With the successful defense of her doctoral dissertation titled “Machine Learning Models for Watercraft Trajectory Analysis and Maritime Infrastructure Inspection“, doctoral candidate Lucija Žužić has officially completed her Doctoral Study Programme.
This doctoral dissertation focuses on applying machine learning methods to vessel trajectory analysis and the visual inspection of underwater maritime infrastructure, with an emphasis on enhancing navigational safety and automating surveillance. It compares classical probabilistic methods with modern deep learning models for trajectory forecasting, anomaly detection, and the identification of potentially hazardous situations. Furthermore, the research proposes a computationally efficient method for detecting unusual vessel movement patterns suitable for real-time applications. In the field of underwater infrastructure inspection, an approach based on semantic image segmentation was developed to enable the automated analysis of underwater imagery. The results contribute to the development of more reliable and efficient systems for vessel movement tracking and the assessment of maritime infrastructure integrity.
The doctoral dissertation was supervised by Prof. Jonatan Lerga (Faculty of Engineering, University of Rijeka).
The Doctoral Dissertation Defense Committee consisted of: Prof. Sandi Ljubić (Chair) from the Faculty of Engineering, University of Rijeka, Assoc. Prof. Marin Bugarić (Member) from the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split and Assoc. Prof. Srđan Žuškin (Member) from the Faculty of Maritime Studies, University of Rijeka.
Congratulations to our colleague!
