On Vessel Location Forecasting and the Effect of Federated Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911894408790016 |
|---|---|
| author | Tritsarolis, Andreas Pelekis, Nikos Bereta, Konstantina Zissis, Dimitris Theodoridis, Yannis |
| author_facet | Tritsarolis, Andreas Pelekis, Nikos Bereta, Konstantina Zissis, Dimitris Theodoridis, Yannis |
| contents | The wide spread of Automatic Identification System (AIS) has motivated several maritime analytics operations. Vessel Location Forecasting (VLF) is one of the most critical operations for maritime awareness. However, accurate VLF is a challenging problem due to the complexity and dynamic nature of maritime traffic conditions. Furthermore, as privacy concerns and restrictions have grown, training data has become increasingly fragmented, resulting in dispersed databases of several isolated data silos among different organizations, which in turn decreases the quality of learning models. In this paper, we propose an efficient VLF solution based on LSTM neural networks, in two variants, namely Nautilus and FedNautilus for the centralized and the federated learning approach, respectively. We also demonstrate the superiority of the centralized approach with respect to current state of the art and discuss the advantages and disadvantages of the federated against the centralized approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19870 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On Vessel Location Forecasting and the Effect of Federated Learning Tritsarolis, Andreas Pelekis, Nikos Bereta, Konstantina Zissis, Dimitris Theodoridis, Yannis Machine Learning The wide spread of Automatic Identification System (AIS) has motivated several maritime analytics operations. Vessel Location Forecasting (VLF) is one of the most critical operations for maritime awareness. However, accurate VLF is a challenging problem due to the complexity and dynamic nature of maritime traffic conditions. Furthermore, as privacy concerns and restrictions have grown, training data has become increasingly fragmented, resulting in dispersed databases of several isolated data silos among different organizations, which in turn decreases the quality of learning models. In this paper, we propose an efficient VLF solution based on LSTM neural networks, in two variants, namely Nautilus and FedNautilus for the centralized and the federated learning approach, respectively. We also demonstrate the superiority of the centralized approach with respect to current state of the art and discuss the advantages and disadvantages of the federated against the centralized approach. |
| title | On Vessel Location Forecasting and the Effect of Federated Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.19870 |