TY - GEN
T1 - Trajectory outlier detection
T2 - 2008 IEEE 24th International Conference on Data Engineering, ICDE'08
AU - Lee, Jae Gil
AU - Han, Jiawei
AU - Li, Xiaolei
N1 - Funding Information:
I would like to acknowledge the contributions of my colleagues and collaborators in FR research over the years, V. Sembugamoorthy, Jon Sticklen, Jack Smith, William Bond, Ashok Goel, Dean Allemang, Anne Keuneke, Lindley Darden, John Josephson, Mike Weintraub, Kathy Johnson, Matt DeJongh, Sunil Thadani, Yumi Iwasaki, Marcos Vescovi, and Richard Fikes. I would like to thank Ashok Goel, Sunil Thadani, Dean Allemang, and Marshall Yovits for reading a draft of this paper and providing a number of useful suggestions for improvement. The research reported here has been supported over the years by DARPA (contract F30602-85- C-0010, monitored by Rome Air Development Center, and contract F-49620-89-C-0110 monitored by Air Force Office of Scientific Research), Air Force Office of Scientific Research (grant 89-OZSO), McDonnell Douglas, and BP America.
PY - 2008
Y1 - 2008
N2 - Outlier detection has been a popular data mining task. However, there is a lack of serious study on outlier detection for trajectory data. Even worse, an existing trajectory outlier detection algorithm has limited capability to detect outlying sub-trajectories. In this paper, we propose a novel partition-and-detect framework for trajectory outlier detection, which partitions a trajectory into a set of line segments, and then, detects outlying line segments for trajectory outliers. The primary advantage of this framework is to detect outlying sub-trajectories from a trajectory database. Based on this partition-and-detect framework, we develop a trajectory outlier detection algorithm TRAOD. Our algorithm consists of two phases: partitioning and detection. For the first phase, we propose a two-level trajectory partitioning strategy that ensures both high quality and high efficiency. For the second phase, we present a hybrid of the distance-based and density-based approaches. Experimental results demonstrate thatTRAOD correctly detects outlying sub-trajectories from real trajectory data.
AB - Outlier detection has been a popular data mining task. However, there is a lack of serious study on outlier detection for trajectory data. Even worse, an existing trajectory outlier detection algorithm has limited capability to detect outlying sub-trajectories. In this paper, we propose a novel partition-and-detect framework for trajectory outlier detection, which partitions a trajectory into a set of line segments, and then, detects outlying line segments for trajectory outliers. The primary advantage of this framework is to detect outlying sub-trajectories from a trajectory database. Based on this partition-and-detect framework, we develop a trajectory outlier detection algorithm TRAOD. Our algorithm consists of two phases: partitioning and detection. For the first phase, we propose a two-level trajectory partitioning strategy that ensures both high quality and high efficiency. For the second phase, we present a hybrid of the distance-based and density-based approaches. Experimental results demonstrate thatTRAOD correctly detects outlying sub-trajectories from real trajectory data.
UR - http://www.scopus.com/inward/record.url?scp=52649161757&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=52649161757&partnerID=8YFLogxK
U2 - 10.1109/ICDE.2008.4497422
DO - 10.1109/ICDE.2008.4497422
M3 - Conference contribution
AN - SCOPUS:52649161757
SN - 9781424418374
T3 - Proceedings - International Conference on Data Engineering
SP - 140
EP - 149
BT - Proceedings of the 2008 IEEE 24th International Conference on Data Engineering, ICDE'08
Y2 - 7 April 2008 through 12 April 2008
ER -