Page 252 - 《软件学报》2021年第5期

1476 Journal of Software 软件学报 Vol.32, No.5, May 2021

据挖掘的研究领域必然会随着数据的演化和技术的进步而不断地发展.而轨迹表示承担着将原始数据转化为
模型输入的重要任务,是轨迹数据挖掘中的一项关键技术,研究者们针对不同应用背景下的轨迹表示做了大量
的工作.本文对近年来轨迹表示的主要研究成果进行了全面的梳理和总结,将轨迹表示按照研究对象的不同尺
度分为对轨迹单元的表示和对整条轨迹的表示,其中,对每一种类别的表示方法按照方法的不同原理进一步做
了详细的对比分析,并给出了相应的轨迹数据挖掘应用.最后,本文对轨迹表示领域现有工作研究不足的问题和
未来值得研究的方向提出了自己的观点.

References:
[1] Li X, Zhao K, Cong G, et al. Deep representation learning for trajectory similarity computation. In: Proc. of the IEEE 34th Int’l
Conf. on Data Engineering (ICDE). 2018. 617−628. [doi: 10.1109/ ICDE.2018.00062]
[2] Zhang Y, Liu A, Liu G, Li Z, Li Q. Deep representation learning of activity trajectory similarity computation. In: Proc. of the 2019
IEEE Int’l Conf. on Web Services (ICWS). 2019. 312−319. [doi: 10.1109/icws.2019.00059]
[3] Yao D, Zhang C, Zhu Z, Huang J, Bi J. Trajectory clustering via deep representation learning. In: Proc. of the Int’l Joint Conf. on
Neural Networks. 2017. 3880−3887. [doi: 10.1109/IJCNN.2017.7966345]
[4] Han B, Liu L, Omiecinski E. A systematic approach to clustering whole trajectories of mobile objects in road networks. IEEE Trans.
on Knowledge and Data Engineering, 2017,29(5):936−949. [doi: 10.1109/TKDE.2017.2652454]
[5] Endo Y, Toda H, Nishida K, Ikedo J. Classifying spatial trajectories using representation learning. Int’l Journal of Data Science and
Analytics, 2016,2(3-4):107−117. [doi: 10.1007/s41060-016-0014-1]
[6] Jiang X, de Souza EN, Pesaranghader A, Hu B, Silver DL, Matwin S. TrajectoryNet: An embedded GPS trajectory representation
for point-based classification using recurrent neural networks. 2017. http://arxiv.org/abs/1705.02636
[7] Chen X, Ye Q, Zou J, Li C, Cui Y, Jiao J. Visual trajectory analysis via replicated softmax-based models. Signal, Image and Video
Processing, 2014,8(1):183−190. [doi: 10.1007/s11760-014-0671-2]
[8] Sillito RR, Fisher RB. Semi-supervised learning for anomalous trajectory detection. In: Proc. of the British Machine Vision Conf.
(BMVC 2008). 2008. [doi: 10.5244/C.22.103]
[9] Feng W, Han C. A novel approach for trajectory feature representation and anomalous trajectory detection. In: Proc. of the 2015
18th Int’l Conf. on Information Fusion. 2015. 1093−1099.
[10] Wu H, Chen Z, Sun W, Zheng B, Wang W. Modeling trajectories with recurrent neural networks. In: Proc. of the Int’l Joint Conf.
on Artificial Intelligence. 2017. 3083–3090. https://doi.org/10.24963/ijcai.2017/430
[11] Wang J, et al. Spatiotemporal modeling and prediction in cellular networks: A big data enabled deep learning approach. 2017. [doi:
10.1109/INFOCOM.2017.8057090]
[12] Chow KH, Hiranandani A, Zhang Y, et al. Representation learning of pedestrian trajectories using actor-critic sequence-to-
sequence autoencoder. arXiv preprint arXiv:1811.08069, 2018.
[13] Yin P, Ye M, Lee WC, Li Z. Mining GPS data for trajectory recommendation. 2014. [doi: 10.1007/978-3-319-06605-9_5]
[14] Yang C, Sun M, Zhao WX, et al. A neural network approach to jointly modeling social networks and mobile trajectories. ACM
Trans. on Information Systems (TOIS), 2017,35(4):1−28. [doi: 10.1145/3041658]
[15] Gao Q, Zhou F, Zhang K, Trajcevski G, Luo X, Zhang F. Identifying human mobility via trajectory embeddings. In: Proc. of the
IJCAI Int’l Joint Conf. on Artificial Intelligence. 2017. 1689−1695.
[16] Zhou F, Gao Q, Trajcevski G, Zhang K, Zhong T, Zhang F. Trajectory-user linking via variational autoencoder. In: Proc. of the
IJCAI Int’l Joint Conf. on Artificial Intelligence. 2018. 3212−3218.
[17] Zheng Y. Trajectory data mining: An overview. ACM Trans. on Intelligent Systems and Technology, 2015,6(3):1−41. [doi:
10.1145/2743025]
[18] Wang S, Cao J, Yu PS. Deep learning for spatio-temporal data mining: A survey. 2019. 1−21. http://arxiv.org/abs/1906.04928
[19] He X, Cormode G, Machanavajjhala A, et al. DPT: Differentially private trajectory synthesis using hierarchical reference systems.
Proc. of the VLDB Endowment, 2015,8(11):1154−1165.
[20] Mao Y, Zhong H, Qi H, et al. An adaptive trajectory clustering method based on grid and density in mobile pattern analysis.
Sensors, 2017,17(9):Article No.2013. [doi: 10.3390/s17092013]