I am a Research Fellow at the INAF Astrophysical Observatory of Catania, where I develop and implement intelligent predictive maintenance systems for astronomical infrastructure. My research is centered on developing novel methodologies that combine segmentation models, change point detection, and heterogeneous ensemble learning to forecast failures in critical infrastructure.

My work demonstrates that these methods significantly enhance the early detection of anomalies across diverse domains. I have successfully applied this framework to ensure the operational resilience of astronomical observatories, such as the Cherenkov Telescope Array Observatory (CTAO), and to optimize reliability in industrial production contexts.

My background in computational biology provided a rigorous foundation in extracting subtle signals from complex, noisy data—a skill I now deploy to diagnose the “health” of everything from telescope sensors to industrial compressors. My goal is to build intelligent, data-driven systems that not only predict failures but also provide actionable insights to ensure the continuous and reliable operation of the technologies that drive science and industry.

Education

PhD in Computational Biology (12/2020) at Selinus University of Science and Literature (Bologna, Italy). Thesis title: Unsupervised clustering approach to characterize the CpG Island distribution of the Andes Hantavirus, Prof. Salvatore Fava Ph D, Prof. Shu-Lin Liu. Examination fields: Bioinformatics, Statistical methods, Clustering techniques, Virology

Master’s Degree in Computer Science (12/2000) at the University of Catania (Catania, Italy). Thesis Title: Covert channel analysis of Linux file system, Prof. V. Cutello. Examination fields: Linux kernel development, security enhancement, information