arXiv EE and SS @arxiv_eess@qoto.org

Limited data is a common problem in remote sensing due to the high cost of obtaining annotated samples. In the few-shot segmentation task, models are typically trained on base classes with abundant annotations and later adapted to novel classes with limited examples. However, this often necessitates specialized model architectures or complex training strategies. Instead, we propose a simple approach that leverages diffusion models to generate diverse variations of novel-class objects within a given scene, conditioned by the limited examples of the novel classes. By framing the problem as an image inpainting task, we synthesize plausible instances of novel classes under various environments, effectively increasing the number of samples for the novel classes and mitigating overfitting. The generated samples are then assessed using a cosine similarity metric to ensure semantic consistency with the novel classes. Additionally, we employ Segment Anything Model (SAM) to segment the generated samples and obtain precise annotations. By using high-quality synthetic data, we can directly fine-tune off-the-shelf segmentation models. Experimental results demonstrate that our method significantly enhances segmentation performance in low-data regimes, highlighting its potential for real-world remote sensing applications.

Beampattern synthesis seeks to optimize array weights to shape radiation patterns, playing a critical role in various wireless applications. In addition to theoretical advancements, recent hardware innovations have facilitated new avenues to enhance beampattern synthesis performance. This paper studies the beampattern synthesis problem using newly proposed electromagnetically reconfigurable antennas (ERAs). By utilizing spherical harmonics decomposition, we simultaneously optimize each antenna's radiation pattern and phase shift to match a desired beampattern of the entire array. The problem is formulated for both far-field and near-field scenarios, with the optimization solved using Riemannian manifold techniques. The simulation results validate the effectiveness of the proposed solution and illustrate that ERAs exhibit superior beampattern synthesis capabilities compared to conventional fixed radiation pattern antennas. This advantage becomes increasingly significant as the array size grows.

Detection of undersea threats is a complex problem of considerable importance for maritime regional surveillance and security. Multistatic sonar systems can provide a means to monitor for underwater threats, where fixed sensors, towed arrays and dipping sonars may be utilised for this purpose. However, it is advantageous to deploy passive sensors to provide a stealthy early warning system. Hence this paper is concerned with determining where a series of passive sonar sensors should be situated in order to provide an initial threat detection capability. In order to facilitate this it is necessary to derive a suitable expression for the probability of threat detection from a passive sensor. This is based upon considerations of the passive sonar equation. It will be demonstrated how the stochastic aspects of this equation may be modelled through appropriate random variables capturing the uncertainty in noise levels. Subsequently this is utilised to produce the system-level probability of threat detection. Since the threat location is also unknown an appropriate statistical model is introduced to account for this uncertainty. This then permits the specification of the probability of detection as a function of sensor locations. Consequently it is then possible to determine optimal sensor placement to maximise the threat detection probability. This provides a new way in which to determine whether a surveillance region is covered adequately by sensors. The methodology will be illustrated through a series of examples utilising passive sonar characteristics sourced from the open literature.

Cardiovascular magnetic resonance (CMR) offers diverse imaging contrasts for assessment of cardiac function and tissue characterization. However, acquiring each single CMR modality is often time-consuming, and comprehensive clinical protocols require multiple modalities with various sampling patterns, further extending the overall acquisition time and increasing susceptibility to motion artifacts. Existing deep learning-based reconstruction methods are often designed for specific acquisition parameters, which limits their ability to generalize across a variety of scan scenarios. As part of the CMRxRecon Series, the CMRxRecon2024 challenge provides diverse datasets encompassing multi-modality multi-view imaging with various sampling patterns, and a platform for the international community to develop and benchmark reconstruction solutions in two well-crafted tasks. Task 1 is a modality-universal setting, evaluating the out-of-distribution generalization of the reconstructed model, while Task 2 follows sampling-universal setting assessing the one-for-all adaptability of the universal model. Main contributions include providing the first and largest publicly available multi-modality, multi-view cardiac k-space dataset; developing a benchmarking platform that simulates clinical acceleration protocols, with a shared code library and tutorial for various k-t undersampling patterns and data processing; giving technical insights of enhanced data consistency based on physic-informed networks and adaptive prompt-learning embedding to be versatile to different clinical settings; additional finding on evaluation metrics to address the limitations of conventional ground-truth references in universal reconstruction tasks.

Non-orthogonal multiple access (NOMA) is widely recognized for enhancing the energy and spectral efficiency through effective radio resource sharing. However, uplink NOMA systems face greater challenges than their downlink counterparts, as their bit error rate (BER) performance is hindered by an inherent error floor due to error propagation caused by imperfect successive interference cancellation (SIC). This paper investigates BER performance improvements enabled by reconfigurable intelligent surfaces (RISs) in multi-user uplink NOMA transmission. Specifically, we propose a novel RIS-assisted uplink NOMA design, where the RIS phase shifts are optimized to enhance the received signal amplitudes while mitigating the phase rotations induced by the channel. To achieve this, we first develop an accurate channel model for the effective user channels, which facilitates our BER analysis. We then introduce a channel alignment scheme for a two-user scenario, enabling efficient SIC-based detection and deriving closed-form BER expressions. We further extend the analysis to a generalized setup with an arbitrary number of users and modulation orders for quadrature amplitude modulation signaling. Using the derived BER expressions, we develop an optimized uplink NOMA power allocation (PA) scheme that minimizes the average BER while satisfying the user transmit power constraints. It will be shown that the proposed NOMA detection scheme, in conjunction with the optimized PA strategy, eliminate SIC error floors at the base station. The theoretical BER expressions are validated using simulations, which confirms the effectiveness of the proposed design in eliminating BER floors.

Motion stages are critical in semiconductor manufacturing equipment for processes like die bonding, wafer loading, and chip packaging, as their performance must meet the industry's stringent precision requirements. Vibration, a significant yet often overlooked adversary to precision motion stages, is challenging to identify and mitigate due to its subtle nature. This study, conducted at a motion stage manufacturer facing frequent vibration-related complaints, proposes a novel approach to resolving vibration issues. By leveraging the DMAIC methodology, it introduces VIBGUARD, an active vibration monitoring and mitigation solution, instead of solely focusing on traditional hardware vibration control. This comprehensive strategy enhances value and competitiveness, increasing UPH (units per hour) by 15.3% from 8,500 to 9,800 and reducing downtime by 68.2% from 2.2 to 0.7 occurrences per month. This case study and the DMAIC methodology offer valuable resources for quality control and problem analysis in the semiconductor industry.

Constrained multi-agent reinforcement learning offers the framework to design scalable and almost surely feasible solutions for teams of agents operating in dynamic environments to carry out conflicting tasks. We address the challenges of multi-agent coordination through an unconventional formulation in which the dual variables are not driven to convergence but are free to cycle, enabling agents to adapt their policies dynamically based on real-time constraint satisfaction levels. The coordination relies on a light single-bit communication protocol over a network with stochastic connectivity. Using this gossiped information, agents update local estimates of the dual variables. Furthermore, we modify the local dual dynamics by introducing a contraction factor, which lets us use finite communication buffers and keep the estimation error bounded. Under this model, we provide theoretical guarantees of almost sure feasibility and corroborate them with numerical experiments in which a team of robots successfully patrols multiple regions, communicating under a time-varying ad-hoc network.

FDI (False Data Injection) attacks are critical to address as they can compromise the integrity and reliability of data in cyber-physical systems, leading to potentially severe consequences in sectors such as power systems. The feasibility of FDI attacks has been extensively studied from various perspectives, including access to measurements and sensors, knowledge of the system, and design considerations using residual-based detection methods. Most research has focused on DC-based FDI attacks; however, designing AC FDI attacks involves solving a nonlinear optimization problem, presenting additional challenges in assessing their feasibility. Specifically, it is often unclear whether the infeasibility of some designed AC FDI attacks is due to the nonconvexity and nonlinearity inherent to AC power flows or if it stems from inherent infeasibility in specific cases, with local solvers returning infeasibility. This paper addresses this issue by leveraging the principle that if a convexified AC FDI attack design problem is infeasible, the attack design itself is infeasible, irrespective of nonlinear solution challenges. We propose an AC FDI attack design based on convexified power flow equations and assess the feasibility of the proposed attack by examining the extent of the attackable region. This approach utilizes a Quadratic Convex (QC) relaxation technique to convexify AC power flows. To evaluate the proposed method, we implement it on the IEEE 118-bus test system and assess the feasibility of an AC FDI attack across various attack zones.

In current molecular communication (MC) systems, performing computational operations at the nanoscale remains challenging, restricting their applicability in complex scenarios such as adaptive biochemical control and advanced nanoscale sensing. To overcome this challenge, this paper proposes a novel framework that seamlessly integrates computation into the molecular communication process. The system enables arithmetic operations, namely addition, subtraction, multiplication, and division, by encoding numerical values into two types of molecules emitted by each transmitter to represent positive and negative values, respectively. Specifically, addition is achieved by transmitting non-reactive molecules, while subtraction employs reactive molecules that interact during propagation. The receiver demodulates molecular counts to directly compute the desired results. Theoretical analysis for an upper bound on the bit error rate (BER), and computational simulations confirm the system's robustness in performing complex arithmetic tasks. Compared to conventional MC methods, the proposed approach not only enables fundamental computational operations at the nanoscale but also lays the groundwork for intelligent, autonomous molecular networks.

The lungs are the essential organs of respiration, and this system is significant in the carbon dioxide and exchange between oxygen that occurs in human life. However, several lung diseases, which include pneumonia, tuberculosis, COVID-19, and lung cancer, are serious healthiness challenges and demand early and precise diagnostics. The methodological study has proposed a new deep learning framework called NASNet-ViT, which effectively incorporates the convolution capability of NASNet with the global attention mechanism capability of Vision Transformer ViT. The proposed model will classify the lung conditions into five classes: Lung cancer, COVID-19, pneumonia, TB, and normal. A sophisticated multi-faceted preprocessing strategy called MixProcessing has been used to improve diagnostic accuracy. This preprocessing combines wavelet transform, adaptive histogram equalization, and morphological filtering techniques. The NASNet-ViT model performs at state of the art, achieving an accuracy of 98.9%, sensitivity of 0.99, an F1-score of 0.989, and specificity of 0.987, outperforming other state of the art architectures such as MixNet-LD, D-ResNet, MobileNet, and ResNet50. The model's efficiency is further emphasized by its compact size, 25.6 MB, and a low computational time of 12.4 seconds, hence suitable for real-time, clinically constrained environments. These results reflect the high-quality capability of NASNet-ViT in extracting meaningful features and recognizing various types of lung diseases with very high accuracy. This work contributes to medical image analysis by providing a robust and scalable solution for diagnostics in lung diseases.

We derive a heuristic nonlinear interference model for 4D probabilistic shaping considering the polarization and time correlation of the 4D symbols. We demonstrate an average SNR prediction gap from split-step Fourier simulations of 0.15~dB.

Due to the domain shifts between training and testing medical images, learned segmentation models often experience significant performance degradation during deployment. In this paper, we first decompose an image into its style code and content map and reveal that domain shifts in medical images involve: \textbf{style shifts} (\emph{i.e.}, differences in image appearance) and \textbf{content shifts} (\emph{i.e.}, variations in anatomical structures), the latter of which has been largely overlooked. To this end, we propose \textbf{StyCona}, a \textbf{sty}le \textbf{con}tent decomposition-based data \textbf{a}ugmentation method that innovatively augments both image style and content within the rank-one space, for domain generalizable medical image segmentation. StyCona is a simple yet effective plug-and-play module that substantially improves model generalization without requiring additional training parameters or modifications to the segmentation model architecture. Experiments on cross-sequence, cross-center, and cross-modality medical image segmentation settings with increasingly severe domain shifts, demonstrate the effectiveness of StyCona and its superiority over state-of-the-arts. The code is available at https://github.com/Senyh/StyCona.

We consider the data-aided channel estimation (CE) problem in a reconfigurable intelligent surface (RIS)-assisted wireless communication system, where the channel and information symbols are estimated jointly during the CE phase, differently from pure pilot-aided methods. We propose a two-stage semi-blind receiver that jointly estimates the combined channel and the data symbols, followed by channel decoupling. To this end, we derive a new modeling framework whose first stage recasts the received signal to allow for the joint estimation of the combined channel and transmitted symbols. In the second stage, channel decoupling is easily achieved via Khatri-Rao factorization, yielding a refined channel estimate. Our solution yields accurate estimates of the cascaded channel at lower computational complexity. Simulation results reveal a similar performance of the proposed method to that of the competitor while providing a substantially reduced computational cost.

Reconfigurable intelligent surface (RIS)-aided vehicle-to-everything (V2X) communication has emerged as a crucial solution for providing reliable data services to vehicles on the road. However, in delay-sensitive or high-mobility communications, the rapid movement of vehicles can lead to random scattering in the environment and time-selective fading in the channel. In view of this, we investigate in this paper an innovative linear model with low-complexity transmitter signal design and receiver detection methods, which boost stability in fast-fading environments and reduce channel training overhead. Specifically, considering the differences in hardware design and signal processing at the receiving end between uplink and downlink communication systems, distinct solutions are proposed. Accordingly, we first integrate the Rician channel introduced by the RIS with the corresponding signal processing algorithms to model the RIS-aided downlink communication system as a Doppler-robust linear model. Inspired by this property, we design a precoding scheme based on the linear model to reduce the complexity of precoding. Then, by leveraging the linear model and the large-scale antenna array at the base station (BS) side, we improve the linear model for the uplink communication system and derive its asymptotic performance in closed-form. Simulation results demonstrate the performance advantages of the proposed RIS-aided high-mobility communication system compared to other benchmark schemes.

Joint utilization of multiple discrete frequency bands can enhance the accuracy of delay estimation. Although some unique challenges of multiband fusion, such as phase distortion, oscillation phenomena, and high-dimensional search, have been partially addressed, further challenges remain. Specifically, under conditions of low signal-to-noise ratio (SNR), insufficient data, and closely spaced delay paths, accurately determining the model order-the number of delay paths-becomes difficult. Misestimating the model order can significantly degrade the estimation performance of traditional methods. To address joint model selection and parameter estimation under such harsh conditions, we propose a multi-model stochastic particle-based variational Bayesian inference (MM-SPVBI) framework, capable of exploring multiple high-dimensional parameter spaces. Initially, we split potential overlapping primary delay paths based on coarse estimates, generating several parallel candidate models. Then, an auto-focusing sampling strategy is employed to quickly identify the optimal model. Additionally, we introduce a hybrid posterior approximation to improve the original single-model SPVBI, ensuring overall complexity does not increase significantly with parallelism. Simulations demonstrate that our algorithm offers substantial advantages over existing methods.

This paper proposes a differentially private recursive least squares algorithm to estimate the parameter of autoregressive systems with exogenous inputs and multi-participants (MP-ARX systems) and protect each participant's sensitive information from potential attackers. We first give a rigorous differential privacy analysis of the algorithm, and establish the quantitative relationship between the added noises and the privacy-preserving level when the system is asymptotically stable. The asymptotic stability of the system is necessary for ensuring the differential privacy of the algorithm. We then give an estimation error analysis of the algorithm under the general and possible weakest excitation condition without requiring the boundedness, independence and stationarity on the regression vectors. Particularly, when there is no regression term in the system output and the differential privacy only on the system output is considered, $\varepsilon$-differential privacy and almost sure convergence of the algorithm can be established simultaneously. To minimize the estimation error of the algorithm with $\varepsilon$-differential privacy, the existence of the noise intensity is proved. Finally, two examples are given to show the efficiency of the algorithm.

Hyperspectral imaging provides detailed spectral information, offering significant potential for monitoring greenhouse gases like CH4 and NO2. However, its application is constrained by limited spatial coverage and infrequent revisit times. In contrast, multispectral imaging delivers broader spatial and temporal coverage but lacks the spectral granularity required for precise GHG detection. To address these challenges, this study proposes Spectral and Spatial-Spectral transformer models that reconstruct hyperspectral data from multispectral inputs. The models in this paper are pretrained on EnMAP and EMIT datasets and fine-tuned on spatio-temporally aligned (Sentinel-2, EnMAP) and (HLS-S30, EMIT) image pairs respectively. Our model has the potential to enhance atmospheric monitoring by combining the strengths of hyperspectral and multispectral imaging systems.

Point cloud upsampling aims to generate dense and uniformly distributed point sets from sparse point clouds. Existing point cloud upsampling methods typically approach the task as an interpolation problem. They achieve upsampling by performing local interpolation between point clouds or in the feature space, then regressing the interpolated points to appropriate positions. By contrast, our proposed method treats point cloud upsampling as a global shape completion problem. Specifically, our method first divides the point cloud into multiple patches. Then, a masking operation is applied to remove some patches, leaving visible point cloud patches. Finally, our custom-designed neural network iterative completes the missing sections of the point cloud through the visible parts. During testing, by selecting different mask sequences, we can restore various complete patches. A sufficiently dense upsampled point cloud can be obtained by merging all the completed patches. We demonstrate the superior performance of our method through both quantitative and qualitative experiments, showing overall superiority against both existing self-supervised and supervised methods.