integrates a Layer-Aware MixturE of LoRA Experts (Lamer) module with a replay strategy. The Lamer module enables flexible balancing between shared and language-specific representations, while layer-aware expert allocation assigns more experts to deeper layers where semantic information is richer. Meanwhile, the replay strategy retains prior knowledge using minimal data, mitigating forgetting during continual training. Experiments on automatic speech recognition (ASR) and language identification (LID) demonstrate that Lamer-SSL extends self-supervised models to new languages effectively while maintaining strong performance on previously learned languages with only 2.14% parameters being trainable.

We study the spectral efficiency (SE) of a ratesplitting multiple access (RSMA) enabled multi-clustered cell-free (CF) massive multiple-input multiple-output (mMIMO) system. The access points (APs) in each cluster serve mobile user equipments (UEs) by employing RSMA. The UEs employ successive interference cancellation to decode their data. This work emphasizes the role of downlink (DL) pilots in realizing RSMA benefits in practical CF systems with spatially-correlated Rician channels which observe random phase shifts, pilot contamination, and channel aging due to UE mobility. We numerically show that DL pilots are required for RSMA in user-centric CF mMIMO systems with channel aging to outperform spatial division multiple access. We show that the degraded channel quality due to higher UE velocity and longer resource block lengths significantly reduces the RSMA SE. Increasing the number of clusters can compensate for the SE loss.

Accurate currency recognition is essential for assistive technologies, particularly for visually impaired individuals who rely on others to identify banknotes. This dependency puts them at risk of fraud and exploitation. To address these challenges, we first build a new Bangladeshi banknote dataset that includes both controlled and real-world scenarios, ensuring a more comprehensive and diverse representation. Next, to enhance the dataset's robustness, we incorporate four additional datasets, including public benchmarks, to cover various complexities and improve the model's generalization. To overcome the limitations of current recognition models, we propose a novel hybrid CNN architecture that combines MobileNetV3-Large and EfficientNetB0 for efficient feature extraction. This is followed by an effective multilayer perceptron (MLP) classifier to improve performance while keeping computational costs low, making the system suitable for resource-constrained devices. The experimental results show that the proposed model achieves 97.95% accuracy on controlled datasets, 92.84% on complex backgrounds, and 94.98% accuracy when combining all datasets. The model's performance is thoroughly evaluated using five-fold cross-validation and seven metrics: accuracy, precision, recall, F1-score, Cohen's Kappa, MCC, and AUC. Additionally, explainable AI methods like LIME and SHAP are incorporated to enhance transparency and interpretability.

In this paper, we propose a standardized framework for automatic tuberculosis (TB) detection from cough audio and routinely collected clinical data using machine learning. While TB screening from audio has attracted growing interest, progress is difficult to measure because existing studies vary substantially in datasets, cohort definitions, feature representations, model families, validation protocols, and reported metrics. Consequently, reported gains are often not directly comparable, and it remains unclear whether improvements stem from modeling advances or from differences in data and evaluation. We address this gap by establishing a strong, well-documented baseline for TB prediction using cough recordings and accompanying clinical metadata from a recently compiled dataset from several countries. Our pipeline is reproducible end-to-end, covering feature extraction, multimodal fusion, cougher-independent evaluation, and uncertainty quantification, and it reports a consistent suite of clinically relevant metrics to enable fair comparison. We further quantify performance for cough audio-only and fused (audio + clinical metadata) models, and release the full experimental protocol to facilitate benchmarking. This baseline is intended to serve as a common reference point and to reduce methodological variance that currently holds back progress in the field.

Over-the-air (OTA) federated learning (FL) has been well recognized as a scalable paradigm that exploits the waveform superposition of the wireless multiple-access channel to aggregate model updates in a single use. Existing OTA-FL designs largely enforce zero-bias model updates by either assuming \emph{homogeneous} wireless conditions (equal path loss across devices) or forcing zero-bias updates to guarantee convergence. Under \emph{heterogeneous} wireless scenarios, however, such designs are constrained by the weakest device and inflate the update variance. Moreover, prior analyses of biased OTA-FL largely address convex objectives, while most modern AI models are highly non-convex. Motivated by these gaps, we study OTA-FL with stochastic gradient descent (SGD) for general smooth non-convex objectives under wireless heterogeneity. We develop novel OTA-FL SGD updates that allow a structured, time-invariant model bias while facilitating reduced variance updates. We derive a finite-time stationarity bound (expected time average squared gradient norm) that explicitly reveals a bias-variance trade-off. To optimize this trade-off, we pose a non-convex joint OTA power-control design and develop an efficient successive convex approximation (SCA) algorithm that requires only statistical CSI at the base station. Experiments on a non-convex image classification task validate the approach: the SCA-based design accelerates convergence via an optimized bias and improves generalization over prior OTA-FL baselines.

Conic programs arise broadly in physics, quantum information, machine learning, and engineering, many of which are defined over sparse graphs. Although such problems can be solved in polynomial time using classical interior-point solvers, the computational complexity scales unfavorably with graph size. In this context, this work proposes a variational quantum paradigm for solving conic programs, including quadratically constrained quadratic programs (QCQPs) and semidefinite programs (SDPs). We encode primal variables via the state of a parameterized quantum circuit (PQC), and dual variables via the probability mass function of a second PQC. The Lagrangian function can thus be expressed as scaled expectations of quantum observables. A primal-dual solution can be found by minimizing/maximizing the Lagrangian over the parameters of the first/second PQC. We pursue saddle points of the Lagrangian in a hybrid fashion. Gradients of the Lagrangian are estimated using the two PQCs, while PQC parameters are updated classically using a primal-dual method. We propose permuting the primal variables so that related observables are expressed in a banded form, enabling efficient measurement. The proposed framework is applied to the OPF problem, a large-scale optimization problem central to the operation of electric power systems. Numerical tests on the IEEE 57-node power system using Pennylane's simulator corroborate that the proposed doubly variational quantum framework can find high-quality OPF solutions. Although showcased for the OPF, this framework features a broader scope, including conic programs with numerous variables and constraints, problems defined over sparse graphs, and training quantum machine learning models to satisfy constraints.