Modern wireless systems require not only position estimates, but also quantified uncertainty to support planning, control, and radio resource management. We formulate localization as posterior inference of an unknown transmitter location from receiver measurements. We propose Monte Carlo Candidate-Likelihood Estimation (MC-CLE), which trains a neural scoring network using Monte Carlo sampling to compare true and candidate transmitter locations. We show that in line-of-sight simulations with a multi-antenna receiver, MC-CLE learns critical properties including angular ambiguity and front-to-back antenna patterns. MC-CLE also achieves lower cross-entropy loss relative to a uniform baseline and Gaussian posteriors. alternatives under a uniform-loss metric.

There is growing interest in using public cellular networks for specialized communication applications, replacing standalone sector-specific networks. One such application is transitioning from the aging GSM-R railway network to public 4G and 5G networks. Finland is modernizing its railway communication system through the Digirail project, leveraging public cellular networks. To evaluate network performance, a nationwide measurement campaign was conducted in two modes: Best Quality and Packet Replication. However, Best Quality mode introduces artificial delays, making it unsuitable for real-world assessments. In this paper, railway network delays are modeled using machine learning based on measurements from the Packet Replication mode. The best-performing model is then employed to generate a dataset estimating network delays across Finland's railway network. This dataset provides a more accurate representation of network performance. Machine learning based network performance prediction is shown to be feasible, and the results indicate that Finland's public cellular network can meet the stringent performance requirements of railway network control.

Performance evaluation of urban autonomous vehicles requires a realistic model of the behavior of other road users in the environment. Learning such models from data involves collecting naturalistic data of real-world human behavior. In many cases, acquisition of this data can be prohibitively expensive or intrusive. Additionally, the available data often contain only typical behaviors and exclude behaviors that are classified as rare events. To evaluate the performance of AV in such situations, we develop a model of traffic behavior based on the theory of bounded rationality. Based on the experiments performed on a large naturalistic driving data, we show that the developed model can be applied to estimate probability of rare events, as well as to generate new traffic situations.

Force control in hydraulic actuators is notoriously difficult due to strong nonlinearities, uncertainties, and the high risks associated with unsafe exploration during learning. This paper investigates safe reinforcement learning (RL) for hy draulic force control with real-world training using contraction metric certificates. A data-driven model of a hydraulic actuator, identified from experimental data, is employed for simulation based pretraining of a Soft Actor-Critic (SAC) policy that adapts the PI gains of a feedback-linearization (FL) controller. To reduce instability during online training, we propose a quadratic-programming (QP) contraction filter that leverages a learned contraction metric to enforce approximate exponential convergence of trajectories, applying minimal corrections to the policy output. The approach is validated on a hydraulic test bench, where the RL controller is trained directly on hardware and benchmarked against a simulation-trained agent and a fixed-gain baseline. Experimental results show that real-hardware training improves force-tracking performance compared to both alternatives, while the contraction filter mitigates chattering and instabilities. These findings suggest that contraction-based certificates can enable safe RL in high force hydraulic systems, though robustness at extreme operating conditions remains a challenge.

Stepwise signals are ubiquitous in single-molecule detections, where abrupt changes in signal levels typically correspond to molecular conformational changes or state transitions. However, these features are inevitably obscured by noise, leading to uncertainty in estimating both signal levels and transition points. Traditional frequency-domain filtering is ineffective for denoising stepwise signals, as edge-related high-frequency components strongly overlap with noise. Although Hidden Markov Model-based approaches are widely used, they rely on stationarity assumptions and are not specifically designed for signal denoising. Here, we propose a diffusion model-based algorithm for stepwise signal denoising, named the Stepwise Signal Diffusion Model (SSDM). During training, SSDM learns the statistical structure of stepwise signals via a forward diffusion process that progressively adds noise. In the following reverse process, the model reconstructs clean signals from noisy observations, integrating a multi-scale convolutional network with an attention mechanism. Training data are generated by simulating stepwise signals through a Markov process with additive Gaussian noise. Across a broad range of signal-to-noise ratios, SSDM consistently outperforms traditional methods in both signal level reconstruction and transition point detection. Its effectiveness is further demonstrated on experimental data from single-molecule Forster Resonance Energy Transfer and nanopore DNA translocation measurements. Overall, SSDM provides a general and robust framework for recovering stepwise signals in various single-molecule detections and other physical systems exhibiting discrete state transitions.

This paper addresses the problem of exponential and accelerated finite-time, as well as nearly fixed-time, stabilization of switched linear MIMO systems. The proposed approach relies on a generalized homogenization framework for switched linear systems and employs implicit Lyapunov functions for control design, covering both common and multiple Lyapunov function settings. Linear matrix equations and inequalities are derived to characterize the dilation generator and to synthesize the controller gains. Robustness of the resulting control laws with respect to system uncertainties and external disturbances is analyzed. The effectiveness of the proposed approach is illustrated through numerical examples.

We propose a geometric model predictive control framework for quantum systems subject to smoothness and state constraints. By formulating quantum state evolution intrinsically on the projective Hilbert space, we penalize covariant accelerations to generate smooth trajectories in the form of Riemannian cubics, while incorporating state-dependent constraints through potential functions. A structure-preserving variational discretization enables receding-horizon implementation, and a Lyapunov-type stability result is established for the closed-loop system. The approach is illustrated on the Bloch sphere for a two-level quantum system, providing a viable pathway toward predictive feedback control of constrained quantum dynamics.

In this work, we propose a deep unified (DU) encoder that embeds source information in a codeword that contains sufficient redundancy to handle both channel and source uncertainties, without enforcing an explicit pilot-data separation. At the receiver, we design a parallel flow-matching (PFM) decoder that leverages flow-based generative priors to jointly estimate the channel and the source, yielding much more efficient inference than the existing diffusion-based approaches. To benchmark performance limits, we derive the Bayesian Cramér-Rao bound (BCRB) for the joint channel and source estimation problem. Extensive simulations over block-fading MIMO-OFDM channels demonstrate that the proposed DU-PFM approach drastically outperforms the state-of-the-art methods in both channel estimation accuracy and source reconstruction quality.

Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose \textsc{FreqLens}, an interpretable forecasting framework that discovers and attributes predictions to learnable frequency components. \textsc{FreqLens} introduces two key innovations: (1) \emph{learnable frequency discovery} -- frequency bases are parameterized via sigmoid mapping and learned from data with diversity regularization, enabling automatic discovery of dominant periodic patterns without domain knowledge; and (2) \emph{axiomatic frequency attribution} -- a theoretically grounded framework that provably satisfies Completeness, Faithfulness, Null-Frequency, and Symmetry axioms, with per-frequency attributions equivalent to Shapley values. On Traffic and Weather datasets, \textsc{FreqLens} achieves competitive or superior performance while discovering physically meaningful frequencies: all 5 independent runs discover the 24-hour daily cycle ($24.6 \pm 0.1$h, 2.5\% error) and 12-hour half-daily cycle ($11.8 \pm 0.1$h, 1.6\% error) on Traffic, and weekly cycles ($10\times$ longer than the input window) on Weather. These results demonstrate genuine frequency-level knowledge discovery with formal theoretical guarantees on attribution quality.

This paper addresses the local stabilization problem for semilinear single-track vehicle models with distributed tire friction dynamics, represented as interconnections of ordinary differential equations (ODEs) and hyperbolic partial differential equations (PDEs). A passivity-exploiting backstepping design is presented, which leverages the strict dissipativity properties of the PDE subsystem to achieve exponential stabilization of the considered ODE-PDE interconnection around a prescribed equilibrium. Sufficient conditions for local well-posedness and exponential convergence are derived by constructing a Lyapunov functional combining the lumped and distributed states. Both state-feedback and output-feedback controllers are synthesized, the latter relying on a cascaded observer. The theoretical results are corroborated with numerical simulations, considering non-ideal scenarios and accounting for external disturbances and uncertainties. Simulation results confirm that the proposed control strategy can effectively and robustly stabilize oversteer vehicles at high speeds, demonstrating the relevance of the approach for improving the safety and performance in automotive applications.

This paper investigates the stability and stabilization of semilinear single-track vehicle models with distributed tire friction dynamics, modeled as interconnections of ordinary differential equations (ODEs) and hyperbolic partial differential equations (PDEs). Motivated by the long-standing practice of neglecting transient tire dynamics in vehicle modeling and control, a rigorous justification is provided for such simplifications using singular perturbation theory. A perturbation parameter, defined as the ratio between a characteristic rolling contact length and the vehicle's longitudinal speed, is introduced to formalize the time-scale separation between rigid-body motion and tire dynamics. For sufficiently small values of this parameter, it is demonstrated that standard finite-dimensional techniques can be applied to analyze the local stability of equilibria and to design stabilizing controllers. Both state-feedback and output-feedback designs are considered, under standard stabilizability and detectability assumptions. Whilst the proposed controllers follow classical approaches, the novelty of the work lies in establishing the first mathematical framework that rigorously connects distributed tire models with conventional vehicle dynamics. The results reconcile decades of empirical findings with a formal theoretical foundation and open new perspectives for the analysis and control of ODE-PDE systems with distributed friction in automotive applications.

Semantic communications (SemComs) have been considered as a promising solution to reduce the amount of transmitted information, thus paving the way for more energy-and spectrum-efficient wireless networks. Nevertheless, SemComs rely heavily on the utilization of deep neural networks (DNNs) at the transceivers, which limit the accuracy between the original and reconstructed data and are challenging to implement in practice due to increased architecture complexity. Thus, hybrid cellular networks that utilize both conventional bit communications (BitComs) and SemComs have been introduced to bridge the gap between required and existing infrastructure. To facilitate such networks, in this work, we investigate reliability by deriving closed-form expressions for the outage probability of the network. Additionally, we propose a generalized outage probability through which the cell radius that achieves a desired outage threshold for a specific range of users is calculated in closed form. Additionally, to consider the practical limitations caused by the specialized dedicated hardware and the increased memory and computational resources that are required to support SemCom, a semantic utilization metric is proposed. Based on this metric, we express the probability that a specific number of users select SemCom transmission and calculate the optimal cell radius for that number in closed form. Simulation results validate the derived analytical expressions and the characterized design properties of the cell radius found through the proposed metrics, providing useful insights.

Time-frequency domain dual-path models have demonstrated strong performance and are widely used in source separation. Because their computational cost grows with the number of frequency bins, these models often use the band-split (BS) module in high-sampling-rate tasks such as music source separation (MSS) and cinematic audio source separation (CASS). The BS encoder compresses frequency information by encoding features for each predefined subband. It achieves effective compression by introducing an inductive bias that places greater emphasis on low-frequency parts. Despite its success, the BS module has two inherent limitations: (i) it is not input-adaptive, preventing the use of input-dependent information, and (ii) the parameter count is large, since each subband requires a dedicated module. To address these issues, we propose Spectral Feature Compression (SFC). SFC compresses the input using a single sequence modeling module, making it both input-adaptive and parameter-efficient. We investigate two variants of SFC, one based on cross-attention and the other on Mamba, and introduce inductive biases inspired by the BS module to make them suitable for frequency information compression. Experiments on MSS and CASS tasks demonstrate that the SFC module consistently outperforms the BS module across different separator sizes and compression ratios. We also provide an analysis showing that SFC adaptively captures frequency patterns from the input.

We consider the problem of active fault-tolerant control in cyber-physical systems composed of strictly passive linear-time invariant dynamic subsystems. We cast the problem as a constrained optimization problem and propose an augmented primal-dual gradient dynamics-based fault-tolerant control framework that enforces network-level constraints and provides optimality guarantees for the post-fault steady-state operation. By suitably interconnecting the primal-dual algorithm with the cyber-physical dynamics, we provide sufficient conditions under which the resulting closed-loop system possesses a unique and exponentially stable equilibrium point that satisfies the Karush--Kuhn--Tucker (KKT) conditions of the constrained problem. The framework's effectiveness is illustrated through numerical experiments on a DC microgrid.

The increasing carrier frequencies and growing physical dimensions of antenna arrays in modern wireless systems are driving renewed interest in localization and sensing under near-field conditions. In this paper, we analyze the Ziv-Zakai Bound (ZZB) for near-field localization and sensing operated with large antenna arrays, which offers a tighter characterization of estimation accuracy compared to traditional bounds such as the Cramér-Rao Bound (CRB), especially in low signal-to-noise ratio or threshold regions. Leveraging spherical wavefront and array geometry in the signal model, we evaluate the ZZB for distance and angle estimation, investigating the dependence of the accuracy on key signal and system parameters such as array geometry, wavelength, and target position. Our analysis highlights the transition behavior of the ZZB and underscores the fundamental limitations and opportunities for accurate near-field sensing.

Thermostatically controlled loads and electric vehicles offer flexibility to reduce power peaks in low-voltage distribution networks. This flexibility can be maximized if the devices are coordinated centrally, given some level of information about the controlled devices. In this paper, we propose novel optimization-based control schemes with prediction capabilities that utilize limited information from heat pumps, electric water heaters, and electric vehicles. The objective is to flatten the total load curve seen by the distribution transformer by restricting the times at which the available flexible loads are allowed to operate, subject to the flexibility constraints of the loads to preserve customers' comfort. The original scheme was tested in a real-world setup, considering both winter and summer days. The pilot results confirmed the technical feasibility but also informed the design of an improved version of the controller. Computer simulations using the adjusted controller show that, compared to the original formulation, the improved scheme achieves greater peak reductions in summer. Additionally, comparisons were made with an ideal controller, which assumes perfect knowledge of the inflexible load profile, the models of the controlled devices, the hot water and space heating demand, and future electric vehicle charging sessions. The proposed scheme with limited information achieves almost half of the potential average daily peak reduction that the ideal controller with perfect knowledge would achieve.

Prior art has proposed a secondary application for Global Navigation Satellite System (GNSS) infrastructure for remote sensing of ground-based and maritime targets. Here, a passive radar receiver is deployed to detect uncooperative targets on Earth's surface by capturing ground-reflected satellite signals. This work demonstrates a hardware prototype of an L-band Navigation with Indian Constellation (NavIC) satellite-based remote sensing receiver system mounted on an AMD Zynq radio frequency system-on-chip (RFSoC) platform. Two synchronized receiver channels are introduced for capturing the direct signal (DS) from the satellite and ground-reflected signal (GRS) returns from targets. These signals are processed on the ARM processor and field programmable gate array (FPGA) of the RFSoC to generate delay-Doppler maps of the ground-based targets. The performance is first validated in a loop-back configuration of the RFSoC. Next, the DS and GRS signals are emulated by the output from two ports of the Keysight Arbitrary Waveform Generator (AWG) and interfaced with the RFSoC where the signals are subsequently processed to obtain the delay-Doppler maps. The performance is validated for different signal-to-noise ratios (SNR).

We propose data-driven nonlinear smoother (DNS) to estimate a hidden state sequence of a complex dynamical process from a noisy, linear measurement sequence. The dynamical process is model-free, that is, we do not have any knowledge of the nonlinear dynamics of the complex process. There is no state-transition model (STM) of the process available. The proposed DNS uses a recurrent architecture that helps to provide a closed-form posterior of the hidden state sequence given the measurement sequence. DNS learns in an unsupervised manner, meaning the training dataset consists of only measurement data and no state data. We demonstrate DNS using simulations for smoothing of several stochastic dynamical processes, including a benchmark Lorenz system. Experimental results show that the DNS is significantly better than a deep Kalman smoother (DKS) and an iterative data-driven nonlinear state estimation (iDANSE) smoother.

Subjective ratings contain inherent noise that limits the model-human correlation, but this reliability issue is rarely quantified. In this paper, we present $ρ$-Perfect, a practical estimation of the highest achievable correlation of a model on subjectively rated datasets. We define $ρ$-Perfect to be the correlation between a perfect predictor and human ratings, and derive an estimate of the value based on heteroscedastic noise scenarios, a common occurrence in subjectively rated datasets. We show that $ρ$-Perfect squared estimates test-retest correlation and use this to validate the estimate. We demonstrate the use of $ρ$-Perfect on a speech quality dataset and show how the measure can distinguish between model limitations and data quality issues.

Flow-based generative models have emerged as powerful priors for solving inverse problems. One option is to directly optimize the initial latent code (noise), such that the flow output solves the inverse problem. However, this requires backpropagating through the entire generative trajectory, incurring high memory costs and numerical instability. We propose MS-Flow, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code. By enforcing the flow dynamics locally and coupling segments through trajectory-matching penalties, MS-Flow alternates between updating intermediate latent states and enforcing consistency with observed data. This reduces memory consumption while improving reconstruction quality. We demonstrate the effectiveness of MS-Flow over existing methods on image recovery and inverse problems, including inpainting, super-resolution, and computed tomography.

Ultra-reliable low-latency communications (URLLC) operate with short packets, where finite-blocklength effects make near-maximum-likelihood (near-ML) decoding desirable but often too costly. This paper proposes a two-stage near-ML decoding framework that applies to any linear block code. In the first stage, we run a low-complexity decoder to produce a candidate codeword and a cyclic redundancy check. When this stage succeeds, we terminate immediately. When it fails, we invoke a second-stage decoder, termed multipoint code-weight sphere decoding (MP-WSD). The central idea behind {MP-WSD} is to concentrate the ML search where it matters. We pre-compute a set of low-weight codewords and use them to generate structured local perturbations of the current estimate. Starting from the first-stage output, MP-WSD iteratively explores a small Euclidean sphere of candidate codewords formed by adding selected low-weight codewords, tightening the search region as better candidates are found. This design keeps the average complexity low: at high signal-to-noise ratio, the first stage succeeds with high probability and the second stage is rarely activated; when it is activated, the search remains localized. Simulation results show that the proposed decoder attains near-ML performance for short-blocklength, low-rate codes while maintaining low decoding latency.

Millimeter wave integrated sensing and communication (ISAC) systems are being researched for next-generation intelligent transportation systems. Here, radar and communication functionalities share a common spectrum and hardware resources in a time-multiplexed manner. The objective of the radar is to first scan the angular search space and detect and localize mobile users/targets in the presence of discrete clutter scatterers. Subsequently, this information is used to direct highly directional beams toward these mobile users for communication service. The choice of radar parameters such as the radar duty cycle and the corresponding beamwidth are critical for realizing high communication throughput. In this work, we use the stochastic geometry-based mathematical framework to analyze the radar operating metrics as a function of diverse radar, target, and clutter parameters and subsequently use these results to study the network throughput of the ISAC system. The results are validated through Monte Carlo simulations.

The proliferation of small unmanned aerial systems (sUAS) operating under autonomous guidance has created an urgent need for non-kinetic neutralization methods that are immune to conventional radio-frequency jamming. This paper presents a comprehensive multi-physics simulation framework for the design and performance evaluation of a high-power microwave (HPM) counter-UAS system operating at 2.45\,GHz. The framework integrates electromagnetic propagation modelling, antenna pattern analysis, electromagnetic coupling to unshielded drone wiring harnesses, and a sigmoid-based semiconductor damage probability model calibrated to published CMOS latchup thresholds. A 10{,}000-trial Monte Carlo analysis incorporating stochastic variations in transmitter power, antenna pointing error, target wire orientation, polarization mismatch, and component damage thresholds yields system-level kill probabilities with 95\% confidence intervals. For a baseline configuration of 25\,kW continuous-wave power and a 60\,cm parabolic reflector (21.2\,dBi gain), the Monte Carlo simulation predicts a kill probability of $51.4\pm1.0$\% at 20\,m, decreasing to $13.1\pm0.7$\% at 40\,m. Pulsed operation at 500\,kW peak power (1\% duty cycle) extends the 90\% kill range from approximately 18\,m to 88\,m. The framework further provides parametric design maps, safety exclusion zone calculations compliant with ICNIRP 2020 guidelines, thermal management requirements, and waveguide mode analysis. All simulation codes and results are provided for full reproducibility.

Optical Camera Communication (OCC) systems can take advantage of the row-by-row scanning process of rolling-shutter cameras to capture the fast variations of light intensity coming from Visible Light Communication (VLC) LED-based transmitters. In order to study the maximum data rate that is feasible in such kind of OCC systems, this paper presents its equivalent digital communication system model in which the rolling-shutter camera is modeled as a rectangular matched-filter whose time width is equal to the exposure time of the camera, followed by a sampling process at the pixel row sweep rate of the camera. Based on the proposed rolling-shutter camera model, the maximum symbol rate that such OCC systems can support is experimentally demonstrated, and the impact of imperfect time synchronization between the VLC transmitter and the rolling-shutter OCC receiver is characterized in the form of Inter-Symbol Interference (ISI). The equivalent three-tap channel model that results from this process is experimentally validated and the generated ISI is compensated with the use of linear equalization in reception. Simulation and experimental results show a strong correlation between them, demonstrating that the proposed approach can be used to make the OCC system work at the Nyquist sampling rate, which is equivalent to the pixel row sweep rate of the rolling-shutter camera used in reception.

Post-collision trajectory restoration is a safety-critical capability for autonomous vehicles, as impact-induced lateral motion and yaw transients can rapidly drive the vehicle away from the intended path. This paper proposes a structured heuristic recovery control law that jointly commands steering and tractive force for a generalized single-track Ackermann vehicle model. The formulation explicitly accounts for time-varying longitudinal velocity in the lateral-yaw dynamics and retains nonlinear steering-coupled interaction terms that are commonly simplified in the literature. Unlike approaches that assume constant longitudinal speed, the proposed design targets the transient post-impact regime where speed variations and nonlinear coupling significantly influence recovery. The method is evaluated in simulation on the proposed generalized single-track model and a standard 3DOF single-track reference model in MATLAB, demonstrating consistent post-collision restoration behaviour across representative initial post-impact conditions.

The describing function method is a useful tool for the qualitative analysis of limit cycles in the stability analysis of nonlinear systems. This method is inherently approximate; therefore, it should be used for a fast qualitative analysis of the considered systems. However, plotting the exact describing function requires heavy mathematical calculations, reducing interest in this method especially from the point of view of control education. The objective of this paper is to enhance the describing function method by providing a new approach for the qualitative plotting of the describing function for piecewise nonlinearities involving discontinuities. Unlike the standard method, the proposed approach allows for a straightforward, hand-drawn plotting of the describing function using the rules introduced in this paper, simply by analyzing the shape of the nonlinearity. The proposed case studies show that the limit cycles estimation performed using the standard exact plotting of the describing function yields the same qualitative results as those obtained using the proposed qualitative method for plotting the describing function.

In millimeter wave integrated sensing and communication (ISAC) systems for intelligent transportation, radar and communication share spectrum and hardware in a time division manner. Radar rapidly detects and localizes mobile users (MUs), after which communication proceeds through narrow beams identified by radar. Achieving fine Doppler resolution for MU clutter discrimination requires long coherent processing intervals, reducing communication time and throughput. To address this, we propose a reconfigurable architecture for Doppler estimation realized on a system on chip using hardware software codesign. The architecture supports algorithm level reconfiguration, dynamically switching between low-complexity, high-speed FFT-based coarse estimation and high complexity ESPRIT based fine estimation. We introduce modifications to ESPRIT that achieve 6.7 times faster execution while reducing memory and multiplier usage by 79% and 63%, respectively, compared to state of the art approaches, without compromising accuracy. Additionally, the reconfigurable architecture can switch to lower slow time packets under high SNR conditions, improving latency further by 2 times with no loss in performance.

Spatially structured beams have emerged as a promising technology for enhancing spectrum efficiency (SE) in sixth-generation (6G) networks. However, structured beam schemes based on fixed-position antennas (FPAs) fail to fully exploit the array aperture, thereby limiting their topological reconfigurability and adaptability to diverse communication scenarios. To overcome these limitations, this paper proposes a novel structured beam communication framework exploiting movable antennas (MAs) to achieve reconfigurable array topologies. Specifically, we develop an MA-based geometric modeling framework to construct a variety of practical array topologies, thereby enabling the realization of diverse array configurations utilizing a unified hardware platform. Furthermore, we investigate the joint design of the array topology and the structured beamforming vector to efficiently exploit the array aperture and facilitate the multiplexing of orthogonal spatial modes. Accordingly, we formulate the corresponding beam generation and demodulation schemes and derive the channel gains under varying array topologies. We also propose an alternating optimization algorithm to jointly optimize the array topology configuration, the antenna element positions, and the structured beamforming vector, with the aim of maximizing the system SE. Numerical results demonstrate that the proposed joint design significantly enhances the SE compared to conventional FPA schemes. By synergizing the spatial multiplexing degrees of freedom (DoFs) of structured beams with the mobility DoFs of MAs within 2D planar regions, this work establishes a reconfigurable and practical framework for structured beam-based wireless communications.

The prediction of electromagnetic spectra for MXene-based solar absorbers is a computationally intensive task, traditionally addressed using full-wave solvers. This study introduces an efficient deep learning framework incorporating transfer learning, multi-channel spectral refinement (MCSR), and Savitzky-Golay smoothing to accelerate and enhance spectral prediction accuracy. The proposed architecture leverages a pretrained MobileNetV2 model, fine-tuned to predict 102-point absorption spectra from $64\times64$ metasurface designs. Additionally, the MCSR module processes the feature map through multi-channel convolutions, enhancing feature extraction, while Savitzky-Golay smoothing mitigates high-frequency noise. Experimental evaluations demonstrate that the proposed model significantly outperforms baseline Convolutional Neural Network (CNN) and deformable CNN models, achieving an average root mean squared error (RMSE) of 0.0245, coefficient of determination \( R^2 \) of 0.9578, and peak signal-to-noise ratio (PSNR) of 32.98 dB. The proposed framework presents a scalable and computationally efficient alternative to conventional solvers, positioning it as a viable candidate for rapid spectral prediction in nanophotonic design workflows.

Aerial base stations mounted on unmanned aerial vehicles (UAVs) support next-generation wireless networks in challenging environments such as urban areas, disaster zones, and remote locations. Further, UAV swarms overcome the challenges of limited battery life and other operational constraints of a single UAV. However, tracking mobile users on the ground by each UAV and the corresponding synchronization between the UAVs is a significant issue that must be addressed before this framework can be deployed in reality. Incorporating additional sensing capabilities to facilitate this additional requirement would introduce significant overhead in terms of hardware, cost, and power to each UAV. Instead, we propose an integrated sensing and communications-enabled swarm UAV system, based on the millimeter-wave IEEE 802.11ad protocol. Further, we show that our proposed system is capable of five-dimensional (5-D) ground target sensing (range, Doppler velocity, azimuth, elevation, and polarization) in an urban environment. Numerical experiments using realistic models demonstrate and validate the performance of 5-D sensing using our proposed 802-11ad-aided UAV system.