Trajectory prediction based on Gauss mixture time series model

doi:10.11772/j.issn.1001-9081.2019010030

Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (8): 2261-2270.DOI: 10.11772/j.issn.1001-9081.2019010030

• Artificial intelligence • Previous Articles Next Articles

Trajectory prediction based on Gauss mixture time series model

GAO Jian, MAO Yingchi, LI Zhitao

College of Computer and Information, Hohai University, Nanjing Jiangsu 211100, China

Received:2019-01-04 Revised:2019-02-28 Online:2019-08-10 Published:2019-04-11
Supported by:
This work is partially supported by the National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2018YFC0407105), the Key Technology Project of China Huaneng Group (HNKJ17-21).

基于高斯混合时间序列模型的轨迹预测

高建, 毛莺池, 李志涛

河海大学计算机与信息学院, 南京 211100

通讯作者: 高建
作者简介:高建(1994-),男,安徽滁州人,硕士研究生,CCF会员,主要研究方向:数据挖掘、人工智能;毛莺池(1976-),女,上海人,教授,博士,CCF会员,主要研究方向:物联网、分布式数据处理;李志涛(1991-),男,河南濮阳人,硕士,主要研究方向:数据挖掘。
基金资助:
“十三五”国家重点研发计划项目（2018YFC0407105）；华能集团重点研发项目（HNKJ17-21）。

Abstract

Abstract: Considering the large change of trajectory prediction error caused by the change of road traffic flow at different time, a Gauss Mixture Time Series Model (GMTSM) based on probability distribution model was proposed. The model regression of mass vehicle historical trajectories and the analysis of road traffic flow were carried out to realize vehicle trajectory prediction. Firstly, aiming at the problem that the uniform grid partition method was easy to cause the splitting of related trajectory points, an iterative grid partition method was proposed to realize the quantity balance of trajectory points. Secondly, Gaussian Mixture Model (GMM) and AutoRegressive Integrated Moving Average model (ARIMA) in time series analysis were trained and combined together. Thirdly, in order to avoid the interference of the instability of GMTSM hybrid model's sub-models on the prediction results, the weights of sub-models were dynamically calculated by analyzing the prediction errors of the sub-models. Finally, based on the dynamic weight, the sub-models were combined together to realize trajectory prediction. Experimental results show that the average prediction accuracy of GMTSM is 92.3% in the case of sudden change of road traffic flow. Compared with Gauss mixed model and Markov model under the same parameters, GMTSM has prediction accuracy increased by about 55%. GMTSM can not only accurately predict vehicle trajectory under normal circumstances, but also effectively improve the accuracy of trajectory prediction under road traffic flow changes, which is applicable to the real road environment.

Key words: intelligent transportation, iterative grid partition, trajectory prediction, model reliability, trajectory similarity

摘要： 针对不同时间道路车流量变化下轨迹预测误差变化大的问题，提出基于概率分布模型的高斯混合-时间序列模型（GMTSM），对海量车辆历史轨迹进行模型回归和路段车流量的分析以实现车辆轨迹预测。首先，针对均匀网格划分方法容易造成相关轨迹点分裂的问题，提出迭代式网格划分来实现轨迹点的数量均衡；其次，训练并结合高斯混合模型（GMM）和时间序列分析中的差分自回归滑动平均模型（ARIMA）；然后，为了避免GMTSM中子模型自身的不稳定性对预测结果产生干扰，对子模型的预测进行误差分析，动态计算子模型的权重；最后，依据动态权重组合子模型实现轨迹预测。实验结果表明，GMTSM在路段车流量突变情况下，平均预测准确率为90.3%；与相同参数设置下的高斯混合模型和马尔可夫模型相比，GMTSM预测准确性提高了55%左右。GMTSM不仅能在正常情况下准确预测车辆轨迹，而且能有效提高道路车流量变化情况下的轨迹预测准确率，适用于现实路况环境。

关键词: 智能交通, 迭代网格划分, 轨迹预测, 模型可靠性, 轨迹相似性

CLC Number:

TP391.4

GAO Jian, MAO Yingchi, LI Zhitao. Trajectory prediction based on Gauss mixture time series model[J]. Journal of Computer Applications, 2019, 39(8): 2261-2270.

高建, 毛莺池, 李志涛. 基于高斯混合时间序列模型的轨迹预测[J]. 计算机应用, 2019, 39(8): 2261-2270.

References

[1] GAMBS S, KILLIJIAN M, del PRADA CORTEZ M N. Next place prediction using mobility Markov chains[C]//Proceedings of the First Workshop on Measurement, Privacy, and Mobility. New York:ACM, 2012:No.3.
[2] 李万高, 赵雪梅, 孙德厂. 基于改进贝叶斯方法的轨迹预测算法研究[J]. 计算机应用, 2013, 33(7):1960-1963. (LI W G, ZHAO X M, SUN D G. Prediction of trajectory based on modified Bayesian inference[J]. Journal of Computer Applications, 2013, 33(7):1960-1963.)
[3] LI Z, ZHU H Z, XUE G, et al. Traffic-known urban vehicular route prediction based on partial mobility patterns[C]//Proceedings of the 2009 International Conference on Parallel and Distributed Systems. Piscataway, NJ:IEEE, 2009:369-375.
[4] ZHENG Y, LIU F, HSIEH H. U-Air:when urban air quality inference meets big data[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2013:1436-1444.
[5] KU Y, LI H, PENG J, et al. Partspan:parallel sequence mining of trajectory patterns[C]//Proceedings of the 4th International Conference on Fuzzy Systems and Knowledge Discovery. Piscataway, NJ:IEEE, 2008:363-367.
[6] TAO Y F, FALOUTSOS C, PAPADIAS D, et al. Prediction and indexing of moving objects with unknown motion patterns[C]//Proceedings of the 2004 ACM SIGMOD International Conference on Management of Data. New York:ACM, 2004:611-622.
[7] 乔少杰, 金琨, 韩楠, 等.一种基于高斯混合模型的轨迹预测算法[J]. 软件学报, 2015, 26(5):1048-1063. (QIAO S J, JIN K, HAN N, et al. Trajectory prediction algorithm based on Gaussian mixture model[J]. Journal of Software, 2015, 26(5):1048-1063.)
[8] 乔少杰, 李天瑞, 韩楠, 等. 大数据环境下移动对象自适应轨迹预测模型[J]. 软件学报, 2015, 26(11):2869-2883. (QIAO S J, LI T R, HAN N, et al. Self-adaptive trajectory prediction model for moving objects in big data environment[J]. Journal of Software, 2015, 26(11):2869-2883.)
[9] BEST G, FITCH R. Bayesian intention inference for trajectory prediction with an unknown goal destination[C]//Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ:IEEE, 2015:5817-5823.
[10] SU I, LEI P, SHEN T J, et al. Exploring spatial-temporal trajectory model for location prediction[C]//Proceedings of the 2011 IEEE International Conference on Mobile Data Management. Piscataway, NJ:IEEE, 2011:58-67.
[11] GAO H J, TANG J L, LIU H. Mobile location prediction in spatio-temporal context[EB/OL].[2018-05-12]. https://www.researchgate.net/profile/Huan_Liu6/publication/265437484_Mobile_Location_Prediction_in_Spatio-Temporal_Context/links/551c9ba80cf20d5fbde557eb.pdf.
[12] JEUNG H, SHEN H, LIU Q, et al. A hybrid prediction model for moving objects[C]//Proceedings of the IEEE 24th International Conference on Data Engineering. Piscataway, NJ:IEEE, 2008:70-79.
[13] 李昇智, 乔建忠, 林树宽, 等. 基于GPS轨迹数据的混合多步Markov位置预测[J]. 东北大学学报(自然科学版), 2017, 38(12):1686-1690. (LI S Z, QIAO J Z, LIN S K, et al. Hybrid multi-step Markov location prediction based on GPS trajectory data[J]. Journal of Northeastern University (Natural Science), 2017, 38(12):1686-1690)
[14] WIEST J, HÖFFKEN M, KREßEL U, et al. Probabilistic trajectory prediction with Gaussian mixture models[C]//Proceedings of the 2012 IEEE Intelligent Vehicles Symposium. Piscataway, NJ:IEEE, 2012:141-146.
[15] 夏卓群, 胡珍珍, 罗君鹏, 等. 不确定环境下移动对象自适应轨迹预测方法[J]. 计算机研究与发展, 2017, 54(11):2434-2444. (XIA Z Q, HU Z Z, LUO J P, et al. Adaptive trajectory prediction for moving objects in uncertain environment[J]. Journal of Computer Research and Development, 2017, 54(11):2434-2444.)
[16] BILJECKI F, LEDOUX H, van OOSTEROM P. Transportation mode-based segmentation and classification of movement trajectories[J]. International Journal of Geographical Information Science, 2013, 27(2):385-407.
[17] WEI Y, ZHENG Y, YANG Q. Transfer knowledge between cities[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York,:ACM, 2016:1905-1914.
[18] ZHENG Y, CAPRA L, WOLFSON O, et al. Urban computing:concepts, methodologies, and applications[J]. ACM Transactions on Intelligent Systems and Technology-Special Section on Urban Computing, 2014, 5(3):No.38.
[19] MUSA J D. A theory of software reliability and its application[J]. IEEE Transactions on Software Engineering, 1975, 1(3):312-327.

Trajectory prediction based on Gauss mixture time series model

基于高斯混合时间序列模型的轨迹预测

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	DAI Yurou, YANG Qing, ZHANG Fengli, ZHOU Fan. Trajectory prediction model of social network users based on self-supervised learning [J]. Journal of Computer Applications, 2021, 41(9): 2545-2551.
[2]	LI Xujuan, PI Jianyong, HUANG Feixiang, JIA Haipeng. Self-generated deep neural network based 4D trajectory prediction [J]. Journal of Computer Applications, 2021, 41(5): 1492-1499.
[3]	LYU Yike, XU Kai, HUANG Zhenqiang. Trajectory similarity measurement method based on area division [J]. Journal of Computer Applications, 2020, 40(2): 578-583.
[4]	SUN Yasheng, JIANG Qi, HU Jie, QI Jin, PENG Yinghong. Attention mechanism based pedestrian trajectory prediction generation model [J]. Journal of Computer Applications, 2019, 39(3): 668-674.
[5]	CHEN Ke. Automatic camera calibration method for video-based vehicle speed detection [J]. Journal of Computer Applications, 2017, 37(8): 2307-2312.
[6]	ZHENG Linjang, LIU Xu, YI Bing. Dynamic weighted real-time map matching algorithm considering spatio-temporal property [J]. Journal of Computer Applications, 2017, 37(8): 2381-2386.
[7]	DONG Junfei, ZHENG Bochuan, YANG Zejing. Character recognition of license plate based on convolution neural network [J]. Journal of Computer Applications, 2017, 37(7): 2014-2018.
[8]	QI Xin, LIANG Weitao, MA Yong. Optimal path planning method based on taxi trajectory data [J]. Journal of Computer Applications, 2017, 37(7): 2106-2113.
[9]	ZHANG Jun, HU Zhenbo, ZHU Xinshan. Real-time traffic accident prediction based on AdaBoost classifier [J]. Journal of Computer Applications, 2017, 37(1): 284-288.
[10]	GAN Ling, LI Rui. Multilane traffic flow detection algorithm based on adaptive virtual loop [J]. Journal of Computer Applications, 2016, 36(12): 3511-3514.
[11]	KOU Lan, YANG Lina, LIU Kezheng, HU Min, MAO Yiding. Cooperative delay and tolerant network routing strategy based on urban public transport mobility model [J]. Journal of Computer Applications, 2016, 36(11): 3021-3027.
[12]	SONG Lujie, MENG Fanrong, YUAN Guan. Moving object location prediction algorithm based on Markov model and trajectory similarity [J]. Journal of Computer Applications, 2016, 36(1): 39-43.
[13]	REN Pengfei, QIN Guihe, DONG Jinnan, LI Bin, ZHENG Xiaotian. Improved Dijkstra algorithm with traffic rule constraints [J]. Journal of Computer Applications, 2015, 35(9): 2503-2507.
[14]	LIU Leijun, ZHU Meng, ZHANG Lei. Sparse trajectory prediction method based on iterative grid partition and entropy estimation [J]. Journal of Computer Applications, 2015, 35(11): 3161-3165.
[15]	WANG Xing JIANG Xinhua LIN Jie XIONG Jinbo. Prediction of moving object trajectory based on probabilistic suffix tree [J]. Journal of Computer Applications, 2013, 33(11): 3119-3122.