About
Dogan Altan serves as a Postdoctoral Fellow at Simula Research Laboratory within the Department of Validation Intelligence for Autonomous Software Systems. His research focuses on developing artificial intelligence solutions for maritime safety and operational efficiency, leveraging advanced machine learning techniques to address complex vessel navigation and performance challenges.
His primary research interests include maritime anomaly detection, vessel traffic prediction, and physics-informed neural modeling for shaft power optimization. Altan specializes in integrating sensor data, passage plans, and environmental features into deep learning frameworks to enhance predictive accuracy in maritime contexts. Key methodologies involve transfer learning, trajectory segmentation, and multi-stream anomaly identification systems applicable to both vessel operations and robotic manipulation.
Analysis of his publication trends reveals a consistent focus on transforming maritime domain knowledge into robust AI frameworks. Recent work demonstrates innovation in temporal graph analysis for port classification, transformer-based waypoint detection, and physics-guided hybrid models that bridge engineering principles with neural network architectures. His contributions span theoretical algorithm development and practical implementations validated through real-world maritime datasets.
