DocumentCode
1906467
Title
Applying data mining to false alarm reduction in an aviation explosives detection system
Author
Merzbacher, Matthew ; Gable, Todd
Author_Institution
Morpho Detection, Inc., Newark, CA, USA
fYear
2010
fDate
5-8 Oct. 2010
Firstpage
161
Lastpage
164
Abstract
Data mining techniques were applied for the reduction of false positives in aviation explosives detection CT (computed tomography) imaging systems. An inductive post-detection classifier (PDC) was trained, implemented, and fielded. The PDC can only eliminate alarms generated from the existing detection system - it does not detect new alarms.
Keywords
aerospace industry; computerised tomography; data mining; explosives; learning (artificial intelligence); object detection; pattern classification; aviation explosives detection; classifier voting; computed tomography; data mining; data set training; false alarm reduction; false positive; post detection classifier; Classification algorithms; Computed tomography; Correlation; Data mining; Detection algorithms; Explosives; Robustness; Data mining; aviation security; classification; image processing; robustness; voting;
fLanguage
English
Publisher
ieee
Conference_Titel
Security Technology (ICCST), 2010 IEEE International Carnahan Conference on
Conference_Location
San Jose, CA
ISSN
1071-6572
Print_ISBN
978-1-4244-7403-5
Type
conf
DOI
10.1109/CCST.2010.5678738
Filename
5678738
Link To Document