Beyond geofencing: Behavior detection using AIS - Aix-Marseille Université Accéder directement au contenu
Article Dans Une Revue Ocean Engineering Année : 2024

Beyond geofencing: Behavior detection using AIS

Résumé

This research paper proposes two different methods for removing biases from geo-spatial trajectories obtained from AIS, enabling the creation of machine learning models that generalize well to areas with no training data. We focus here on the task of behavior detection such as moored, underway or drifting from AIS. The first method utilizes data augmentation techniques specifically designed for augmenting geo-spatial trajectories that include angled information such as direction, while the second method is based on engineering features that eliminate these geographical biases. These two methods are compared using different types of machine learning models, including random forests, hidden Markov models, LSTMs, and transformer networks.
Fichier principal
Vignette du fichier
Sturgis2024BeyondGeofencing.pdf (2.89 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04584163 , version 1 (23-05-2024)

Identifiants

Citer

Raphael Sturgis, Valentin Emiya, Basile Couëtoux, Pierre Garreau. Beyond geofencing: Behavior detection using AIS. Ocean Engineering, 2024, 293, pp.116630. ⟨10.1016/j.oceaneng.2023.116630⟩. ⟨hal-04584163⟩
39 Consultations
13 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More