Volume 8 Issue 1
Mar.  2019
Turn off MathJax
Article Contents
Article Navigation >  Journal of Radars  > 2019  >  8(1): 36-43
HAN Zhaorong, HUANG Tinglei, REN Wenjuan, et al. Trajectory outlier detection algorithm based on Bi-LSTM model[J]. Journal of Radars, 2019, 8(1): 36–43. doi: 10.12000/JR18039
Citation: HAN Zhaorong, HUANG Tinglei, REN Wenjuan, et al. Trajectory outlier detection algorithm based on Bi-LSTM model[J]. Journal of Radars, 2019, 8(1): 36–43. doi: 10.12000/JR18039
shu

Trajectory Outlier Detection Algorithm Based on Bi-LSTM Model

doi: 10.12000/JR18039
  • ①.

    University of Chinese Academy of Sciences, Beijing 100049, China

  • ②.

    Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China

  • ③.

    Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing 100190, China

Funds:  The National Natural Science Foundation of China (61725105, 61331017)
More Information
  • Corresponding author: HUANG Tinglei, tlhuang@mail.ie.ac.cn
  • Received Date: 2018-05-14
  • Rev Recd Date: 2018-05-30
    • Available Online: 2018-07-09
  • Publish Date: 2019-02-28
    Abstract
  • The rapid advances in positioning technology have created huge spatio-temporal trajectory data, and there are always obvious aberrant outliers in trajectory data. Detecting outliers in the trajectory is critical to improving data quality and the accuracy of subsequent trajectory data mining tasks. In this paper, we propose a trajectory outlier detection algorithm based on a Bidirectional Long Short-Term Memory (Bi-LSTM) model. First, a six-dimensional motion feature vector is extracted for each trajectory point, and then we construct a Bi-LSTM model. The model input is the trajectory data feature vector of a certain sequence length, and its output is the class type of the current track point. In addition, a combination method of undersampling and oversampling is applied to mitigate the effect of data distribution imbalance on detection performance. The Bi-LSTM model can automatically learn the difference between the normal points and adjacent abnormal points in the motion characteristics by combining the LSTM unit and the bidirectional network. Experimental results based on a real ship trajectory annotation data show that the detection performance of our proposed algorithm significantly exceeds those of the constant velocity threshold algorithm, non-sequential classical machine learning classification algorithms, and convolutional neural network model. Especially, the recall value of the proposed algorithm reaches 0.902, which verifies its effectiveness.

     

    • FullText(HTML)
  • loading
    • References(24)
  • [1]
    LEE J G, HAN J W, and WHANG K Y. Trajectory clustering: A partition-and-group framework[C]. Proceedings of the 2007 ACM SIGMOD International Conference on Management of Data, Beijing, China, 2007: 593–604.
    [2]
    李万春, 黄成峰. 基于角度和多普勒频率的外辐射源定位系统的接收器最优航迹分析[J]. 雷达学报, 2014, 3(6): 660–665. doi: 10.12000/JR14118

    LI Wan-chun and HUANG Cheng-feng. Optimal trajectory analysis for the receiver of passive location systems using direction of arrival and Doppler measurements[J]. Journal of Radars, 2014, 3(6): 660–665. doi: 10.12000/JR14118
    [3]
    齐林, 王海鹏, 刘瑜. 基于统计双门限的中断航迹配对关联算法[J]. 雷达学报, 2015, 4(3): 301–308. doi: 10.12000/JR14077

    QI Lin, WANG Hai-peng, and LIU Yu. Track segment association algorithm based on statistical binary thresholds[J]. Journal of Radars, 2015, 4(3): 301–308. doi: 10.12000/JR14077
    [4]
    ZHENG Y, LIU L K, WANG L H, et al. Learning transportation mode from raw GPS data for geographic applications on the web[C]. Proceedings of the 17th International Conference on World Wide Web, Beijing, China, 2008: 247–256. doi: 10.1145/1367497.1367532.
    [5]
    BAO J, ZHENG Y, and MOKBEL M F. Location-based and preference-aware recommendation using sparse geo-social networking data[C]. Proceedings of the 20th International Conference on Advances in Geographic Information Systems, Redondo Beach, California, 2012: 199–208. doi: 10.1145/2424321.2424348.
    [6]
    ZHANG D Q, LI N, ZHOU Z H, et al. iBAT: Detecting anomalous taxi trajectories from GPS traces[C]. Proceedings of the 13th International Conference on Ubiquitous Computing, Beijing, China, 2011: 99–108. doi: 10.1145/2030112.2030127.
    [7]
    ZHENG Y and ZHOU X F. Computing with Spatial Trajectories[M]. New York: Springer Science & Business Media, 2011.
    [8]
    HAWKINS D M. Identification of Outliers[M]. Dordrecht: Springer, 1980.
    [9]
    HAN J W, KAMBER M, and PEI J. Data Mining: Concepts and Techniques[M]. Amsterdam: Elsevier, 2011.
    [10]
    ALVARES L O, OLIVEIRA G, and BOGORNY V. A framework for trajectory data preprocessing for data mining[C]. Proceedings of the 21st Interantional Conference on Software Engineering & Knowledge Engineering, SEKE, Boston, USA, 2009, 21: 698–702.
    [11]
    CHEN L, LV M Q, YE Q, et al. A personal route prediction system based on trajectory data mining[J]. Information Sciences, 2011, 181(7): 1264–1284. doi: 10.1016/j.ins.2010.11.035
    [12]
    ZHENG Y, XIE X, and MA W Y. Geolife: A collaborative social networking service among user, location and trajectory[J]. IEEE Data Engineering Bulletin, 2010, 33(2): 32–39.
    [13]
    CHEN X J, CUI T T, FU J H, et al. Trend-residual dual modeling for detection of outliers in low-cost GPS trajectories[J]. Sensors, 2016, 16(12): 2036. doi: 10.3390/s16122036
    [14]
    胡晶. 基于AIS的船舶轨迹分析与应用系统的设计与实现[D]. [硕士论文], 华中师范大学, 2015.

    HU Jing. Design and implementation of vessel trajectory analysis and application system based on AIS[D]. [Master dissertation], Central China Normal University, 2015.
    [15]
    吴建华, 吴琛, 刘文, 等. 舶舶AIS轨迹异常的自动检测与修复算法[J]. 中国航海, 2017, 40(1): 8–12, 101. doi: 10.3969/j.issn.1000-4653.2017.01.003

    WU Jian-hua, WU Chen, LIU Wen, et al. Automatic detection and restoration algorithm for trajectory anomalies of ship AIS[J]. Navigation of China, 2017, 40(1): 8–12, 101. doi: 10.3969/j.issn.1000-4653.2017.01.003
    [16]
    BESSA A, DE MESENTIER SILVA F, NOGUEIRA R F, et al. RioBusData: Outlier detection in bus routes of rio de janeiro[OL]. arXiv: 160106128, 2016.
    [17]
    FERNANDO T, DENMAN S, SRIDHARAN S, et al. Soft+ hardwired attention: An lstm framework for human trajectory prediction and abnormal event detection[OL]. arXiv: 1702.05552, 2017.
    [18]
    HOCHREITER S and SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735–1780. doi: 10.1162/neco.1997.9.8.1735
    [19]
    GRAVES A and SCHMIDHUBER J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks, 2005, 18(5/6): 602–610. doi: 10.1016/j.neunet.2005.06.042
    [20]
    SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15: 1929–1958.
    [21]
    BATISTA G E A P A, PRATI R C, and MONARD M C. A study of the behavior of several methods for balancing machine learning training data[J]. ACM SIGKDD Explorations Newsletter, 2004, 6(1): 20–29. doi: 10.1145/1007730.1007735
    [22]
    周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.

    ZHOU Zhi-hua. Machine Learning[M]. Beijing: Tsinghua University Press, 2016.
    [23]
    FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2006, 27(8): 861–874. doi: 10.1016/j.patrec.2005.10.010
    [24]
    PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al. Scikit-learn: Machine learning in python[J]. Journal of Machine Learning Research, 2011, 12: 2825–2830.
    • Relative Articles
    • Supplements(0)
    • Cited By
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索
    Get Citation
    PDF
    XML
    Article views(5230) PDF downloads(482) Cited by()
    Proportional views
    Related

    京ICP备20021838号-8   Supported by: Beijing Renhe Information Technology Co. Ltd     百度统计

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return