In this paper, we introduce an approach to enhance maritime Situation Awareness (SA) through a multilevel and multiview representation of situations using Rough K-means clustering with variable granularity of information. We evaluate the approach by comparing Rough K-means with standard K-means clustering. The results demonstrate that Rough K-means achieves comparable accuracy to standard K-means while providing the added benefit of identifying upper and lower approximation clusters, thereby handling uncertainty in data and improving SA. The approach aligns with the principles of Granular Computing, offering a user-centered and dynamic method for enhancing maritime SA.
Granular Clustering for Maritime Situation Awareness
Aliberti Luca;D'Aniello Giuseppe
;Gaeta Matteo;
2024-01-01
Abstract
In this paper, we introduce an approach to enhance maritime Situation Awareness (SA) through a multilevel and multiview representation of situations using Rough K-means clustering with variable granularity of information. We evaluate the approach by comparing Rough K-means with standard K-means clustering. The results demonstrate that Rough K-means achieves comparable accuracy to standard K-means while providing the added benefit of identifying upper and lower approximation clusters, thereby handling uncertainty in data and improving SA. The approach aligns with the principles of Granular Computing, offering a user-centered and dynamic method for enhancing maritime SA.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
