Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICDMW.2009.45
Title: Analyzing abnormal events from spatio-temporal trajectories
Authors: Patel, D. 
Bhatt, C.
Hsu, W. 
Lee, M.L. 
Kankanhalli, M. 
Keywords: Abnormal events
Representation scheme
Trajectory classification
Issue Date: 2009
Source: Patel, D., Bhatt, C., Hsu, W., Lee, M.L., Kankanhalli, M. (2009). Analyzing abnormal events from spatio-temporal trajectories. ICDM Workshops 2009 - IEEE International Conference on Data Mining : 616-621. ScholarBank@NUS Repository. https://doi.org/10.1109/ICDMW.2009.45
Abstract: Advances in RFID based sensor technologies has been used in applications which requires the tracking of assets, products and individuals. The recording of such movements is captured in a trajectory database and can be analyzed for the monitoring of abnormal events. In this paper, we describe a system called InViTA for analyzing abnormal events from spatio-temporal trajectories captured during an office evacuation after an explosion. InViTA utilizes a trajectory representation scheme and extract the features to derive a set of rules that label each person's trajectory as belonging to a suspect, witness, or victim, etc. We run the system on the office evacuation data provided in VAST 2008 challenge and obtain comparable results with that obtained from visualization and human analysis. The system includes a user-friendly graphical interface for parameter tuning and intuitive result analysis. © 2009 IEEE.
Source Title: ICDM Workshops 2009 - IEEE International Conference on Data Mining
URI: http://scholarbank.nus.edu.sg/handle/10635/40960
ISBN: 9780769539027
DOI: 10.1109/ICDMW.2009.45
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

3
checked on Dec 6, 2017

WEB OF SCIENCETM
Citations

2
checked on Nov 20, 2017

Page view(s)

60
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.