Federated Learning for Anomaly Detection in Maritime Movement Data

This paper introduces M 3 fed, a novel solution for federated learning of movement anomaly detection models. This innovation has the potential to improve data privacy and reduce communication costs in machine learning for movement anomaly detection. We present the novel federated learning (FL) strat...

Full description

Saved in:
Bibliographic Details
Published in2024 25th IEEE International Conference on Mobile Data Management (MDM) pp. 77 - 82
Main Authors Graser, Anita, Weissenfeld, Axel, Heistracher, Clemens, Dragaschnig, Melitta, Widhalm, Peter
Format Conference Proceeding
LanguageEnglish
Published IEEE 24.06.2024
Subjects
AIS
Anomaly detection
Costs
Data models
Data privacy
Federated learning
mobility data science
Technological innovation
Online AccessGet full text

Cover

More Information
Summary:This paper introduces M 3 fed, a novel solution for federated learning of movement anomaly detection models. This innovation has the potential to improve data privacy and reduce communication costs in machine learning for movement anomaly detection. We present the novel federated learning (FL) strategies employed to train M 3 fed, perform an example experiment with maritime AIS data, and evaluate the results with respect to communication costs and FL model quality by comparing classic centralized M 3 and the new federated M 3 fed.
ISSN:2375-0324
DOI:10.1109/MDM61037.2024.00030