Authors:
Nadeem Iftikhar
1
;
Cosmin-Stefan Raita
1
;
Aziz Kadem
1
;
David Buncek
1
;
Matthew Haze Trinh
2
;
Yi-Chen Lin
2
;
Anders Vestergaard
1
and
Gianna Belle
1
Affiliations:
1
University College of Northern Denmark, Sofiendalsvej 60, 9000 Aalborg, Denmark
;
2
Frugal Technologies ApS, C.A. Olesens Gade 4, 9000 Aalborg, Denmark
Keyword(s):
Anomaly Detection, Anomaly Characterization, Maritime IoT, Hybrid Models, Time-Series Analysis.
Abstract:
Effective knowledge discovery from industrial sensor data depends on a deep understanding of data quality issues. In the maritime domain, sensor streams often suffer from a diverse set of problems, from simple signal freezes to complex, context-dependent behavioral shifts. Merely detecting these events as a monolithic “anomaly” class provides limited actionable insight. This paper argues for a shift from anomaly detection to anomaly characterization. We propose a novel, layered hybrid framework that systematically identifies and classifies data issues into distinct types. Our pipeline effectively combines the reliability of statistical methods with the advanced pattern-finding ability of machine/deep learning. Each layer acts as a specialized filter that identifies a specific type of anomaly and cleans the data for the next, more advanced analysis. We demonstrate on real-world vessel data that this layered characterization not only achieves high detection accuracy but, more important
ly, transforms raw detection flags into actionable knowledge for operational decision-making.
(More)