Electrical Engineering and Systems Science
PulseAugur coverage of Electrical Engineering and Systems Science — every cluster mentioning Electrical Engineering and Systems Science across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New framework tracks concrete crack evolution across views and time
Researchers have developed a new framework to track crack evolution in concrete structures, addressing the challenge of maintaining crack identity across different camera views and over time. This geometry-assisted, mor…
-
New self-supervised sonar imaging technique suppresses noise and blur
Researchers have developed a novel self-supervised framework for enhancing multibeam imaging sonar data. This method jointly addresses speckle noise and system-induced blur without requiring clean ground truth images. B…
-
New runtime monitor audits learned safety certificates for stochastic systems
Researchers have developed a new runtime monitor designed to audit learned barrier certificates for stochastic systems. This monitor aims to detect when the validity of a deployed safety certificate deteriorates due to …
-
New one-pass network challenges recursion for medical image registration
Researchers have developed M2CG, a novel one-pass deep learning network for deformable image registration that aims to achieve high accuracy without the computational overhead of recursive methods. M2CG utilizes multi-l…
-
EarLog system monitors hearing risk using acoustic reflex detection
Researchers have developed EarLog, a novel system designed to monitor hearing risk by detecting the acoustic reflex (AR) during everyday listening. Unlike traditional methods that only identify damage after it occurs, E…
-
New algorithm simplifies fractional-order dynamical system identification
Researchers have developed a new algorithm for identifying discrete-time fractional-order dynamical systems (FoDS). This algorithm simplifies the identification process by reformulating it as a least squares estimation,…
-
New optimization framework enhances VP-SVM training for road abnormality detection
Researchers have developed a new second-order optimization framework designed to improve the training of variable projection functionals, particularly for kernel methods. This framework has been applied to efficiently t…
-
New ZAGNet model uses graph neural networks for lung ultrasound diagnosis
Researchers have developed ZAGNet, a novel Zone-Aware Graph Neural Network designed for patient-level lung ultrasound diagnosis. This network addresses limitations in current AI methods by representing pathology finding…
-
New multi-agent system enhances auditory scene analysis speed and robustness
Researchers have developed a new multi-agent system for auditory scene analysis (ASA) that significantly improves localization speed and robustness. This system models an ASA as multiple agents, each handling specific t…
-
New control architecture ensures safe coordination for scalar agents
This paper introduces a novel networked Admissibility-Preserving Control (APC) architecture designed for safety-critical coordination among scalar agents. The system ensures that agents' outputs remain within a common m…
-
New framework audits bias and safety in voice AI customer care
A new research paper introduces a framework for auditing bias and safety in voice AI systems used for customer care. The proposed method categorizes voice AI architectures, including cascaded ASR-to-language model-to-TT…
-
$S^3$ method optimizes neural network abstractions for dynamical systems
Researchers have developed a new method called a smooth simulation surrogate ($S^3$) to optimize discrete abstractions of dynamical systems, particularly those with neural network controllers. This differentiable object…
-
Adaptive control problem solved: Exact value for adversarial scenarios determined
Researchers have solved a fundamental problem in adaptive control theory, determining the exact value of scalar adversarial adaptive control under significant parametric uncertainty. The study establishes that the least…
-
New dynamic programming approach optimizes multi-agent communication-control
Researchers have developed a new dynamic-programming approach to optimize joint communication-control strategies in multi-agent linear systems. This method specifically addresses problems with quadratic costs and partia…
-
AI research questions reliability of distance-based estimation in medical imaging representations
A new research paper published on arXiv explores the reliability of distance-based estimation methods for AI-generated representations, particularly in the context of medical imaging. The study found that while disentan…
-
New method optimizes foundation model self-refinement as optimal stopping problem
Researchers have introduced a novel method to optimize the self-refinement process of foundation models, treating it as an optimal stopping problem. This approach aims to determine the ideal number of refinement iterati…
-
New method infers immune cell network topology from limited data
Researchers have developed a novel method for inferring the topology of immune cell networks using cell amount data. This approach addresses challenges like the absence of standard analytical models and limited experime…
-
New framework streamlines patient-specific surgical registration using synthetic pretraining
Researchers have developed a new framework for patient-specific 2D/3D registration, a crucial process for image-guided surgeries that aligns preoperative CT scans with intraoperative X-ray images. The proposed method ut…
-
New Bayesian Signal Decomposition Method Uses Diffusion-Gibbs Sampling
Researchers have developed a novel Bayesian framework for signal component decomposition, combining Gibbs sampling with diffusion priors. This new method, termed Diffusion-within-Gibbs (DiG), allows for the unified inco…
-
Ensemble classifiers boost power line outage localization performance
Researchers have explored the use of ensemble classifiers to improve the performance of line outage localization in power systems. Their study compared various ensemble methods against single-model approaches, utilizing…