Explainable AI for Car Crash Detection using Multivariate Time Series
Lorenzo Tronchin, Rosa Sicilia, Ermanno Cordelli, Lorenzo Ricciardi Celsi, Daniele Maccagnola, Massimo Natale, Paolo Soda · 2021
The pervasiveness of Artificial Intelligence approaches in effectively supporting the decision process in many applications has raised the need to explain their behaviour. In this context, we present the application and evaluation of three eXplainable Artificial Intelligence methods in a real-world multimodal task of anomaly detection on telematics data. We cope with the challenge of explaining Multivariate Time Series and of translating methods designed for images to this domain.