1. POMDP inference and robust solution via deep reinforcement learning: an application to railway optimal maintenance 

   Arcieri, Giacomo; Hoelzl, Cyprien; Schwery, Oliver; et al. (2024)

   Machine Learning

   Partially Observable Markov Decision Processes (POMDPs) can model complex sequential decision-making problems under stochastic and uncertain environments. A main reason hindering their broad adoption in real-world applications is the unavailability of a suitable POMDP model or a simulator thereof. Available solution algorithms, such as Reinforcement Learning (RL), typically benefit from the knowledge of the transition dynamics and the ...

   Journal Article

2. Dual Functional Antibacterial-Antioxidant Core/Shell Alginate/Poly(ε-caprolactone) Nanofiber Membrane: A Potential Wound Dressing 

   Norouzi, Mohammad-Reza; Ghasemi-Mobarakeh, Laleh; Itel, Fabian; et al. (2024)

   ACS Omega

   Core/shell nanofibers offer the advantage of encapsulating multiple drugs with different hydrophilicity in the core and shell, thus allowing for the controlled release of pharmaceutic agents. Specifically, the burst release of hydrophilic drugs from such fiber membranes causes an instantaneous high drug concentration, whereas a long and steady release is usually desired. Herein, we tackle the problem of the initial burst release by the ...

   Journal Article

3. Habitat suitability models reveal the spatial signal of environmental DNA in riverine networks 

   Brantschen, Jeanine; Fopp, Fabian; Adde, Antoine; et al. (2024)

   Ecography

   The rapid loss of biodiversity in freshwater systems asks for a robust and spatially explicit understanding of species' occurrences. As two complementing approaches, habitat suitability models provide information about species' potential occurrence, while environmental DNA (eDNA) based assessments provide indication of species' actual occurrence. Individually, both approaches are used in ecological studies to characterize biodiversity, ...

   Journal Article

4. Deep-learning-based decomposition of overlapping-sparse images: application at the vertex of simulated neutrino interactions 

   Alonso-Monsalve, Saul; Sgalaberna, Davide; Zhao, Xingyu; et al. (2024)

   Communications Physics

   Image decomposition plays a crucial role in various computer vision tasks, enabling the analysis and manipulation of visual content at a fundamental level. Overlapping and sparse images pose unique challenges for decomposition algorithms due to the scarcity of meaningful information to extract components. Here, we present a solution based on deep learning to accurately extract individual objects within multi-dimensional overlapping-sparse ...

   Journal Article

5. Development of an Intelligent Tutoring System That Assesses Internal Visualization Skills in Engineering Using Multimodal Triangulation 

   Sung, Hanall; Rau, Martina A.; Van Veen, Barry D. (2024)

   IEEE Transactions on Learning Technologies

   In many science, technology, engineering, and mathematics (STEM) domains, instruction on foundational concepts heavily relies on visuals. Instructors often assume that students can mentally visualize concepts but students often struggle with internal visualization skills-the ability to mentally visualize information. In order to address this issue, we developed a formal, as well as an informal assessment of students' internal visualization ...

   Journal Article

Mehr anzeigen