Empirical Evaluation of Visualizations of Normal Behavioral Models for Supporting Maritime Anomaly Detection

GeoViz: Linking Geovisualization with Spatial Analysis and Modeling, 10-11 March 2011, Hamburg, Germany

Maria Riveiro and G¨oran Falkman

“Many approaches for anomaly detection use statistical based methods that build profiles of normality. In these cases, anomalies are defined as deviations from normal models build from representative data. Detection capabilities based solely on these approaches typically generate high false alarm rates due to the difficulty of creating flawless models. In order to support the comprehension, validation, update and use of such models, our latest work has been devoted to the visualization of normal behavioral models of maritime traffic and their usability evaluation. This paper presents the results of a usability assessment carried out in order to evaluate the ability of previously suggested visualizations to support the detection and identification of anomalous vessel behavior.”