no code implementations • 3 Feb 2023 • Giovanni Soldi, Domenico Gaglione, Simone Raponi, Nicola Forti, Enrica d'Afflisio, Paweł Kowalski, Leonardo M. Millefiori, Dimitris Zissis, Paolo Braca, Peter Willett, Alain Maguer, Sandro Carniel, Giovanni Sembenini, Catherine Warner
The explosions on September 26th, 2022, which damaged the gas pipelines of Nord Stream 1 and Nord Stream 2, have highlighted the need and urgency of improving the resilience of Underwater Critical Infrastructures (UCIs).
no code implementations • 16 Jan 2023 • Paolo Braca, Leonardo M. Millefiori, Augusto Aubry, Antonio De Maio, Peter Willett
We study the performance of machine learning binary classification techniques in terms of error probabilities.
no code implementations • 22 Jul 2022 • Paolo Braca, Leonardo M. Millefiori, Augusto Aubry, Stefano Marano, Antonio De Maio, Peter Willett
In other words, the classification error probability convergence to zero and its rate can be computed on a portion of the dataset available for training.
no code implementations • 11 May 2022 • Samuele Capobianco, Nicola Forti, Leonardo M. Millefiori, Paolo Braca, Peter Willett
Recent deep learning methods for vessel trajectory prediction are able to learn complex maritime patterns from historical Automatic Identification System (AIS) data and accurately predict sequences of future vessel positions with a prediction horizon of several hours.
no code implementations • 12 Jan 2021 • Giovanni Soldi, Nicola Forti, Domenico Gaglione, Paolo Braca, Leonardo M. Millefiori, Stefano Marano, Peter Willett, Krishna Pattipati
The COVID-19 pandemic has, worldwide and up to December 2020, caused over 1. 7 million deaths, and put the world's most advanced healthcare systems under heavy stress.
1 code implementation • 7 Jan 2021 • Samuele Capobianco, Leonardo M. Millefiori, Nicola Forti, Paolo Braca, Peter Willett
Experimental results on vessel trajectories from an AIS dataset made freely available by the Danish Maritime Authority show the effectiveness of deep-learning methods for trajectory prediction based on sequence-to-sequence neural networks, which achieve better performance than baseline approaches based on linear regression or on the Multi-Layer Perceptron (MLP) architecture.
no code implementations • 23 Nov 2020 • Giovanni Soldi, Domenico Gaglione, Nicola Forti, Alessio Di Simone, Filippo Cristian Daffinà, Gianfausto Bottini, Dino Quattrociocchi, Leonardo M. Millefiori, Paolo Braca, Sandro Carniel, Peter Willett, Antonio Iodice, Daniele Riccio, Alfonso Farina
Maritime surveillance (MS) is of paramount importance for search and rescue operations, fishery monitoring, pollution control, law enforcement, migration monitoring, and national security policies.
no code implementations • 23 Nov 2020 • Giovanni Soldi, Domenico Gaglione, Nicola Forti, Alessio Di Simone, Filippo Cristian Daffinà, Gianfausto Bottini, Dino Quattrociocchi, Leonardo M. Millefiori, Paolo Braca, Sandro Carniel, Peter Willett, Antonio Iodice, Daniele Riccio, Alfonso Farina
Maritime surveillance (MS) is crucial for search and rescue operations, fishery monitoring, pollution control, law enforcement, migration monitoring, and national security policies.
no code implementations • 20 Nov 2020 • Paolo Braca, Domenico Gaglione, Stefano Marano, Leonardo M. Millefiori, Peter Willett, Krishna Pattipati
This paper develops an easily-implementable version of Page's CUSUM quickest-detection test, designed to work in certain composite hypothesis scenarios with time-varying data statistics.