Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Electrical Engineering and Systems Science

eess Watch Electrical Engineering and Systems Science

Sunday 10 May

Image and Video Processing

Annotation-free deep learning for detection and segmentation of fetal germinal matrix-intraventricular hemorrhage in brain MRI

Mingxuan Liu, Yingqi Hao, Yi Liao et al. (+17 more)

Prenatal germinal matrix-intraventricular hemorrhage (GMH-IVH) is a leading cause of infant mortality and neurodevelopmental impairment, yet its manual diagnosis and lesion segmentation on fetal brain MRI are labor-intensive and error-prone. Although supervised deep learning offers potential for automation, it typically requires large amounts of annotated GMH-IVH data, which are challenging to obtain for such a rare condition (0.5-0.9 per 1000 pregnancies). To address these problems, an annotation-free deep learning framework, FreeHemoSeg, was developed for automated detection and segmentation of GMH-IVH without any real patient annotations. Instead of learning from expert labels, FreeHemoSeg was trained on pseudo GMH-IVH images synthesized from normal fetal data guided by medical priors. The framework was evaluated in a retrospective multicentre study of 1,674 stacks of 2D T2-weighted MRI from 558 pregnant women, using data from one hospital for internal training and validation and two hospitals for external validation. FreeHemoSeg achieved the highest diagnostic and segmentation performance in both internal validation (AUROC: 0.959; AUPR: 0.928; sensitivity: 0.914; specificity: 0.966; DSC: 0.559) and external validation (AUROC: 0.930; AUPR: 0.884; sensitivity: 0.824; specificity: 0.943; DSC: 0.512), outperforming a supervised model trained on limited empirical data and unsupervised anomaly detection methods. Moreover, FreeHemoSeg assistance improved radiologists' sensitivity (from 0.882 to 0.941-1.000) and diagnostic confidence, while reducing interpretation time by 16.0-52.7%. We anticipate its immediate utility in supporting earlier diagnosis, prognostic counselling, and perinatal planning for fetal GMH-IVH. Code: https://github.com/Arktis2022/FreeHemoSeg.

Read the full abstract

All authors Mingxuan Liu, Yingqi Hao, Yi Liao, Juncheng Zhu, Haoxiang Li, Hongjia Yang, Yifei Chen, Yijin Li, Kasidit Anmahapong, Zihan Li, Jialan Zheng, Min Kang, Yan Song, Hua Lai, Xiaoling Zhou, Nan Sun, Rong Hu, Gang Ning, Haibo Qu, Qiyuan Tian

Audio and Speech Processing

RADAR Challenge 2026: Robust Audio Deepfake Recognition under Media Transformations

Hieu-Thi Luong, Xuechen Liu, Ivan Kukanov et al. (+2 more)

RADAR Challenge 2026 is an APSIPA Grand Challenge on Robust Audio Deepfake Recognition under Media Transformations, designed to simulate realistic media conditions in real-world audio distribution pipelines, including compression, resampling, noise, and reverberation. It consists of two phases: an English development phase with labeled data for analysis and paper writing, and a multilingual evaluation phase containing more than 100,000 utterances in English, Singapore English, Mandarin Chinese, Taiwanese Mandarin, Japanese, and Vietnamese. Systems are evaluated using equal error rate (EER) for binary real/fake classification. This paper describes the challenge task, the construction of the data set, the evaluation protocol, and the overall results. During the challenge, 33 teams submitted to the development phase and 22 teams submitted to the final evaluation phase. The reported results highlight the remaining challenges of robust audio deepfake detection under multilingual and media-transformed conditions.

Read the full abstract

All authors Hieu-Thi Luong, Xuechen Liu, Ivan Kukanov, Zheng Xin Chai, Kong Aik Lee

Systems and Control

PolarNet: Single-Minima Neural Network for Modeling Lyapunov Functions

Yuan Zhong, Jiaxin Cheng, Hefu Ye et al. (+1 more)

Learning control strategies with provable stability guarantees continues to be a challenging problem. In this work, we examine a family of training-time behaviors exhibited by existing neural Lyapunov control methods under specific conditions, which can hinder the synthesis of a provably stable controller. We identify the root cause as the lack of neural network architectural guarantees on the learned Lyapunov function, and propose PolarNet, a network architecture that provably addresses these issues by structurally guarantee to have a single critical point. We provide theoretical guarantee regarding the properness and universality of PolarNet for modeling Lyapunov functions, and show that using it as a drop-in replacement in existing neural Lyapunov control methods can effectively circumvent particular difficulties in training. We conduct a set of numerical experiments to verify that PolarNet consistently maintains a single critical point and, when used as a drop-in replacement in existing neural Lyapunov control methods, successfully avoids training failures caused by the lack of architectural guarantees. The code of this paper is available at https://github.com/23-zy/PolarNet.

Read the full abstract

All authors Yuan Zhong, Jiaxin Cheng, Hefu Ye, Yicong Zhou

Systems and Control · Cross-listed from math.OC

Diagnostic Certificates of Data Quality and Regression Identifiability for Koopman Identification

Yue Wu

Classical persistent excitation criteria usually assess whether an input or regressor signal is sufficiently rich. In Koopman and EDMD with control (EDMDc), however, data quality is determined by the concatenation of lifted state features and control inputs. Input-rich data can still visit a narrow state region, well-spread state samples can still produce degenerate lifted features, and both can fail to condition the final regression problem. This paper develops a diagnostic certificate framework for locating these failures. The certificates separate state-space coverage and clustering, lifted-feature nondegeneracy, and the final regression spectrum. The regression-spectrum certificate is the layer with direct theoretical guarantees: it controls the active standardized design's smallest singular value, has Fisher-information and one-step EDMDc stability interpretations, and admits a finite-sample lower bound under a population spectral gap. We also give structural examples and a Schur-complement condition showing why state, lifted, input, and regression diagnostics cannot be substituted for one another. As a sampling example, IGPE-DOPT uses these certificates to score candidate trajectory segments. Experiments on Duffing, Van der Pol, and Lorenz systems compare input-, state-, lifted-, and regression-oriented baselines. The results show that certificate layers separate, budget and weights shift bottlenecks, and downstream prediction or control performance is not monotone in any single certificate. The framework is therefore intended as an interpretable diagnostic and data-collection guide, not as a universal optimality claim.

Read the full abstract

Systems and Control

Risk-Aware Safe Throughput Forecasting for Starlink Networks

Hongjun Xie, Chao Zhang, Pengcheng Luo et al. (+4 more)

As a representative low Earth orbit (LEO) broadband system, Starlink exhibits highly variable access throughput, making short-term forecasting essential for network resource management. Existing forecasting methods mainly optimize symmetric point-prediction metrics such as MAE and RMSE, but they do not explicitly control the asymmetric risk of overestimating future throughput, which can cause over-admission, bandwidth overbooking, and service violations. This paper formulates Starlink throughput prediction as a risk-budgeted safe forecasting problem, where the predictor must satisfy a prescribed overestimation budget while maintaining competitive accuracy. We propose Budget-Guided Coarse-to-Fine Quantile Selection (BG-CFQS), a data-driven framework that trains a family of lower-quantile predictors, locates the quantile boundary satisfying the risk budget, and refines the boundary region to select the most accurate feasible predictor. Experiments on three real-world Starlink throughput datasets show that BG-CFQS satisfies the risk budget on all datasets and achieves the lowest average MAE, mean positive error, and tail positive error among budget-feasible methods. In high-risk and severe-risk low-throughput regimes, BG-CFQS reduces harmful positive errors by 11.0% and 12.6%, respectively. An admission-control evaluation further shows that the proposed safe forecasts reduce dropped sessions, demonstrating that risk-aware forecasting can translate prediction safety into application-level benefits.

Read the full abstract

All authors Hongjun Xie, Chao Zhang, Pengcheng Luo, Zenghui Zhang, Genke Yang, Xiaojuan Zhang, Boon-Hee Soong

Image and Video Processing

ML-CLIPSim: Multi-Layer CLIP Similarity for Machine-Oriented Image Quality

Feng Ding, Haisheng Fu, Jie Liang et al. (+3 more)

We study full-reference image quality assessment from a machine-centric perspective, where images are evaluated by how well they preserve information for downstream models. We formulate machine-oriented quality as a latent machine utility and approximate it through pairwise predictive-consistency comparisons. To this end, we construct PCMP, a dataset of PSNR-matched distortion pairs labeled by consistency votes from multiple pretrained models. We further propose ML-CLIPSim, a differentiable quality metric built on a frozen CLIP visual encoder, which aggregates intermediate patch-token similarities and global image embeddings. Experiments on machine-preference benchmarks, human-IQA datasets, and learned image compression show that ML-CLIPSim better aligns with machine-oriented preferences than conventional fidelity and perceptual metrics, while remaining competitive for human quality prediction. Used as a compression distortion term, it improves rate–task trade-offs across multiple downstream tasks.

Read the full abstract

All authors Feng Ding, Haisheng Fu, Jie Liang, Qihan Xu, Siyu Zhu, Jingning Han

Systems and Control · Cross-listed from math.OC

Barrier Certificates for Uncertain Temporal Specifications

Mohammad H. Mamduhi and Sadegh Soudjani

This paper studies satisfying temporal logic specifications on stochastic dynamical systems, where the predicates evolve randomly over time. Such randomness may arise from uncertain environment models or external stochastic processes causing the sets associated with predicate satisfaction to vary in a non-deterministic manner. As a result, verifying whether a stochastic dynamical system satisfies a temporal specification depends also on the uncertainty in the predicates. We develop a certificate-based framework to bound the probability of satisfying temporal logic specifications with randomly evolving predicates. We first show that temporal logic specifications with stochastic predicates can be transformed to specifications with deterministic predicates on an augmented space which is extended to include the stochastic space of predicate's uncertainty. We then utilize barrier certificates on an augmented space to provide tractable optimization-based conditions and to avoid the computational burden of dynamic programming. Focusing on linear dynamics and safety-type specifications, we derive analytical conditions under which barrier certificates guarantee bounds on the probability of violating the stochastic safety predicates. The approach is demonstrated on numerical case studies.

Read the full abstract

Audio and Speech Processing

Evaluating the Expressive Appropriateness of Speech in Rich Contexts

Tianrui Wang, Ziyang Ma, Yizhou Peng et al. (+26 more)

Evaluating expressive speech remains challenging, as existing methods mainly assess emotional intensity and overlook whether a speech sample is expressively appropriate for its contextual setting. This limitation hinders reliable evaluation of speech systems used in narrative-driven and interactive applications, such as audiobooks and conversational agents. We introduce CEAEval, a Context-rich framework for Evaluating Expressive Appropriateness in speech, which assesses whether a speech sample expressively aligns with the underlying communicative intent implied by its discourse-level narrative context. To support this task, we construct CEAEval-D, the first context-rich speech dataset with real human performances in Mandarin conversational speech, providing narrative descriptions together with fifteen dimensions of human annotations covering expressive attributes and expressive appropriateness. We further develop CEAEval-M, a model that integrates knowledge distillation, planner-based multi-model collaboration, adaptive audio attention bias, and reinforcement learning to perform context-rich expressive appropriateness evaluation. Experiments on a human-annotated test set demonstrate that CEAEval-M substantially outperforms existing speech evaluation and analysis systems.

Read the full abstract

All authors Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Wei Yang, Zhongqian Sun, Haifeng Hu, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

Signal Processing

Subsurface Propagation Characteristics of Medium-Wave Electromagnetic Fields Revealed by Measurements in the Nanatsuo-guchi Quarry: Conceptual Framework of the Subground Wave and the Rainfall Model

Eiichi Shoji

This paper presents field observations of medium-wave (MW; 300 kHz-3 MHz) radio signals propagating in the subsurface rock environment of the Nanatsuo-guchi quarry, an underground Shakudani Ishi excavation site on Mt. Asuwayama in Fukui City, Japan. MW broadcast signals from a nearby local station (JOFG, 927 kHz, 5 kW), received mainly as a surface wave, and from a distant station (JOAB, 693 kHz, 500 kW), received via ionospheric reflection, were successfully received deep inside the quarry, whereas very-high-frequency frequency-modulated (FM) broadcast signals attenuated rapidly and became undetectable near the entrance. This contrasting behavior highlights the strong wavelength dependence of electromagnetic-wave propagation in subsurface environments. Two-axis rotation measurements were performed using loop antennas to analyze the arrival direction and angular dependence of the received signals. In addition to the horizontal magnetic field component (Hx), dominant near the ground surface, a vertical magnetic field component (Hz) was consistently observed inside the quarry. The relative contribution of Hz increased with depth and was accompanied by systematic variations in the apparent arrival direction. Inclination measurements further revealed a characteristic minimum in reception sensitivity near 40-50 degrees, suggesting a composite magnetic field structure involving both Hx and Hz. These observations cannot be fully explained by conventional surface-wave propagation models based on the Zenneck-Sommerfeld formulation, and instead suggest the formation of a characteristic electromagnetic field structure under subsurface boundary conditions. This study provides experimental evidence for previously unreported MW field behavior in underground spaces and offers new perspectives for subsurface communication and disaster-resilient information systems.

Read the full abstract

Audio and Speech Processing

Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech

Dong Yang, Yiyi Cai, Haoyu Zhang et al. (+2 more)

Metric-induced discrete flow matching (MI-DFM) exploits token-latent geometry for discrete generation, but its practical use is limited by two issues: heuristic schedulers requiring hyperparameter search, and finite-step path-tracking error from its first-order continuous-time Markov chain (CTMC) solver. We address both issues. First, we derive a kinetic-optimal scheduler for prescribed scalar-parameterized probability paths, and instantiate it for MI-DFM as a training-free numerical schedule that traverses the path at constant Fisher-Rao speed. Second, we introduce a finite-step moment correction that adjusts the jump probability while preserving the CTMC jump destination distribution. We validate the resulting method, GibbsTTS, on codec-based zero-shot text-to-speech (TTS). Under controlled comparisons with a unified architecture and large-scale dataset, GibbsTTS achieves the best objective naturalness and is preferred in subjective evaluations over masked discrete generative baselines. Additionally, in comparison with the evaluated state-of-the-art TTS systems, GibbsTTS shows strong speaker similarity, achieving the highest similarity on three of four test sets and ranking second on the fourth. Project page: https://ydqmkkx.github.io/GibbsTTSProject

Read the full abstract

All authors Dong Yang, Yiyi Cai, Haoyu Zhang, Yuki Saito, Hiroshi Saruwatari

Systems and Control

A Stochastic Hybrid Automaton for Smartphone Battery Dynamics: Electro-Thermal Coupling and First-Passage Time-to-Empty Estimation

Xiaoyang Li and Runni Zhou

Smartphone time-to-empty (TTE) is difficult to predict because shutdown is governed not only by remaining charge, but also by instantaneous power capability under temperature-, aging-, and load-dependent voltage sag. We develop a stochastic hybrid automaton for smartphone battery dynamics that couples a first-order Thevenin equivalent-circuit model with a lumped thermal model and a stochastic user-activity process. The continuous state includes state of charge, polarization voltage, and battery temperature; user behavior is represented as a piecewise deterministic Markov process switching among idle, social/web, video, gaming, and weak-signal modes. Shutdown is formulated as a first-passage event when terminal voltage crosses a cutoff threshold or when requested power exceeds the instantaneous feasibility envelope. The model captures a voltage-collapse mechanism that simple Coulomb-counting or linear discharge models miss: cold temperature or battery aging increases internal resistance, so high-power bursts can drive terminal voltage below cutoff even when substantial charge remains. Monte Carlo simulation yields a full TTE distribution rather than a single countdown, allowing lower-tail risk to be quantified by the 5th percentile. Sensitivity analysis identifies ambient temperature, internal resistance, weak-signal radio penalty, and screen brightness as major drivers of premature shutdown risk. These results motivate practical user guidance and an operating-system-level resistance-aware throttling policy that limits peak power in the power-limited regime. The framework provides a physically grounded, risk-aware approach for explaining and extending usable smartphone battery life under real-world uncertainty.

Read the full abstract

Systems and Control

Transceiver-Integrated BD-RIS: Wave-Domain Signal Processing for Sustainable and Inclusive 6G

Mahmoud Raeisi, Ayoub Ammar Boudjelal, Henk Wymeersch et al. (+2 more)

The shift toward sixth-generation (6G) wireless communications demands transceiver architectures that simultaneously support high-data-rate communications, pervasive sensing, and sub-meter-level localization. Beyond these performance targets, 6G systems are also expected to align with long-term societal goals, including sustainability and inclusiveness. Conventional radio designs, however, remain heavily reliant on digital baseband processing, whose cost, power consumption, and computational complexity scale unfavorably with increasing array size and carrier frequency, making them poorly aligned with these emerging requirements. Beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) introduce a new paradigm by enabling direct manipulation of electromagnetic waves in the analog domain. This article presents BD-RIS as a wave-domain analog processing unit embedded within the transceiver aperture. By migrating linear signal processing functions from the digital baseband to the wave domain, BD-RISs significantly reduce computational load and energy consumption, enabling scalable and sustainable operation for extra-large antenna array systems. Owing to their ability to jointly provide high operational flexibility, modularity, and energy-efficient analog processing, transceiver-integrated BD-RISs offer a compelling architectural trade-off and emerge as a strong candidate for next-generation wireless transceivers.

Read the full abstract

All authors Mahmoud Raeisi, Ayoub Ammar Boudjelal, Henk Wymeersch, Ertugrul Basar, Huseyin Arslan

Systems and Control · Cross-listed from math.OC

Mutual Information Optimal Density Control of Linear Systems and Generalized Schrödinger Bridges with Reference Refinement

Shoju Enami and Kenji Kashima

We consider a mutual information (MI) regularized optimal density control of a discrete-time linear system. MI optimal control has been utilized for exploration in reinforcement learning and privacy protection in control. MI regularization induces stochasticity in the policy, which poses challenges for applications of MI optimal control in safety-critical scenarios. To remedy this situation, we impose Gaussian density constraints at specified times to directly control state uncertainty. For this MI optimal density control problem, we propose an alternating optimization algorithm and investigate its convergence properties. In addition, we reveal a relationship between the MI optimal density control problem and a so-called generalized Schrödinger bridge problem associated with the discrete-time linear system. Based on the results of MI optimal density control and this relationship, we also investigate alternating optimization for the Schrödinger bridge problem and its convergence properties.

Read the full abstract

Systems and Control

Price Distortions in Korea's Electricity Market: Barriers to Renewable Integration and Reform Pathways

Ryungyeong Lee, Minhan Yoon and Hunyoung Shin

Structural distortions in price signals within the Korean electricity market, governed by a cost-based pool (CBP) and a uniform pricing mechanism, fundamentally undermine the nation's energy transition goals. The current market design fails to reflect transmission constraints, real-time supply and demand dynamics, and generator-specific costs, leading to inefficient resource allocation and hindering long-term investments in renewable energy and grid flexibility. This paper identifies the key drivers of these distortions and proposes a holistic reform package to enhance market efficiency. The package includes four key reforms: \stepcounter{excep}(\roman{excep}) introducing a locational marginal pricing system to manage transmission constraints; \stepcounter{excep}(\roman{excep}) establishing a real-time market to reflect temporal value; \stepcounter{excep}(\roman{excep}) integrating market and system operations to resolve inconsistencies; and \stepcounter{excep}(\roman{excep}) transitioning from CBP to a price-based bidding system. Each reform targets a distinct source of inefficiency. The broader contribution of this study, however, lies in showing that, under the current Korean market design, the market cannot readily provide effective price signals. These reforms therefore need to be implemented jointly to establish a coherent market design in which price signals are aligned with Korea's energy policy objectives.

Read the full abstract

Signal Processing

Bootstrap-Based Receiver Synchronization and System Discovery in B2X: An Extension of ATSC 3.0

Raj Kumar Thenua, Essam Sourour, David Starks et al. (+3 more)

Addressing the increasing and diversified demands of multicast and broadcast services require highly efficient multicast and broadcast technologies. Broadcast networks, such as Advanced Television Systems Committee 3.0 (ATSC 3.0), are inherently designed to support these services and continue to evolve to meet growing performance and scalability requirements. At the same time, smartphones are increasingly used for video streaming and other high-volume services, placing growing pressure on mobile network capacity. Interworking between broadcast and mobile networks is therefore an important enabler for efficient and seamless service delivery. In this context, Broadcast-to-Everything (B2X) extends ATSC 3.0 to support enhanced interoperability with Third Generation Partnership Project (3GPP) mobile systems while maintaining low cross-correlation with ATSC 3.0 bootstrap signals, supporting reliable system identification in scenarios where multiple waveforms may be present. Bootstrap signaling, which enables initial signal detection and synchronization, is a key feature of ATSC-based waveform discovery and synchronization, and B2X further extends this capability through a scalable bootstrap framework supporting a range of bandwidth configurations. This paper investigates system discovery through bootstrap signal detection at the B2X receiver and presents key design-related findings, including parameter selection and cross-testing with ATSC 3.0. We present extensive simulations of the receiver performance under diverse propagation and mobility conditions, ranging from stationary to high-speed scenarios. The results demonstrate the robustness of the B2X bootstrap signaling design across a broad range of channel conditions relevant to multicast and broadcast operation.

Read the full abstract

All authors Raj Kumar Thenua, Essam Sourour, David Starks, Rashmi Kamran, Michael Simon, Kumar Appaiah

Image and Video Processing · Cross-listed from cs.GR

CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting

Daheng Yin, Yili Jin, Jianxin Shi et al. (+7 more)

Volumetric video (VV) streaming enables real-time, immersive access to remote 3D environments, powering telepresence, ecological monitoring, and robotic teleoperation. These applications turn VV streaming into a real-time interface to remote physical environments, imposing new system-level demands for photorealistic scene representation, low-latency interaction, and robust performance under heterogeneous networks. 3D Gaussian Splatting (3DGS) has been widely used for real-time photorealistic rendering, offering superior visual quality and rendering performance, but it faces challenges due to bandwidth consumption. Furthermore, as the foundation of adaptive VV streaming, existing Levels of Detail (LoD) methods based on density are not well-suited to Gaussian representations, leading to visible gaps and severe quality degradation. Recent studies have also explored attribute compression techniques to reduce bandwidth consumption. Our preliminary studies reveal that aggressive attribute compression primarily causes color distortion, which can be effectively corrected in the rendered image using a reference image. Motivated by these findings, we propose a novel Color-Adaptive scheme for adaptive VV streaming that uses vector quantization (VQ) to establish LoDs and correct color distortions with low-resolution reference images. We further present CAGS, an adaptive VV streaming system compatible with diverse Gaussian representations, which integrates the Color-Adaptive scheme by rendering reference images on the streaming server and performing color restoration on the client. Extensive experiments on our prototype system demonstrate that CAGS outperforms the existing adaptive streaming systems in PSNR by 5$\sim$20 dB under fluctuating bandwidth, operates significantly faster than existing scalable Gaussian compression methods, and generalizes across different Gaussian representations.

Read the full abstract

All authors Daheng Yin, Yili Jin, Jianxin Shi, Isaac Ding, Miao Zhang, Fangxin Wang, Zhaowu Huang, Cong Zhang, Jiangchuan Liu, Fang Dong

Systems and Control · Cross-listed from physics.med-ph

Moving MRI: Imaging a moving body with a moving magnet

Jingting Yao, Artan Kaso, Nikhil Patel et al. (+4 more)

Current magnetic resonance imaging (MRI) requires the subject to remain stationary to limit motion artifacts and avoid unwanted field-induced brain stimulation. However, imaging during large-scale motion could enable studies in which motion itself is central. One example is the study of brain networks involved in vestibular function, which senses head motion. Here, we demonstrate Moving MRI (mMRI), a system that enables imaging during large-scale motion by moving the subject and scanner together to minimize relative motion. We implemented a proof-of-concept platform using a compact, cryogen-free superconducting magnet mounted on a pneumatically actuated tilt mechanism that moves the magnet, gradients, and RF coil as a unit during scanning. Phantom and in vivo rat brain scans were acquired during repetitive tilting. We characterized artifacts arising from tilt-induced field shifts and residual subject-scanner motion, and partially reduced these effects. mMRI enables imaging during large-scale movement and may broaden access to naturalistic vestibular paradigms while providing a foundation for future human systems.

Read the full abstract

All authors Jingting Yao, Artan Kaso, Nikhil Patel, Yin-Ching Iris Chen, Andre van der Kouwe, Daniel M. Merfeld, Jerome L. Ackerman

Image and Video Processing

Cross-Modal Semantic-Enhanced Diffusion Framework for Diabetic Retinopathy Grading

Yiqun Wang

Automated grading of diabetic retinopathy (DR) faces several critical challenges: subtle inter-grade visual distinctions in fine-grained lesion patterns, distributional discrepancies induced by heterogeneous imaging devices and acquisition conditions, and the inherent inability of purely visual approaches to exploit clinical semantic knowledge. In this paper, we propose CLIP-Guided Semantic Diffusion (CGSD), a DR grading framework that synergistically integrates vision-language pretraining with diffusion probabilistic modeling. We adopt a domain-specific vision-language model tailored for DR grading as the semantic guidance module and adapt it to the target domain via Low-Rank Adaptation (LoRA), effectively bridging the distributional gap between the pretrained model and the target dataset with only a minimal number of trainable parameters. Building on this foundation, we construct a cross-modal semantic conditioning vector by computing the dot product between image features and the text description features of each DR grade, yielding a joint representation that simultaneously encodes visual content and clinical-grade semantics. This vector serves as the conditioning signal for the diffusion denoising network, replacing the structurally complex dual-branch visual prior employed in existing diffusion-based classification methods. Experiments on the APTOS 2019 dataset demonstrate that the proposed approach achieves an accuracy of 87.5% and a macro-averaged F1 score of 0.731, outperforming a variety of representative methods. Ablation studies further validate the independent contribution of each constituent module.

Read the full abstract

Saturday 9 May

Signal Processing

Learning Displacement-Aware WiFi Representations for Weakly Supervised Relative Localization

Tzu-Ti Wei, Po-Cheng Chen, Yu-Chee Tseng et al. (+1 more)

WiFi fingerprint-based indoor localization has been widely studied, but most existing approaches focus on absolute positioning and rely on dense coordinate annotations, which are costly to obtain at scale. In this paper, we study a fundamentally different problem: relative localization, where the goal is to directly estimate the displacement between two WiFi fingerprint traces without predicting their absolute positions. To reduce annotation overhead, we adopt weak supervision in the form of stepwise motion vectors obtained from inertial sensing. We propose Intersection Pathway (IP), a cross-modal learning framework that aligns fingerprint traces (f-traces) and displacement traces (d-traces) in a shared latent space. The key idea is to enforce an additive structure in the latent space, such that latent addition and subtraction correspond to physical motion composition, enabling direct relative-displacement inference. Experiments on a synthesized dataset derived from real measurements demonstrate that the proposed method learns displacement-aware WiFi representations and achieves accurate relative localization across varying displacement ranges. Furthermore, the learned model can be extended to few-shot absolute localization with sparse anchors.

Read the full abstract

All authors Tzu-Ti Wei, Po-Cheng Chen, Yu-Chee Tseng, Jen-Jee Chen

Signal Processing

PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation

Xiaoda Wang, Minxiao Wang, Kaiqiao Han et al. (+10 more)

Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring. Photoplethysmography (PPG) is ubiquitous in wearables but lacks ECG-specific diagnostic morphology and is corrupted by motion and sensor noise. PPG-to-ECG generation aims to bridge this gap by recovering electrical morphology and timing from peripheral pulse signals. However, existing methods largely rely on statistical alignment and data-driven generation. They fail to explicitly structure the latent space around physiology-aware electro-hemodynamic factors and lack constraints from forward physiological dynamics. To address these challenges, we propose PG-LRF, a physiology-guided latent rectified flow framework. PG-LRF introduces an electro-hemodynamic simulator that co-models ECG and PPG through shared cardiac phase dynamics. Guided by this simulator, a Physiology-Aware AutoEncoder learns a structured electro-hemodynamic latent space. Then we integrate this simulator guidance into a PPG-conditioned latent rectified flow, enforcing ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. Experiments on the large-scale MC-MED dataset demonstrate that PG-LRF significantly improves PPG-to-ECG generation and downstream cardiovascular disease classification, proving its ability to generate ECGs that are both signal-faithful and physiologically plausible under the ECG-to-PPG hemodynamic pathway

Read the full abstract

All authors Xiaoda Wang, Minxiao Wang, Kaiqiao Han, Defu Cao, Ching Chang, Yidan Shi, Runze Yan, Xiao Luo, Yan Liu, Xiao Hu, Yizhou Sun, Wei Wang, Carl Yang

Image and Video Processing

Streaming of rendered content with adaptive frame rate and resolution

Yaru Liu, Joseph G. March and Rafal K. Mantiuk

Streaming rendered content is an attractive way to bring high-quality graphics to billions of mobile devices that do not have sufficient rendering power. Existing solutions render content on a server at a fixed frame rate, typically 30 or 60 frames per second, and reduce resolution when bandwidth is restricted. However, this strategy leads to suboptimal rendering quality under the bandwidth constraints. In this work, we exploit the spatio-temporal limits of the human visual system to improve perceived quality while reducing rendering costs by adaptively adjusting both frame rate and resolution based on scene content and motion. Our approach is codec-agnostic and requires only minimal modifications to existing rendering infrastructure. We propose a system in which a lightweight neural network predicts the optimal combination of frame rate and resolution for a given transmission bandwidth, content, and motion velocity. This prediction significantly enhances perceptual quality while minimizing computational cost under bandwidth constraints. The network is trained on a large dataset of rendered content labeled with a perceptual video quality metric. The dataset and further information can be found at the project web page: https://www.cl.cam.ac.uk/research/rainbow/projects/adaptive_streaming/.

Read the full abstract

Image and Video Processing · Cross-listed from cs.CV

Establishing Robust Retinal Eye Tracking: A Weakly Supervised Algorithmic Framework

Bo Wen, Dillon Lohr, Yatong An et al. (+8 more)

Retinal image-based eye tracking is widely used in ophthalmic imaging and vision science, and is a promising path to deliver higher gaze accuracy than the pupil- and cornea-based approaches commonly used in modern AR/VR devices. Nevertheless, existing retinal tracking algorithms still primarily rely on classical template-matching registration, which can be insufficiently robust to retinal feature variability and real-world imaging conditions. In this work, we propose a novel weakly-supervised, learning-based framework for robust retinal eye tracking. Initial studies demonstrate high accuracy, achieving the 95th-percentile gaze error < 0.45 deg across a cohort of 6 participants.

Read the full abstract

All authors Bo Wen, Dillon Lohr, Yatong An, Pushkar Anand, Alexander Fix, Ruobing Qian, Catherine A.Fromm, Yimin Ding, Truong Nguyen, Mohamed El-Haddad, Francesco La Rocca

Signal Processing

An Open-Source Framework for Coupled Vehicle-Bridge Interaction Analysis Using OpenSees

Mohammad Talebi-Kalaleh and Qipei Mei

Vehicle-bridge interaction (VBI) is important for simulating bridge response under moving vehicular loads and supports applications such as dynamic amplification studies, weigh-in-motion, and indirect bridge monitoring. Although VBI theory is well established, many existing implementations use custom finite element code or research-specific solvers, which limits their reuse. This paper presents an open-source Python framework for VBI analysis built on OpenSees. The bridge and vehicle are modeled as separate OpenSees subsystems and connected through an iterative scheme that exchanges displacement and force values at each time step until convergence. Five vehicle model types are supported, from a single axle spring-mass system to two-axle composite half-cars with body pitch and separate tyre and suspension elements. A decoupled mode is also provided: the vehicle static weight is applied as a moving load on the bridge, and the resulting bridge motion is then used as base excitation for the vehicle. Validation against three published benchmarks (quarter-car, half-car with pitch, and full composite models) shows close agreement, with R2 above 0.998 in all cases. A parametric study reports the accuracy of the decoupled mode as a function of vehicle-to-bridge mass ratio, span length, speed, road roughness class, and background traffic density, and indicates when the decoupled mode is adequate and when full coupling is needed. The complete framework and benchmark configurations are released as open-source software to support reproducible research in vehicle-bridge dynamics.

Read the full abstract

Systems and Control

Data-Driven Inverse Reinforcement Learning of Linear Systems with Model Uncertainty: A Convex Optimization View

Duc Cuong Nguyen and Phuong Nam Dao

Inverse reinforcement learning (IRL) for linear systems seeks a cost function whose optimal controller reproduces an expert policy from data. Existing data-driven methods for discrete-time linear systems are largely built on iterative policy/value updates, repeated matrix inversions, and, in some cases, an initial stabilizing controller, which can limit numerical robustness and practical applicability. This paper develops a convex-optimization framework for data-driven inverse reinforcement learning of discrete-time linear systems with model uncertainty. For nominal systems, we derive a semidefinite characterization of inverse optimality and a relaxed formulation that recovers an equivalent state-cost matrix together with a stabilizing controller from expert trajectories. We then obtain a model-free, off-policy reformulation by replacing the unknown system matrices with a regressed kernel matrix identified from local input–state data. For uncertain local systems, we show that a standard LQR cost is generally insufficient to represent every stabilizing target gain and therefore introduce a generalized LQR cost with a state–input cross term. Based on this model, we develop a convex data-driven inverse-RL method and extend it to robust cost design over a population of perturbations via differentiable semidefinite programming and stochastic approximation. Simulations on a discrete-time power-system example show accurate recovery of expert behavior, improved robustness to gain-estimation error and model mismatch, and a simpler computational pipeline than classical iterative inverse-RL schemes.

Read the full abstract

Systems and Control

Fault-Aware MPC for Robotic Fleet Communications Scheduling

Carlo Schreiber, Duncan Eddy and Mykel J. Kochenderfer

Operating a fleet of remote robotic systems with intermittent communications requires scheduling limited contact opportunities to maintain fleet health awareness, complete mission objectives, and intervene on faulted assets before their permanent loss. This scheduling problem is complicated by observational ambiguity: when an asset fails to check in, the operator cannot distinguish between a lethal hardware fault and a benign communications failure. If the system's failure modes are structured through a fault model, a scheduler can exploit mode-specific lethality, timing, and recoverability properties to prioritize correctly - but only if it can distinguish between modes that produce identical observations under standard actions. We present Interacting Multiple Model Model Predictive Control (IMM-MPC), a receding-horizon framework that maintains a probabilistic belief over discrete fault modes with time-inhomogeneous dynamics and optimizes a two-term objective coupling acquisition value with information gain. We characterize when observationally aliased fault modes can be disambiguated through scheduled actions and when aliasing is permanently unresolvable. Applied to satellite launch and early orbit communications scheduling, IMM-MPC recovers 59.8% of spacecraft experiencing lethal-faults versus 9.0% for binary-MPC and 2.0% for a bipartite graph-based formulation solved through matching. These results hold across 200 randomized trials, while maintaining identical acquisition of healthy satellites and near-identical solve times.

Read the full abstract

Systems and Control · Cross-listed from econ.EM

Engineering Economy: A New Paradigm for Escaping the Middle-Income Trap

Mustafa Ergen

This paper introduces the concept of Engineering Economy as a new paradigm for understanding and managing macroeconomic policy in middle-income countries seeking to escape the middle-income trap. Drawing on Turkiye's post-2001 economic trajectory and South Korea's successful transition from a low-income to a high-income economy, the study argues that conventional frameworks whether the Washington Consensus's market liberalization prescriptions or the institutionalist critique alone are insufficient. Instead, it proposes treating the economy as a dynamic control system requiring continuous calibration rather than static equilibrium. The paper develops a road-surface metaphor (highway, side-road, off-road) to characterize different global economic regimes and presents eleven interconnected policy pillars spanning venture capital formation, regulatory sandboxes, technology-focused industrial policy, and human capital development. By synthesizing insights from endogenous growth theory (Romer), institutional economics (Acemoglu), the catching-up literature (Lee), cybernetic systems theory (Wiener), and Schumpeterian creative destruction, the framework reconceptualizes macroeconomic instruments through control-engineering analogies: interest rates as energy gradients, fiscal policy as energy flow, exchange rates as balance motors, and regulation as adaptive suspension. The analysis demonstrates that Turkiye's structural challenge is not merely institutional weakness but a systemic absence of R&D demand from its dominant enterprise structures, creating a vicious cycle that conventional reforms cannot break. Seven specific opportunity windows arising from US-China technological rivalry are identified, and a phased implementation roadmap is proposed.

Read the full abstract

Systems and Control

Transfer Learning of Multiobjective Indirect Low-Thrust Trajectories Using Diffusion Models and Markov Chain Monte Carlo

Jannik Graebner and Ryne Beeson

Preliminary low-thrust spacecraft mission design is a global search problem characterized by a complex solution landscape, multiple objectives, and numerous local minima. During this phase, mission parameters are often not yet fully defined, requiring new solutions to be generated at a high cadence across varying parameter values. When combined with the indirect approach to optimal control, diffusion models can accelerate this search by learning distributions that represent high-quality initial costates. However, generating training data remains expensive, and opportunities exist to better exploit past data. We propose a transfer-learning framework that combines homotopy in a mission parameter with Markov chain Monte Carlo (MCMC) to generate training data more efficiently. The approach reformulates a multiobjective optimization problem as sampling from an unnormalized target distribution in costate space. We compare three MCMC algorithms on a planar multi-revolution transfer in the circular restricted three-body problem, with homotopy in the system mass parameter. The results show that gradient-based MCMC variants achieve the best trade-off between sample quality and computational cost. For the test transfer, the proposed framework generates 40 % more feasible solutions and achieves a higher-quality Pareto front than a state-of-the-art indirect approach based on adjoint control transformations and gradient-based optimization. Finally, the MCMC-generated samples are used to fine-tune a diffusion model conditioned on the mass parameter, enabling it to learn a global representation of the underlying solution distribution and efficiently generate new solutions. These findings establish the transfer-learning framework as a practical method for efficiently solving indirect trajectory optimization problems with varying parameters.

Read the full abstract

Systems and Control · Cross-listed from cs.RO

HyDRA Scorpion: A Cost-effective and Modular ROV for Real-Time Underwater Inspection, Intervention, and Object Detection

Anika Tabassum Orchi, Md Farhan Zaman, Md Darain Khan et al. (+16 more)

A Remotely Operated Vehicle (ROV) is a tethered underwater robot used for tasks like inspection and intervention. While essential tools for underwater science, the high cost of commercial ROVs and a persistent gap between mechanically capable platforms and those with integrated intelligence create a significant barrier to access. HyDRA Scorpion differs from conventional systems by addressing these challenges, integrating an advanced, AI-driven perception stack with in-situ measurement capabilities onto a low-cost, locally manufacturable platform. The system combines 4-DoF maneuverability, dual manipulators, and a custom pressure-tested housing. Experimental results validate the system's robustness and performance. Leak-free operation was confirmed through prolonged pressure testing of the electronics housing to 4 bar, equivalent to the pressure of a 304.8-meter water depth approximately in a simulated environment, with no moisture ingress detected. The vehicle also demonstrated stable station-keeping, maintaining its position within a tight tolerance of $$\pm$0.15$ meters under external disturbances. The onboard AI module achieved underwater object detection mean Average Precision (mAP) of 0.89 with real-time inference, length and 3D-mapping based distance measurement. Also, 4-DoF manipulator arm can grip and maintain dual-function manipulator feature which support 360 degree tangle-free rotation.

Read the full abstract

All authors Anika Tabassum Orchi, Md Farhan Zaman, Md Darain Khan, Md Alamgir, Mahbubul Islam, Md. Jobayer Rahman, A. M. Zayed Abdullah, Md Mehrab Hossain Khan, Md. Kutub Al Baki, Iftekharul Islam, Shakil Ahmed, Md Sadique Hossain, Md Muzahidul Islam, Shah Mohammad Seaman, Nusrat Jahan Piyal, Shekh Md. Saifur Rahman, Fahim Hafiz, A.K.M. Muzahidul Islam, M. Rezwan Khan

Image and Video Processing · Cross-listed from physics.med-ph

Combined Diffusion-Relaxation MRI to Assess Muscle Microstructure and Composition

Matteo Figini, Paddy J. Slator, Valeria E. Contarino et al. (+3 more)

Quantifying muscle tissue properties is crucial for understanding pathophysiological changes occurring in skeletal muscle (SM). In particular, T2 relaxation and diffusion MRI (dMRI) are promising techniques. However, typical methods measure T2 and diffusion separately, making them less specific to microstructure than emerging combined diffusion-relaxation techniques. Here we demonstrate a combined diffusion-relaxation MRI approach for disentangling T2 and diffusivity properties in SM. A diffusion-relaxation acquisition was implemented on a 3 T scanner, combining six b-values and four echo times within a 12-min single-slice protocol. Five healthy participants were enrolled. Data were analysed with six microstructural diffusion and diffusion-relaxation models. Mean parameter values were extracted from manually segmented calf muscles. Models neglecting T2 relaxation showed strong TE dependence: mean diffusivity (MD) decreased by up to 47%, fractional anisotropy (FA) increased by up to 75%, and vascular fraction fv increased by up to 297% when TE increased from 50 to 90 ms. Diffusion-relaxation models produced TE-independent estimates. Tissue and vascular relaxation times ranged 31-36 ms T2t and 66-86 ms T2v, respectively. Simulations confirmed improved accuracy for fv estimation (r=0.95; RMSE=0.03) and reduced TE-related bias. Combined diffusion-relaxation MRI provides robust, TE-independent estimates of muscle microstructural and perfusion-related biomarkers. The quantitative improvements observed - particularly in the estimation of fv - show its potential to provide non-invasive biomarkers for the assessment of muscle physiology, exercise adaptation, rehabilitation, and neuromuscular pathology.

Read the full abstract

All authors Matteo Figini, Paddy J. Slator, Valeria E. Contarino, Eleftheria Panagiotaki, Giovanna Rizzo, Alfonso Mastropietro

Systems and Control

Solar Cars: A Comprehensive Review

Afsaneh Mollasalehi and Armin Farhadi

Energy crisis has forced many countries to think of a replacement for energy supply. Renewable energy sources as firendly environment sources play a pivotal role in producing clean energy for various sectors in industry. Gas emissions originating from the transportation industry is another contributing factor to air pollution. Hence, designing and utilizing vehicles that run on renewable energy is crucial, as it provides a dependable energy source that is naturally abundant, leaves nearly no carbon footprint, and is sustainable. Solar powered electric cars make a significant impact on global climate change. To better understand this impact and building upon the plenty of research done on this topic, this paper aims to provide a comprehensive review of the various factors related to solar cars. Specifically, this review will examine the following key factors: Types and sizing of solar cars, solar vehicle power source configurations, leading solar car nations, and solar car challenges.

Read the full abstract