Presenting our feature-aware deep learning models for maritime intent recognition, achieving ~97% accuracy on seven maritime behaviors using only initial trajectory segments.
Nov 2, 2025
Two papers accepted and presented by coauthors on deep learning for maritime intent recognition—early classification of vessel intentions and proactive threat prediction using LSTMs and transformers with a sliding-window approach.
Aug 17, 2025
Presented ThreatMap, a framework that fuses sensor coverage, vulnerability fields, and CPA-based threat estimates for interpretable real-time maritime risk visualization.
Sep 18, 2024
Presented NavySim, our Unity-based multi-vessel naval simulator with real-time threat heatmaps and HMM-based intent recognition for maritime training and research.
Aug 5, 2024