The recent advancements in the research area demonstrate a strong focus on enhancing the reliability and robustness of systems through the integration of uncertainty quantification and real-time monitoring techniques. A significant trend is the adoption of Bayesian and conformal prediction methods to address the inherent uncertainties in various applications, ranging from autonomous robotics to healthcare. These methods not only improve the accuracy of predictions but also provide a measure of confidence, which is crucial for decision-making in critical domains. Additionally, the use of digital twins and ensemble deep learning models is gaining traction, offering continuous validation and adaptive control mechanisms. These developments are particularly noteworthy in dynamic and uncertain environments, such as autonomous navigation and intensive care unit interventions. The integration of theoretical guarantees with practical implementations is a common theme, ensuring that the proposed solutions are both robust and reliable. Overall, the field is moving towards more intelligent, adaptive, and trustworthy systems that can operate effectively under uncertainty.
Enhancing System Reliability through Uncertainty Quantification and Real-Time Monitoring
Sources
Digital Twin Enabled Runtime Verification for Autonomous Mobile Robots under Uncertainty
Pixel Intensity Tracking for Remote Respiratory Monitoring: A Study on Indonesian Subject
Conformal Prediction on Quantifying Uncertainty of Dynamic Systems
Finite Sample Analysis of Tensor Decomposition for Learning Mixtures of Linear Systems
U-FaceBP: Uncertainty-aware Bayesian Ensemble Deep Learning for Face Video-based Blood Pressure Measurement
Reliable Breast Cancer Molecular Subtype Prediction based on uncertainty-aware Bayesian Deep Learning by Mammography
Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework
Quantitative Predictive Monitoring and Control for Safe Human-Machine Interaction