logo

SCIENTIA SINICA Informationis, Volume 47, Issue 8: 1023(2017) https://doi.org/10.1360/N112016-00268

Discovering abnormal civil aviation requirements by analyzing users' online query behaviors

More info
  • ReceivedNov 27, 2016
  • AcceptedMar 6, 2017
  • PublishedJul 4, 2017

Abstract

Changes of users' query volume in online fight ticketing systems indicate the changes of requirements in civil aviation markets. By analyzing the big data of users' online query behaviors, we can timely and accurately discover abnormal civil aviation requirements. This ability is very conducive for airlines and agencies for taking immediate and effective marketing actions. In this paper, we propose a novel method to discover abnormal civil aviation requirements based on time-series curves of users' query volumes. In addition, we utilize the domestic airline route network to optimize the anomaly detection results from the perspective of a global network rather than that of a single airline. We conduct experiments on real-world users' query datasets collected from an online ticketing site. The experimental results demonstrate that the proposed method can effectively discover abnormal civil aviation requirements from users' online query logs.


Funded by

国家自然科学基金(61403028)

教育部–中国移动科研基金(MCM20150513)

中央高校基本科研业务费(2016JBM017)


References

[1] Civil Aviation Administration of China. The civil aviation industry development statistical bulletin in 2016. 2017. http://www.caac.gov.cn . Google Scholar

[2] Barlés-Arizón M J, Fraj-Andrés E, Martínez-Salinas E. Family Vacation Decision Making: The Role of Woman. J Travel Tourism Marketing, 2013, 30: 873-890 CrossRef Google Scholar

[3] Ma W, Kleinschmidt T, Fookes C, et al. Check-in processing: simulation of passengers with advanced traits. In: Proceedings of the Winter Simulation Conference, Phoenix, 2011. 1783--1794. Google Scholar

[4] Budesca G C, Juan A A, Casas P F. Optimization of aircraft boarding processes considering passengers' grouping characteristics. In: Proceedings of the Winter Simulation Conference, Savannah, 2014. 1977--1988. Google Scholar

[5] Lin Y, Wan H, Jiang R. Inferring the Travel Purposes of Passenger Groups for Better Understanding of Passengers. IEEE Trans Intell Transport Syst, 2015, 16: 235-243 CrossRef Google Scholar

[6] Wan H Y, Wang Z W, Lin Y F. Discovering Family Groups in Passenger Social Networks. J Comput Sci Technol, 2015, 30: 1141-1153 CrossRef Google Scholar

[7] Lin Y F, Wang K K, Zhou C, et al. Modeling the preference of air passengers based on social networks. J Beijing Jiaotong Univ, 2014, 6: 33--39 . Google Scholar

[8] Lin Y F, Zhang A S, Wan H Y, et al. Predicting the growth of new passengers in civil aviation based on social networks. J Beijing Jiaotong Univ, 2014, 6: 40--46 . Google Scholar

[9] Xiao H. Similarity search and outlier detection in time series. Dissertation for Ph.D. Degree. Shanghai: Fudan University, 2005 . Google Scholar

[10] Protopapas P, Giammarco J M, Faccioli L. Finding outlier light curves in catalogues of periodic variable stars. Mon Not R Astronl Soc, 2006, 369: 677-696 CrossRef ADS Google Scholar

[11] Das M, Parthasarathy S. Anomaly detection and spatio-temporal analysis of global climate system. In: Proceedings of the 3rd International Workshop on Knowledge Discovery From Sensor Data, Paris, 2009. 142--150. Google Scholar

[12] Chandola V, Banerjee A, Kumar V. Anomaly detection for discrete sequences: a survey. IEEE Trans Knowl Data Eng, 2012, 24: 832--839. Google Scholar

[13] Yao Z, Mark P, Rabbat M. Anomaly Detection Using Proximity Graph and PageRank Algorithm. IEEE TransInformForensic Secur, 2012, 7: 1288-1300 CrossRef Google Scholar

[14] Izakian H, Pedrycz W, Jamal I. Clustering Spatiotemporal Data: An Augmented Fuzzy C-Means. IEEE Trans Fuzzy Syst, 2013, 21: 855-868 CrossRef Google Scholar

[15] Qiao Z, He J, Cao J, et al. Multiple time series anomaly detection based on compression and correlation analysis: a medical surveillance case study. In: Proceedings of the 14th Asia-Pacific Web Conference, Kunming, 2012. 294--305. Google Scholar

[16] Akoglu L, Tong H, Koutra D. Graph based anomaly detection and description: a survey. Data Min Knowl Disc, 2015, 29: 626-688 CrossRef Google Scholar

[17] Cleveland R B, Cleveland W S, McRae J E, et al. STL: a seasonal-trend decomposition procedure based on loess. J Off Stat, 1990, 6: 3--73. Google Scholar

[18] Faloutsos C, Ranganathan M, Manolopoulos Y. Fast subsequence matching in time-series databases. ACM Sigmod Rec, 2001, 23: 419--429. Google Scholar

  •   

    Algorithm 1 航线异常值的网络迭代优化算法

    Require:所有航线异常值序列初始值集合$\varPhi=\{\varPhi^{\langle{o,d}\rangle}\}$, 航线网络$G=(V,E)$.

    Output:所有航线异常值序列优化值集合$ \widetilde{\varPhi}=\{\widetilde{\varPhi}^{\langle{o,d}\rangle}\}$.

    $k \Leftarrow 1$;

    repeat

    for all ${c}\in {V}$

    根据式(6)计算出发地异常值序列$ \varPhi_{(k)}^{\langle{c}, \cdot\rangle}$;

    根据式(7)计算目的地异常值序列$ \varPhi_{(k)}^{\langle\cdot, {c}\rangle}$;

    end for

    for all $\langle{o,d}\rangle\in {E}$

    根据式(8)计算航线异常修正值序列$ \varPhi_{(k)}^{\prime\langle{o,d}\rangle}$;

    根据式(9)更新航线异常值序列$\varPhi_{(k)}^{\langle{o,d}\rangle}$;

    end for

    $k++$;

    until $k$达到最大迭代次数$\|$所有航线的异常值不再发生较大改变.

  • Table 1   Experimental data set statistics
    Item Value
    Number of cities in the entire data set 159
    Number of air routes in the entire data set 23416
    Query intervals in the entire data set $2015/5/5\sim2015/5/11$, $2015/5/7\sim2015/5/13$,
    $2015/5/9\sim2015/5/15$, $2015/5/11\sim2015/5/17$
    Number of air routes in the testing set Beijing-Kunming, Kunming-Beijing, Beijing-Xining,
    Xining-Beijing, Kunming-Xining, Xining-Kunming
    Number of positive examples in the testing set 378
    Number of negative examples in the testing set 1014

Copyright 2020 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1       京公网安备11010102003388号