Adjunct Professor of "Mathematics and Statistics" (MAT/07)

◈ Main tasks:• Responsible for the development of "ASPIS", a real-time ML-based GNSS Spoofing Detection Algorithm (GSD) within the CERTIFLIGHT project (Horizon EUSPA Space). A preliminary version of ASPIS has been validated during the JammerTest 2024• Responsible for the development of the “Sentinel-Eyes” devices for the SENTINEL project (ESA NAVISP programme)• Design, configuration and validation of the "MARLIN" device, a multi-sensor portable device for GNSS and IMU data acquisition and analysis in different domains (Maritime, Terrestrial, Aerospace)• Responsabile for the company's Computing Facility (NeXus Lab)◈ Partecipation in the "Jammer Test 2024" (https://jammertest.no) ◈ Partecipation in the "International Astronautical Congress (IAC) 2024"

Teaching courses of Machine Learning applied to Biological Systems

"Molecular Modeling" Research Group (https://molmod.dsf.unica.it/former-members/)◈ Main research interests:• Developing of EDES (Ensemble Docking with Enhanced sampling of pocket Shape), a protocol based on enhanced-sampling molecular dynamics simulations to improve the predictive power of "molecular docking" and "virtual screening"• Developing of new algorithms to characterize the shape and volume of protein binding pockets • Investigating the structural assembly and the stability of RND efflux pumps• Studying the interactions between different classes of antibiotics and the protein "AcrB"-------------------------------------------------◈ Lecturer (University of Cagliari) - A.A. 2022/2023:➮ Module of "Machine learning methods in Computational Biophysics"("Molecular Modeling of Biological Systems" course for graduate Physics students)Syllabus:• Introduction to big data and to machine learning• Unsupervised learning: clustering algorithms• Supervised learning: classification vs. regression tasks• K-Nearest Neighbors (KNN) and Support-Vector Machines (SVM) models• Introduction to "Natural language processing" (NLP)➮ Module of "Machine learning methods in Computational Biophysics"("Methods and Models in Computational Biophysics" course for graduate Physics students)Syllabus:• Machine and deep learning. Unsupervised vs supervised learning• Clustering methods: the K-means algorithm• Introduction to the Principal Component Analysis (PCA)• Supervised learning: training, validation and testing• K-fold cross validation and overfitting• The confusion matrix. Sensitivity, specificity, precision and accuracy metrics• Support-Vector Machine (SVM) and Random Forest (RF) models• Deep Learning: perceptrons, recurrent and convolutional networks

Trainer at the BioExcel Summer/Winter School on "Biomolecular Simulations" from 2018 to 2022, including both virtual and live (face-to-face) editions• Lectures on computational techniques to reproduce ligand-induced structural rearrangements in proteins• Hands-on tutorials on a metadynamics-based protocol to improve the predictive power of "molecular docking" (EDES Tutorial)