ODIN AD: a framework supporting the life-cycle of time series anomaly detection applications

Feb 4, 2023·
Niccolò Zangrando
,
Piero Fraternali
,
Rocio Nahime Torres
,
Marco Petri
Nicolò Pinciroli
Nicolò Pinciroli
,
Sergio Luis Herrera Gonzalez
· 0 min read
PDF
Abstract
Anomaly detection (AD) in numerical temporal data series is a prominent task in many domains, including the analysis of industrial equipment operation, the processing of IoT data streams, and the monitoring of appliance energy consumption. The life-cycle of an AD application with a Machine Learning (ML) approach requires data collection and preparation, algorithm design and selection, training, and evaluation. All these activities contain repetitive tasks which could be supported by tools. This paper describes ODIN AD, a framework assisting the life-cycle of AD applications in the phases of data preparation, prediction performance evaluation, and error diagnosis.
Type
Publication
International Workshop on Advanced Analytics and Learning on Temporal Data
publications
Nicolò Pinciroli
Authors
Postdoctoral Research Fellow

I am a postdoctoral research fellow at Politecnico di Milano, working at the intersection of artificial intelligence and astrophysics. I develop methods that combine spectra, images, time series, and scientific literature to study rare astronomical sources and transient phenomena. My research spans multimodal representation learning, explainable AI, gravitationally lensed transients, and the search for candidate pulsating ultraluminous X-ray sources.

I collaborate with INAF’s Osservatorio Astronomico di Roma and AstroAI at the Center for Astrophysics | Harvard & Smithsonian. I also work on time-series anomaly detection, predictive maintenance, and language-model applications for energy efficiency, and lead Work Package 3 of the Horizon Europe ENERGENIUS project.

I completed my PhD in Information Technology at Politecnico di Milano in June 2026, with the thesis “Making discoveries with multimodal astrophysics.”