Inferential measurements for situation awareness: enhancing traffic surveillance by machine learning.

Rattadilok, Prapa; Petrovski, Andrei

Abstract

The paper proposes a generic approach to building inferential measurement systems. The large amount of data needed to be acquired and processed by such systems necessitates the use of machine learning techniques. In this study, an inferential measurement system aimed at enhancing situation awareness has been developed and tested on simulated traffic surveillance data. The performance of several Computational Intelligence techniques within this system has been examined and compared on the data containing anomalous driving patterns.

Citation

RATTADILOK, P. and PETROVSKI, A. 2013. Inferential measurements for situation awareness: enhancing traffic surveillance by machine learning. In Proceedings of the 2013 IEEE international conference on computational intelligence and virtual environments for measurement systems and applications (CIVEMSA 2013), 15-17 July 2013, Milan, Italy. New York: IEEE [online], article number 6617402, pages 93-98. Available from: https://doi.org/10.1109/CIVEMSA.2013.6617402

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2013 IEEE international conference on computational intelligence and virtual environments for measurement systems and applications (CIVEMSA 2013)
• Start Date: Jul 15, 2013
• End Date: Jul 17, 2013
• Acceptance Date: Jul 31, 2013
• Online Publication Date: Jul 31, 2013
• Publication Date: Oct 3, 2013
• Deposit Date: Feb 12, 2015
• Publicly Available Date: Feb 12, 2015
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Article Number: 6617402
• Pages: 93-98
• Series Title: Proceedings of the IEEE international conference on computational intelligence and virtual environments for measurement systems and applications
• ISBN: 9781467347013
• DOI: https://doi.org/10.1109/CIVEMSA.2013.6617402
• Keywords: Inferential measurement; Situation awareness; Machine learning; Anomaly detection; Unmanned aerial vehicles
• Public URL: http://hdl.handle.net/10059/1145
• Contract Date: Feb 12, 2015