Skip to Main Content
This paper describes the theoretical basis and practical implementation of PARSEC, a knowledge-based system that uses probabilistic case based reasoning. PARSEC is a major component in the PANDA surveillance system, developed under DARPA leadership to support maritime situation awareness monitoring on a global scale. PANDA detects unusual vessel motions (deviations) based on learned normalcy models and then flags those particular deviations that an analyst is likely to describe as remarkable or suspicious, given the available context for the deviation. The context data include information on weather and sea-state, notices to mariners, piracy events, vessel ownership changes, commodity prices, and other information. Performance evaluation results with real data confirm that PARSEC greatly reduces the probability of false alarm while maintaining a high probability of detecting those deviations that require an analyst's attention.