A multi-level weighted alarm security system for passenger and checked-baggage screening

Abstract

Persistent and ever-changing threat of terrorism has led to the evolution of security systems in the air transportation industry. Passenger and checked-baggage screening prior to boarding an aircraft has become a priority for the airport security system. We propose a two-stage screening system by integrating the passenger prescreening and a multi-level checked-baggage screening. Based on the concept of the weighted k-out-of-n system, we introduce an integrated weighted alarm security screening system for a multi-level baggage screening system, where the system alarms when the total weight of its working levels is greater than a predefined system alarm threshold. To improve the security and efficiency of aviation systems, two optimization models are formulated to enhance the detection of possible threats in the passenger and baggage screening with consideration of the system life cycle cost. The optimal solutions of the threshold values are obtained for screening technologies and passenger classes to achieve the maximum security and efficiency. Numerical analysis is implemented to demonstrate the effectiveness of the proposed two-stage screening system.

An Efficient Approach to Human Security Screening Image Recognition Through a Lightweight CNN Utilizing Yolov5s and GhostNet

“…While research related to X-ray image recognition in baggage screening abounds, direct application to human security systems is hindered by the distinctive mono-energy detector imaging methods used in the latter, resulting in greyscale rather than color images. Several deep learning models, such as CNNs, have been applied to baggage screening [1][2][3][4][5][6], capitalizing on their capacity to learn hierarchical representations. Although their ability to discern intricate features and patterns has been leveraged to address various security threats, the high computational complexity and memory requirements limit their applicability in resourceconstrained environments.…”