Signal Processing
Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis
Yongwei Yi, Xinping Yi, Wenjin Wang et al. (+2 more)
In practical Multiuser Multiple-Input Multiple-Output (MU-
MIMO) systems, symbol detection remains challenging due to severe inter-user interference and sensitivity to Channel State Information (CSI) uncertainty. In contrast to the mostly studied belief propagation-type model-driven methods, which incur high computational complexity, Soft Interference Cancellation (SIC) strikes a good balance between performance and complexity. To further address CSI mismatch and nonlinear effects, the recently proposed data-driven deep neural receivers, such as DeepSIC, leverage the advantages of deep neural networks for interference cancellation and symbol detection, demonstrating strong empirical performance. However, there is still a lack of theoretical underpinning for why and to what extent DeepSIC could generalize with the number of training samples. This paper proposes inspecting the fully data-driven DeepSIC detection within a Network-of-MLPs architecture, which is composed of multiple interconnected MLPs via outer and inner Directed Acyclic Graphs (DAGs). Within such an architecture, DeepSIC can be upgraded as a graph-based message-passing process using Graph Neural Networks (GNNs), termed GNNSIC, with shared model parameters across users and iterations. Notably, GNNSIC achieves excellent expressivity comparable to DeepSIC with substantially fewer trainable parameters, resulting in improved sample efficiency and enhanced user generalization. By conducting a norm-based generalization analysis using Rademacher complexity, we reveal that an exponential dependence on the number of iterations for DeepSIC can be eliminated in GNNSIC due to parameter sharing. Simulation results demonstrate that GNNSIC attains comparable or improved Symbol Error Rate (SER) performance to DeepSIC with significantly fewer parameters and training samples.
Read the full abstract ▾
All authors Yongwei Yi, Xinping Yi, Wenjin Wang, Xiao Li, Shi Jin
Audio and Speech Processing · Cross-listed from cs.SD
Speech to Speech Synthesis for Voice Impersonation
Bjorn Johnson and Jared Levy
Numerous models have shown great success in the fields of
speech recognition as well as
speech synthesis, but models for
speech to
speech processing have not been heavily explored. We propose
Speech to
Speech Synthesis Network (STSSN), a model based on current state of the art systems that fuses the two disciplines in order to perform effective
speech to
speech style transfer for the purpose of voice impersonation. We show that our proposed model is quite powerful, and succeeds in generating realistic audio samples despite a number of drawbacks in its capacity. We
benchmark our proposed model by comparing it with a generative
adversarial model which accomplishes a similar task, and show that ours produces more convincing results.
Read the full abstract ▾
Image and Video Processing
Frequency-Enhanced Hilbert Scanning Mamba for Short-Term Arctic Sea Ice Concentration Prediction
Feng Gao, Zheng Gong, Wenli Liu et al. (+4 more)
While Mamba models offer efficient sequence modeling, vanilla versions struggle with temporal correlations and boundary details in Arctic sea ice concentration (SIC) prediction. To address these limitations, we propose Frequency-enhanced
Hilbert scanning Mamba Framework (FH-Mamba) for short-term Arctic SIC prediction. Specifically, we introduce a 3D
Hilbert scan mechanism that traverses the 3D spatiotemporal grid along a locality-preserving path, ensuring that adjacent indices in the flattened sequence correspond to neighboring voxels in both spatial and temporal dimensions. Additionally, we incorporate wavelet transform to amplify high-frequency details and we also design a Hybrid Shuffle
Attention module to adaptively aggregate sequence and frequency features. Experiments conducted on the OSI-450a1 and AMSR2
datasets demonstrate that our FH-Mamba achieves superior prediction performance compared with state-of-the-art baselines. The results confirm the effectiveness of
Hilbert scanning and frequency-aware
attention in improving both temporal consistency and edge reconstruction for Arctic SIC
forecasting. Our codes are publicly available at https://github.com/oucailab/FH-Mamba.
Read the full abstract ▾
All authors Feng Gao, Zheng Gong, Wenli Liu, Yanhai Gan, Zhuoran Zheng, Junyu Dong, Qian Du
Signal Processing
Sub Specie Aeternitatis: Fourier Transforms from the Theory of Heat to Musical Signals
Victor Lazzarini
J. B.
Fourier in his Théorie Analytique de la Chaleur of 1822 introduced, amongst other things, two ideas that have made a fundamental impact in fields as diverse as Mathematical Physics, Electrical Engineering, Computer Science, and Music. The first one of these, a method to find the coefficients for a trigonometric series describing an arbitrary function, was very early on picked up by G. Ohm and H. Helmholtz as the foundation for a theory of musical tones. The second one, which is described by
Fourier's double integral, became the basis for treating certain kinds of infinity in discontinuous functions, as shown by A. De Morgan in his 1842 The Differential and Integral Calculus. Both make up the fundamental basis for what is now commonly known as the
Fourier theorem. With the help of P. A. M. Dirac's insights into the nature of these infinities, we can have a compact description of the frequency spectrum of a function of time, or conversely of a waveform corresponding to a given function of frequency. This paper, using solely primary sources, takes us from the physics of heat propagation to the modern theory of musical signals. It concludes with some considerations on the inherent duality of time and frequency emerging from
Fourier's
theorem.
Read the full abstract ▾
Image and Video Processing
A real-time UAS hyperspectral anomaly detection system
Thomas P. Watson, Kevin McKenzie, Joseph Conroy et al. (+1 more)
Detecting anomalies in hyperspectral image data, i.e. regions which are spectrally distinct from the image background, is a common task in hyperspectral imaging. Such regions may represent interesting objects to human operators, but obtaining results often requires post-processing of captured data, delaying insight. To address this limitation, we apply an anomaly detection
algorithm to a visible and near-infrared (VNIR) push-broom hyperspectral image sensor in real time onboard a small uncrewed aerial system (UAS), exploring how UAS limitations affect the
algorithm. As the generated anomaly information is much more concise than the raw hyperspectral data, it can feasibly be transmitted wirelessly. To detection, we couple an innovative and fast georectification
algorithm that enables anomalous areas to be interactively investigated and characterized immediately by a human operator receiving the anomaly data at a ground station. Using these elements, we demonstrate a novel and complete end-to-end solution from data capture and preparation, through anomaly detection and transmission, to ground station display and interaction, all in real time and with relatively low cost components.
Read the full abstract ▾
All authors Thomas P. Watson, Kevin McKenzie, Joseph Conroy, Eddie L. Jacobs
Signal Processing
Feasibility of simultaneous EEG-fMRI at 0.55 T: Recording, Denoising, and Functional Mapping
Parsa Razmara, Takfarinas Medani, Majid Abbasi Sisara et al. (+6 more)
Simultaneous recording of electroencephalography (
EEG) and functional MRI (fMRI) can provide a more complete view of
brain function by merging high temporal and spatial resolutions. This proof-of-concept study presents initial evidence for the feasibility of simultaneous
EEG-fMRI at 0.55T in a visual task. We characterize the gradient and ballistocardiogram (BCG) artifacts inherent to this environment and demonstrate that the lower field strength suggests a reduction in the magnitude of the BCG artifact compared to high-field (1.5T, 3T, 7T) systems. This reduction shows promise for facilitating effective denoising while preserving signal integrity. Furthermore, we tested a
multimodal integration pipeline that uses the
EEG power envelope to compute a predictor of the hemodynamic BOLD response, demonstrating the potential for
EEG-based estimation of neurovascular coupling in this environment. We demonstrate that combined
EEG-fMRI at 0.55T is feasible and represents a promising environment for
multimodal neuroimaging.
Read the full abstract ▾
All authors Parsa Razmara, Takfarinas Medani, Majid Abbasi Sisara, Anand A. Joshi, Rui Chen, Woojae Jeong, Ye Tian, Krishna S. Nayak, Richard M. Leahy
Signal Processing
Blind Deconvolution Demixing using Modulated Inputs
Humera Hameed and Ali Ahmed
This paper focuses on solving a challenging problem of blind deconvolution demixing involving modulated inputs. Specifically, multiple input signals $s_n(t)$, each bandlimited to $B$ Hz, are modulated with known random sequences $r_n(t)$ that alter at rate $Q$. Each modulated signal is convolved with a different M tap channel of impulse response $h_n(t)$, and the outputs of each channel are added at a common receiver to give the observed signal $y(t)=\sum_{n=1}^N (r_n(t)\odot s_n(t))\circledast h_n(t)$, where $\odot$ is the point wise multiplication, and $\circledast$ is circular convolution. Given this observed signal $y(t)$, we are concerned with recovering $s_n(t)$ and $h_n(t)$. We employ deterministic subspace assumption for the input signal $s_n(t)$ and keep the channel impulse response $h_n(t)$ arbitrary. We show that if modulating sequence is altered at a rate $Q \geq N^2 (B+M)$ and sample complexity bound is obeyed then all the signals and the channels, $\{s_n(t),h_n(t)\}_{n=1}^N$, can be estimated from the observed mixture $y(t)$ using gradient descent
algorithm. We have performed extensive simulations that show the robustness of our
algorithm and used phase transitions to numerically investigate the theoretical guarantees provided by our
algorithm.
Read the full abstract ▾
Signal Processing
Towards Causality-Aware Modeling for Multimodal Brain-Muscle Interactions
Farwa Abbas, Wei Dai, Zoran Cvetkovic et al. (+1 more)
Robust characterization of dynamic causal interactions in multivariate biomedical signals is essential for advancing computational and algorithmic methods in biomedical imaging. Conventional approaches, such as Dynamic
Bayesian Networks (DBNs), often assume linear or simple statistical dependencies, while
manifold based techniques like Convergent Cross Mapping (CCM) capture nonlinear, lagged interactions but lack probabilistic quantification and interventional modeling. We introduce a DBN informed CCM framework that integrates
geometric manifold reconstruction with probabilistic temporal modeling. Applied to
multimodal EEG-EMG recordings from dystonic and neurotypical children, the method quantifies uncertainty, supports interventional simulation, and reveals distinct frequency specific reorganization of corticomuscular pathways in dystonia. Experimental results show marked improvements in predictive consistency and causal stability as compared to baseline approaches, demonstrating the potential of causality aware
multimodal modeling for developing quantitative biomarkers and guiding targeted neuromodulatory interventions.
Read the full abstract ▾
All authors Farwa Abbas, Wei Dai, Zoran Cvetkovic, Verity McClelland
Systems and Control
Bayesian Model-based Generation of Synthetic Unbalanced Distribution Networks Incorporating Reliability Indices
Henrique O. Caetano, Rahul K. Gupta, Cristhian G. da R. de Oliveira et al. (+2 more)
Real-world power distribution data are often inaccessible due to
privacy and security concerns, highlighting the need for tools for generating realistic synthetic networks. Existing methods typically overlook critical reliability metrics such as the Customer Average Interruption Frequency Index (CAIFI) and the Customer Average Interruption Duration Index (CAIDI). Moreover, these methods often neglect phase consistency during the design stage, necessitating the use of a separate phase assignment
algorithm. This work proposes a
Bayesian Hierarchical Model (BHM) that generates phase-consistent unbalanced three-phase distribution systems, and incorporates reliability indices. The BHM learns the joint distribution of phase configuration, power demand, and reliability indices from a reference network, conditioning these attributes on topological features. We apply the proposed methodology to generate synthetic power distribution networks in Brazil, and validated it on known Brazilian networks. The results show that the BHM accurately reproduces the distributions of phase allocation, power demand, and reliability metrics on the training system. Furthermore, in out-of-sample validation on unseen data, the model generates phase-consistent networks and accurately predicts the reliability indices for the synthetic systems. The generated networks are also electrically feasible: three-phase power flows converge and voltages remain within typical operating limits, enabling studies of planning, reliability, and resilience.
Read the full abstract ▾
All authors Henrique O. Caetano, Rahul K. Gupta, Cristhian G. da R. de Oliveira, João B. A. London Jr, Carlos Dias Maciel
Signal Processing
Sample-level EEG-based Selective Auditory Attention Decoding with Markov Switching Models
Yuanyuan Yao, Simon Geirnaert, Tinne Tuytelaars et al. (+1 more)
Selective auditory
attention decoding aims to identify the speaker of interest from listeners' neural signals, such as electroencephalography (
EEG), in the presence of multiple concurrent speakers. Most existing methods operate at the window level, facing a trade-off between temporal resolution and decoding accuracy. Recent work has shown that hidden Markov model (HMM)-based post-processing can smooth window-level decoder outputs to improve this trade-off. Instead of using a separate smoothing step, we propose to integrate the decoding and smoothing components into a single probabilistic framework using a Markov switching model (MSM). It directly models the relationship between the
EEG and
speech envelopes under each
attention state while incorporating the temporal dynamics of
attention. This formulation enables sample-level
attention decoding, with model parameters and
attention states jointly estimated via the expectation-maximization
algorithm. Experimental results demonstrate that this integrated MSM formulation achieves comparable decoding accuracy to HMM post-processing while providing faster
attention switch detection. The code for the proposed method is available at https://github.com/YYao-42/MSM.
Read the full abstract ▾
All authors Yuanyuan Yao, Simon Geirnaert, Tinne Tuytelaars, Alexander Bertrand
Signal Processing · Cross-listed from cs.IT
End-to-End NOMA with Perfect and Quantized CSI Over Rayleigh Fading Channels
Selma Benouadah, Mojtaba Vaezi, Ruizhan Shen et al. (+1 more)
An end-to-end autoencoder (AE) framework is developed for downlink non-orthogonal multiple access (NOMA) over Rayleigh fading channels, which learns interference-aware and channel-adaptive super-constellations. While existing works either assume additive white Gaussian noise channels or treat fading channels without a fully end-to-end learning approach, our framework directly embeds the wireless channel into both training and inference. To account for practical channel state information (CSI), we further incorporate limited feedback via both uniform and Lloyd-Max quantization of channel gains and analyze their impact on AE training and bit error rate (BER) performance. Simulation results show that, with perfect CSI, the proposed AE outperforms the existing analytical NOMA schemes. In addition, Lloyd-Max quantization achieves superior BER performance compared to uniform quantization. These results demonstrate that end-to-end AEs trained directly over Rayleigh fading can effectively learn robust, interference-aware signaling strategies, paving the way for NOMA deployment in fading environments with realistic CSI constraints.
Read the full abstract ▾
All authors Selma Benouadah, Mojtaba Vaezi, Ruizhan Shen, Hamid Jafarkhani
Image and Video Processing
FUTON: Fourier Tensor Network for Implicit Neural Representations
Pooya Ashtari, Pourya Behmandpoor, Nikos Deligiannis et al. (+1 more)
Implicit neural representations (INRs) have emerged as powerful tools for encoding signals, yet dominant MLP-based designs often suffer from slow convergence, overfitting to noise, and poor extrapolation. We introduce FUTON (
Fourier Tensor Network), which models signals as generalized
Fourier series whose coefficients are parameterized by a low-rank tensor decomposition. FUTON implicitly expresses signals as weighted combinations of orthonormal, separable basis functions, combining complementary inductive biases:
Fourier bases capture smoothness and periodicity, while the low-rank parameterization enforces low-dimensional spectral structure. We provide theoretical guarantees through a universal approximation
theorem and derive an inference
algorithm with complexity linear in the spectral resolution and the input dimension. On image and volume representation, FUTON consistently outperforms state-of-the-art MLP-based INRs while training 2–5$\times$ faster. On inverse problems such as image denoising and super-resolution, FUTON generalizes better and converges faster.
Read the full abstract ▾
All authors Pooya Ashtari, Pourya Behmandpoor, Nikos Deligiannis, Aleksandra Pizurica
Systems and Control · Cross-listed from math.OC
A Data-Driven Algorithm for Model-Free Control Synthesis
Sean Bowerfind, Matthew R. Kirchner and Gary Hewer
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 input-output data. A necessary condition that relates the optimal LQR gain to any arbitrary solution trajectory of the system is presented. An
algorithm using this necessary condition, based on constrained optimization, is developed that estimates the LQR gain
matrix. In addition to calculating the standard feedback 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 flight on a real scale aircraft with unknown dynamics.
Read the full abstract ▾
Systems and Control
3-D Reconfigurable Intelligent Surface: From Reflection to Transmission and From Single Hemisphere to Full 3-D Coverage
Ruiqi Wang, Yiming Yang and Atif Shamim
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.
Read the full abstract ▾
Signal Processing
Properties of Near Field Focusing for Three-Dimensional Large Intelligent Surface
Jiawang Li, Mats Gustafsson, Alireza Saberkari et al. (+1 more)
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.
Read the full abstract ▾
All authors Jiawang Li, Mats Gustafsson, Alireza Saberkari, Buon Kiong Lau
Systems and Control
Encoder initialisation methods in the model augmentation setting
J.H. Hoekstra, B. Györök, R. Töth et al. (+1 more)
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.
Read the full abstract ▾
All authors J.H. Hoekstra, B. Györök, R. Töth, M. Schoukens
Signal Processing · Cross-listed from cs.LG
Quantization-Aware Collaborative Inference for Large Embodied AI Models
Zhonghao Lyu, Ming Xiao, Mikael Skoglund et al. (+2 more)
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.
Read the full abstract ▾
All authors Zhonghao Lyu, Ming Xiao, Mikael Skoglund, Merouane Debbah, H. Vincent Poor
Image and Video Processing
Efficient Plug-and-Play method for Dynamic Imaging Via Kalman Smoothing
Benjamin Hawkes, Mike Davies, Victor Elvira et al. (+1 more)
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.
Read the full abstract ▾
All authors Benjamin Hawkes, Mike Davies, Victor Elvira, Audrey Repetti
Signal Processing
Near-Field Beampointing with Low Exposure Regions: a Dominant Subspace Projection Approach
Laurence Defraigne, Gilles Monnoyer, Jérôme Louveaux et al. (+1 more)
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.
Read the full abstract ▾
All authors Laurence Defraigne, Gilles Monnoyer, Jérôme Louveaux, Luc Vandendorpe
Systems and Control
Bayesian Optimization Based Grid Point Allocation for LPV and Robust Control
E. Javier Olucha, Arash Sadeghzadeh, Amritam Das et al. (+1 more)
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.
Read the full abstract ▾
All authors E. Javier Olucha, Arash Sadeghzadeh, Amritam Das, Roland Tóth
Audio and Speech Processing
A two-step approach for speech enhancement in low-SNR scenarios using cyclostationary beamforming and DNNs
Giovanni Bologni, Nicolás Arrieta Larraza, Richard Heusdens et al. (+1 more)
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.
Read the full abstract ▾
All authors Giovanni Bologni, Nicolás Arrieta Larraza, Richard Heusdens, Richard C. Hendriks
Signal Processing
Represent Micro-Doppler Signature in Orders
Weicheng Gao
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.
Read the full abstract ▾
Signal Processing
RIS Nearfield Position and Velocity Estimation Using a Validated Propagation Model
Thomas Zemen, Musa Furkan Keskin, Moustafa Rahal et al. (+5 more)
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.
Read the full abstract ▾
All authors Thomas Zemen, Musa Furkan Keskin, Moustafa Rahal, Thomas Wilding, Hamed Radpour, Markus Hofer, Benoit Denis, Henk Wymeersch
Systems and Control
Data Augmentation and Attention for massive MIMO-based Indoor Localization in Changing Environments
Luisa Schuhmacher, Hazem Sallouha, Ihsane Gryech et al. (+1 more)
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.
Read the full abstract ▾
All authors Luisa Schuhmacher, Hazem Sallouha, Ihsane Gryech, Sofie Pollin
Signal Processing
HoRAMA: Holistic Reconstruction with Automated Material Assignment for Ray Tracing using NYURay
Mingjun Ying, Guanyue Qian, Xinquan Wang et al. (+3 more)
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.
Read the full abstract ▾
All authors Mingjun Ying, Guanyue Qian, Xinquan Wang, Peijie Ma, Dipankar Shakya, Theodore S. Rappaport
Image and Video Processing
Dual-Phase Cross-Modal Contrastive Learning for CMR-Guided ECG Representations for Cardiovascular Disease Assessment
Laura Alvarez-Florez, Angel Bujalance-Gomez, Femke Raijmakers et al. (+7 more)
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.
Read the full abstract ▾
All authors Laura Alvarez-Florez, Angel Bujalance-Gomez, Femke Raijmakers, Samuel Ruiperez-Campillo, Maarten Z. H. Kolk, Jesse Wiers, Julia Vogt, Erik J. Bekkers, Ivana Išgum, Fleur V. Y. Tjong
Image and Video Processing · Cross-listed from cs.IT
Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding
Andriy Enttsel and Vincent Corlay
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.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.IT
EARL: Energy-Aware Adaptive Antenna Control with Reinforcement Learning in O-RAN Cell-Free Massive MIMO Networks
Zilin Ge, Ozan Alp Topal, Irshad Ahmad Meer et al. (+2 more)
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.
Read the full abstract ▾
All authors Zilin Ge, Ozan Alp Topal, Irshad Ahmad Meer, Pei Xiao, Cicek Cavdar
Systems and Control · Cross-listed from cs.RO
SKYSURF: A Self-learning Framework for Persistent Surveillance using Cooperative Aerial Gliders
Houssem Eddine Mohamadi and Nadjia Kara
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).
Read the full abstract ▾
Image and Video Processing
3DLAND: 3D Lesion Abdominal Anomaly Localization Dataset
Mehran Advand, Zahra Dehghanian, Navid Faraji et al. (+3 more)
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.
Read the full abstract ▾
All authors Mehran Advand, Zahra Dehghanian, Navid Faraji, Reza Barati, Seyed Amir Ahmad Safavi-Naini, Hamid R. Rabiee