Federated Learning for Anomaly Detection in Maritime Movement Data
By: Anita Graser , Axel Weißenfeld , Clemens Heistracher and more
Potential Business Impact:
Finds strange movements without sharing private data.
This paper introduces M3fed, 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 M3fed, 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 M3 and the new federated M3fed.
Similar Papers
Federated Learning and Trajectory Compression for Enhanced AIS Coverage
Machine Learning (CS)
Ships become sensors, spotting trouble far away.
A Robust Federated Learning Approach for Combating Attacks Against IoT Systems Under non-IID Challenges
Machine Learning (CS)
Helps computers learn to spot internet dangers.
Federated Anomaly Detection for Multi-Tenant Cloud Platforms with Personalized Modeling
Machine Learning (CS)
Finds computer problems without sharing private data.