Signal Processing
Robust Radar Mounting Angle Estimation in Operational Driving Conditions
Simin Zhu, Satish Ravindran, Lihui Chen et al. (+2 more)
The robust estimation of the mounting angle for millimeter-wave automotive radars installed on moving vehicles is investigated. We propose a novel signal processing pipeline that combines radar and inertial measurement unit (IMU) data to achieve accurate and reliable performance in realistic driving scenarios. Unlike previous studies, the method employs neural networks to process sparse and noisy radar measurements, reject detections from moving objects, and estimate radar motion. In addition, a measurement model is introduced to correct IMU bias and scale factor errors. Using vehicle kinematics, the radar mounting angle is then computed from the estimated radar motion and the vehicle's yaw rate. To
benchmark performance, the proposed approach is comprehensively compared with two problem formulations and four estimation techniques reported in the literature. Validation is carried out on the challenging RadarScenes
dataset, covering over 79 km of real-world driving. Results show that the proposed method achieves state-of-the-art accuracy and robustness, with reliable estimates obtained within approximately 25 seconds of driving. To the best of our knowledge, this is the first study to demonstrate that automotive radar mounting angles can be accurately estimated in complex, real traffic conditions, without requiring controlled environments, dedicated targets, or specially designed driving routes.
Read the full abstract ▾
All authors Simin Zhu, Satish Ravindran, Lihui Chen, Alexander Yarovoy, Francesco Fioranelli
Image and Video Processing · Cross-listed from cs.CV
Extremal Contours: Gradient-driven contours for compact visual attribution
Reza Karimzadeh, Albert Alonso, Frans Zdyb et al. (+2 more)
Faithful yet compact explanations for
vision models remain a challenge, as commonly used dense perturbation masks are often fragmented and overfitted, needing careful post-processing. Here, we present a training-free explanation method that replaces dense masks with smooth tunable contours. A
star-convex region is parameterized by a truncated
Fourier series and optimized under an extremal preserve/delete objective using the classifier gradients. The approach guarantees a single, simply connected mask, cuts the number of free parameters by orders of magnitude, and yields stable boundary updates without cleanup. Restricting solutions to low-dimensional, smooth contours makes the method robust to
adversarial masking artifacts. On ImageNet classifiers, it matches the extremal fidelity of dense masks while producing compact, interpretable regions with improved run-to-run consistency. Explicit area control also enables importance contour maps, yielding a transparent fidelity-area profiles. Finally, we extend the approach to multi-contour and show how it can localize multiple objects within the same framework. Across
benchmarks, the method achieves higher relevance mass and lower complexity than gradient and perturbation based baselines, with especially strong gains on self-supervised DINO models where it improves relevance mass by over 15% and maintains positive faithfulness correlations.
Read the full abstract ▾
All authors Reza Karimzadeh, Albert Alonso, Frans Zdyb, Julius B. Kirkegaard, Bulat Ibragimov
Signal Processing
AoI-Aware Machine Learning for Constrained Multimodal Sensing-Aided Communications
Abolfazl Zakeri, Nhan Thanh Nguyen, Ahmed Alkhateeb et al. (+1 more)
Using environmental sensory data can enhance communications beam training and reduce its overhead compared to conventional methods. However, the availability of fresh sensory data during inference may be limited due to sensing constraints or sensor failures, necessitating a realistic model for
multimodal sensing. This paper proposes a joint
multimodal sensing and beam prediction framework that operates under a constraint on the average sensing rate, i.e., how often fresh sensory data should be obtained. The proposed method combines deep reinforcement learning, i.e., a deep Q-network (DQN), with a neural network (NN)-based beam predictor. The DQN determines the sensing decisions, while the NN predicts the best beam from the codebook. To capture the effect of limited fresh data during inference, the age of information (AoI) is incorporated into the training of both the DQN and the beam predictor. Lyapunov optimization is employed to design a reward function that enforces the average sensing constraint. Simulation results on a real-world
dataset show that AoI-aware training improves top-1 and top-3 inference accuracy by 44.16% and 52.96%, respectively, under a strict sensing constraint. The performance gain, however, diminishes as the sensing constraint is relaxed.
Read the full abstract ▾
All authors Abolfazl Zakeri, Nhan Thanh Nguyen, Ahmed Alkhateeb, Markku Juntti
Signal Processing
MM-2FSK: Multimodal Frequency Shift Keying for Ultra-Efficient and Robust High-Resolution MIMO Radar Imaging
Vanessa Wirth, Johanna Bräunig, Martin Vossiek et al. (+2 more)
Accurate reconstruction of dynamic targets demands three-dimensional imaging at high temporal resolution. Radar is a particularly attractive sensing modality for this purpose due to its fast capture capabilities and robustness under varying lighting and weather conditions. Consequently, it has been successfully employed in a variety of dynamic applications, such as automotive and robotic perception. Nevertheless, dynamic sensing remains comparatively unexplored in operating regimes requiring near-field, high-fidelity surface reconstruction, as commonly targeted by large-aperture mmWave
MIMO radars. Here, achieving high frame rates is challenged by the substantial computational cost of reconstruction, imposing stringent constraints on bandwidth, compute resources, and ultimately sensor capture rate. To enable fast captures at reduced computation cost, prior work explored few-tone imaging, reducing the number of transmitted frequencies at the expense of increased range-phase ambiguity; however, this requires coarse knowledge of the target position and is primarily designed to reconstruct flat surface geometries. We present MM-2FSK, which extends two-tone stepped frequency imaging with an external modality-agnostic per-point depth prior for precise near-field 3D imaging of geometrically complex surfaces. To address range-phase ambiguities, the prior is processed to mitigate inter-modality data mismatch, transformed into a radar-compatible representation, and integrated into signal processing as a phase constraint. In experiments with a mmWave FSCW
MIMO radar and with representative priors obtained from a co-located optical sensor, we demonstrate superior depth accuracy of our method over comparable near-field few-tone radar imaging approaches in static and dynamic scenes, competitive with time- and resource-intensive measurements of many-tone backprojection.
Read the full abstract ▾
All authors Vanessa Wirth, Johanna Bräunig, Martin Vossiek, Tim Weyrich, Marc Stamminger
Systems and Control
Risk Aware Safe Control with Multi-Modal Sensing for Dynamic Obstacle Avoidance
Pei Yu Chang, Qizhe Xu, Vishnu Renganathan et al. (+1 more)
Safe control in dynamic traffic environments remains a major challenge for autonomous vehicles (AVs), as ego vehicle and obstacle states are inherently affected by sensing noise and estimation uncertainty. However, existing studies have not sufficiently addressed how uncertain multi-modal sensing information can be systematically incorporated into tail-risk-aware safety-critical control. To address this gap, this paper proposes a risk-aware safe control framework that integrates probabilistic state estimation with a conditional value-at-risk (CVaR) control barrier function (CBF) safety filter. Obstacle detections from cameras,
LiDAR, and vehicle-to-everything (V2X) communication are combined using a Wasserstein barycenter (WB) to obtain a probabilistic state estimate. A model predictive controller generates the nominal control, which is then filtered through a CVaR-CBF quadratic program to enforce risk-aware safety constraints. The approach is evaluated through numerical studies and further validated on a full-scale AV. Results demonstrate improved safety and robustness over a baseline MPC-CBF design, with an average improvement of 12.7% in success rate across the evaluated scenarios.
Read the full abstract ▾
All authors Pei Yu Chang, Qizhe Xu, Vishnu Renganathan, Qadeer Ahmed
Signal Processing
CRMD: Complex Robust Modal Decomposition
Wang Hao, Kuang Zhang, Hou Chengyu et al. (+4 more)
Compared to real-valued signals, complex-valued signals provide a unique and intuitive representation of the phase of real physical systems and processes, which holds fundamental significance and is widely applied across many fields of science and engineering. In this paper, we propose a robust modal decomposition (RMD) in the complex domain as a natural and general extension of the original real-valued RMD. We revisit and derive the mathematical principles of RMD in the complex domain, and develop an algorithmic version tailored for this domain. Extensive experiments are conducted on synthetic simulation
datasets and real-world
datasets from diverse fields, including a millimeter-wave radar physiological signal detection
dataset, a faulty bearing
dataset, a
radio-frequency unmanned aerial vehicle identification
dataset, and a WiFi CSI-based respiration detection
dataset. The results demonstrate that the proposed complex-domain robust modal decomposition significantly improves performance across these various applications.
Read the full abstract ▾
All authors Wang Hao, Kuang Zhang, Hou Chengyu, Tan Chenxing, Cui Weiming, Fu Weifeng, Yao Xinran
Audio and Speech Processing
AudioNet: Supervised Deep Hashing for Retrieval of Similar Audio Events
Sagar Dutta and Vipul Arora
This work presents a supervised deep hashing method for retrieving similar audio events. The proposed method, named AudioNet, is a deep-learning-based system for efficient hashing and
retrieval of similar audio events using an audio example as a query. AudioNet achieves high
retrieval performance on multiple standard
datasets by generating binary hash codes for similar audio events, setting new
benchmarks in the field, and highlighting its efficacy and effectiveness compare to other hashing methods. Through comprehensive experiments on standard
datasets, our research represents a pioneering effort in evaluating the
retrieval performance of similar audio events. A novel loss function is proposed which incorporates weighted contrastive and weighted pairwise loss along with hashcode balancing to improve the efficiency of audio event
retrieval. The method adopts discrete gradient propagation, which allows gradients to be propagated through discrete variables during backpropagation. This enables the network to optimize the discrete hash codes using standard gradient-based optimization
algorithms, which are typically used for continuous variables. The proposed method showcases promising
retrieval performance, as evidenced by the experimental results, even when dealing with imbalanced
datasets. The systematic analysis conducted in this study further supports the significant benefits of the proposed method in
retrieval performance across multiple
datasets. The findings presented in this work establish a baseline for future studies on the efficient
retrieval of similar audio events using deep audio
embeddings.
Read the full abstract ▾
Signal Processing
Classification of motor faults based on transmission coefficient and reflection coefficient of omni-directional antenna using DCNN
Sagar Dutta, Banani Basu and Fazal Ahmed Talukdar
The most commonly used electrical rotary machines in the field are induction machines. In this paper, we propose an
antenna based approach for the classification of motor faults in induction motors using the reflection coefficient S11 and the transmission coefficient S21 of the
antenna. The spectrograms of S11 and S21 are seen to possess unique signatures for various fault conditions that are used for the classification. To learn the required characteristics and classification boundaries, deep convolution neural network (DCNN) is applied to the spectrogram of the S-parameter. DCNN has been found to reach classification accuracy 93% using S11, 98.1% using S21 and 100% using both S11 and S21. The effect of
antenna operating frequency, its location and duration of signal on the classification accuracy is also presented and discussed.
Read the full abstract ▾
Systems and Control
Orthogonal-by-construction augmentation of physics-based input-output models
Bendegúz M. Györök, Maarten Schoukens, Tamás Péni et al. (+1 more)
This paper proposes a novel orthogonal-by-construction parametrization for augmenting physics-based input-output models with a learning component in an additive sense. The parametrization allows to jointly optimize the parameters of the physics-based model and the learning component. Unlike the commonly applied additive (parallel) augmentation structure, the proposed formulation eliminates overlap in representation of the system dynamics, thereby preserving the uniqueness of the estimated physical parameters, ultimately leading to enhanced model interpretability. By theoretical analysis, we show that, under mild conditions, the method is statistically consistent and guarantees recovery of the true physical parameters. With further analysis regarding the asymptotic covariance
matrix of the identified parameters, we also prove that the proposed structure provides a clear separation between the physics-based and learning components of the augmentation structure. The effectiveness of the proposed approach is demonstrated through simulation studies, showing accurate reproduction of the data-generating dynamics without sacrificing consistent estimation of the physical parameters.
Read the full abstract ▾
All authors Bendegúz M. Györök, Maarten Schoukens, Tamás Péni, Roland Tóth
Audio and Speech Processing
Towards General Auditory Intelligence: Large Multimodal Models for Machine Listening and Speaking
Siyin Wang, Zengrui Jin, Changli Tang et al. (+26 more)
In the era of large
language models (LLMs) and artificial general intelligence (AGI), computer audition must evolve beyond traditional paradigms to fully leverage the capabilities of foundation models, towards more comprehensive understanding, more natural generation and more human-like interaction. Audio, as a modality rich in semantic, emotional, and contextual cues, plays a vital role in achieving naturalistic and
embodied machine intelligence. This survey provides a comprehensive review of recent progress in integrating audio into LLMs, with a focus on four key areas: audio comprehension, audio generation,
speech-based interaction, and audio-visual understanding. We analyze how LLMs are reshaping audio perception and
reasoning, enabling systems to understand sound at a deeper semantic level, generate expressive audio outputs, and engage in human-like spoken interaction. Furthermore, we explore how the fusion of audio and visual modalities enhances situational awareness and cross-modal
reasoning, pushing the boundaries of
multimodal intelligence. This survey not only synthesizes existing research but also identifies critical challenges and future directions for building audio-native AGI systems capable of perceiving, understanding, and interacting through sound as naturally as humans do.
Read the full abstract ▾
All authors Siyin Wang, Zengrui Jin, Changli Tang, Qiujia Li, Bo Li, Chen Chen, Yuchen Hu, Wenyi Yu, Yixuan Li, Jimin Zhuang, Yudong Yang, Mingqiu Wang, Michael Han, Yifan Ding, Junwen Bai, Tom Ouyang, Shuo-yiin Chang, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Lu Lu, Guangzhi Sun, Zhehuai Chen, Ji Wu, Bowen Zhou, Yuxuan Wang, Tara Sainath, Yonghui Wu, Chao Zhang
Systems and Control · Cross-listed from cs.RO
A High-Speed Capable Spherical Robot
Bixuan Zhang, Fengqi Zhang, Haojie Chen et al. (+4 more)
This paper designs a new spherical
robot structure capable of supporting high-speed motion at up to 10 m/s. Building upon a single-pendulum-driven spherical
robot, the design incorporates a momentum wheel with an axis aligned with the secondary pendulum, creating a novel spherical
robot structure. Practical experiments with the physical prototype have demonstrated that this new spherical
robot can achieve stable high-speed motion through simple decoupled control, which was unattainable with the original structure. The spherical
robot designed for high-speed motion not only increases speed but also significantly enhances obstacle-crossing performance and terrain robustness.
Read the full abstract ▾
All authors Bixuan Zhang, Fengqi Zhang, Haojie Chen, You Wang, Jie Hao, Zhiyuan Luo, Guang Li
Systems and Control · Cross-listed from cs.LG
Koopman-based Prediction of Connectivity for Flying Ad Hoc Networks
Sivaram Krishnan, Jinho Choi, Jihong Park et al. (+2 more)
The application of machine learning (ML) to communication systems is expected to play a pivotal role in future artificial intelligence (AI)-based next-generation wireless networks. While most existing works focus on ML techniques for static wireless environments, they often face limitations when applied to highly dynamic environments, such as flying ad hoc networks (FANETs). This paper explores the use of data-driven Koopman approaches to address these challenges. Specifically, we investigate how these approaches can model
UAV trajectory dynamics within FANETs, enabling more accurate predictions and improved network performance. By leveraging Koopman operator theory, we propose two possible approaches – centralized and distributed – to efficiently address the challenges posed by the constantly changing
topology of FANETs. To demonstrate this, we consider a FANET performing surveillance with
UAVs following pre-determined trajectories and predict signal-to-interference-plus-noise ratios (SINRs) to ensure reliable communication between
UAVs. Our results show that these approaches can accurately predict connectivity and isolation events that lead to modelled communication outages. This capability could help
UAVs schedule their transmissions based on these predictions.
Read the full abstract ▾
All authors Sivaram Krishnan, Jinho Choi, Jihong Park, Gregory Sherman, Benjamin Campbell
Audio and Speech Processing · Cross-listed from cs.SD
Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
Jiatong Shi, Jionghao Han, Yichen Lu et al. (+6 more)
Evaluating spoken role-play requires judging not only linguistic content but also prosody, emotional expression, character embodiment, and contextual fit. Existing automatic evaluation methods often collapse these aspects into coarse scores and are evaluated primarily on synthesized
speech. We introduce
Speech-DRAME, a framework comprising
Speech-DRAME-EvalBench, a bilingual, human-annotated
benchmark with contrastive role-, context-, and delivery-mismatch conditions, and DRAME-Eval, a fine-tuned audio-
language evaluator. The
benchmark supports two complementary protocols: top-down archetype evaluation and bottom-up realism evaluation, with predominantly synthesized
benchmark-distribution data and a held-out stress test consisting entirely of authentic human acting. On the
benchmark-distribution sets, DRAME-Eval achieves pooled Pearson correlations of 0.629 for archetype evaluation and 0.602 for realism evaluation, significantly outperforming the evaluated zero- and few-shot audio-
language judges; modality controls show that its judgments depend on both
speech and textual context. This
alignment does not transfer to the authentic-
speech test set, where DRAME-Eval obtains an average correlation of -0.142 and a within-speaker correlation of +0.029, compared with matched human single-rater agreement of +0.34. These results identify a substantial synthetic-to-authentic transfer gap and establish
Speech-DRAME as a resource for studying and improving evaluation of acting differences among real human performances.
Read the full abstract ▾
All authors Jiatong Shi, Jionghao Han, Yichen Lu, Santiago Pascual, Pengfei Wu, Chenye Cui, Shinji Watanabe, Chao Weng, Cong Zhou
Signal Processing
Hi-WaveTST: A Hybrid High-Frequency Wavelet-Transformer for Time-Series Classification
Huseyin Goksu
Transformers have become state-of-the-art (SOTA) for time-series classification, with models like PatchTST demonstrating exceptional performance. These models rely on patching the time series and learning relationships between raw temporal data blocks. We argue that this approach is blind to critical, non-obvious high-frequency information that is complementary to the temporal dynamics. In this letter, we propose Hi-WaveTST, a novel Hybrid architecture that augments the original temporal patch with a learnable, High-Frequency wavelet feature stream. Our wavelet stream uses a deep Wavelet Packet Decomposition (WPD) on each patch and extracts features using a learnable Generalized Mean (GeM) pooling layer. On the UCI-HAR
benchmark dataset, our hybrid model achieves a mean accuracy of 93.38 percent plus-minus 0.0043, significantly outperforming the SOTA PatchTST baseline (92.59 percent plus-minus 0.0039). A comprehensive ablation study proves that every component of our design-the hybrid architecture, the deep high-frequency wavelet decomposition, and the learnable GeM pooling-is essential for this state-of-the-art performance.
Read the full abstract ▾
Systems and Control · Cross-listed from quant-ph
Experimental Demonstration of Software-Orchestrated Quantum Network Applications over a Campus-Scale Testbed
Md. Shariful Islam, Joaquin Chung, Ely Marcus Eastman et al. (+3 more)
To fulfill their promise,
quantum networks must transform from isolated testbeds into scalable infrastructures for distributed
quantum applications. In this paper, we present a prototype orchestrator for the Argonne
Quantum Network (ArQNet) testbed that leverages design principles of software-defined networking (SDN) to automate typical
quantum communication experiments across buildings in the Argonne campus connected over deployed, telecom fiber. Our implementation validates a scalable architecture supporting service-level abstraction of
quantum networking tasks, distributed time synchronization, and
entanglement verification across remote nodes. We present a prototype service of continuous, stable
entanglement distribution between remote sites that ran for 12 hours, which defines a promising path towards scalable
quantum networks.
Read the full abstract ▾
All authors Md. Shariful Islam, Joaquin Chung, Ely Marcus Eastman, Robert J. Hayek, Prem Kumar, Rajkumar Kettimuthu
Systems and Control
Deep Learning-Accelerated Shapley Value for Fair Allocation in Power Systems: The Case of Carbon Emission Responsibility
Yuanhao Feng, Tao Sun, Yan Meng et al. (+2 more)
Allocating costs, benefits, and emissions fairly among power system participant entities represents a persistent challenge. The Shapley value provides an axiomatically fair solution, yet computational barriers have limited its adoption beyond small-scale applications. This paper presents SurroShap, a scalable Shapley value approximation framework combining efficient coalition sampling with deep learning surrogate models that accelerate characteristic function evaluations. Exemplified through carbon emission responsibility allocation in power networks, SurroShap enables Shapley-based fair allocation for power systems with thousands of entities for the first time. We derive theoretical error bounds proving that time-averaged SurroShap allocations converge to be $\varepsilon$-close to exact Shapley values. Experiments on nine systems ranging from 26 to 1,951 entities demonstrate completion within the real-time operational window even at maximum scale, achieving 10^4-10^5 speedups over other sampling-based methods while maintaining tight error bounds. The resulting Shapley-based carbon allocations possess six desirable properties aligning individual interests with decarbonization goals. Year-long simulations on the Texas 2000-bus system validate real-world applicability, with regional analysis revealing how renewable-rich areas offset emission responsibility through exports while load centers bear responsibility for driving system-wide generation.
Read the full abstract ▾
All authors Yuanhao Feng, Tao Sun, Yan Meng, Xuxin Yang, Donghan Feng
Signal Processing · Cross-listed from cs.IT
Conditional Diffusion Model-Enabled Scenario-Specific Neural Receivers for Superimposed Pilot Schemes
Xingyu Zhou, Le Liang, Xinjie Li et al. (+4 more)
Neural receivers have demonstrated strong performance in wireless communication systems. However, their effectiveness typically depends on access to large-scale, scenario-specific channel data for training, which is often difficult to obtain in practice. Recently, generative artificial intelligence (AI) models, particularly
diffusion models (DMs), have emerged as effective tools for synthesizing high-dimensional data. This paper presents a scenario-specific channel generation method based on conditional DMs, which accurately model channel distributions conditioned on user location and velocity information. The generated synthetic channel data are then employed for data augmentation to improve the training of a neural receiver designed for superimposed pilot-based transmission. Experimental results show that the proposed method generates high-fidelity channel samples and significantly enhances neural receiver performance in the target scenarios, outperforming conventional data augmentation and generative
adversarial network-based techniques.
Read the full abstract ▾
All authors Xingyu Zhou, Le Liang, Xinjie Li, Jing Zhang, Peiwen Jiang, Xiao Li, Shi Jin
Signal Processing · Cross-listed from cs.LG
Adapt under Attack and Domain Shift: Unified Adversarial Meta-Learning and Domain Adaptation for Robust Automatic Modulation Classification
Ali Owfi, Amirmohammad Bamdad, Tolunay Seyfi et al. (+1 more)
Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to
adversarial attacks and susceptibility to data distribution shifts hinder their practical deployment in real-world, dynamic environments. To address these threats, we propose a novel, unified framework that integrates meta-learning with domain adaptation, making AMC systems resistant to both
adversarial attacks and environmental changes. Our framework utilizes a two-phase strategy. First, in an offline phase, we employ a meta-learning approach to train the model on clean and adversarially perturbed samples from a single source domain. This method enables the model to generalize its defense, making it resistant to a combination of previously unseen attacks. Subsequently, in the online phase, we apply domain adaptation to align the model's features with a new target domain, allowing it to adapt without requiring substantial labeled data. As a result, our framework achieves a significant improvement in modulation classification accuracy against these combined threats, offering a critical solution to the deployment and operational challenges of modern AMC systems.
Read the full abstract ▾
All authors Ali Owfi, Amirmohammad Bamdad, Tolunay Seyfi, Fatemeh Afghah
Image and Video Processing · Cross-listed from stat.ML
Few-Shot Multimodal Medical Imaging: A Theoretical Framework
Md Talha Mohsin and Ismail Abdulrashid
Medical imaging often operates under limited labeled data, especially in rare disease and low resource clinical environments. Existing
multimodal and meta learning approaches improve performance in these settings but lack a theoretical explanation of why or when they succeed. This paper presents a unified theoretical framework for few shot
multimodal medical imaging that jointly characterizes sample complexity, uncertainty quantification, and interpretability. Using PAC learning, VC theory, and PAC
Bayesian analysis, we derive bounds that describe the minimum number of labeled samples required for reliable performance and show how complementary modalities reduce effective capacity through an information gain term. We further introduce a formal metric for explanation stability, proving that explanation variance decreases at an inverse n rate. A sequential
Bayesian interpretation of Chain of Thought
reasoning is also developed to show stepwise posterior contraction. To illustrate these ideas, we implement a controlled
multimodal dataset and evaluate an additive CNN MLP fusion model under few shot regimes, confirming predicted
multimodal gains, modality interference at larger sample sizes, and shrinking predictive uncertainty. Together, the framework provides a principled foundation for designing data efficient, uncertainty aware, and interpretable diagnostic models in low resource settings.
Read the full abstract ▾