Systems and Control
Learning Control Barrier Functions with Deterministic Safety Guarantees
Amy K. Strong, Ali Kashani, Claus Danielson et al. (+1 more)
Barrier functions (BFs) characterize safe sets of dynamical systems, where hard constraints are never violated as the system evolves over time. Computing a valid safe set and BF for a nonlinear (and potentially unmodeled), non-autonomous dynamical system is a difficult task. This work explores the design of BFs using data to obtain safe sets with deterministic assurances of control invariance. We leverage ReLU neural networks (NNs) to create continuous piecewise affine (CPA) BFs with deterministic safety guarantees for Lipschitz continuous, discrete-time dynamical system using sampled one-step trajectories. The CPA structure admits a novel classifier term to create a relaxed \ac{bf} condition and construction via a data driven constrained optimization. We use iterative convex overbounding (ICO) to solve this nonconvex optimization problem through a series of convex optimization steps. We then demonstrate our method's efficacy on two-dimensional autonomous and non-autonomous dynamical systems.
Read the full abstract ▾
All authors Amy K. Strong, Ali Kashani, Claus Danielson, Leila Bridgeman
Signal Processing
Digital Twin-Assisted High-Precision Massive MIMO Localization in Urban Canyons
Ziqin Zhou, Hui Chen, Gerhard Steinböck et al. (+1 more)
High-precision wireless localization in urban canyons is challenged by noisy measurements and severe non-line-of-sight (NLOS) propagation. This paper proposes a robust three-stage
algorithm synergizing a digital twin (DT) model with the random sample consensus (RANSAC)
algorithm to overcome these limitations. The method leverages the DT for
geometric path association and employs RANSAC to identify reliable line-of-sight (LOS) and single-bounce NLOS paths while rejecting multi-bounce outliers. A final optimization on the resulting inlier set estimates the user's position and clock bias. Simulations validate that by effectively turning NLOS paths into valuable
geometric information via the DT, the approach enables accurate localization, reduces reliance on direct LOS, and significantly lowers system deployment costs, making it suitable for practical deployment.
Read the full abstract ▾
All authors Ziqin Zhou, Hui Chen, Gerhard Steinböck, Henk Wymeersch
Systems and Control
Adaptive Meshing for CPA Lyapunov Function Synthesis
Amy K. Strong, Samuel Akinwande and Leila Bridgeman
Continuous Piecewise Affine (CPA) Lyapunov function synthesis is one method to perform Lyapunov stability analysis for nonlinear systems. This method first generates a mesh over the region of interest in the system's state space and then solves a linear program (LP), which enforces constraints on each vertex of the mesh, to synthesize a Lyapunov function. Finer meshes broaden the class of Lyapunov function candidates, but CPA function synthesis is more computationally expensive for finer meshes – particularly so in higher dimensional systems. This paper explores methods to mesh the region of interest more efficiently so that a Lyapunov function can be synthesized using less computational effort. Three methods are explored – adaptive meshing, meshing using knowledge of the system model, and a combination of the two. Numerical examples for two and three dimensional nonlinear dynamical systems are used to compare the efficacy of the three methods.
Read the full abstract ▾
Systems and Control · Cross-listed from math.PR
Nonuniform-Grid Markov Chain Approximation of Continuous Processes with Time-Linear Moments
Do Hyun Kim and Ahmet Cetinkaya
We propose a method to approximate continuous-time, continuous-state
stochastic processes by a discrete-time Markov chain defined on a nonuniform grid. Our method provides exact moment matching for processes whose first and second moments are linear functions of time. In particular, we show that, under certain conditions, the transition probabilities of a Markov chain can be chosen so that its first two moments match prescribed linear functions of time. These conditions depend on the grid points of the Markov chain and the coefficients of the linear mean and variance functions. Our proof relies on two recurrence relations for the expectation and variance across time. This approach enables simulation-based numerical analysis of continuous processes while preserving their key characteristics. We illustrate its efficacy by approximating continuous processes describing heat
diffusion and
geometric Brownian motion (GBM). For heat
diffusion, we show that the heat profile at a set of points can be investigated by
embedding those points inside the nonuniform grid of our Markov chain. For GBM, numerical simulations demonstrate that our approach, combined with suitable nonuniform grids, yields accurate approximations, with consistently small empirical Wasserstein-1 distances at long time horizons.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Self-Identifying Internal Model-Based Online Optimization
Wouter J. A. van Weerelt, Lantian Zhang, Silun Zhang et al. (+1 more)
In this paper, we propose a novel online optimization
algorithm built by combining ideas from control theory and system identification. The foundation of our
algorithm is a control-based design that makes use of the internal model of the online problem. Since such prior knowledge of this internal model might not be available in practice, we incorporate an identification routine that learns this model on the fly. The
algorithm is designed starting from quadratic online problems but can be applied to general problems. For quadratic cases, we characterize the asymptotic convergence to the optimal solution trajectory. We compare the proposed
algorithm with existing approaches, and demonstrate how the identification routine ensures its adaptability to changes in the underlying internal model. Numerical results also indicate strong performance beyond the quadratic setting.
Read the full abstract ▾
All authors Wouter J. A. van Weerelt, Lantian Zhang, Silun Zhang, Nicola Bastianello
Systems and Control
Accelerating Time-Optimal Trajectory Planning for Connected and Automated Vehicles with Graph Neural Networks
Viet-Anh Le and Andreas A. Malikopoulos
In this paper, we present a learning-based framework that accelerates time- and energy-optimal trajectory planning for connected and automated vehicles (CAVs) using graph neural networks (GNNs). We formulate the multi-
agent coordination problem encountered in traffic scenarios as a cooperative trajectory planning problem that minimizes travel time, subject to motion primitives derived from energy-optimal solutions. The performance of this framework can be further improved through replanning at each time step, enabling the system to incorporate newly observed information. To achieve real-time execution, we employ a graph isomorphism network with edge features (GINEConv) to learn the solutions of the time-optimal trajectory planning problem from offline-generated data. The trained model produces online predictions that serve as warm-starts for numerical optimization, thereby enabling rapid computation of minimal exit times and the associated feasible trajectories. This learning-to-warm-start approach substantially reduces computation time while preserving the control performance of the time- and energy-optimal trajectory planning framework.
Read the full abstract ▾
Signal Processing
Bridging the Educational Divide: A Delay-Tolerant Networking Approach for Equitable Digital Learning in Rural Areas
Salah Abdeljabar and Mohamed-Slim Alouini
Access to quality education remains unequal, particularly in rural areas where Internet connectivity is limited or nonexistent. This paper introduces a framework for a digital learning platform that uses Delay Tolerant Networking (DTN) to extend educational opportunities to underserved communities. Unlike conventional models that rely on continuous Internet access, DTN offers an affordable and sustainable solution by leveraging existing transportation infrastructure. Beyond its technical contributions, the framework addresses ethical imperatives by promoting educational equity and digital inclusion. We present a prototype tested on a university campus, demonstrating the feasibility of DTN for educational delivery. By addressing the digital divide, this framework aligns with global goals of inclusive education and sustainable development.
Read the full abstract ▾
Signal Processing
Next-Generation MIMO Transceivers for Integrated Sensing and Communications: Unique Security Vulnerabilities and Solutions
Kawon Han, Christos Masouros, Taneli Riihonen et al. (+1 more)
Integrated sensing and communications (
ISAC), which is recognized as a key enabler for sixth generation (6G), has brought new opportunities for intelligent, sustainable, and connected wireless networks. Multiple-input multiple-output (
MIMO) transceiver technology lies at the core of this paradigm, providing the degrees of freedom required for simultaneous data transmission and accurate radar sensing. The tight integration of sensing and communication introduces unique security vulnerabilities that extend beyond conventional physical-layer security (PLS). In particular, high-power transmissions directed at sensing targets may empower
adversarial eavesdroppers, whereas passive interception of
ISAC echoes can reveal sensitive information such as target locations and mobility patterns. This article presents an overview of recent advances in
MIMO ISAC transceiver design, considering transmitter perspectives, receiver architectures, and full-duplex implementations. We examine
MIMO transceiver designs under unique security threats specific to
ISAC and highlight emerging countermeasures, including secure signaling design, interference exploitation, and transceiver optimization under
adversarial conditions. Finally, we discuss challenges and research opportunities for developing secure
ISAC systems in next-generation wireless networks.
Read the full abstract ▾
All authors Kawon Han, Christos Masouros, Taneli Riihonen, Moeness G. Amin
Signal Processing
Log-Mu Fading Process: Second-Order Statistics for Diversity-Combining Techniques
Godfred Kumi Tenkorang and Michel Daoud Yacoub
This paper derives second-order statistics for diversity-combining techniques over Log-mu fading channels. Closed-form expressions for the level crossing rate (LCR) and average fading duration (AFD) are derived for pure selection combining (PSC), while exact multidimensional integral expressions are obtained for equal gain combining (EGC) and maximal ratio combining (MRC). The analysis considers M unbalanced, independent, and non-identically distributed (i.n.i.d.) Log-mu fading channels. Monte Carlo simulations are conducted to validate the theoretical results, demonstrating excellent agreement and confirming the accuracy of the proposed expressions.
Read the full abstract ▾
Systems and Control
SAFE-IMM: Robust and Lightweight Radar-Based Object Tracking on Mobile Platforms
Dnyandeep Mandaokar and Bernhard Rinner
Tracking maneuvering targets requires
estimators that are both responsive and robust. Interacting Multiple Model (IMM) filters are a standard tracking approach, but fusing models via Gaussian mixtures can lag during maneuvers. Recent winnertakes-all (WTA) approaches react quickly but may produce discontinuities. We propose SAFE-IMM, a lightweight IMM variant for tracking on mobile and resource-limited platforms with a safe covariance-aware gate that permits WTA only when the implied jump from the mixture to the winner is provably bounded. In simulations and on nuScenes front-radar data, SAFE-IMM achieves high accuracy at real-time rates, reducing ID switches while maintaining competitive performance. The method is simple to integrate, numerically stable, and clutter-robust, offering a practical balance between responsiveness and smoothness.
Read the full abstract ▾
Systems and Control
LLM-Driven Transient Stability Assessment: From Automated Simulation to Neural Architecture Design
Lianzhe Hu, Yu Wang and Bikash Pal
This paper presents an LLM-driven, end-to-end workflow that addresses the lack of automation and intelligence in power system transient stability assessment (TSA). The proposed agentic framework integrates large
language models (LLMs) with a professional simulator (ANDES) to automatically generate and filter disturbance scenarios from natural
language, and employs an LLM-driven Neural Network Design (LLM-NND) pipeline to autonomously design and optimize TSA models through performance-guided, closed-loop feedback. On the IEEE 39-bus system, the LLM-NND models achieve 93.71% test accuracy on four-class TSA with only 4.78M parameters, while maintaining real-time inference latency (less than 0.95 ms per sample). Compared with a manually designed DenseNet (25.9M parameters, 80.05% accuracy), the proposed approach jointly improves accuracy and efficiency. Ablation studies confirm that the synergy among domain-grounded
retrieval,
reasoning augmentation, and feedback mechanisms is essential for robust automation. The results demonstrate that LLM
agents can reliably accelerate TSA research from scenario generation and data acquisition to model design and interpretation, offering a scalable paradigm that is readily extensible to other power system tasks such as optimal power flow, fault analysis, and
market operations.
Read the full abstract ▾
Signal Processing
Segment-Wise Flow Matching for Vision-Aided mmWave V2I Beam Prediction
Can Zheng, Jiguang He, Chung G. Kang et al. (+3 more)
This paper proposes a
vision-conditioned flow matching (FM) framework for beam prediction in millimeter-wave vehicle-to-infrastructure links. Instead of modeling discrete beam-index sequences, the proposed method learns the temporal
evolution of normalized beam receive power vectors through a continuous vector field governed by an ordinary differential equation, enabling smooth dynamics and efficient sampling. By imposing FM over beam-state transitions and jointly optimizing beam prediction and flow consistency, the proposed framework provides a unified model for future beam prediction. Experimental results show that the proposed FM-based model significantly improves beam prediction performance over baselines, approaches the performance of large
language model-based methods, and reduces predictor-side inference latency by about $6.9\times$ on GPU and $2.8\times10^3\times$ on CPU, respectively.
Read the full abstract ▾
All authors Can Zheng, Jiguang He, Chung G. Kang, Guofa Cai, Chongwen Huang, Henk Wymeersch
Systems and Control
Occlusion-Aware Multi-Object Tracking via Expected Probability of Detection
Jan Krejčí, Oliver Kost, Yuxuan Xia et al. (+2 more)
This paper addresses multi-object systems, where objects may occlude one another relative to the sensor. The standard point-object model for detection-based sensors is enhanced so that the probability of detection considers the presence of all objects. A principled tracking method is derived, assigning each object an expected probability of detection, where the expectation is taken over the reduced Palm density, which means conditionally on the object's existence. The assigned probability thus considers the object's visibility relative to the sensor, under the presence of other objects. Unlike existing methods, the proposed method systematically accounts for uncertainties related to all objects in a clear and manageable way. The method is demonstrated through a visual tracking application using the multi-Bernoulli mixture (MBM) filter with marks.
Read the full abstract ▾
All authors Jan Krejčí, Oliver Kost, Yuxuan Xia, Lennart Svensson, Ondřej Straka
Systems and Control
Reinforcement Learning to Initialize Newton-Raphson for AC Power Flow with Quantum Annealing-Based Environment Updates
Zeynab Kaseb, Matthias Moller, Lindsay Spoor et al. (+4 more)
The Newton-Raphson (NR) method is widely used for solving power flow (PF) equations due to its quadratic convergence. However, its performance deteriorates under poor initialization or extreme operating scenarios, e.g., high levels of renewable energy penetration. We propose the use of reinforcement learning (RL) to optimize the initialization of NR, and introduce a
quantum-enhanced RL environment update mechanism that addresses the combinatorially large action space at each RL timestep by formulating the voltage adjustment task as a Quadratic Unconstrained Binary Optimization (QUBO) problem, solved with an Ising machine. RL initialization is benchmarked against flat start and start from the DC (linearized) PF solution on a standard 4-bus system, Iwamoto's ill-conditioned 11-bus system, and the IEEE 118-bus system under normal and stressed loading and reactive power limits, with verified operational solutions. On all systems, a supervised initializer refined by RL requires fewer NR iterations than flat and DC starts and than the same initializer without RL, for all seeds. For example, on the 118-bus system under normal and stressed loading, it reached 2.04 and 2.86 NR iterations, compared with 3.02 and 5.13 from DC start and 2.61 and 3.09 without RL. In wall-clock time, this pays off only for an initializer integrated into the solver and reused for many solves on a fixed
topology. On the 4-bus system, a
quantum-enhanced RL
agent with a
quantum-inspired annealer moved challenging initial states that required 29 and 44 NR iterations to initializations that required three NR iterations within one RL timestep.
Read the full abstract ▾
All authors Zeynab Kaseb, Matthias Moller, Lindsay Spoor, Jerry J. Guo, Yu Xiang, Peter Palensky, Pedro P. Vergara
Systems and Control · Cross-listed from cs.LG
Communication-Efficient Learning for Satellite Constellations
Ruxandra-Stefania Tudose, Moritz H.W. Grüss, Grace Ra Kim et al. (+2 more)
Satellite constellations in low-Earth orbit are now widespread, enabling positioning, Earth imaging, and communications. In this paper we address the solution of learning problems using these satellite constellations. In particular, we focus on a
federated approach, where satellites collect and locally process data, with the ground station aggregating local models. We focus on designing a novel, communication-efficient
algorithm that still yields accurate trained models. To this end, we employ several mechanisms to reduce the number of communications with the ground station (local training) and their size (compression). We then propose an error feedback mechanism that enhances accuracy, which yields, as a byproduct, an
algorithm-agnostic error feedback scheme that can be more broadly applied. We analyze the convergence of the resulting
algorithm, and compare it with the state of the art through simulations in a realistic space scenario, showcasing superior performance.
Read the full abstract ▾
All authors Ruxandra-Stefania Tudose, Moritz H.W. Grüss, Grace Ra Kim, Karl H. Johansson, Nicola Bastianello
Signal Processing
Optimal Waveform Design for Continuous Aperture Array (CAPA)-aided ISAC Systems
Junjie Ye, Zhaolin Wang, Yuanwei Liu et al. (+3 more)
A novel continuous-aperture-array (CAPA)-aided integrated sensing and communication (
ISAC) framework is proposed. Specifically, an optimal continuous
ISAC waveform is designed to form a directive beampattern for multi-target sensing while suppressing the multi-user interference (MUI). To achieve the goal of optimal waveform design, the directional beampattern of CAPA is first derived based on Green's function, whereafter a reference sensing waveform is obtained through wavenumber-domain optimization. Based on the reference sensing waveform, a weighted functional programming on the tradeoff between sensing beampattern mismatch and MUI is formulated. To solve the resulting problem, an optimal CAPA-
ISAC waveform structure is analytically derived using a Lagrangian-transformation and calculus-of-variations method, where the Lagrangian multiplier associated with the optimal waveform structure is determined via Bisection search. The obtained optimal waveform reveals that it is concurrently affected by the reference sensing waveform, the channel correlations and the channel-symbol correlations. Finally, numerical results validate the effectiveness of the proposed system and waveform design, demonstrating that CAPA can achieve significant performance gains against the
ISAC designs based on conventional spatially discrete array in both sensing accuracy and communication reliability.
Read the full abstract ▾
All authors Junjie Ye, Zhaolin Wang, Yuanwei Liu, Peichang Zhang, Lei Huang, Arumugam Nallanathan
Signal Processing · Cross-listed from cs.IT
CSI Prediction Frameworks for Enhanced 5G Link Adaptation: Performance-Complexity Trade-offs
Francisco Díaz-Ruiz, Francisco J. Martín-Vega, Jose A. Cortés et al. (+2 more)
Accurate and timely channel state information (CSI) is fundamental for efficient link adaptation. However, challenges such as channel aging, user mobility, and feedback delays significantly impact the performance of adaptive modulation and coding (AMC). This paper proposes and evaluates two CSI prediction frameworks applicable to both time division duplexing (TDD) and frequency division duplexing (FDD) systems. The proposed methods operate in the effective signal to interference plus noise ratio (SINR) domain to reduce complexity while preserving predictive accuracy. A comparative analysis is conducted between a classical Wiener filter and state-of-the-art deep learning frameworks based on gated recurrent units (GRUs), long short-term
memory (LSTM) networks, and a delayed deep neural network (DNN). The evaluation considers the accuracy of the prediction in terms of mean squared error (MSE), the performance of the system, and the complexity of the implementation regarding floating point operations (FLOPs). Furthermore, we investigate the generalizability of both approaches under various propagation conditions. The simulation results show that the Wiener filter performs close to GRU in terms of MSE and throughput with lower computational complexity, provided that the second-order statistics of the channel are available. However, the GRU model exhibits enhanced generalization across different channel scenarios. These findings suggest that while learningbased solutions are well-suited for TDD systems where the base station (BS) handles the computation, the lower complexity of classical methods makes them a preferable choice for FDD setups, where prediction occurs at the power-constrained user equipment (UE).
Read the full abstract ▾
All authors Francisco Díaz-Ruiz, Francisco J. Martín-Vega, Jose A. Cortés, Gerardo Gómez, Mari Carmen Aguayo
Signal Processing
Joint Bit-Partitioning and Modulation Design for Digital AirComp
Xiaojing Yan and Carlo Fischione
For digital over-the-air computation, the ChannelComp framework has recently been proposed to design digital modulations to compute any arbitrary function over a multiple access channel. To reduce modulation design complexity while increasing computation reliability, this paper integrates a bit-partitioning procedure into ChannelComp. The key process is to partition the input bit sequence into several groups, map each group to a single modulation symbol and transmit the encoded symbol sequence across multiple time slots. With the objective to maximize a worst-case constellation distance, we develop two bit-partitioning methods. In uniform bit-partitioning, bits are evenly distributed across groups and modulation is designed via a max-min optimization, which is handled by a CCCP that solves a sequence of second-order cone programming subproblems. In importance-adaptive bit-partitioning (IABP), the bit allocation is adapted to the significance of individual bit positions, and the modulation and partitioning are jointly optimized. To keep the overall complexity manageable, simulated annealing is employed in the outer loop to update the partitioning, while a CCCP-based solver is used in the inner loop for modulation design. Numerical results show that both methods provide robust computation in noisy channels, and IABP achieves up to a 5 dB reduction in computation error compared to Sequential Modulation for AirComp, especially for product computation.
Read the full abstract ▾
Audio and Speech Processing · Cross-listed from cs.CL
Mispronunciation Detection and Diagnosis Without Model Training: A Retrieval-Based Approach
Huu Tuong Tu, Ha Viet Khanh, Tran Tien Dat et al. (+4 more)
Mispronunciation Detection and Diagnosis (MDD) is crucial for
language learning and
speech therapy. Unlike conventional methods that require scoring models or training phoneme-level models, we propose a novel training-free framework that leverages
retrieval techniques with a pretrained Automatic
Speech Recognition model. Our method avoids phoneme-specific modeling or additional task-specific training, while still achieving accurate detection and diagnosis of pronunciation errors. Experiments on the L2-ARCTIC
dataset show that our method achieves a superior F1 score of 69.60% while avoiding the complexity of model training.
Read the full abstract ▾
All authors Huu Tuong Tu, Ha Viet Khanh, Tran Tien Dat, Vu Huan, Thien Van Luong, Nguyen Tien Cuong, Nguyen Thi Thu Trang
Signal Processing
Sparse MIMO-OFDM Channel Estimation via RKHS Regularization
James Delfeld, Gian Marti and Chris Dick
We propose a method for channel estimation in multiple-input multiple-output (
MIMO) orthogonal frequency-division multiplexing (OFDM) wireless communication systems. The method exploits the band-sparsity of wireless channels in the delay-beamspace domain by solving a regularized optimization problem in a reproducing kernel
Hilbert space (RKHS). A suitable representer
theorem allows us to transform the infinite-dimensional optimization problem into a finite-dimensional one, which we then approximate with a low-dimensional surrogate. We solve the resulting optimization problem using a forward-backward splitting (FBS)-based
algorithm. By exploiting the problem's modulation structure, we achieve a computational complexity per iteration that is quasi-linear in the number of unknown variables. We also propose a data-driven deep-unfolding based extension to improve the performance at a reduced number of iterations. We evaluate our channel
estimators on ray-traced channels generated with SionnaRT. The results show that our methods significantly outperform linear methods such as linear minimum mean squared error (LMMSE) channel estimation based on aggregate channel statistics, both in terms of raw estimation accuracy as well as in downstream performance.
Read the full abstract ▾
Systems and Control
Assessing the Technical and Environmental Impacts of Energy Management Systems in Smart Ports
Youzhe Yang, Hafiz Majid Hussain, Juha Haakana et al. (+1 more)
A vital strategy for ports to mitigate the environmental impact of the maritime industry, while complying with frameworks such as the European Green Deal and the Sustainable Development Goals (SDGs), entails the systematic implementation of comprehensive energy management solutions. This paper provides a baseline evaluation of the energy management systems (EMSs) implementation and their impact on energy consumption, carbon emissions, and operational costs in smart ports. Initially, we provide a systematic review of the literature focusing on case studies from prominent ports, including Hamburg, Genoa, Jurong, and Shanghai Yangshan Phase IV. The analysis emphasises key aspects such as energy efficiency, reductions in emissions, and the minimization of operational costs. Subsequently, we formulate an optimisation model to simulate load dispatch, carbon emission reduction, and transport scheduling. Results indicate that EMS deployment reduces annual energy consumption and carbon emissions significantly by approximately 7%-8% and 11%-12% respectively, while achieving substantial cost savings of 30%. The study also identifies critical challenges, including system integration, data quality issues, cybersecurity risks, and the need for standardization. These findings provide valuable insights for port authorities and policymakers, supporting the transition toward more sustainable and efficient port operations.
Read the full abstract ▾
All authors Youzhe Yang, Hafiz Majid Hussain, Juha Haakana, Pedro Nardelli
Systems and Control · Cross-listed from cs.LG
iRadioDiff: Physics-Informed Diffusion Model for Indoor Radio Map Construction and Localization
Xiucheng Wang, Tingwei Yuan, Yang Cao et al. (+3 more)
Radio maps (RMs) serve as environment-aware electromagnetic (EM) representations that connect scenario geometry and material properties to the spatial distribution of signal strength, enabling localization without costly in-situ measurements. However, constructing high-fidelity indoor RMs remains challenging due to the prohibitive latency of EM solvers and the limitations of learning-based methods, which often rely on sparse measurements or assumptions of homogeneous material, which are misaligned with the heterogeneous and multipath-rich nature of indoor environments. To overcome these challenges, we propose iRadioDiff, a sampling-free
diffusion-based framework for indoor RM construction. iRadioDiff is conditioned on access point (AP) positions, and physics-informed
prompt encoded by material reflection and transmission coefficients. It further incorporates multipath-critical priors, including diffraction points, strong transmission boundaries, and line-of-sight (LoS) contours, to guide the generative process via conditional channels and boundary-weighted objectives. This design enables accurate modeling of nonstationary field discontinuities and efficient construction of physically consistent RMs. Experiments demonstrate that iRadioDiff achieves state-of-the-art performance in indoor RM construction and received signal strength based indoor localization, which offers effective generalization across layouts and material configurations. Code is available at https://github.com/UNIC-Lab/iRadioDiff.
Read the full abstract ▾
All authors Xiucheng Wang, Tingwei Yuan, Yang Cao, Nan Cheng, Ruijin Sun, Weihua Zhuang
Audio and Speech Processing
BERT-APC: A Reference-free Framework for Automatic Pitch Correction via Musical Context Inference
Sungjae Kim, Kihyun Na, Jinyoung Choi et al. (+1 more)
Automatic Pitch Correction (APC) enhances vocal recordings by aligning pitch deviations with intended musical notes. However, existing APC systems either rely on reference pitches, which limits practical applicability, or employ simple pitch estimation
algorithms that often fail to preserve expressiveness and naturalness. We propose BERT-APC, a reference-free APC framework that corrects pitch errors while maintaining the expressiveness and naturalness of vocal performances. In BERT-APC, a stationary pitch predictor first estimates the stationary pitch of each note from the detuned singing voice, where stationary pitch is the continuous pitch from the stable region of a note and approximates its perceived pitch. A context-aware note pitch predictor then infers the intended pitch sequence using a repurposed music
language model that incorporates musical context. Finally, a note-level correction
algorithm fixes pitch errors while preserving intentional deviations for emotional expression. We also introduce a learnable data augmentation strategy that improves robustness by simulating realistic detuning patterns. Compared to two recent singing voice transcription models, BERT-APC demonstrated superior target note pitch prediction, outperforming the second-best model, ROSVOT, by 10.49 percentage points on highly detuned samples in raw pitch accuracy. In the MOS test, BERT-APC achieved the highest quality rating of $4.32 \pm 0.15$, significantly higher than Auto-Tune ($3.22 \pm 0.18$) and Melodyne ($3.08 \pm 0.18$), while maintaining a comparable ability to preserve expressive nuances. To the best of our knowledge, this is the first APC model that leverages a music
language model to achieve reference-free pitch correction with symbolic musical context. The corrected audio samples are available at https://joshua-1995.github.io/BERT-APC-Demo/.
Read the full abstract ▾
All authors Sungjae Kim, Kihyun Na, Jinyoung Choi, Injung Kim
Signal Processing
Redefining Radar Segmentation: Simultaneous Static-Moving Segmentation and Ego-Motion Estimation using Radar Point Clouds
Simin Zhu, Satish Ravindran, Alexander Yarovoy et al. (+1 more)
Conventional radar
segmentation research has typically focused on learning category labels for different moving objects. Although fundamental differences between radar and optical sensors lead to differences in the reliability of predicting accurate and consistent category labels, a review of common radar perception tasks in automotive reveals that determining whether an object is moving or static is a prerequisite for most tasks. To fill this gap, this study proposes a neural network based solution that can simultaneously segment static and moving objects from radar point clouds. Furthermore, since the measured radial velocity of static objects is correlated with the motion of the radar, this approach can also estimate the instantaneous 2D velocity of the moving platform or vehicle (ego motion). However, despite performing dual tasks, the proposed method employs very simple yet effective building blocks for feature extraction: multi layer perceptrons (MLPs) and recurrent neural networks (RNNs). In addition to being the first of its kind in the literature, the proposed method also demonstrates the feasibility of extracting the information required for the dual task directly from unprocessed point clouds, without the need for cloud aggregation, Doppler compensation, motion compensation, or any other intermediate signal processing steps. To measure its performance, this study introduces a set of novel evaluation metrics and tests the proposed method using a challenging real world radar
dataset, RadarScenes. The results show that the proposed method not only performs well on the dual tasks, but also has broad application potential in other radar perception tasks.
Read the full abstract ▾
All authors Simin Zhu, Satish Ravindran, Alexander Yarovoy, Francesco Fioranelli
Signal Processing
Cross-Modal Semantic Communication for Heterogeneous Collaborative Perception
Mingyi Lu, Guowei Liu, Le Liang et al. (+3 more)
Collaborative perception, an emerging paradigm in autonomous driving, has been introduced to mitigate the limitations of single-vehicle systems, such as limited sensor range and occlusion. To improve the robustness of inter-vehicle data sharing, semantic communication has recently further been integrated into collaborative perception systems to enhance overall performance. However, practical deployment of such systems is challenged by the heterogeneity of sensors across different connected autonomous vehicles (CAVs). This diversity in perceptual data complicates the design of a unified communication framework and impedes the effective fusion of shared information. To address this challenge, we propose a novel cross-modal semantic communication (CMSC) framework to facilitate effective collaboration among CAVs with disparate sensor configurations. Specifically, the framework first transforms heterogeneous perceptual features from different sensor modalities into a unified and standardized semantic space. Subsequently, encoding, transmission, and decoding are performed within this semantic space, enabling seamless and effective information fusion. Extensive experiments demonstrate that CMSC achieves significantly stronger perception performance than existing methods, particularly in low signal-to-noise ratio (SNR) regimes.
Read the full abstract ▾
All authors Mingyi Lu, Guowei Liu, Le Liang, Chongtao Guo, Hao Ye, Shi Jin
Systems and Control
Toward Trustworthy Digital Twins in AI Agent-based Wireless Network Optimization: Challenges, Solutions, and Opportunities
Zhenyu Tao, Wei Xu and Xiaohu You
Optimizing modern wireless networks is exceptionally challenging due to their high dynamism and complexity. While the AI
agent powered by reinforcement learning (RL) offers a promising solution, its practical application is limited by prohibitive exploration costs and potential risks in the real world. The emerging digital twin (DT) technology provides a safe and controlled virtual environment for
agent training, but its effectiveness critically depends on the DT's reliability. Policies trained in an unreliable DT that does not accurately represent the physical network may experience severe performance degradation upon real-world deployment. In this article, we introduce a new DT evaluation framework to ensure trustworthy DTs in AI
agent-based network optimization. This framework shifts from model-level accuracy, such as wireless channel and user trajectory similarities, to a more holistic, task-centric DT assessment, which relies on the Markov decision process that the
agent actually perceives. We demonstrate it as an effective guideline for design, selection, and lifecycle management of wireless network DTs. A comprehensive case study on a real-world wireless network testbed shows how this evaluation framework is used to pre-filter candidate DTs, leading to a significant reduction in training and testing costs without sacrificing deployment performance. Finally, potential research opportunities are discussed.
Read the full abstract ▾
Signal Processing · Cross-listed from cs.IT
Towards Edge General Intelligence: Knowledge Distillation for Mobile Agentic AI
Yuxuan Wu, Linghan Ma, Ruichen Zhang et al. (+9 more)
Edge General Intelligence (EGI) represents a paradigm shift in mobile edge computing, where intelligent
agents operate autonomously in dynamic, resource-constrained environments. However, the deployment of advanced agentic AI models on mobile and edge devices faces significant challenges due to limited computation, energy, and storage resources. To address these constraints, this survey investigates the integration of Knowledge
Distillation (KD) into EGI, positioning KD as a key enabler for efficient, communication-aware, and scalable intelligence at the wireless edge. In particular, we emphasize KD techniques specifically designed for wireless communication and mobile networking, such as channel-aware self-
distillation, cross-model Channel State Information (CSI) feedback
distillation, and robust modulation/classification
distillation. Furthermore, we review novel architectures natively suited for KD and edge deployment, such as Mamba, RWKV (Receptance, Weight, Key, Value) and Cross-Architecture
distillation, which enhance generalization capabilities. Subsequently, we examine diverse applications in which KD-driven architectures enable EGI across
vision,
speech, and
multimodal tasks. Finally, we highlight the key challenges and future directions for KD in EGI. This survey aims to provide a comprehensive reference for researchers exploring KD-driven frameworks for mobile agentic AI in the era of EGI.
Read the full abstract ▾
All authors Yuxuan Wu, Linghan Ma, Ruichen Zhang, Yinqiu Liu, Dusit Niyato, Shunpu Tang, Zehui Xiong, Zhu Han, Zhaohui Yang, Kaibin Huang, Zhaoyang Zhang, Kai-Kit Wong
Signal Processing
AI/ML based Joint Source and Channel Coding for HARQ-ACK Payload
Akash Doshi, Pinar Sen, Kirill Ivanov et al. (+7 more)
Channel coding from 2G to 5G has assumed the inputs bits at the physical layer to be uniformly distributed. However, hybrid automatic repeat request acknowledgement (HARQ-ACK) bits transmitted in the uplink are inherently non-uniformly distributed. For such sources, significant performance gains could be obtained by employing joint source channel coding, aided by deep learning-based techniques. In this paper, we learn a
transformer-based encoder using a novel "free-lunch" training
algorithm and propose per-codeword power shaping to exploit the source prior at the encoder whilst being robust to small changes in the HARQ-ACK distribution. Furthermore, any HARQ-ACK decoder has to achieve a low negative acknowledgement (NACK) error rate to avoid
radio link failures resulting from multiple NACK errors. We develop an extension of the Neyman-Pearson test to a coded bit system with multiple information bits to achieve Unequal Error Protection of NACK over ACK bits at the decoder. Finally, we apply the proposed encoder and decoder designs to a 5G New
Radio (NR) compliant uplink setup under a fading channel, describing the optimal receiver design and a low complexity coherent approximation to it. Our results demonstrate 3-6 dB reduction in the average transmit power required to achieve the target error rates compared to the NR baseline, while also achieving a 2-3 dB reduction in the maximum transmit power, thus providing for significant coverage gains and power savings.
Read the full abstract ▾
All authors Akash Doshi, Pinar Sen, Kirill Ivanov, Wei Yang, June Namgoong, Runxin Wang, Rachel Wang, Taesang Yoo, Jing Jiang, Tingfang Ji
Image and Video Processing
DLADiff: A Dual-Layer Defense Framework against Fine-Tuning and Zero-Shot Customization of Diffusion Models
Jun Jia, Hongyi Miao, Yingjie Zhou et al. (+8 more)
With the rapid advancement of
diffusion models, a variety of fine-tuning methods have been developed, enabling high-fidelity image generation with high similarity to the target content using only 3 to 5 training images. More recently, zero-shot generation methods have emerged, capable of producing highly realistic outputs from a single reference image without altering model weights. However, technological advancements have also introduced significant risks to facial
privacy. Malicious actors can exploit
diffusion model customization with just a few or even one image of a person to create synthetic identities nearly identical to the original identity. Although research has begun to focus on defending against
diffusion model customization, most existing defense methods target fine-tuning approaches and neglect zero-shot generation defenses. To address this issue, this paper proposes Dual-Layer Anti-
Diffusion (DLADiff) to defense both fine-tuning methods and zero-shot methods. DLADiff contains a dual-layer protective mechanism. The first layer provides effective protection against unauthorized fine-tuning by leveraging the proposed Dual-Surrogate Models (DSUR) mechanism and Alternating Dynamic Fine-Tuning (ADFT), which integrates
adversarial training with the prior knowledge derived from pre-fine-tuned models. The second layer, though simple in design, demonstrates strong effectiveness in preventing image generation through zero-shot methods. Extensive experimental results demonstrate that our method significantly outperforms existing approaches in defending against fine-tuning of
diffusion models and achieves unprecedented performance in protecting against zero-shot generation.
Read the full abstract ▾
All authors Jun Jia, Hongyi Miao, Yingjie Zhou, Linhan Cao, Yanwei Jiang, Wangqiu Zhou, Dandan Zhu, Hua Yang, Wei Sun, Xiongkuo Min, Guangtao Zhai
Signal Processing
Joint Classification and Regression Deep Learning Model for Universal Phase-based Ranging in Multiple Environments
Pantelis Stefanakis and Ming Shen
Phase-Based Ranging (PBR) offers several advantages for estimating distances between wirelessly connected devices, including high accuracy over large distances and the removal of the need for
antenna arrays at each transceiver. This study investigates the use of Neural Network (NN)-based models for accurate PBR in three distinct environments: Openfield, Office, and Near Buildings, comparing their performance with established non-NN methods. A novel 2NN Model is proposed, integrating two neural networks: one to classify the environment and another to predict distances. Performance was evaluated over 20 trials for each method and
dataset using root mean square error (RMSE) and maximum prediction error. Results show that the 2NN Model consistently outperformed other methods, frequently ranking among the top methods in minimizing both RMSE and maximum error. In addition, the 2NN Model achieved the best average RMSE and the lowest maximum error. To assess the effect of environment misclassification, filtered versions of the NN models were evaluated by omitting misclassified measurements prior to RMSE calculation. Although unsuitable for production use, the filtered models revealed that misclassifications in the 2NN Model had a significant impact. Its filtered variant achieved the lowest RMSE and maximum error across all
datasets, and ranked first in the frequency of attaining the lowest maximum error over 20 trials. Overall, the findings show that NN models deliver robust, high-accuracy ranging across diverse environments, outperforming non-NN methods and reinforcing their potential as universal PBR solutions when trained on comprehensive distance
datasets.
Read the full abstract ▾