Papers

In this work, receiver diversity in advection-dominated diffusion-advection channels is investigated. Strong directed flow fundamentally alters the communication-theoretic properties of molecular communication systems (MC). Specifically, advection preserves the temporal ordering and shape of transmitted pulses, enabling pulse-based and higher-order modulation schemes that are typically infeasible in purely diffusive environments. Focusing on a single transmitter and a single type of information molecule, it is demonstrated that spatially distributed receivers can observe distinct realizations of the same transmitted signal, giving rise to diversity gain. Several receiver combining strategies are evaluated and shown to improve detection performance compared to single-receiver operation, particularly in low-to-moderate signal-to-noise ratio (SNR) regimes. The results provide a structured framework for understanding receiver-side diversity in molecular communication, highlighting the role of advection as a key enabler for reliable pulse-based signaling. This perspective establishes a foundation for future studies on advanced modulation, joint equalization and detection, and multi-molecule MIMO extensions that can further enhance the performance and physical applicability of MC systems.

We study the joint operation and sizing of cooling infrastructure for commercial HVAC systems using reinforcement learning, with the objective of minimizing life-cycle cost over a 30-year horizon. The cooling system consists of a fixed-capacity electric chiller and a thermal energy storage (TES) unit, jointly operated to meet stochastic hourly cooling demands under time-varying electricity prices. The life-cycle cost accounts for both capital expenditure and discounted operating cost, including electricity consumption and maintenance. A key challenge arises from the strong asymmetry in capital costs: increasing chiller capacity by one unit is far more expensive than an equivalent increase in TES capacity. As a result, identifying the right combination of chiller and TES sizes, while ensuring zero loss-of-cooling-load under optimal operation, is a non-trivial co-design problem. To address this, we formulate the chiller operation problem for a fixed infrastructure configuration as a finite-horizon Markov Decision Process (MDP), in which the control action is the chiller part-load ratio (PLR). The MDP is solved using a Deep Q Network (DQN) with a constrained action space. The learned DQN RL policy minimizes electricity cost over historical traces of cooling demand and electricity prices. For each candidate chiller-TES sizing configuration, the trained policy is evaluated. We then restrict attention to configurations that fully satisfy the cooling demand and perform a life-cycle cost minimization over this feasible set to identify the cost-optimal infrastructure design. Using this approach, we determine the optimal chiller and thermal energy storage capacities to be 700 and 1500, respectively.

Underwater images suffer severe degradation due to wavelength-dependent attenuation, scattering, and illumination non-uniformity that vary across water types and depths. We propose an unsupervised Domain-Invariant Visual Enhancement and Restoration (DIVER) framework that integrates empirical correction with physics-guided modeling for robust underwater image enhancement. DIVER first applies either IlluminateNet for adaptive luminance enhancement or a Spectral Equalization Filter for spectral normalization. An Adaptive Optical Correction Module then refines hue and contrast using channel-adaptive filtering, while Hydro-OpticNet employs physics-constrained learning to compensate for backscatter and wavelength-dependent attenuation. The parameters of IlluminateNet and Hydro-OpticNet are optimized via unsupervised learning using a composite loss function. DIVER is evaluated on eight diverse datasets covering shallow, deep, and highly turbid environments, including both naturally low-light and artificially illuminated scenes, using reference and non-reference metrics. While state-of-the-art methods such as WaterNet, UDNet, and Phaseformer perform reasonably in shallow water, their performance degrades in deep, unevenly illuminated, or artificially lit conditions. In contrast, DIVER consistently achieves best or near-best performance across all datasets, demonstrating strong domain-invariant capability. DIVER yields at least a 9% improvement over SOTA methods in UCIQE. On the low-light SeaThru dataset, where color-palette references enable direct evaluation of color restoration, DIVER achieves at least a 4.9% reduction in GPMAE compared to existing methods. Beyond visual quality, DIVER also improves robotic perception by enhancing ORB-based keypoint repeatability and matching performance, confirming its robustness across diverse underwater environments.

Achieving precise and controllable emotional expression is crucial for producing natural and context-appropriate speech in text-to-speech (TTS) synthesis. However, many emotion-aware TTS systems, including large language model (LLM)-based designs, rely on scaling fixed emotion embeddings or external guidance, limiting their ability to model emotion-specific latent characteristics. To address this gap, we present EmoShift, a lightweight activation-steering framework incorporating a EmoSteer layer, which learns a steering vector for each target emotion in the output embedding space to capture its latent offset and maintain stable, appropriate expression across utterances and categories. With only 10M trainable parameters,less than 1/30 of full fine-tuning, EmoShift outperforms zero-shot and fully fine-tuned baselines in objective and subjective evaluations, enhancing emotional expressiveness while preserving naturalness and speaker similarity. Further analysis confirms the proposed EmoSteer layer's effectiveness and reveals its potential for controllable emotional intensity in speech synthesis.

Battery energy storage systems are increasingly deployed as fast-responding resources for grid balancing services such as frequency regulation and for mitigating renewable generation uncertainty. However, repeated charging and discharging induces cycling degradation and reduces battery lifetime. This paper studies the real-time scheduling of a heterogeneous battery fleet that collectively tracks a stochastic balancing signal subject to per-battery ramp-rate and capacity constraints, while minimizing long-term cycling degradation. Cycling degradation is fundamentally path-dependent: it is determined by charge-discharge cycles formed by the state-of-charge (SoC) trajectory and is commonly quantified via rainflow cycle counting. This non-Markovian structure makes it difficult to express degradation as an additive per-time-step cost, complicating classical dynamic programming approaches. We address this challenge by formulating the fleet scheduling problem as a Markov decision process (MDP) with constrained action space and designing a dense proxy reward that provides informative feedback at each time step while remaining aligned with long-term cycle-depth reduction. To scale learning to large state-action spaces induced by fine-grained SoC discretization and asymmetric per-battery constraints, we develop a function-approximation reinforcement learning method using an Extreme Learning Machine (ELM) as a random nonlinear feature map combined with linear temporal-difference learning. We evaluate the proposed approach on a toy Markovian signal model and on a Markovian model trained from real-world regulation signal traces obtained from the University of Delaware, and demonstrate consistent reductions in cycle-depth occurrence and degradation metrics compared to baseline scheduling policies.

We present CALM, a joint Contextual Acoustic-Linguistic Modeling framework for multi-speaker automatic speech recognition (ASR). In personalized AI scenarios, the joint availability of acoustic and linguistic cues naturally motivates the integration of target-speaker conditioning with contextual biasing in overlapping conversations. CALM implements this integration in an end-to-end framework through speaker embedding-driven target-speaker extraction and dynamic vocabulary-based contextual biasing. We evaluate CALM on simulated English (LibriSpeechMix) and Japanese (Corpus of Spontaneous Japanese mixtures, CSJMix). On two-speaker mixtures, CALM reduces biased word error rate (B-WER) from 12.7 to 4.7 on LibriSpeech2Mix and biased character error rate (B-CER) from 16.6 to 8.4 on CSJMix2 (eval3), demonstrating the effectiveness of joint acoustic-linguistic modeling across languages. We additionally report results on the AMI corpus (IHM-mix condition) to validate performance on standardized speech mixtures.

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose a novel streaming ASR approach that integrates a read/write policy network with monotonic chunkwise attention (MoChA) to dynamically segment speech embeddings. These segments are interleaved with label sequences during training, enabling seamless integration with the LLM. During inference, the audio stream is buffered until the MoChA module triggers a read signal, at which point the buffered segment together with the previous token is fed into the LLM for the next token prediction. We also introduce a minimal-latency training objective to guide the policy network toward accurate segmentation boundaries. Furthermore, we adopt a joint training strategy in which a non-streaming LLM-ASR model and our streaming model share parameters. Experiments on the AISHELL-1 and AISHELL-2 Mandarin benchmarks demonstrate that our method consistently outperforms recent streaming ASR baselines, achieving character error rates of 5.1% and 5.5%, respectively. The latency optimization results in a 62.5% reduction in average token generation delay with negligible impact on recognition accuracy

The completion of a Euclidean distance matrix (EDM) from sparse and noisy observations is a fundamental challenge in signal processing, with applications in sensor network localization, acoustic room reconstruction, molecular conformation, and manifold learning. Traditional approaches, such as rank-constrained optimization and semidefinite programming, enforce geometric constraints but often struggle under sparse or noisy conditions. This paper introduces a hierarchical Bayesian framework that places structured priors directly on the latent point set generating the EDM, naturally embedding geometric constraints. By incorporating a hierarchical prior on latent point set, the model enables automatic regularization and robust noise handling. Posterior inference is performed using a Metropolis-Hastings within Gibbs sampler to handle coupled latent point posterior. Experiments on synthetic data demonstrate improved reconstruction accuracy compared to deterministic baselines in sparse regimes.

Hyperspectral single image super-resolution (HS-SISR) aims to enhance the spatial resolution of hyperspectral images to fully exploit their spectral information. While considerable progress has been made in this field, most existing methods are supervised and require ground truth data for training-data that is often unavailable in practice. To overcome this limitation, we propose a novel unsupervised training framework for HS-SISR, based on synthetic abundance data, where no high-resolution ground-truth reference is required for training. The approach begins by unmixing the hyperspectral image into endmembers and abundances. A neural network is then trained to perform abundance super-resolution using synthetic abundances only. These synthetic abundance maps are generated from a dead leaves model whose characteristics are inherited from the low-resolution image to be super-resolved and from the known point spread function (PSF) of the hyperspectral sensor. This trained network is subsequently used to enhance the spatial resolution of the original image's abundances, and the final super-resolution hyperspectral image is reconstructed by combining them with the endmembers. Experimental results demonstrate both the training value of the synthetic data and the effectiveness of the proposed method across 3 datasets, 3 scaling factors, and several evaluation metrics. The code is available at https://github.com/xinxinxu99/SISR-DL.git

This study addresses the demand for real-time detection of tomatoes and tomato flowers by agricultural robots deployed on edge devices in greenhouse environments. Under practical imaging conditions, object detection systems often face challenges such as large scale variations caused by varying camera distances, severe occlusion from plant structures, and highly imbalanced class distributions. These factors make conventional object detection approaches that rely on fully annotated datasets difficult to simultaneously achieve high detection accuracy and deployment efficiency. To overcome these limitations, this research proposes an active learning driven lightweight object detection framework, integrating data analysis, model design, and training strategy. First, the size distribution of objects in raw agricultural images is analyzed to redefine an operational target range, thereby improving learning stability under real-world conditions. Second, an efficient feature extraction module is incorporated to reduce computational cost, while a lightweight attention mechanism is introduced to enhance feature representation under multi-scale and occluded scenarios. Finally, an active learning strategy is employed to iteratively select high-information samples for annotation and training under a limited labeling budget, effectively improving the recognition performance of minority and small-object categories. Experimental results demonstrate that, while maintaining a low parameter count and inference cost suitable for edge-device deployment, the proposed method effectively improves the detection performance of tomatoes and tomato flowers in raw images. Under limited annotation conditions, the framework achieves an overall detection accuracy of 67.8% mAP, validating its practicality and feasibility for intelligent agricultural applications.

In this paper, a new reconfigurable intelligent surface (RIS) hardware architecture, called self-organized RIS (SORIS), is proposed. The architecture incorporates a microcontroller connected to a single-antenna receiver operating at the same frequency as the RIS unit elements, operating either in transmission or reflection mode. The transmitting RIS elements enable the low latency estimation of both the incoming and outcoming channels at the microcontroller's side. In addition, a machine learning approach for estimating the incoming and outcoming channels involving the remaining RIS elements operating in reflection mode is devised. Specifically, by appropriately selecting a small number of elements in transmission mode, and based on the channel reciprocity principle, the respective channel coefficients are first estimated, which are then fed to a low-complexity neural network that, leveraging spatial channel correlation over RIS elements, returns predictions of the channel coefficients referring to the rest of elements. In this way, the SORIS microcontroller acquires channel state information, and accordingly reconfigures the panel's metamaterials to assist data communication between a transmitter and a receiver, without the need for separate connections with them. Moreover, the impact of channel estimation on the proposed solution, and a detailed complexity analysis for the used model, as well as a wiring density and control signaling analysis, is performed. The feasibility and efficacy of the proposed self-organized RIS design and operation are verified by Monte Carlo simulations, providing useful guidelines on the selection of the RIS elements for operating in transmission mode for initial channel estimation.

IR-drop is a critical power integrity challenge in modern VLSI designs that can cause timing degradation, reliability issues, and functional failures if not detected early in the design flow. Conventional IR-drop analysis relies on physics-based signoff tools, which provide high accuracy but incur significant computational cost and require near-final layout information, making them unsuitable for rapid early-stage design exploration. In this work, we propose a deep learning-based surrogate modeling approach for early-stage IR-drop estimation using a CNN. The task is formulated as a dense pixel-wise regression problem, where spatial physical layout features are mapped directly to IR-drop heatmaps. A U-Net-based encoder-decoder architecture with skip connections is employed to effectively capture both local and global spatial dependencies within the layout. The model is trained on a physics-inspired synthetic dataset generated by us, which incorporates key physical factors including power grid structure, cell density distribution, and switching activity. Model performance is evaluated using standard regression metrics such as Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR). Experimental results demonstrate that the proposed approach can accurately predict IR-drop distributions with millisecond-level inference time, enabling fast pre-signoff screening and iterative design optimization. The proposed framework is intended as a complementary early-stage analysis tool, providing designers with rapid IR-drop insight prior to expensive signoff analysis. The implementation, dataset generation scripts, and the interactive inference application are publicly available at: https://github.com/riteshbhadana/IR-Drop-Predictor. The live application can be accessed at: https://ir-drop-predictor.streamlit.app/.

Gliomas are placing an increasingly clinical burden on Sub-Saharan Africa (SSA). In the region, the median survival for patients remains under two years, and access to diagnostic imaging is extremely limited. These constraints highlight an urgent need for automated tools that can extract the maximum possible information from each available scan, tools that are specifically trained on local data, rather than adapted from high-income settings where conditions are vastly different. We utilize the Brain Tumor Segmentation (BraTS) Africa 2025 Challenge dataset, an expert annotated collection of glioma MRIs. Our objectives are: (i) establish a strong baseline with nnUNet on this dataset, and (ii) explore whether the celebrated "grokking" phenomenon an abrupt, late training jump from memorization to superior generalization can be triggered to push performance without extra labels. We evaluate two training regimes. The first is a fast, budget-conscious approach that limits optimization to just a few epochs, reflecting the constrained GPU resources typically available in African institutions. Despite this limitation, nnUNet achieves strong Dice scores: 92.3% for whole tumor (WH), 86.6% for tumor core (TC), and 86.3% for enhancing tumor (ET). The second regime extends training well beyond the point of convergence, aiming to trigger a grokking-driven performance leap. With this approach, we were able to achieve grokking and enhanced our results to higher Dice scores: 92.2% for whole tumor (WH), 90.1% for tumor core (TC), and 90.2% for enhancing tumor (ET).

This work proposes Bonnet, an ultra-fast sparse-volume pipeline for whole-body bone segmentation from CT scans. Accurate bone segmentation is important for surgical planning and anatomical analysis, but existing 3D voxel-based models such as nnU-Net and STU-Net require heavy computation and often take several minutes per scan, which limits time-critical use. The proposed Bonnet addresses this by integrating a series of novel framework components including HU-based bone thresholding, patch-wise inference with a sparse spconv-based U-Net, and multi-window fusion into a full-volume prediction. Trained on TotalSegmentator and evaluated without additional tuning on RibSeg, CT-Pelvic1K, and CT-Spine1K, Bonnet achieves high Dice across ribs, pelvis, and spine while running in only 2.69 seconds per scan on an RTX A6000. Compared to strong voxel baselines, Bonnet attains a similar accuracy but reduces inference time by roughly 25x on the same hardware and tiling setup. The toolkit and pre-trained models will be released at https://github.com/HINTLab/Bonnet.

This paper considers the constrained sampling multi-stream quickest change detection problem, also known as the bandit quickest change detection problem. One stream contains a change-point that shifts its mean by an unknown amount. The goal is to quickly detect this change while controlling for false alarms, while being only able to sample one stream at each time. We propose an algorithm that combines a decaying-$\epsilon$-greedy stream switching rule with a Generalized Likelihood Ratio detection procedure for unknown post-change means. We provide performance bounds for our algorithm and show it achieves approximate asymptotic first-order optimality with respect to a commonly used surrogate. We are the first to provide guarantees in this setting without assumptions such as a discretized post-change parameter set or a lower bound on the magnitude of change. We provide guarantees for a wide range of light-tailed distributions, including sub-Gaussian and bounded support distributions.

Endoscopic image analysis is vital for colorectal cancer screening, yet real-world conditions often suffer from lens fogging, motion blur, and specular highlights, which severely compromise automated polyp detection. We propose EndoCaver, a lightweight transformer with a unidirectional-guided dual-decoder architecture, enabling joint multi-task capability for image deblurring and segmentation while significantly reducing computational complexity and model parameters. Specifically, it integrates a Global Attention Module (GAM) for cross-scale aggregation, a Deblurring-Segmentation Aligner (DSA) to transfer restoration cues, and a cosine-based scheduler (LoCoS) for stable multi-task optimisation. Experiments on the Kvasir-SEG dataset show that EndoCaver achieves 0.922 Dice on clean data and 0.889 under severe image degradation, surpassing state-of-the-art methods while reducing model parameters by 90%. These results demonstrate its efficiency and robustness, making it well-suited for on-device clinical deployment. Code is available at https://github.com/ReaganWu/EndoCaver.

Orthogonal time frequency space (OTFS) modulation has emerged as a promising candidate to overcome the performance degradation of orthogonal frequency division multiplexing (OFDM), which are commonly encountered in high-mobility wireless communication scenarios. However, conventional OTFS transceivers rely on multiple separately designed signal-processing modules, whose isolated optimization often limits global optimal performance. To overcome limitations, this paper proposes a modular deep learning (DL) based end-to-end OTFS transceiver framework that consists of trainable and interchangeable neural network (NN) modules, including constellation mapping/demapping, superimposed pilot placement, inverse Zak (IZak)/Zak transforms, and a U-Net-enhanced NN tailored for joint channel estimation and detection (JCED), while explicitly accounting for the impact of the cyclic prefix. This physics-informed modular architecture provides flexibility for integration with conventional OTFS systems and adaptability to different communication configurations. Simulations demonstrate that the proposed design significantly outperforms baseline methods in terms of both normalized mean squared error (NMSE) and detection reliability, maintaining robustness under integer and fractional Doppler conditions. The results highlight the potential of DL-based end-to-end optimization to enable practical and high-performance OTFS transceivers for next-generation high-mobility networks.

To advance immersive communication, the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge recently introduced Task 4 on Spatial Semantic Segmentation of Sound Scenes (S5). An S5 system takes a multi-channel audio mixture as input and outputs single-channel dry sources along with their corresponding class labels. Although the DCASE 2025 Challenge simplifies the task by constraining class labels in each mixture to be mutually exclusive, real-world mixtures frequently contain multiple sources from the same class. The presence of duplicated labels can significantly degrade the performance of the label-queried source separation (LQSS) model, which is the key component of many existing S5 systems, and can also limit the validity of the official evaluation metric of DCASE 2025 Task 4. To address these issues, we propose a class-aware permutation-invariant loss function that enables the LQSS model to handle queries involving duplicated labels. In addition, we redesign the S5 evaluation metric to eliminate ambiguities caused by these same-class sources. To evaluate the proposed method within the S5 system, we extend the label prediction model to support same-class labels. Experimental results demonstrate the effectiveness of the proposed methods and the robustness of the new metric on mixtures both with and without same-class sources.

Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight adaptation module. However, most SSL models are not trained for noise robustness, which can lead to corrupted semantic representations. Moreover, the adaptation module is trained jointly with the SE model, potentially prioritizing acoustic details over semantic information, contradicting the original purpose. To address this issue, we first analyze the behavior of SSL models on noisy speech from an information-theoretic perspective. Specifically, we measure the mutual information (MI) between the corrupted SSL representations and the corresponding phoneme labels, focusing on preservation of linguistic contents. Building upon this analysis, we introduce the linguistic aggregation layer, which is pre-trained to maximize MI with phoneme labels (with optional dynamic aggregation) and then frozen during SE training. Experiments show that this decoupled approach improves Word Error Rate (WER) over jointly optimized baselines, demonstrating the benefit of explicitly aligning the adaptation module with linguistic contents.

We propose a lightweight compressed-domain tracking model that operates directly on video streams, without requiring full RGB video decoding. Using motion vectors and transform coefficients from compressed data, our deep model propagates object bounding boxes across frames, achieving a computational speed-up of order up to 3.7 with only a slight 4% mAP@0.5 drop vs RGB baseline on MOTS15/17/20 datasets. These results highlight codec-domain motion modeling efficiency for real-time analytics in large monitoring systems.

The demand for accurate on-device pattern recognition in edge applications is intensifying, yet existing approaches struggle to reconcile accuracy with computational constraints. To address this challenge, a resource-aware hierarchical network based on multi-spectral fusion and interpretable modules, namely the Hierarchical Parallel Pseudo-image Enhancement Fusion Network (HPPI-Net), is proposed for real-time, on-device Human Activity Recognition (HAR). Deployed on an ARM Cortex-M4 microcontroller for low-power real-time inference, HPPI-Net achieves 96.70% accuracy while utilizing only 22.3 KiB of RAM and 439.5 KiB of ROM after optimization. HPPI-Net employs a two-layer architecture. The first layer extracts preliminary features using Fast Fourier Transform (FFT) spectrograms, while the second layer selectively activates either a dedicated module for stationary activity recognition or a parallel LSTM-MobileNet network (PLMN) for dynamic states. PLMN fuses FFT, Wavelet, and Gabor spectrograms through three parallel LSTM encoders and refines the concatenated features using Efficient Channel Attention (ECA) and Depthwise Separable Convolution (DSC), thereby offering channel-level interpretability while substantially reducing multiply-accumulate operations. Compared with MobileNetV3, HPPI-Net improves accuracy by 1.22% and reduces RAM usage by 71.2% and ROM usage by 42.1%. These results demonstrate that HPPI-Net achieves a favorable accuracy-efficiency trade-off and provides explainable predictions, establishing a practical solution for wearable, industrial, and smart home HAR on memory-constrained edge platforms.

3-D object detection based on 4-D radar-vision is an important part in Internet of Vehicles (IoV). However, there are two challenges which need to be faced. First, the 4-D radar point clouds are sparse, leading to poor 3-D representation. Second, vision datas exhibit representation degradation under low-light, long distance detection and dense occlusion scenes, which provides unreliable texture information during fusion stage. To address these issues, a framework named SDCM is proposed, which contains Simulated Densifying and Compensatory Modeling Fusion for radar-vision 3-D object detection in IoV. Firstly, considering point generation based on Gaussian simulation of key points obtained from 3-D Kernel Density Estimation (3-D KDE), and outline generation based on curvature simulation, Simulated Densifying (SimDen) module is designed to generate dense radar point clouds. Secondly, considering that radar data could provide more real time information than vision data, due to the all-weather property of 4-D radar. Radar Compensatory Mapping (RCM) module is designed to reduce the affects of vision datas' representation degradation. Thirdly, considering that feature tensor difference values contain the effective information of every modality, which could be extracted and modeled for heterogeneity reduction and modalities interaction, Mamba Modeling Interactive Fusion (MMIF) module is designed for reducing heterogeneous and achieving interactive Fusion. Experiment results on the VoD, TJ4DRadSet and Astyx HiRes 2019 dataset show that SDCM achieves best performance with lower parameter quantity and faster inference speed. Our code will be available.

Uncrewed aerial vehicles (UAVs) have played an important role in the low-altitude economy and have been used in various applications. However, with the increasing number of UAVs and explosive wireless data, the existing bit-oriented communication network has approached the Shannon capacity, which cannot satisfy the quality of service (QoS) with ultra-reliable low-latency communication (URLLC) requirements for command and control (C&C) transmission in bit-oriented UAV communication networks. To address this issue, we propose a novel semantic-aware C&C transmission for multi-UAVs under limited wireless resources. Specifically, we leverage semantic similarity to measure the variation in C&C messages for each UAV over continuous transmission time intervals (TTIs) and capture the correlation of C&C messages among UAVs, enabling multicast transmission. Based on the semantic similarity and the importance of UAV commands, we design a trigger function to quantify the QoS of UAVs. Then, to maximize the long-term QoS and exploit multicast opportunities of C&C messages induced by semantic similarity, we develop a proximal policy optimization (PPO) algorithm to jointly determine the transmission mode (unicast/multicast/idle) and the allocation of limited resource blocks (RBs) between a base station (BS) and UAVs. Experimental results show that our proposed semantic-aware framework significantly increases transmission efficiency and improves effectiveness compared with bit-oriented UAV transmission.

The max-min fair (MMF) multicasting problem is known to be NP-hard. In this work, we analytically derive the optimal solution to this NP-hard problem and establish the equivalence between rate balancing and the optimal MMF multicasting solution under certain conditions. Based on this theoretical insight, we propose a low-complexity algorithm for MMF multicasting that yields closed-form solutions. Simulation results validate our analysis and demonstrate that the proposed algorithm outperforms the state-of-the-art methods while being computationally more efficient.

The complex electrochemical behavior of lithium-ion batteries results in non-linear dynamics and appropriate modeling of this non-linear dynamical system is of interest for better management and control. In this work, we proposed a family of dynamic mode decomposition (DMD)-based data-driven models that do not require detailed knowledge of the composition of the battery materials but can essentially capture the non-linear dynamics with higher computational efficiency. Only voltage and current data obtained from hybrid pulse power characterization (HPPC) tests were utilized to form the state space matrices and subsequently used for predicting the future terminal voltage at different state of charge (SoC) and aging levels. To construct the system model, 60% of the data from a single HPPC test was utilized to generate time-delay embedded snapshots, with embedding dimension ranging from 40 to 2000. Among these, an embedding dimension of 1810 resulted in the least residual sum of squares (RSS) error of 3.86 for the dynamic mode decomposition with control (DMDc) model and 30 for the standard DMD model. For DMDc model, delay embeddings (ranging from 1 to 12) were also incorporated into the input current signals. For the input matrix, an embedding dimension of 6 resulted in a minimum RSS error of 1.74. Furthermore, the system matrices A and B, identified from the HPPC test when the cell is in its healthy state, were held fixed and used to simulate the system dynamics for aged batteries by updating only the control input. Despite the presence of nonlinear degradation effects in later cycles, the DMDc model effectively captured key inner dynamics such as voltage dips and transient responses for subsequent charge and discharge cycles.

The widespread adoption of battery electric vehicles (BEVs) holds promise for mitigating emission-related health impacts, particularly for low-income communities disproportionately affected by exposure to traffic-related air pollution. However, designing effective charging infrastructure necessitates a regional modeling approach that accounts for the inherent cross-jurisdictional nature of mobility patterns. This study underscores the importance of regional modeling in optimizing charging station deployment and evaluating the environmental justice implications for equity priority communities. We present a large-scale regional transportation modeling analysis leveraging Mobiliti, a cloud-based platform that employs parallel discrete event simulation to enable rapid computation. Our approach identifies the spatial demand density for charging infrastructure by analyzing over 19 million trips in the San Francisco Bay Area and determining the threshold points where BEVs may require charging across a typical day. By transitioning these trips that originate outside equity priority communities to BEVs, we quantify the potential emission reductions within these vulnerable areas. The regional modeling framework captures the complex interactions between travel behavior, vehicle characteristics, and charging needs, while accounting for the interconnectivity of infrastructure across municipal boundaries. This study demonstrates the critical role of regional modeling in designing equitable BEV charging networks that address environmental justice concerns. The findings inform strategies for deploying charging infrastructure that maximizes accessibility, minimizes range anxiety, and prioritizes the health and well-being of communities disproportionately burdened by transportation emissions.

Evasion attacks pose significant threats to AI systems, exploiting vulnerabilities in machine learning models to bypass detection mechanisms. The widespread use of voice data, including deepfakes, in promising future industries is currently hindered by insufficient legal frameworks. Adversarial attack methods have emerged as the most effective countermeasure against the indiscriminate use of such data. This research introduces masked energy perturbation (MEP), a novel approach using power spectrum for energy masking of original voice data. MEP applies masking to small energy regions in the frequency domain before generating adversarial perturbations, targeting areas less noticeable to the human auditory model. The study primarily employs advanced speaker recognition models, including ECAPA-TDNN and ResNet34, which have shown remarkable performance in speaker verification tasks. The proposed MEP method demonstrated strong performance in both audio quality and evasion effectiveness. The energy masking approach effectively minimizes the perceptual evaluation of speech quality (PESQ) degradation, indicating that minimal perceptual distortion occurs to the human listener despite the adversarial perturbations. Specifically, in the PESQ evaluation, the relative performance of the MEP method was 26.68% when compared to the fast gradient sign method (FGSM) and iterative FGSM.

Movable signals have emerged as a third approach to enable smart radio environments (SREs), complementing reconfigurable intelligent surfaces (RISs) and flexible antennas. This paper investigates their potential to enhance multi-user wireless systems. Focusing on two-user systems in line-of-sight (LoS), we characterize the capacity regions of the multiple access channel (MAC) and broadcast channel (BC). Interestingly, movable signals can dynamically adjust the operating frequency to orthogonalize the user channels, thereby significantly expanding the capacity regions. We also study frequency optimization, constraining it in a limited frequency range, and show that movable signals provide up to 45% sum rate gain.

Indoor localization is a critical enabler for a wide range of location-based services in smart environments, including navigation, asset tracking, and safety-critical applications. Recent graph-based models leverage spatial relationships between Wire-less Fidelity (Wi-Fi) Access Points (APs) and devices, offering finer localization granularity, but fall short in quantifying prediction uncertainty, a key requirement for real-world deployment. In this paper, we propose Spatially-Adaptive Conformal Graph Transformer (SAC-GT), a framework for accurate and reliable indoor localization. SAC-GT integrates a Graph Transformer (GT) model that captures network's spatial topology and signal strength dynamics, with a novel Spatially-Adaptive Conformal Prediction (SACP) method that provides region-specific uncertainty estimates. This allows SAC-GT to produce not only precise two-dimensional (2D) location predictions but also statistically valid confidence regions tailored to varying environmental conditions. Extensive evaluations on a large-scale real-world dataset demonstrate that the proposed SAC-GT solution achieves state-of-the-art localization accuracy while delivering robust and spatially adaptive reliability guarantees.

The human voice is a promising non-invasive digital biomarker, yet deep learning for voice-based health analysis is hindered by data scarcity and domain mismatch, where models pre-trained on general audio fail to capture the subtle pathological features characteristic of clinical voice data. To address these challenges, we investigate domain-adaptive self-supervised learning (SSL) with Masked Autoencoders (MAE) and demonstrate that standard configurations are suboptimal for health-related audio. Using the Bridge2AI-Voice dataset, a multi-institutional collection of pathological voices, we systematically examine three performance-critical factors: reconstruction loss (Mean Absolute Error vs. Mean Squared Error), normalization (patch-wise vs. global), and masking (random vs. content-aware). Our optimized design, which combines Mean Absolute Error (MA-Error) loss, patch-wise normalization, and content-aware masking, achieves a Macro F1 of $0.688 \pm 0.009$ (over 10 fine-tuning runs), outperforming a strong out-of-domain SSL baseline pre-trained on large-scale general audio, which has a Macro F1 of $0.663 \pm 0.011$. The results show that MA-Error loss improves robustness and content-aware masking boosts performance by emphasizing information-rich regions. These findings highlight the importance of component-level optimization in data-constrained medical applications that rely on audio data.