@inbook{5b7841fd1e244af3bc795ccc4a6ede6a,
title = "Suspect vehicle identification for border safety",
abstract = "Border safety is a critical part of national and international security. The U.S. Department of Homeland Security searches vehicles entering the country at land borders for drugs and other contraband. Customs and Border Protection (CBP) agents believe that such vehicles operate in groups and if the criminal links of one vehicle are known then their border crossing patterns can be used to identify other partner vehicles. We perform this association analysis by using mutual information (MI) to identify vehicles that may be involved in criminal activity. CBP agents also suggest that criminal vehicles may cross at certain times or ports to try and evade inspection. In a partnership with border-area law enforcement agencies and CBP, we include these heuristics in the MI formulation and identify suspect vehicles using large-scale, real-world data collections. Statistical tests and selected cases judged by domain experts show that the heuristic-enhanced MI performs significantly better than classical MI in identifying pairs of potentially criminal vehicles. The techniques described can be used to assist CBP agents perform their functions both efficiently and effectively.",
author = "Siddharth Kaza and Hsinchun Chen",
year = "2008",
doi = "10.1007/978-3-540-69209-6_16",
language = "English (US)",
isbn = "9783540692072",
series = "Studies in Computational Intelligence",
pages = "305--318",
editor = "Hsinchun Chen and Christopher Yang",
booktitle = "Intelligence and Security Informatics",
}