Bayesian analysis models for aviation baggage screening

Abstract

This paper not only develops Bayesian analysis models for addressing both single-level and sequential multiple-level baggage screening problems but also provides a new perspective on the design and evaluation of aviation security systems. Using the Bayesian approach, the operator's prior knowledge about the status of a bag is incorporated with present data. The posterior distributions for single-level and multiple-level screenings are developed, respectively. To evaluate the performance for Bayesian screening, two metrics are introduced and implemented: (i) system risk bounded to the posterior mean of undetected threats; and (ii) system direct cost per bag that incorporates purchasing costs, operating costs and processing rates. By evaluating the trade-off between system risk and system cost, this paper assesses different screening technologies and combinations of them for single-level and two-level systems. The findings from numerical analyses provide recommendations for cost-effective selections of technologies with low risk levels.

[Supplementary materials are available for this article. Go to the publisher's online edition of IIE Transactions for the following free supplemental resource: Appendix]

Keywords:

• Bayesian analysis
• aviation baggage screening
• single-level screening
• multiple-level sequential screening
• risk assessment
• cost-effectiveness assessment

Acknowledgement

The insightful comments from the editor and anonymous reviewers are sincerely appreciated. Their constructive suggestions on the earlier version have significantly improved this paper.