Title :
Establishing traveler identity using collective identity resolution
Author :
Kretz, Donald R. ; Paulk, Roderic W.
Author_Institution :
Predictive Analytics Technol. Center, Raytheon Intell. & Inf. Syst., Garland, TX, USA
Abstract :
Every day, millions of people cross international borders by air or sea. A nation´s ability to identify and neutralize threats posed by travelers depends heavily on an accurate and proactive methodology for establishing traveler identity. Lacking both a common reference model and a globally unique identification scheme, the “system” must confront the problem of multiple distinct or imprecise references to each single real-world entity when analyzing vast amounts of data. Additionally, the emergent patterns of relationships between entities are often complex, fuzzy, and/or novel. Methodologies that depend solely on exact or approximate name matches are subject to defeat simply by using aliases, and are typically prone to high levels of false positives. In order for identity resolution to be effective, information from multiple, diverse sources must be analyzed (e.g., biometric, biographic, social, etc.). Furthermore, identity analysis must be a continuous process that enables accurate pre-assessment when travel intentions first become known. To that end, this paper presents an identity resolution methodology called Collective Identity Resolution.
Keywords :
data handling; risk management; travel industry; collective identity resolution; traveler identity; Clustering algorithms; Correlation; Data mining; Facebook; Feature extraction; Risk management; US Department of Energy; entity resolution; identity; risk assessment;
Conference_Titel :
Technologies for Homeland Security (HST), 2010 IEEE International Conference on
Conference_Location :
Waltham, MA
Print_ISBN :
978-1-4244-6047-2
DOI :
10.1109/THS.2010.5655036