|本期目录/Table of Contents|

[1]孙禾,陈一新.基于多标准和改进Siamese网络的相似航班号判断方法研究*[J].中国安全生产科学技术,2023,19(1):47-53.[doi:10.11731/j.issn.1673-193x.2023.01.007]
　SUN He,CHEN Yixin.Research on judgment method of similar call signs based on multi standards and improved Siamese network[J].Journal of Safety Science and Technology,2023,19(1):47-53.[doi:10.11731/j.issn.1673-193x.2023.01.007]
点击复制

基于多标准和改进Siamese网络的相似航班号判断方法研究*()

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
19
期数:
2023年1期
页码:
47-53
栏目:
学术论著
出版日期:
2023-01-31

文章信息/Info

Title:
Research on judgment method of similar call signs based on multi standards and improved Siamese network
文章编号:
1673-193X(2023)-01-0047-07
作者:
孙禾; 陈一新
（1.中国民航大学 空中交通管理学院，天津 300300；
2.中国民用航空厦门空中交通管理站，福建 厦门 361006）
Author(s):
SUN He;  CHEN Yixin
(1.College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China;
2.CAAC Xiamen Air Traffic Control Station,Xiamen Fujian 361006,China)
关键词:
航空运输; 空中交通管理; 主成分分析法; Siamese网络; 航班号
Keywords:
aviation transportation;  air traffic management;  principal component analysis;  Siamese network;  call sign;  similarity
分类号:
X949
DOI:
10.11731/j.issn.1673-193x.2023.01.007
文献标志码:
A
摘要:
为了合理区分和有效识别不同航班号，首先提出基于多标准的判断准则，使用主成分分析法量化得到统一的相似度；其次建立改进的Siamese网络模型，获得文本的语义信息；最后采用文本之间的Jaro-Winkler距离客观修正网络对比损失函数，综合网络输出判定2个航班号的相似情况。研究结果表明：多标准准则判定方法速度快且通用性强，改进后的Siamese网络虽受到训练样本的直接影响，但收敛速度明显提高，识别率比原网络平均提高约2.7%，比多标准判断准则提高约3%。研究结果可为相似航班号识别与预警提供理论依据。
Abstract:
In order to reasonably distinguish and effectively identify different call signs,firstly,the judgment criteria based on multi standards were proposed,and the unified similarity degree was quantified using the principal component analysis method.Secondly,an improved Siamese network model was established to obtain the semantic information of texts,and the Jaro-Winkler distance between texts was used to objectively modify the network contrast loss function,and the integrated network output was used to determine the similarity of two call signs.The results showed that the judgment method of multi standards criteria was fast and general,while the improved Siamese network,although directly influenced by the training samples,had a significantly higher convergence speed,and the recognition rate was on average about 2.7% higher than the original network and about 3% higher than the multi standards judgment criteria.The research results can provide theoretical basis for the identification and early warning of similar call signs.

参考文献/References:

［1］中国民航局.中国/欧洲航班运行对比报告（2019—2021）［R］.北京：中国民航局运行监控中心,2021.
［2］COX S,VINAGRE L.Modelling of confusions in aircraft call-signs［J］.Speech Communication,2004,42(3-4):289-312.
［3］KIM S,MILLER M E,RUSNOCK C F,et al.Spatialized audio improves call sign recognition during multi-aircraftcontrol［J］.Applied Ergonomics,2018,70:51-58.
［4］孔金凤,王煜.基于异或编辑距离算法的航班号相似度研究［J］.湘潭大学自然科学学报,2015,37(2):116-120.KONG Jingfeng,WANG Yu.Research on flight numbers similarity based on Xor Levenshtein distance algorithm ［J］.Natural Science Journal of Xiangtan University,2015,37(2):116-120.
［5］黄承慧,印鉴,侯昉.一种结合词项语义信息和TF-IDF方法的文本相似度量方法［J］.计算机学报,2011,34(5):856-864.HUANG Chenghui,YIN Jian,HOU Fang.A text similarity measurement combining word semantic information with TF-IDF method ［J］.Chinese Journal of Computers,2011,34(5):856-864.
［6］李岩.基于深度学习的短文本分析与计算方法研究［D］.北京;北京科技大学,2016.
［7］中国民用航空局空中交通管理局.民航空管系统相似航空器呼号管制运行操作指引［R］.北京：中国民用航空局空中交通管理局,2020.
［8］LIN Q X,LUO C J,JIN L W,et al.STAN:A sequential transformation attention-based network for scene text recognition［J］.Pattern Recognition,2021,111:107692.
［9］FATEMEH N,VAHID G,HASSAN K.A novel pipeline framework for multi oriented scene text image detection and recognition［J］.Expert Systems with Applications,2021,170:114549.
［10］SOUVIK G,SPANDAN G,Pradeep K,et al.A novel spatio-temporal Siamese network for 3D signature recognition［J］.Pattern Recognition Letters,2021,144:13-20.
［11］姜逸凡,叶青.基于孪生神经网络的时间序列相似性度量［J］.计算机应用,2019,39(4):1041-1045.JIANG Yifan,YE Qing.Time series similarity measure based on Siamese neural network ［J］.Journal of Computer Applications,2019,39(4):1041-1045.
［12］BERTINETTO L,VALMADRE J,HENRIQUES J F,et al.Fully-convolutional Siamese networks for object tracking ［C］//European Conference on Computer Vision.2016.
［13］THYAGARAJAN A.Siamese recurrent architectures for learning sentence similarity ［C］//AAAI-16.AAAI Press,2015.
［14］NECULOIU P,VERSTEEGH M,ROTARU M,et al.Learningtext similarity with Siamese recurrent networks［C］//The 1st Workshop on Representation Learning for NLP.Berlin,2016:148-157.

相似文献/References:

[1]杨新湦,任治.基于尾涡强度的无人机与民机纵向安全间隔评估研究[J].中国安全生产科学技术,2018,14(10):64.[doi:10.11731/j.issn.1673-193x.2018.10.010]
　YANG Xinsheng,REN Zhi.Research on assessment of longitudinal safety separation between UAV and civil aircraft based on trailing vortex intensity[J].Journal of Safety Science and Technology,2018,14(1):64.[doi:10.11731/j.issn.1673-193x.2018.10.010]
[2]康瑞,杨凯.考虑等待位置的航空器交叉滑行冲突概率模型[J].中国安全生产科学技术,2019,15(8):64.[doi:10.11731/j.issn.1673-193x.2019.08.010]
　KANG Rui,YANG Kai.Model on conflict probability of aircraft crosstaxiing considering holding position[J].Journal of Safety Science and Technology,2019,15(1):64.[doi:10.11731/j.issn.1673-193x.2019.08.010]
[3]岳仁田,李君尉.基于多因素耦合的航空运输系统脆弱性分析*[J].中国安全生产科学技术,2020,16(12):150.[doi:10.11731/j.issn.1673-193x.2020.12.024]
　YUE Rentian,LI Junwei.Vulnerability analysis of air transportation system based on multifactor coupling[J].Journal of Safety Science and Technology,2020,16(1):150.[doi:10.11731/j.issn.1673-193x.2020.12.024]
[4]张洪海,沈雪,瞿昕宜,等.基于BIRCH聚类的航空器自主运行风险状态评价*[J].中国安全生产科学技术,2024,20(9):188.[doi:10.11731/j.issn.1673-193x.2024.09.023]
　ZHANG Honghai,SHEN Xue,QU Xinyi,et al.Risk state evaluation on autonomous operation of aircraft based on BIRCH clustering[J].Journal of Safety Science and Technology,2024,20(1):188.[doi:10.11731/j.issn.1673-193x.2024.09.023]
[5]苏佳明,胡明华,尹嘉男,等.不同雪情条件下离场航班除冰与滑行协同调度方法研究*[J].中国安全生产科学技术,2025,21(12):177.[doi:10.11731/j.issn.1673-193x.2025.12.022]
　SU Jiaming,HU Minghua,YIN Jianan,et al.Research on coordinated scheduling methods for deicing and taxiing of departure flights under different snow conditions[J].Journal of Safety Science and Technology,2025,21(1):177.[doi:10.11731/j.issn.1673-193x.2025.12.022]
[6]张洪海,石宗北,李一可,等.基于结构主题模型的民航管制不安全事件主题识别*[J].中国安全生产科学技术,2024,20(11):163.[doi:10.11731/j.issn.1673-193x.2024.11.021]
　ZHANG Honghai,SHI Zongbei,LI Yike,et al.Topic identification of air traffic control unsafe events based on structural topic model[J].Journal of Safety Science and Technology,2024,20(1):163.[doi:10.11731/j.issn.1673-193x.2024.11.021]
[7]罗诗涵,张晨阳,朱文兵,等.基于非接触式感知的飞行学员认知负荷评估研究*[J].中国安全生产科学技术,2025,21(2):67.[doi:10.11731/j.issn.1673-193x.2025.02.009]
　LUO Shihan,ZHANG Chenyang,ZHU Wenbing,et al.Study on cognitive load assessment of flight students based on non-contact perception[J].Journal of Safety Science and Technology,2025,21(1):67.[doi:10.11731/j.issn.1673-193x.2025.02.009]
[8]康瑞,杨凯.考虑驾驶方式的车辆与航空器交叉冲突评估*[J].中国安全生产科学技术,2023,19(2):218.[doi:10.11731/j.issn.1673-193x.2023.02.030]
　KANG Rui,YANG Kai.Assessment on cross conflict of vehicle and aircraft considering driving modes[J].Journal of Safety Science and Technology,2023,19(1):218.[doi:10.11731/j.issn.1673-193x.2023.02.030]
[9]刘颖俪,胡明华,苏佳明,等.基于多目标优化的机场机坪管制区域划分方法研究*[J].中国安全生产科学技术,2023,19(8):150.[doi:10.11731/j.issn.1673-193x.2023.08.022]
　LIU Yingli,HU Minghua,SU Jiaming,et al.Division method of airport apron control areas based on multi-objective optimization[J].Journal of Safety Science and Technology,2023,19(1):150.[doi:10.11731/j.issn.1673-193x.2023.08.022]

备注/Memo

备注/Memo:
收稿日期： 2021-09-10
* 基金项目： 国家重点研发计划项目（2021YFF0603902）；中央高校基本科研业务费项目（3122019133）
作者简介： 孙禾，硕士，实验师，主要研究方向为安全智能、空管运行安全。
更新日期/Last Update: 2023-02-14