Design of airport security screening using queueing theory augmented with particle swarm optimisation
- Springer Science and Business Media LLC
- Publication Type:
- Conference Proceeding
- Service Oriented Computing and Applications, 2020, 14, (2), pp. 119-133
- Issue Date:
|Design of Airport Security Screening Using Queueing Theory Augmented with Particle Swarm Optimisation.pdf||Published version||1.99 MB|
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is new to OPUS and is not currently available.
© 2020, Springer-Verlag London Ltd., part of Springer Nature. Designing an efficient and reliable airport security screening system is a critical and challenging task. It is an essential element of airline and passenger safety which aims to provide the expected level of confidence and to ensure the safety of passengers and the aviation industry. In recent years, security at airports has gone through noticeable improvements with the utilisation of advanced technology and highly trained security officers. However, for many airports, it is important to find the best compromise between the capacity of the security area, the number of passengers and the number of screening machines and officers to maintain a high level of security and to ensure that the cost and waiting times for passengers and airlines are at acceptable levels. This paper proposes a novel method based on queueing theory augmented with particle swarm optimisation (QT-PSO) to predict passenger waiting times in a security screening context. This model consists of multiple servers operating in parallel and takes into consideration the complete scenario such as normal, slow and express lanes. Such an approach has the potential to be a reliable model that is able to assimilate variations in the number of passengers, security officers and security machines on the service time. To evaluate our proposed method, we collected real-world security screening data from an Australian airport from December to March for the two consecutive years of 2016 and 2017. The results show that our proposed QT-PSO method is superior to predict the average waiting time of passengers compared to the state of the art.
Please use this identifier to cite or link to this item: