Maritime Anomaly Detection
An ST-based method using failure-pattern knowledge to detect tiny anomalies in manufacturing time-series data.
2020.01 – 2022.01
·Motivation
The maritime industry is a key component of the global economy — a complex adaptive system that must adjust quickly to changing situations by solving many decision-making problems.
·Goal
- Construct the best-planned route (the reference line)
- Develop a novel statistical (low-likelihood) anomaly detector
- Ensure maritime situational awareness and surveillance
·Methodology
- Quantify the route probability
- Detect spatial and temporal anomalies
