基本情况 主编致辞 收录获奖
 编委会 编辑部 审稿专家
 本刊学术规范 行业规范

doi: 10.11925/infotech.2096-3467.2018.0812

Early Warning for Civil Aviation Security Checks Based on Deep Learning

【目的】基于数据分析进行分级分类安检, 提升机场安全检查的工作效率和用户体验。【方法】针对民航乘客安检最为关注的时效问题, 提出一种特征级的深度学习方法, 基于民航数据库和公安数据库, 构建包括时序特征、空序特征、环境特征三层深度神经网络, 通过训练获得联合表示层——旅客风险因素, 基于此得出旅客安检和航班预警模型。【结果】旅客安检和航班预警模型可以较好地缓解民航安检压力, 提前做好高风险旅客和航班的防范处置准备。【局限】只针对大型机场进行分析, 结论对小型机场是否适用需要进一步验证。【结论】基于深度学习获得的旅客风险因素构建的预警模型可以有效提升机场安全检查的工作效率和用户体验。

Abstract:

[Objective]This paper proposes a hierarcical classification screening method, aiming to improve the airport security system and passenger experience. [Methods] We proposed a feature deep learning method based on the civil aviation and public security databases. Then, we trained the deep neural network of three layers: time seriers, space seriers, and environmental features to obtain the joint representing feature of passenger risk factors. Finally, we generated the early warning models for passenger security check. [Results] The proposed early warning models could relieve the pressure of civil aviation security check. [Limitaions] More research is needed to examine the proposed model with data from small airports. [Conclusions] The early-warning model based on deep learning could effectively improve work efficiency of airport security checks and passanger experience.

Key words: Civil Aviation Security ; Questionnaire Survey ; Deep Learning ; Flight Warning

1 引 言

1.1 民航安保事件概况

2016年全民航行业共发生安保相关事件16 141起, 其中发生在航站楼内11 029起, 发生在货运区 1 454起, 全年总体分布平均, 且随月份呈现逐步下降的趋势, 各地区安保事件发生数量与航空业务量成正比关系。由安保事件造成航班延误、返航和备降合计131起[2]。绝大部分的民航安保事件发生在公共区域, 即安检前后, 如能实现快速安检, 则可能减少这类事件的发生。

1.2 研究综述

1.3 民航安检现状

《民用航空安全检查规则》规定, 民航安检工作的职责之一是对旅客及其行李物品进行安全检查, 包括证件检查、人身检查、随身行李物品检查、托运行李检查等4个环节。当前民航安检面临的压力巨大, 如2017年全国民航安检部门共检查旅客5.66亿人次, 检查旅客托运行李3.19亿件次。随着民航出行旅客大量增加, 安检工作量将越来越大。对于传统安检方法而言, 需要消耗大量人力物力, 也需要占据旅客较长的等待时间。如图1所示, 从流程描述可见安检由于安全压力, 所有措施和手段都已达到极致, 但由于流程复杂、措施多重叠加, 导致效率逐步放缓, 效率和安全能力之间的效能比逐步降低。如果能基于数据分析, 进行分级分类安检, 既可以提高工作效率和用户体验, 且安全可控性并没有降低。通过构建旅客白名单和黑名单, 将有限的安全防范资源集中在高风险应对方面, 针对少量重点人员加强安检措施, 而对大量的常规旅客降低安检措施, 实现优化效能比, 在提升安全性的同时优化旅客出行体验。

2 B机场安检调研分析
2.1 概 述

B机场作为国内最大和最繁忙的国际机场之一, 2017年完成旅客吞吐量0.96亿人次, 连续8年位居世界第二。在问卷调查中, 笔者通过走近旅客单独调查收集数据, 将抽样限制在18岁以上的成年人, 总共调查了450人。

2.2 调研及分析

(1) 旅客出行频率调查

(2) 旅客过检满意度调查

3 民航旅客安保流程系统
3.1 基于风险预警的旅客安检和航班预警模型

3.2 基于风险预警的旅客安检分类模型

(1) 深度神经网络模型

①数据来源

②模型分析

(2) 旅客安检积分预警模型

$K=A-\frac{1}{\vartheta }B+\frac{1}{\rho }C$ (1)

3.3 基于旅客风险等级分类航班座位分配分析

${{L}_{1}}=({{K}_{1}}+{{K}_{2}}+\cdot \cdot \cdot +{{K}_{\text{s}}}+\cdot \cdot \cdot +{{K}_{p}})/P$ (2)

${{L}_{2}}={{K}_{1}}+{{K}_{2}}+{{K}_{\text{s}}}+\cdot \cdot \cdot +{{K}_{p}}$ (3)

$L=\frac{1}{{{\xi }_{1}}}{{L}_{1}}+\frac{1}{{{\xi }_{2}}}{{L}_{2}}+\frac{1}{{{\xi }_{3}}}P$ (4)

3.4 收益分析

4 结 语

[1] 冯文刚. 民航案事件. mdf. 民航案事件数据库.

 [1] CAAC. 2017年民航行业发展统计公报[R]. 中国民用航空局, 2018. [本文引用:1] (CAAC. 2017 Civil Aviation Industry Development Statistics Bulletin[R]. Civil Aviation Administration of China, 2018.) [2] CAAC. 2016年民用航空安全保卫事件信息统计报告[R]. 中国民用航空局公安局, 2017. [本文引用:1] (CAAC. 2016 Civil Aviation Security Incident Statistics Report [R]. Public Security Bureau of Civil Aviation Administration of China, 2017.) [3] Enders W, Sandler T.Is Transnational Terrorism Becoming More Threatening? A Time-Series Investigation[J]. Journal of Conflict Resolution, 2000, 44(3): 307-332.      URL     [本文引用:1] [4] Lum C.Does the ‘Race of Places’ Influence Police Officer Decision Making?[R]. W.E.B. DuBois Fellowship,National Institute of Justice, 2010. [本文引用:1] [5] Clarke R.Building a Safer Society: Strategic Approaches to Crime Prevention: Situational Crime Prevention[J]. Crime and Justice, 1995, 19: 91-150. DOI:10.1086/449230      URL     [本文引用:1] [6] Clarke R, Newman G.Outsmarting the Terrorists[R]. Westport,CT: Praeger Security International, 2006. [本文引用:1] [7] Eck J.Preventing Crime at Places Evidence-based Crime Prevention[M]. New York, NY: Routledge, 2002. [本文引用:1] [8] US Department of Justice. Federal Bureau of Investigation. Crime in the United States[EB/OL].(2010).[2018-07-08]. . URL     [本文引用:1] [9] Alves L G, Ribeiro H V, Lenzi E K, et al.Distance to the Scaling Law: A Useful Approach for Unveiling Relationships Between Crime and Urban Metrics[J]. PLoS One, 2013, 8(8): 1-8. We report on a quantitative analysis of relationships between the number of homicides, population size and ten other urban metrics. By using data from Brazilian cities, we show that well-defined average scaling laws with the population size emerge when investigating the relations between population and number of homicides as well as population and urban metrics. We also show that the fluctuations around the scaling laws are log-normally distributed, which enabled us to model these scaling laws by a stochastic-like equation driven by a multiplicative and log-normally distributed noise. Because of the scaling laws, we argue that it is better to employ logarithms in order to describe the number of homicides in function of the urban metrics via regression analysis. In addition to the regression analysis, we propose an approach to correlate crime and urban metrics via the evaluation of the distance between the actual value of the number of homicides (as well as the value of the urban metrics) and the value that is expected by the scaling law with the population size. This approach has proved to be robust and useful for unveiling relationships/behaviors that were not properly carried out by the regression analysis, such asthe non-explanatory potential of the elderly population when the number of homicides is much above or much below the scaling law,the fact that unemployment has explanatory potential only when the number of homicides is considerably larger than the expected by the power law, anda gender difference in number of homicides, where cities with female population below the scaling law are characterized by a number of homicides above the power law.      PMID:24348946      URL     [本文引用:1] [10] Chen P, Yuan H Y, Shu X.Forecasting Crime Using the ARIMA Model[C]// Proceedings of the 5th IEEE International Conference on Fuzzy Systems and Knowledge Discovery. 2008: 627-630. [本文引用:1] [11] Gerber M S.Predicting Crime Using Twitter and Kernel Density Estimation[J]. Decision Support Systems, 2014, 61(1): 115-125. 61We model 25 crime types in a major United States city.61We incorporate spatiotemporally tagged Twitter messages into a kernel density model.61Twitter messages improve the prediction of many of the 25 crime types we studied.61The runtime of some text processing modules must be improved to be practical.      URL     [本文引用:1] [12] Gorr W, Olligschlaeger A, Thompson Y.Short-term Forecasting of Crime[J]. International Journal of Forecasting, 2003, 19(4): 579-594. The major question investigated is whether it is possible to accurately forecast selected crimes 1 month ahead in small areas, such as police precincts. In a case study of Pittsburgh, PA, we contrast the forecast accuracy of univariate time series models with na ve methods commonly used by police. A major result, expected for the small-scale data of this problem, is that average crime count by precinct is the major determinant of forecast accuracy. A fixed-effects regression model of absolute percent forecast error shows that such counts need to be on the order of 30 or more to achieve accuracy of 20% absolute forecast error or less. A second major result is that practically any model-based forecasting approach is vastly more accurate than current police practices. Holt exponential smoothing with monthly seasonality estimated using city-wide data is the most accurate forecast model for precinct-level crime series.      URL     [本文引用:1] [13] Liao R, Wang X, Li L, et al.A Novel Serial Crime Prediction Model Based on Bayesian Learning Theory[C]// Proceedings of the 2010 IEEE International Conference on Machine Learning and Cybernetics. 2010: 1757-1762. [本文引用:1] [14] Mohler G O, Short M B, Brantingham P J, et al.Self-Exciting Point Process Modeling of Crime[J]. Journal of the American Statistical Association, 2011, 106(493): 100-108.      URL     [本文引用:1] [15] Wang P, Mathieu R, Ke J, et al.Predicting Criminal Recidivism with Support Vector Machine[C]// Proceedings of the 2010 IEEE International Conference on Management and Service Science. 2010: 1-9. [本文引用:1] [16] Anderson C A, Anderson D C.Ambient Temperature and Violent Crime: Tests of the Linear and Curvilinear Hypotheses[J]. Journal of Personality and Social Psychology,2004, 46(1): 91-97. Abstract Laboratory research on the effects of temperature has led theorists to propose a curvilinear model relating negative affect and aggression. Two alternative explanations of these lab findings are proposed--one artifactual, one based on attributions for arousal. Both alternatives predict a linear relationship between temperature and aggression in real-world settings, whereas the negative affect curvilinear model predicts a specific curvilinear effect. Two studies are reported that investigated the relationship between temperature and violent crime. Both studies yielded significant linear relationships and failed to demonstrate the specified curvilinear relationship. Also, both studies yielded significant day-of-the-week effects. Implications of these findings for the study of aggression are discussed.      PMID:6694060      URL     [本文引用:1]

PDF下载数
RichHTML 浏览数

 相关文章:

Civil Aviation Security
Questionnaire Survey
Deep Learning
Flight Warning

Feng Wengang
Huang Jing
 版权所有 © 2015 《数据分析与知识发现》编辑部 地址：北京市海淀区中关村北四环西路33号 邮编：100190 电话/传真：(010)82626611-6626，82624938 E-mail:jishu@mail.las.ac.cn