Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Supported Decision-Making by Explainable Predictions of Ship Trajectories

: Burkart, Nadia; Huber, Marco; Anneken, Mathias


Herrero, Álvaro (Ed.):
15th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2020 : Burgos (Spain), September 2020
Cham: Springer Nature, 2021 (Advances in Intelligent Systems and Computing 1268)
ISBN: 978-3-030-57801-5 (Print)
ISBN: 978-3-030-57802-2 (Online)
International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO) <15, 2020, Online>
Fraunhofer IOSB ()
Fraunhofer IPA ()
machine learning; black box; explainability; interpretability; trust; Künstliche Intelligenz; neuronales Netz; Entscheidungsfindung; Explainable Artificial Intelligence (XAI); maschinelles Lernen

Machine Learning and Deep Learning models make accurate predictions based on a specifically trained task. For instance, models that classify ship vessel types based on their trajectory and other features. This can support human experts while they try to obtain information on the ships, e.g., to control illegal fishing. Besides the support in predicting a certain ship type, there is a need to explain the decision-making behind the classification. For example, which features contributed the most to the classification of the ship type. This paper introduces existing explanation approaches to the task of ship classification. The underlying model is based on a Residual Neural Network. The model was trained on an AIS data set. Further, we illustrate the explainability approaches by means of an explanatory case study and conduct a first experiment with a human expert.