Maritime abnormality detection using Gaussian processes

作者：Smith Mark^*; Reece Steven; Roberts Stephen; Psorakis Ioannis; Rezek Iead

来源：Knowledge and Information Systems, 2014, 38(3): 717-741.

DOI：10.1007/s10115-013-0685-z

• Gaussian processes
• Extreme value theory
• Novelty detection
• Hellinger distance
• Nonnegative matrix factorisation
• Maritime traffic
• Outlier detection

Novelty, or abnormality, detection aims to identify patterns within data streams that do not conform to expected behaviour. This paper introduces novelty detection techniques using a combination of Gaussian processes, extreme value theory and divergence measurement to identify anomalous behaviour in both streaming and batch data. The approach is tested on both synthetic and real data, showing itself to be effective in our primary application of maritime vessel track analysis.

• 出版日期2014-3