Open AccessTrajectory Outlier Detection Algorithm for ship AIS Data based on Dynamic Differential Threshold
Author(s) -
Songlin Sun,
Yan Chen,
Jinsong Zhang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1437/1/012013
Subject(s) - trajectory , outlier , anomaly detection , computer science , acceleration , differential (mechanical device) , algorithm , data mining , artificial intelligence , pattern recognition (psychology) , engineering , physics , classical mechanics , astronomy , aerospace engineering
Trajectory outlier detection is one of the most important branches of data mining topics. Most existing outlier detection algorithms only utilized location of trajectory points and neglected some important factors such as speed, acceleration, and corner. In this paper, we propose a trajectory outlier detection algorithm based on dynamic differential threshold, called TODDT. Considering the influence of target motion information in a period of time, TODDT improves the traditional distance-based algorithm by combining dynamic differential threshold into outlier detection to discover more meaningful trajectory outliers. The experiments with real trajectory data sets in ship AIS (Automatic Identification System) show that TODDT algorithm performs efficiently and effectively when applied to the problem of trajectory outlier detection and the quality of trajectory data is greatly improved.