Contribution to a book

This study investigates four feature selection methods ($χ^2$, ANOVA F-test, Lasso, and a Tree-based method) to enhance Acute Respiratory Distress Syndrome (ARDS) classification in time-series intensive care unit data using an existing Random Forest algorithm. While feature selection did not significantly improve ARDS classification performance, using a reduced number of features achieved comparable results to using the entire dataset. [...]

Protein–membrane interactions are increasingly recognized as key factors in amyloid-related pathologies, where amyloid proteins associate with lipid bilayers in ways that influence aggregation pathways and cytotoxic effects. Molecular dynamics (MD) simulations have become essential tools for investigating the molecular mechanisms underlying these interactions. [...]

Graph representation is a powerful abstraction of real-world objects and relations. Computing the Graph Edit Distance (GED) between graphs is critical in domains such as bioinformatics, machine learning, and pattern recognition [...]

Fluorine-18 plays a pivotal role in radiopharmaceuticals for positron emission tomography (PET) due to its favorable nuclear decay properties. Depending on the production method, fluorine-18 can be obtained in two distinct chemical forms: electrophilic [18F]fluorine gas and nucleophilic [18F]fluoride. [...]

We propose an improved Fourier Neural Operator (FNO) for modeling two-dimensional Rayleigh-Bénard convection by predicting time increments instead of full solutions, achieving higher accuracy than a standard FNO baseline. The resulting model is compact (314k parameters, 1.26 MB) and fast (7 ms inference), while maintaining similar accuracy as demonstrated in previous benchmarks. [...]

The PREFER (Polarization REsearch for Fusion Experiments and Reactors) collaboration aimsto address the know-hows in different fields and techniques to the challenging bet on energyproduction by nuclear fusion with polarized fuel. The collaboration involves different institutionsand researchers, sharing skills and peculiar abilities, having then possibilities to span over a varietyof tasks and objectives, which are under the responsibility of the authors of this contribution,leading their groups. [...]

Nuclear spin polarization has important applications across various fields, including physics andmedicine. It also offers several advantages, such as cross-section enhancement, in the five-nucleonfusion reactions, namely the D–T and D–$^3$He reactions. [...]

A new theoretical concept of the quantum mechanical processes in spin filter for the separation ofmetastable hydrogen atoms in individual hyperfine substates enables a number of new applications.For example, it is now possible to build a new generation of Lamb-shift polarimeter that canseparate not only 𝛼 but also the 𝛽 substates with $𝑚_𝐽 = −1/2$. This opens up completely newpossibilities for the search of hydrogen atoms in forbidden substates after the bound beta decayof the neutron. [...]

The LHCspin project is a future experimental project to install a polarized gas target within theLHCb detector at CERN Large Hadron Collider (LHC) in order to study the internal (spin-)structure of protons and neutrons. A key requirement of the project is the development of ahigh-performance polarized target system, which consists of three major components: an AtomicBeam Source (ABS), a target chamber, and a polarization measurement system. [...]