Dynamic Filling of Data Gaps in Large AIS Datasets
Fragment książki (Materiały konferencyjne)
MNiSW
140
konferencja
| Status: | |
| Autorzy: | Czerwiński Dariusz, Kiersztyn Adam, Oniszczuk-Jastrząbek Aneta, Czermański Ernest, Gorgol Izolda, Pluciński Michał |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Język: | angielski |
| Strony: | 300 - 313 |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | TAK |
| Nazwa konferencji: | 28th European Conference on Artifical Intelligence |
| Skrócona nazwa konferencji: | 28th ECAI 2025 |
| URL serii konferencji: | LINK |
| Termin konferencji: | 25 października 2025 do 30 października 2025 |
| Miasto konferencji: | Bolonia |
| Państwo konferencji: | WŁOCHY |
| Publikacja OA: | TAK |
| Licencja: | |
| Sposób udostępnienia: | Witryna wydawcy |
| Wersja tekstu: | Ostateczna wersja opublikowana |
| Czas opublikowania: | W momencie opublikowania |
| Data opublikowania w OA: | 2 października 2025 |
| Abstrakty: | angielski |
| Purpose: This study examines some novel approach for filling missing data in AIS databases. Proposed solution is designed for filling dynamic data in AIS systems. Need for the study: In the era of globalization and intensive international trade, accurate monitoring of vessel and container ship routes is essential for efficient maritime logistics and ensuring the safety and security of maritime traffic. Although widely implemented, the Automatic Identification System (AIS) frequently generates data gaps, particularly in regions with limited signal coverage. These missing entries reduce the reliability of analyses and forecasts, thus undermining operational and strategic decision-making. Such lack of data implies also limits for a modern Artificial Intelligence involvment into the decision-making. Methodology: This paper presents a novel approach to dynamically filling data gaps in large AIS datasets, based on spatio-temporal analysis using weighted averages and data similarity estimation methods. The method was validated on a real-world dataset comprising approximately 32 million records and demonstrated high accuracy and strong potential for practical deployment. Findings: Effectively completing and correcting AIS data not only enhances dataset integrity but also provides a more reliable foundation for decision-making in the maritime sector. Practical Implications: Improved data precision supports the deployment of intelligent management tools for route planning, maritime traffic coordination, port operation optimization, and fleet supervision. In the long term, it also enables the implementation of advanced artificial intelligence (AI)-based systems, paving the way toward predictive and autonomous maritime transport management. |
