- 无标题文档
查看论文信息

中文题名:

 

基于多源数据的车辆出行目的地预测方法研究

    

姓名:

 黄腾飞    

学号:

 1049721702705    

保密级别:

 公开    

论文语种:

 chi    

学科代码:

 080204    

学科名称:

 车辆工程    

学生类型:

 硕士    

学位:

 工学硕士    

学校:

 武汉理工大学    

院系:

 汽车工程学院    

专业:

 车辆工程    

研究方向:

 车辆网与大数据    

第一导师姓名:

 胡杰    

第一导师院系:

 武汉理工大学    

完成日期:

 2020-05-30    

答辩日期:

 2020-05-18    

中文关键词:

 

多源数据 ; 车辆轨迹 ; 车辆出行目的地预测 ; 多头自注意力机制 ; 时间卷积神经网络

    

中文摘要:

随着车载GPS的普及和汽车智能网联化的推广应用,汽车行业积累了海量的车辆轨迹数据。这些数据表征着人们的出行意图,具有丰富的应用价值,如移动位置推荐、出行线路规划和智慧交通等智能位置服务。智能位置服务的核心是基于车辆轨迹数据的位置预测技术,其中对车辆出行目的地的预测是研究的热点和难点,为解决现有预测方法中预测精度和计算效率较低的问题,提出了基于多源数据和深度学习的车辆出行目的地预测方法。

首先,在数据预处理及分析中,通过对轨迹数据进行坐标转换、轨迹分割、异常检测、网格编码和冗余处理操作,消除了数据噪声,过滤了异常数据,简化了轨迹表征形式;通过对出租车运营数据、地理兴趣点数据、行程起终点数据和天气数据进行分析,探索了时间、兴趣点和天气对居民出行的影响规律,为后续的特征工程提供依据。

其次,在特征工程中,提出了基于Geo2vec的轨迹网格表征方法,改善了表征效果,解决了未登陆词问题;提出了基于循环编码的时间数据表征方法,解决了时间数据循环特性难以表征的问题;提出了基于OD-POI状态转移概率矩阵的地理兴趣点表征方法,解决了兴趣点数据挖掘不充分的问题。研究表明,在平均距离偏差和均方根距离偏差上,Geo2vec相比于Word2vec分别降低了4.31%和5.03%,循环编码相对于标签编码分别降低了4.33%和5.88%,基于OD-POI状态转移概率矩阵的方法相对于基于起点概率的方法分别降低了3.37%和4.38%,基于多源数据的模型相比于仅基于轨迹数据的模型分别降低了14.67%和18.21%;在数据维度上,循环编码相对于独热编码在数据维度上减少了48.66%。

最后,在算法研究中,提出了基于多头自注意力机制的时间卷积神经网络,并将其应用于车辆出行目的预测领域,提高了预测精度,解决了现有算法计算效率低的问题。研究表明,该模型相比于常用的循环神经网络,在模型训练和预测时间上分别减少了63.51%和80.92%,同时在平均距离偏差和均方根距离偏差上分别降低了5.24%和6.82%。

本文所提出的基于多源数据的车辆出行目的地预测方法可有效地提高预测精度和计算效率,为该领域的研究提供了新的方法,具有较强的工程应用价值。

参考文献:

[1] 张亮. 基于工业大数据协同的汽车智能制造体系构建[J]. 上海汽车, 2019(11): 7-12.

[2] 吴华意, 黄蕊, 游兰等. 出租车轨迹数据挖掘进展[J]. 测绘学报, 2019, 48(11): 1341-1356.

[3] Xue A Y, Zhang R, Zheng Y, et al. Destination Prediction by Sub-Trajectory Synthesis and Privacy Protection Against Such Prediction[C]. Proceedings of the 2013 IEEE 29th International Conference on Data Engineering. IEEE, 2013.

[4] 赵鹏. 基于部分初始轨迹的目的地预测方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2017.

[5] 董莹, 董鹏, 唐猛. 我国智慧交通的现状和发展对策研究[J]. 公路交通科技(应用技术版), 2019, 15(08): 264-266.

[6] 郑宇. 城市计算:用大数据和AI打造未来城市[J]. 卫星与网络, 2018, 189(12): 34-37.

[7] Zhang X, Zhao Z, Zheng Y, et al. Prediction of Taxi Destinations Using a Novel Data Embedding Method and Ensemble Learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2019: 1-11.

[8] 朱自升. 基于神经网络的车辆轨迹预测算法的研究与实现[D]. 西安: 西安电子科技大学, 2018.

[9] 柯扬斌. 基于深度学习和回归型分类模型的出行目的地预测[D]. 杭州: 浙江大学, 2018.

[10] 陈轶嵩, 赵俊玮, 刘永涛. 面向未来智慧城市的汽车共享出行发展战略[J]. 中国工程科学, 2019, 21(03): 114-121.

[11] L. Liu, Z. Qiu, G. Li, et al. Contextualized Spatial–Temporal Network for Taxi Origin-Destination Demand Prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(10): 3875-3887.

[12] Besse P C, Guillouet B, Loubes J M, et al. Destination Prediction by Trajectory Distribution-Based Model[J]. IEEE Transactions on Intelligent Transportation Systems, 2017: 1-12.

[13] 郑宇. 城市计算概述[J]. 武汉大学学报: 信息科学版, 2015(40): 13.

[14] 张竣伟. 基于出租车GPS数据的用户出行热点挖掘与交通流波动分析[D]. 重庆: 西南大学, 2017.

[15] 何亚楠. 基于马尔科夫模型的出行目的地预测[D]. 长春: 吉林大学, 2017.

[16] 陈勐. 轨迹预测与意图挖掘问题研究[D]. 济南: 山东大学, 2016.

[17] 李科. 出租车新运营模式下LED广告精准投放策略研究[D]. 大连: 大连理工大学, 2018.

[18] Cai Z, He Z, Guan X, et al. Collective Data-Sanitization for Preventing Sensitive Information Inference Attacks in Social Networks[J]. IEEE Transactions on Dependable & Secure Computing, 2016: 1-1.

[19] Han Q, Liang S, Zhang H. Mobile cloud sensing, big data, and 5G networks make an intelligent and smart world[J]. Network, IEEE, 2015, 29(2): 40-45.

[20] Teevan J, Karlson A K, Amini S, et al. Understanding the importance of location, time, and people in mobile local search behavior[C]. Proceedings of the 13th Conference on Human-Computer Interaction with Mobile Devices and Services, Mobile HCI 2011, Stockholm, Sweden, 2011.

[21] 周灵通. 基于历史行车轨迹的目的地预测算法研究[D]. 广州: 华南理工大学, 2015.

[22] Karlaftis M G, Vlahogianni E I. Statistical methods versus neural networks in transportation research: Differences, similarities and some insights[J]. Transportation Research Part C Emerging Technologies, 2011, 19(3):387-399.

[23] Wu R, Luo G, Shao J, et al. Location prediction on trajectory data: A review[J]. Big Data Mining and Analytics, 2018, 1(2): 108-127.

[24] 张迎亚. 基于隐马尔可夫模型的车辆轨迹预测算法的研究[D]. 南京: 南京邮电大学, 2017.

[25] Simmons R, Browning B, Zhang Y, et al. Learning to Predict Driver Route and Destination Intent[C]. IEEE Intelligent Transportation Systems Conference. IEEE, 2006.

[26] Alvarez-Garcia J A, Ortega J A, Gonzalez-Abril L, et al. Trip destination prediction based on past GPS log using a Hidden Markov Model[J]. Expert Systems with Applications, 2010, 37(12): 8166-8171.

[27] 张国兴. 具有长期依赖的出租车轨迹目的地预测[D]. 徐州: 中国矿业大学, 2019.

[28] Yang J, Xu J, Xu M, et al. Predicting next location using a variable order Markov model[C]. Acm Sigspatial International Workshop on Geostreaming. ACM, 2014.

[29] 乔岩磊, 杜永萍, 赵东玥. 基于高斯分析的马尔可夫位置预测方法[J]. 计算机技术与发展, 2018, v.28; No.249(01): 47-50+56.

[30] 王津铭. 基于变阶Markov和LSTM的位置预测技术研究[D]. 北京: 北京邮电大学, 2018.

[31] Horvitz E. Predestination: Inferring Destinations from Partial Trajectories[M]. UbiComp 2006: Ubiquitous Computing. Springer Berlin Heidelberg, 2006.

[32] Wiest J, Hoffken M, Kresel U, et al. Probabilistic trajectory prediction with Gaussian mixture models[C]. Intelligent Vehicles Symposium (IV), 2012 IEEE. IEEE, 2012.

[33] Besse P C, Guillouet B, Loubes J M, et al. Destination Prediction by Trajectory Distribution-Based Model[J]. IEEE Transactions on Intelligent Transportation Systems, 2017:1-12.

[34] Cui Xie, Hao Yang, Guangxiao Ma, and Junyu Dong. Visual analysis of tropical cyclone trajectory prediction[C]. Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106155H (10 April 2018).

[35] D. Tiesyte and C. S. Jensen. Similarity-based prediction of travel times for vehicles traveling on known routes. in Proc. GIS, 2008, pp. 1–10.

[36] Chen L, Lv M, Chen G. A system for destination and future route prediction based on trajectory mining[J]. Pervasive and Mobile Computing, 2010, 6(6): 657-676.

[37] Xu M, Wang D, Li J. DESTPRE: a data-driven approach to destination prediction for taxi rides[C]. The 2016 ACM International Joint Conference. ACM, 2016.

[38] 江婧, 张怀峰, 皮德常. 基于卷积神经网络的移动对象目的地预测[J]. 小型微型计算机系统, 2019, 40(12): 2519-2525.

[39] Xue A Y, Zhang R, Zheng Y, et al. Destination prediction by subtrajectory synthesis and privacy protection against such prediction [C]. IEEE International Conference on Data Engineering,2012: 254-265.

[40] Xue A Y, Zhang R, Zheng Y, et al. DesTeller: a system for destination prediction based on trajectories with privacy protection[C]. International Conference on Very Large Data Bases, 2013: 1198-1201.

[41] Xue A Y, Qi J, Xie X, et al. Solving the data sparsity problem in destination prediction [J].Vldb Journal, 2015, 2 4(2): 219-243.

[42] Wang L, Yu Z, Guo B, et al. Moving Destination Prediction Using Sparse Dataset[J]. ACM Transactions on Knowledge Discovery from Data, 2017, 11(3):1-33.

[43] Li X, Li M, Gong Y J, et al. T-DesP: Destination Prediction Based on Big Trajectory Data[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(8):2344-2354.

[44] Krause, Cory M. & Zhang, Lei. Short-term travel behavior prediction with GPS, land use, and point of interest data. Transportation Research Part B: Methodological, Elsevier, 2019, vol. 123(C), pages 349-361.

[45] Horvitz E. Predestination: Inferring Destinations from Partial Trajectories[M]. UbiComp 2006: Ubiquitous Computing. Springer Berlin Heidelberg, 2006.

[46] John Krumm, Eric Horvitz. Predestination: Where Do You Want to Go Today? [J]. Computer, 2007, 40(4):105-107.

[47] Ziebart B D , Maas A L , Dey A K , et al. Navigate like a cabbie: Probabilistic reasoning from observed context-aware behavior[C]. International Conference on Ubiquitous Computing. ACM, 2008.

[48] Horvitz E, Krumm J. Some help on the way: opportunistic routing under uncertainty[C]. Acm Conference on Ubiquitous Computing. ACM, 2012.

[49] de Brébisson, Alexandre, Simon, étienne, Auvolat A , et al. Artificial Neural Networks Applied to Taxi Destination Prediction[J]. Computer Science, 2015.

[50] Pang-Ning Tan, Michael Steinbach, Vipin Kumar. 数据挖掘导论[M]. 北京: 人民邮电出版社, 2011.

[51] Rendle, Steffen, et al. BPR: Bayesian personalized ranking from implicit feedback[C]. Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. AUAI Press, 2009.

[52] Davd. Rumhar, offry. Hnon, RonadJ. Wams. Learning representations by back-propagating errors[J]. 1986.

[53] 张国兴, 李亚东, 张磊等. 基于SDZ-RNN的出租车出行目的地预测方法[J]. 计算机工程与应用, 2018, 54(06): 143-149.

[54] Endo Y, Nishida K, Toda H, et al. Predicting Destinations from Partial Trajectories Using Recurrent Neural Network[C]. Pacific-asia Conference on Knowledge Discovery & Data Mining. Springer, Cham, 2017.

[55] BENGIO Y. Learning Long-term Dependencies With Gradient Descent is Difficult[J]. IEEE Trans Neural Netw, 1994, 5.

[56] Hochreiter, S, Schmidhuber, J. Long Short-Term Memory[J]. Neural Computation, 1997. 9(8):1735-1780.

[57] Chung J, Gulcehre C, Cho K H, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[J]. Neural and Evolutionary Computing, 2014.

[58] Lv J, Li Q, Wang X. T-CONV: A Convolutional Neural Network For Multi-scale Taxi Trajectory Prediction[J]. 2016.

[59] Bai S, Kolter J Z, Koltun V. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling[J]. 2018.

[60] Ryo Imai, Kota Tsubouchi, Tatsuya Konishi, and Masamichi Shimosaka. Early destination prediction with spatio-temporal user behavior patterns[J]. IMWUT, 2017, 1(4):142:1–142:19.

[61] Sung Jun Lee, Junseok Lim, Jonghun Park, and Kwanho Kim. Next place prediction based on spatiotemporal pattern mining of mobile device logs[J]. Sensors, 2016, 16(2):145.

[62] DataCastle.交通线路通达时间预[OL]. DC竞赛. 2017. https://www.dcjingsai.com/common/ cmptIndex. html.

[63] Lars Briem, Michael Heilig,Christian Klinkhardt,Peter Vortisch. Analyzing OpenStreetMap as data source for travel demand models A case study in Karlsruhe[J]. Transportation Research Procedia,2019,41.

[64] 刁丰华. 基于无参考数据的众源地理信息质量评价方法研究[D]. 徐州: 中国矿业大学, 2019.

[65] Wunderground. Chengdu, Sichuan, People's Republic of China Weather Conditions[OL]. TWC Product and Technology. 2015. https://www.wunderground.com.

[66] Wandergis. Coordtransform 坐标转换[OL]. Github. 2017. https://github.com/wandergis/ coordtransform

[67] de Villiers, Michael. Heavenly Mathematics: The Forgotten Art of Spherical Trigonometry[J]. The European Legacy, 2015. 20(5): 560-561.

[68] 周艺华, 李广辉, 杨宇光, 侍伟敏. 基于GeoHash的近邻查询位置隐私保护方法[J]. 计算机科学, 2019, 46(08): 212-216.

[69] 李航. 统计学习方法[M]. 北京: 清华大学出版社, 2012.

[70] Harris, Sarah, Harris, et al. Digital design and computer architecture [M]. Chian Machine Press, 2014.

[71] Bengio, Y., Ducharme, R., Vincent, P., & Janvin, A neural probabilistic language model[J]. The Journal of Machine Learning Research, 2003. 3, 1137-1155.

[72] 高崇铭. 轨迹语义表征与地点推荐研究[D]. 成都: 电子科技大学,2019.

[73] 卢照旭. 基于改进的BiLSTM目的地位置预测技术研究[D]. 北京: 北京邮电大学,2019.

[74] T Mikolov, K Chen,G Corrado, et al. Efficient Estimation of Word Representations in Vector Space[J]. Computer Science, 2013: 1-12.

[75] Bojanowski P, Grave E, Joulin A, et al. Enriching Word Vectors with Subword Information[J]. Transactions of the Association for Computational Linguistics, 2017, 5:135-146.

[76] Agarwal S. Data Mining: Data Mining Concepts and Techniques[C]. 2013 International Conference on Machine Intelligence and Research Advancement (ICMIRA). IEEE, 2013.

[77] Han, Qilong, Dan Lu, Kejia Zhang, et al. A Prediction Method for Destination Based on the Semantic Transfer Model. IEEE Access 7 (2019): 73756-73763.

[78] B. W. White, Frank Rosenblatt. Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms[J]. The American Journal of Psychology, 1963, 76(4):705.

[79] Jie Hu, Tengfei Huang, Jiaopeng Zhou, et al. Electronic Systems Diagnosis Fault in Gasoline Engines Based on Multi-Information Fusion [J]. Sensors. 2018. 18. 2917. 10.3390/s18092917.

[80] Dupond, Samuel. A thorough review on the current advance of neural network structures[J]. Annual Reviews in Control. 2019. 14: 200–230.

[81] BENGIO Y. Learning Long-term Dependencies with Gradient Descent is Difficult[J]. IEEE Trans Neural Netw, 1994, 5.

[82] 裴君楠, 陈一萱. 一维卷积神经网络在轴承故障检测中的应用[J]. 现代矿业, 2019, 35(10): 190-193

[83] Barret Zoph, Vijay Vasudevan, Jonathon Shlens, Quoc V. Le; Learning Transferable Architectures for Scalable Image Recognition[C]. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8697-8710

[84] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Deep Residual Learning for Image Recognition[C]. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778

[85] 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(08): 2261-2270.

[86] 朱张莉, 饶元, 吴渊等. 注意力机制在深度学习中的研究进展[J]. 中文信息学报, 2019, 33(06): 1-11.

[87] Mnih V, Heess N, Graves A, et al. Recurrent Models of Visual Attention[J]. Advances in neural information processing systems, 2014.

[88] Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate[J] Computer Science, 2014.

[89] Yang Z, Yang D, Dyer C, et al. Hierarchical Attention Networks for Document Classification[C] Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

[90] Vaswani A, Shazeer N, Parmar N, et al. Attention Is All You Need[J]. Computation and Language, 2017.

[91] 常新旭, 张杨, 杨林等. 融合多头自注意力机制的语音增强方法[J]. 西安电子科技大学学报. 2020. 1-8.

[92] Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]. International Conference on International Conference on Machine Learning. JMLR.org, 2015.

[93] 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(1):1929-1958.

[94] Kingma D , Ba J . Adam: A Method for Stochastic Optimization[J]. Computer ence, 2014.

[95] Prechelt L. Neural Networks: Tricks of the Trade [M]. Berlin, Heidelberg: Springer, 2012.

中图分类号:

 U491    

馆藏号:

 U491/2705/2020    

备注:

 403-西院分馆博硕论文库;203-余家头分馆博硕论文库    

无标题文档

   建议浏览器: 谷歌 火狐 360请用极速模式,双核浏览器请用极速模式