arXiv EE and SS @arxiv_eess@qoto.org

Due to its ability to work in non-line-of-sight and low-light environments, radio frequency (RF) imaging technology is expected to bring new possibilities for embodied intelligence and multimodal sensing. However, widely used RF devices (such as Wi-Fi) often struggle to provide high-precision electromagnetic measurements and large-scale datasets, hindering the application of RF imaging technology. In this paper, we combine the ideas of PINN to design the RINN network, using physical constraints instead of true value comparison constraints and adapting it with the characteristics of ubiquitous RF signals, allowing the RINN network to achieve RF imaging using only one sample without phase and with amplitude noise. Our numerical evaluation results show that compared with 5 classic algorithms based on phase data for imaging results, RINN's imaging results based on phaseless data are good, with indicators such as RRMSE (0.11) performing similarly well. RINN provides new possibilities for the universal development of radio frequency imaging technology.

Diabetic retinopathy (DR) is a leading cause of blindness worldwide, underscoring the importance of early detection for effective treatment. However, automated DR classification remains challenging due to variations in image quality, class imbalance, and pixel-level similarities that hinder model training. To address these issues, we propose a robust preprocessing pipeline incorporating image cropping, Contrast-Limited Adaptive Histogram Equalization (CLAHE), and targeted data augmentation to improve model generalization and resilience. Our approach leverages the Swin Transformer, which utilizes hierarchical token processing and shifted window attention to efficiently capture fine-grained features while maintaining linear computational complexity. We validate our method on the Aptos and IDRiD datasets for multi-class DR classification, achieving accuracy rates of 89.65% and 97.40%, respectively. These results demonstrate the effectiveness of our model, particularly in detecting early-stage DR, highlighting its potential for improving automated retinal screening in clinical settings.

Magnetic resonance imaging (MRI) reconstruction has largely been dominated by deep neural networks (DNN); however, many state-of-the-art architectures use black-box structures, which hinder interpretability and improvement. Here, we propose an interpretable DNN architecture for self-supervised MRI reconstruction and denoising by directly parameterizing and learning the classical primal-dual splitting, dubbed LPDSNet. This splitting algorithm allows us to decouple the observation model from the signal prior. Experimentally, we show other interpretable architectures without this decoupling property exhibit failure in the self-supervised learning regime. We report state-of-the-art self-supervised joint MRI reconstruction and denoising performance and novel noise-level generalization capabilities, where in contrast black-box networks fail to generalize.

This article presents a unified approach to quadratic optimal control for both linear and nonlinear discrete-time systems, with a focus on trajectory tracking. The control strategy is based on minimizing a quadratic cost function that penalizes deviations of system states and control inputs from their desired trajectories. For linear systems, the classical Linear Quadratic Regulator (LQR) solution is derived using dynamic programming, resulting in recursive equations for feedback and feedforward terms. For nonlinear dynamics, the Iterative Linear Quadratic Regulator (iLQR) method is employed, which iteratively linearizes the system and solves a sequence of LQR problems to converge to an optimal policy. To implement this approach, a software service was developed and tested on several canonical models, including: Rayleigh oscillator, inverted pendulum on a moving cart, two-link manipulator, and quadcopter. The results confirm that iLQR enables efficient and accurate trajectory tracking in the presence of nonlinearities. To further enhance performance, it can be seamlessly integrated with Model Predictive Control (MPC), enabling online adaptation and improved robustness to constraints and system uncertainties.

In this work, we explore the application of barrier states (BaS) in the realm of safe nonlinear adaptive control. Our proposed framework derives barrier states for systems with parametric uncertainty, which are augmented into the uncertain dynamical model. We employ an adaptive nonlinear control strategy based on a control Lyapunov functions approach to design a stabilizing controller for the augmented system. The developed theory shows that the controller ensures safe control actions for the original system while meeting specified performance objectives. We validate the effectiveness of our approach through simulations on diverse systems, including a planar quadrotor subject to unknown drag forces and an adaptive cruise control system, for which we provide comparisons with existing methodologies.

Underwater optical wireless technologies offer multiple advantages over the acoustic technology. Acoustic signals, for instance, are susceptible to noise from marine sources due to marine life and human activities. This is not the case with optical signals. However, absorption and scattering significantly attenuate optical signals. This limits the communication range and requires higher transmission power or more sensitive receivers to detect transmitted light. Therefore, it is necessary to design underwater optical systems with a higher transmission rate and reduced attenuation. To this end, we introduce a framework for designing optical signaling constellations employing multi-wavelength light sources to account for the transmission distance and achievable rate. In particular, we redefine the color-shift keying (CSK) constraint region to target blue light and adapt to marine environments. We discuss an example of 4-point underwater CSK. The corresponding analytical results demonstrate the trade-offs between the symbol error probability, achievable rate, and transmission range of the proposed scheme.

The State-Dependent Riccati Equation (SDRE) approach has emerged as a systematic and effective means of designing nearly optimal nonlinear controllers. The Barrier States (BaS) embedding methodology was developed recently for safe multi-objective controls in which the safety condition is manifested as a state to be controlled along with other states of the system. The overall system, termed the safety embedded system, is highly nonlinear even if the original system is linear. This paper develops a nonlinear nearly optimal safe feedback control technique by combining the two strategies effectively. First, the BaS is derived in an extended linearization formulation to be subsequently used to form an extended safety embedded system. A new optimal control problem is formed thereafter, which is used to construct a safety embedded State-Dependent Riccati Equation, termed BaS-SDRE, whose solution approximates the solution of the optimal control problem's associated Hamilton-Jacobi-Bellman (HJB) equation. The BaS-SDRE is then solved online to synthesize the nearly optimal safe control. The proposed technique's efficacy is demonstrated on an unstable, constrained linear system that shows how the synthesized control reacts to nonlinearities near the unsafe region, a nonlinear flight control system with limited path angular velocity that exists due to structural and dynamic concerns, and a planar quadrotor system that navigates safely in a crowded environment.

We propose a perceptual chromatic adaptation transform for white balance that makes use of split-quaternions. The novelty of the present work, which is motivated by a recently developed quantum-like model of color perception, consists at stressing the link between the algebraic structures appearing in this model and a certain sub-algebra of the split-quaternions. We show the potentiality of this approach for color image processing applications by proposing a chromatic adaptation transform, implemented via an appropriate use of the split-quaternion multiplication. Moreover, quantitative comparisons with the widely used state-of-the art von Kries chromatic adaptation transform are provided.

Machine learning (ML)-based feedback channel coding has garnered significant research interest in the past few years. However, there has been limited research exploring ML approaches in the so-called "two-way" setting where two users jointly encode messages and feedback for each other over a shared channel. In this work, we present a general architecture for ML-based two-way feedback coding, and show how several popular one-way schemes can be converted to the two-way setting through our framework. We compare such schemes against their one-way counterparts, revealing error-rate benefits of ML-based two-way coding in certain signal-to-noise ratio (SNR) regimes. We then analyze the tradeoffs between error performance and computational overhead for three state-of-the-art neural network coding models instantiated in the two-way paradigm.

As a revolutionary paradigm for intelligently controlling wireless channels, intelligent reflecting surface (IRS) has emerged as a promising technology for future sixth-generation (6G) wireless communications. While IRS-aided communication systems can achieve attractive high channel gains, existing schemes require plenty of IRS elements to mitigate the ``multiplicative fading'' effect in cascaded channels, leading to high complexity for real-time beamforming and high signaling overhead for channel estimation. In this paper, the concept of sustainable intelligent element-grouping IRS (IEG-IRS) is proposed to overcome those fundamental bottlenecks. Specifically, based on the statistical channel state information (S-CSI), the proposed grouping strategy intelligently pre-divide the IEG-IRS elements into multiple groups based on the beam-domain grouping method, with each group sharing the common reflection coefficient and being optimized in real time using the instantaneous channel state information (I-CSI). Then, we further analyze the asymptotic performance of the IEG-IRS to reveal the substantial capacity gain in an extremely large-scale IRS (XL-IRS) aided single-user single-input single-output (SU-SISO) system. In particular, when a line-of-sight (LoS) component exists, it demonstrates that the combined cascaded link can be considered as a ``deterministic virtual LoS'' channel, resulting in a sustainable squared array gain achieved by the IEG-IRS. Finally, we formulate a weighted-sum-rate (WSR) maximization problem for an IEG-IRS-aided multiuser multiple-input single-output (MU-MISO) system and a two-stage algorithm for optimizing the beam-domain grouping strategy and the multi-user active-passive beamforming is proposed.

The rapid advancement of deep learning (DL) has transformed healthcare, particularly in cancer detection and diagnosis. DL surpasses traditional machine learning and human accuracy, making it a critical tool for identifying diseases. Despite numerous reviews on DL in healthcare, a comprehensive analysis of its role in cancer detection remains limited. Existing studies focus on specific aspects, leaving gaps in understanding its broader impact. This paper addresses these gaps by reviewing advanced DL techniques, including transfer learning (TL), reinforcement learning (RL), federated learning (FL), Transformers, and large language models (LLMs). These approaches enhance accuracy, tackle data scarcity, and enable decentralized learning while maintaining data privacy. TL adapts pre-trained models to new datasets, improving performance with limited labeled data. RL optimizes diagnostic pathways and treatment strategies, while FL fosters collaborative model development without sharing sensitive data. Transformers and LLMs, traditionally used in natural language processing, are now applied to medical data for improved interpretability. Additionally, this review examines these techniques' efficiency in cancer diagnosis, addresses challenges like data imbalance, and proposes solutions. It serves as a resource for researchers and practitioners, providing insights into current trends and guiding future research in advanced DL for cancer detection.

Cancer remains one of the leading causes of mortality worldwide, and among its many forms, brain tumors are particularly notorious due to their aggressive nature and the critical challenges involved in early diagnosis. Recent advances in artificial intelligence have shown great promise in assisting medical professionals with precise tumor segmentation, a key step in timely diagnosis and treatment planning. However, many state-of-the-art segmentation methods require extensive computational resources and prolonged training times, limiting their practical application in resource-constrained settings. In this work, we present a novel dual-decoder U-Net architecture enhanced with attention-gated skip connections, designed specifically for brain tumor segmentation from MRI scans. Our approach balances efficiency and accuracy by achieving competitive segmentation performance while significantly reducing training demands. Evaluated on the BraTS 2020 dataset, the proposed model achieved Dice scores of 85.06% for Whole Tumor (WT), 80.61% for Tumor Core (TC), and 71.26% for Enhancing Tumor (ET) in only 50 epochs, surpassing several commonly used U-Net variants. Our model demonstrates that high-quality brain tumor segmentation is attainable even under limited computational resources, thereby offering a viable solution for researchers and clinicians operating with modest hardware. This resource-efficient model has the potential to improve early detection and diagnosis of brain tumors, ultimately contributing to better patient outcomes

This paper investigates backdoor attack planning in stochastic control systems modeled as Markov Decision Processes (MDPs). In a backdoor attack, the adversary provides a control policy that behaves well in the original MDP to pass the testing phase. However, when such a policy is deployed with a trigger policy, which perturbs the system dynamics at runtime, it optimizes the attacker's objective instead. To solve jointly the control policy and its trigger, we formulate the attack planning problem as a constrained optimal planning problem in an MDP with augmented state space, with the objective to maximize the attacker's total rewards in the system with an activated trigger, subject to the constraint that the control policy is near optimal in the original MDP. We then introduce a gradient-based optimization method to solve the optimal backdoor attack policy as a pair of coordinated control and trigger policies. Experimental results from a case study validate the effectiveness of our approach in achieving stealthy backdoor attacks.

This paper investigates the application of a Model Predictive Controller (MPC) for the cruise control system of a quadrotor, focusing on hovering point stabilization and reference tracking. Initially, a full-state-feedback MPC is designed for the ideal scenario. To account for real-world conditions, a constant disturbance is introduced to the quadrotor, simulating a gust of wind in a specific direction. In response, an output-feedback offset-free MPC is developed to stabilize the quadrotor while rejecting the disturbance. We validate the design of the controller by conducting stability analysis, as well as numerical simulations under different circumstances. It is shown that the designed controller can achieve all the expected goals for the cruise control, including reference tracking and disturbance rejection. This project was implemented using Python and the CVXPY library for convex optimization.

This paper studies the synthesis of a joint control and active perception policy for a stochastic system modeled as a partially observable Markov decision process (POMDP), subject to temporal logic specifications. The POMDP actions influence both system dynamics (control) and the emission function (perception). Beyond task completion, the planner seeks to maximize information gain about certain temporal events (the secret) through coordinated perception and control. To enable active information acquisition, we introduce minimizing the Shannon conditional entropy of the secret as a planning objective, alongside maximizing the probability of satisfying the temporal logic formula within a finite horizon. Using a variant of observable operators in hidden Markov models (HMMs) and POMDPs, we establish key properties of the conditional entropy gradient with respect to policy parameters. These properties facilitate efficient policy gradient computation. We validate our approach through graph-based examples, inspired by common security applications with UAV surveillance.

The operation of CMOS Field Programmable Gate Arrays (FPGAs) at extremely cold environments as low as 4 K is demonstrated. Various FPGA and periphery hardware design techniques spanning from HDL design to improvements of peripheral circuitry such as discrete voltage regulators are displayed, and their respective performances are reported. While general operating conditions for voltage regulators are widened, FPGAs see a broader temperature range with improved jitter performance, reduced LUT delays, and enhanced transceiver performance at extremely low temperatures.

To improve ATR identification of ships at sea requires an advanced ISAR processor - one that not only provides focused images but can also determine the pose of the ship. This tells us whether the image shows a profile (vertical plane) view, a plan (horizontal plane) view or some view in between. If the processor can provide this information, then the ATR processor can try to match the images with known vertical or horizontal features of ships and, in conjunction with estimated ship length, narrow the set of possible identifications. This paper extends the work of Melendez and Bennett [M-B, Ref. 1] by combining a focus algorithm with a method that models the angles of the ship relative to the radar. In M-B the algorithm was limited to a single angle and the plane of rotation was not determined. This assumption may be fine for a short time image where there is limited data available to determine the pose. However, the present paper models the ship rotation with two angles - aspect angle, representing rotation in the horizontal plane, and tilt angle, representing variations in the effective grazing angle to the ship.

Accurate estimation of state of health (SOH) is critical for battery applications. Current model-based SOH estimation methods typically rely on low C-rate constant current tests to extract health parameters like solid phase volume fraction and lithium-ion stoichiometry, which are often impractical in real-world scenarios due to time and operational constraints. Additionally, these methods are susceptible to modeling uncertainties that can significantly degrade the estimation accuracy, especially when jointly estimating multiple parameters. In this paper, we present a novel reference voltage-based method for robust battery SOH estimation. This method utilizes the voltage response of a battery under a predefined current excitation at the beginning of life (BOL) as a reference to compensate for modeling uncertainty. As the battery degrades, the same excitation is applied to generate the voltage response, which is compared with the BOL trajectory to estimate the key health parameters accurately. The current excitation is optimally designed using the Particle Swarm Optimization algorithm to maximize the information content of the target parameters. Simulation results demonstrate that our proposed method significantly improves parameter estimation accuracy under different degradation levels, compared to conventional methods relying only on direct voltage measurements. Furthermore, our method jointly estimates four key SOH parameters in only 10 minutes, making it practical for real-world battery health diagnostics, e.g., fast testing to enable battery repurposing.

Menisci are cartilaginous tissue found within the knee that contribute to joint lubrication and weight dispersal. Damage to menisci can lead to onset and progression of knee osteoarthritis (OA), a condition that is a leading cause of disability, and for which there are few effective therapies. Accurate automated segmentation of menisci would allow for earlier detection and treatment of meniscal abnormalities, as well as shedding more light on the role the menisci play in OA pathogenesis. Focus in this area has mainly used variants of convolutional networks, but there has been no attempt to utilise recent large vision transformer segmentation models. The Segment Anything Model (SAM) is a so-called foundation segmentation model, which has been found useful across a range of different tasks due to the large volume of data used for training the model. In this study, SAM was adapted to perform fully-automated segmentation of menisci from 3D knee magnetic resonance images. A 3D U-Net was also trained as a baseline. It was found that, when fine-tuning only the decoder, SAM was unable to compete with 3D U-Net, achieving a Dice score of $0.81\pm0.03$, compared to $0.87\pm0.03$, on a held-out test set. When fine-tuning SAM end-to-end, a Dice score of $0.87\pm0.03$ was achieved. The performance of both the end-to-end trained SAM configuration and the 3D U-Net were comparable to the winning Dice score ($0.88\pm0.03$) in the IWOAI Knee MRI Segmentation Challenge 2019. Performance in terms of the Hausdorff Distance showed that both configurations of SAM were inferior to 3D U-Net in matching the meniscus morphology. Results demonstrated that, despite its generalisability, SAM was unable to outperform a basic 3D U-Net in meniscus segmentation, and may not be suitable for similar 3D medical image segmentation tasks also involving fine anatomical structures with low contrast and poorly-defined boundaries.

The ability to update a path plan is a required capability for autonomous mobile robots navigating through uncertain environments. This paper proposes a re-planning strategy using a multilayer planning and control framework for cases where the robot's environment is partially known. A medial axis graph-based planner defines a global path plan based on known obstacles where each edge in the graph corresponds to a unique corridor. A mixed-integer model predictive control (MPC) method detects if a terminal constraint derived from the global plan is infeasible, subject to a non-convex description of the local environment. Infeasibility detection is used to trigger efficient global re-planning via medial axis graph edge deletion. The proposed re-planning strategy is demonstrated experimentally.