Fault Detection and Control Systems

Últimos artículos

• Causal Learning in Biomedical Applications: Krebs Cycle as a Benchmark

  Xiaoyu He, Petr Ry\v{s}av\'y, Jakub Mare\v{c}ek · 23 de marzo de 2026

  Learning causal relationships from time series data is an important but challenging problem. Existing synthetic datasets often contain hidden artifacts that can be exploited by causal discovery methods, reducing their usefulness for benchmarking. We present a new benchmark dataset based on simulatio…

• HEP Statistical Inference for UAV Fault Detection: CLs, LRT, and SBI Applied to Blade Damage

  Khushiyant · 20 de marzo de 2026

  This paper transfers three statistical methods from particle physics to multirotor propeller fault detection: the likelihood ratio test (LRT) for binary detection, the CLs modified frequentist method for false alarm rate control, and sequential neural posterior estimation (SNPE) for quantitative fau…

• Nonlinear Bayesian Doppler Tomography for Simultaneous Reconstruction of Flow and Temperature

  Kenji Ueda, Masaki. Nishiura · 17 de marzo de 2026

  We present a nonlinear Bayesian tomographic framework for Doppler spectral imaging that enables simultaneous reconstruction of emissivity, ion temperature, and flow velocity from line-integrated spectra. The method employs nonlinear Gaussian process tomography (GPT) with a Laplace approximation whil…

• Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness

  Tsubasa Takahashi, Shojiro Yamabe, Futa Waseda, Kento Sasaki · 17 de marzo de 2026

  Differential Attention (DA) has been proposed as a refinement to standard attention, suppressing redundant or noisy context through a subtractive structure and thereby reducing contextual hallucination. While this design sharpens task-relevant focus, we show that it also introduces a structural frag…

• Disentangling Slow and Fast Temporal Dynamics in Degradation Inference with Hierarchical Differential Models

  Mengjie Zhao, Olga Fink · 13 de marzo de 2026

  Reliable inference of system degradation from sensor data is fundamental to condition monitoring and prognostics in mechanical and infrastructural systems. Since degradation is rarely directly observable and measurable, it must be inferred to enable accurate health assessment and decision-making. Th…

• Testability of Instrumental Variables in Additive Nonlinear, Non-Constant Effects Models

  Xichen Guo, Zheng Li, Biwei Huang, Yan Zeng, Zhi Geng, Feng Xie · 13 de marzo de 2026

  We address the issue of the testability of instrumental variables derived from observational data. Most existing testable implications are centered on scenarios where the treatment is a discrete variable, e.g., instrumental inequality (Pearl, 1995), or where the effect is assumed to be constant, e.g…

• Prognostics for Autonomous Deep-Space Habitat Health Management under Multiple Unknown Failure Modes

  Benjamin Peters, Ayush Mohanty, Xiaolei Fang, Stephen K. Robinson, Nagi Gebraeel · 11 de marzo de 2026

  Deep-space habitats (DSHs) are safety-critical systems that must operate autonomously for long periods, often beyond the reach of ground-based maintenance or expert intervention. Monitoring health and anticipating failures are essential for safe operations. Prognostics based on remaining useful life…

• Quantum parameter estimation with uncertainty quantification from continuous measurement data using neural network ensembles

  Amanuel Anteneh · 3 de marzo de 2026

  We show that ensembles of deep neural networks, called deep ensembles, can be used to perform quantum parameter estimation while also providing a means for quantifying uncertainty in parameter estimates, which is a key advantage of using Bayesian inference for parameter estimation that is lost when …

• Rethinking Disentanglement under Dependent Factors of Variation

  Antonio Almud\'evar, Alfonso Ortega · 25 de febrero de 2026

  Representation learning is an approach that allows to discover and extract the factors of variation from the data. Intuitively, a representation is said to be disentangled if it separates the different factors of variation in a way that is understandable to humans. Definitions of disentanglement and…

• The MAPS Algorithm: Fast model-agnostic and distribution-free prediction intervals for supervised learning

  Daniel Salnikov, Dan Leonte, Kevin Michalewicz · 24 de febrero de 2026

  A fundamental problem in modern supervised learning is computing reliable conditional prediction intervals in high-dimensional settings: existing methods often rely on restrictive modelling assumptions, do not scale as predictor dimension increases, or only guarantee marginal (population-level) rath…

• A Unifying Framework for Robust and Efficient Inference with Unstructured Data

  Jacob Carlson, Melissa Dell · 20 de febrero de 2026

  To analyze unstructured data (text, images, audio, video), economists typically first extract low-dimensional structured features with a neural network. Neural networks do not make generically unbiased predictions, and biases will propagate to estimators that use their predictions. While structured …

• Robust Causal Discovery in Real-World Time Series with Power-Laws

  Matteo Tusoni, Giuseppe Masi, Andrea Coletta, Aldo Glielmo, Viviana Arrigoni, Novella Bartolini · 19 de febrero de 2026

  Exploring causal relationships in stochastic time series is a challenging yet crucial task with a vast range of applications, including finance, economics, neuroscience, and climate science. Many algorithms for Causal Discovery (CD) have been proposed; however, they often exhibit a high sensitivity …

• Permutation-based Inference for Variational Learning of Directed Acyclic Graphs

  Edwin V. Bonilla, Pantelis Elinas, He Zhao, Maurizio Filippone, Vassili Kitsios, Terry O'Kane · 17 de febrero de 2026

  Estimating the structure of Bayesian networks as directed acyclic graphs (DAGs) from observational data is a fundamental challenge, particularly in causal discovery. Bayesian approaches excel by quantifying uncertainty and addressing identifiability, but key obstacles remain: (i) representing distri…

• Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization

  Amit Attia, Tomer Koren · 17 de febrero de 2026

  The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid search, especially for training modern large-scale models with billions of parameters. We identify a theoretical advantage of learning rate annealing schemes that decay …

• Sensor-fusion based Prognostics for Deep-space Habitats Exhibiting Multiple Unlabeled Failure Modes

  Benjamin Peters, Ayush Mohanty, Xiaolei Fang, Nagi Gebraeel, Stephen K. Robinson · 17 de febrero de 2026

  Deep-space habitats are complex systems that must operate autonomously over extended durations without ground-based maintenance. These systems are vulnerable to multiple, often unknown, failure modes that affect different subsystems and sensors in mode-specific ways. Developing accurate remaining us…

• AMAQA: A Metadata-based QA Dataset for RAG Systems

  Davide Bruni, Marco Avvenuti, Nicola Tonellotto, Maurizio Tesconi · 13 de febrero de 2026

  Retrieval-augmented generation (RAG) systems are widely used in question-answering (QA) tasks, but current benchmarks lack metadata integration, limiting their evaluation in scenarios requiring both textual data and external information. To address this, we present AMAQA, a new open-access QA datase…

• Uncertainty-driven Embedding Convolution

  Sungjun Lim, Kangjun Noh, Youngjun Choi, Heeyoung Lee, Kyungwoo Song · 12 de febrero de 2026

  Text embeddings are essential components in modern NLP pipelines. Although numerous embedding models have been proposed, no single model consistently dominates across domains and tasks. This variability motivates the use of ensemble techniques to combine complementary strengths. However, most existi…

• Towards Transparent and Efficient Anomaly Detection in Industrial Processes through ExIFFI

  Davide Frizzo, Francesco Borsatti, Alessio Arcudi, Antonio De Moliner, Roberto Oboe, Gian Antonio Susto · 10 de febrero de 2026

  Anomaly Detection (AD) is crucial in industrial settings to streamline operations by detecting underlying issues. Conventional methods merely label observations as normal or anomalous, lacking crucial insights. In Industry 5.0, interpretable outcomes become desirable to enable users to understand th…

• Energy Guided smoothness to improve Robustness in Graph Classification

  Farooq Ahmad Wani, Maria Sofia Bucarelli, Andrea Giuseppe Di Francesco, Oleksandr Pryymak, Fabrizio Silvestri · 6 de febrero de 2026

  Graph Neural Networks (GNNs) are powerful at solving graph classification tasks, yet applied problems often contain noisy labels. In this work, we study GNN robustness to label noise, demonstrate GNN failure modes when models struggle to generalise on low-order graphs, low label coverage, or when a …

• Causal Graph Spatial-Temporal Autoencoder for Reliable and Interpretable Process Monitoring

  Xiangrui Zhang, Chunyue Song, Wei Dai, Zheng Zhang, Kaihua Gao, Furong Gao · 4 de febrero de 2026

  To improve the reliability and interpretability of industrial process monitoring, this article proposes a Causal Graph Spatial-Temporal Autoencoder (CGSTAE). The network architecture of CGSTAE combines two components: a correlation graph structure learning module based on spatial self-attention mech…

• Exact Solution to Data-Driven Inverse Optimization of MILPs in Finite Time via Gradient-Based Methods

  Akira Kitaoka · 4 de febrero de 2026

  A data-driven inverse optimization problem (DDIOP) seeks to estimate an objective function (i.e., weights) that is consistent with observed optimal-solution data, and is important in many applications, including those involving mixed integer linear programs (MILPs). In the DDIOP for MILPs, the predi…

• Agnostic Learning of Arbitrary ReLU Activation under Gaussian Marginals

  Anxin Guo, Aravindan Vijayaraghavan · 4 de febrero de 2026

  We consider the problem of learning an arbitrarily-biased ReLU activation (or neuron) over Gaussian marginals with the squared loss objective. Despite the ReLU neuron being the basic building block of modern neural networks, we still do not understand the basic algorithmic question of whether one ar…

• Frictional Q-Learning

  Hyunwoo Kim, Hyo Kyung Lee · 3 de febrero de 2026

  Off-policy reinforcement learning suffers from extrapolation errors when a learned policy selects actions that are weakly supported in the replay buffer. In this study, we address this issue by drawing an analogy to static friction in classical mechanics. From this perspective, the replay buffer is …

• From drift to adaptation to the failed ml model: Transfer Learning in Industrial MLOps

  Waqar Muhammad Ashraf, Talha Ansar, Fahad Ahmed, Jawad Hussain, Muhammad Mujtaba Abbas, Vivek Dua · 3 de febrero de 2026

  Model adaptation to production environment is critical for reliable Machine Learning Operations (MLOps), less attention is paid to developing systematic framework for updating the ML models when they fail under data drift. This paper compares the transfer learning enabled model update strategies inc…

• Exploring the Limitations of kNN Noisy Feature Detection and Recovery for Self-Driving Labs

  Qiuyu Shi, Kangming Li, Yao Fehlis, Runze Zhang, Daniel Persaud, Robert Black, Jason Hattrick-Simpers · 3 de febrero de 2026

  Self-driving laboratories (SDLs) have shown promise to accelerate materials discovery by integrating machine learning with automated experimental platforms. However, errors in the capture of input parameters may corrupt the features used to model system performance, compromising current and future c…