Departure Security Inspection for Special Passengers based on Deep Learning Optimization Method for Setting up Dedicated Channels

Guihong Zhao; Shanshan Wang

doi:10.6919/ICJE.202507_11(7).0029

Authors

Guihong Zhao
Shanshan Wang

DOI:

https://doi.org/10.6919/ICJE.202507_11(7).0029

Keywords:

Convolutional Neural Network; Special Passengers; Queue; Airport Security.

Abstract

In response to the current situation where the allocation of security inspection service resources for special passengers at airports is to be further optimised, this study constructs an optimisation model for special passenger security inspection lanes that integrates service perception.By analysing the dynamic features of special passengers' facial expressions through a convolutional neural network and combining queue behaviour data, a service perception threshold was established, with 7 minutes determined as the maximum waiting time threshold for positive service perception.Based on the characteristics of the log-normal distribution, we established models for passenger arrival volumes across multiple flights, security check queue lengths, and estimated waiting times. We innovatively constructed an optimisation framework for two modes: the addition of dedicated lanes for special passengers and the mixed use of dedicated and general lanes. We proposed a time-series dynamic adjustment strategy, which has a certain degree of practical value.

Downloads

Download data is not yet available.

References

[1] Zhao Zhenwu, Wang Junjie, Zheng Wenyue, Research on Security Screening Costs of a Dual-Equipment System for Airport Passenger Screening, J. Operations Research and Management. 3 (2024) 111-117.

[2] Zeng Junjie, Airport Security Checkpoint Configuration and Optimization, J. Knowledge Economy, 12 (2009) 173-174.

[3] Gu Yang, Zheng Min, Zhou Hang, Li Yue, Research on Dynamic Allocation Methods for Airport Security Screening Resources, J. Aeronautical Computing Technology, 5 (2016) 67-72.

[4] Qin Shuaixing, Optimization of Passenger Safety Management and Resource Allocation in Airport Terminals under Flight Delays, J. Science and Innovation, 16 (2017) 98-100.

[5] Wang Chunhua, Li Yongyi, Lin Jiaxing, et al, Research on Dynamic Optimization and Allocation Methods for Airport Security Screening Lanes, J. Electromechanical Engineering Technology, 09 (2021) 41-44+103.

[6] Chen Q,Zhang J, Configuration research of toll square on freeways, J. Advances in Transportation Studies, 3 (2017)69-82.

[7] Cowdrey k W ,Lange J D,Malekian R,et al, Applying gueueing theory for the opfimization of a banking model, J. Joural of lnteret Technology, 2 (2018)381-389.

[8] Zhao Yuandi, Jiang Xiaolei, Research on Optimization Methods for the Number of Security Screening Lanes in Airport Terminals, J. Mathematics in Practice and Theory, 20 (2017) 293-301.

[9] Yiru W,Jinhua Z,Guipu W,Yichen W,Peizhou Y,Xiaoyin H,Zhibin L, A network flow approach for optimizing the passenger throughput at an airport security checkpoint, J. IOP Conference Series: Materials Science and Engineering, 04 (2019) 2047.

[10] Seo s,Choi s, Lee C, Security Manpower Scheduling for Smart Airports, J. Lecture Notes in Electrical Engineering, 114 (2012) 519-527.

[11] An Daoqin, Tian Tao, An Empirical Study on the Factors Influencing Customers' Perceived Value in the Queuing Process of Food and Beverage Services, J. Journal of Liaoning University of Technology (Social Sciences Edition), 06 (2016) 48-51.

[12] HE K M,ZHANG X Y,REN S Q,et al, Deep residual learning for image recognition, C. IEEE.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016) 770-778.

[13] Trentacosta CJ,Crespo LM, Development of emotional competence, John Wiley & Sons, New York,2020.

[14] ALFI V, GABRIELLI A, PIETRONERO L, How people react to a deadline, J. Central European Journal of Physics, 3 (2009) 483-489.

[15] Liang Yan, Huang Runchai, Lu Shiceng. Multi-modal micro-expression recognition based on improved 3D ResNet18, J. Computer Application Research, 3 (2025) 903-910.