基于贝叶斯网络的稀疏出租车GPS轨迹路径还原方法
PDF下载 (336)李广耀,黄正锋,楼乐依.基于贝叶斯网络的稀疏出租车GPS轨迹路径还原方法[J].宁波大学学报(理工版),2021,34(2):17-24.DOI:
LI Guangyao,HUANG Zhengfeng,LOU Leyi.Bayesian network-based GPS path restoration for sparse taxi trajectories[J].Journal of Ningbo University(Natural Science & Engineering Edition),2021,34(2):17-24.DOI:
| Title: | Bayesian network-based GPS path restoration for sparse taxi trajectories |
| 作者: | 李广耀, 黄正锋, 楼乐依 |
| Author(s): | LI Guangyao, HUANG Zhengfeng, LOU Leyi |
| 关键词: | 稀疏出租车GPS数据; 贝叶斯网络; 多因素; 轨迹还原; 缺失率 |
| Keywords: | sparse taxi GPS data; Bayesian network; multiple factors; trajectory restoration; missing rate |
| 分类号: | U491.1 |
| 文献标识码: | A |
| 摘要: | 为提高出租车GPS大数据的可用性, 提出一种基于贝叶斯网络研究稀疏出租车GPS轨迹路径还原的方法. 与传统仅基于时空变量的研究方法不同, 新算法同时考虑天气条件、驾驶员特性、车辆行驶特性与出租车的载客状态等因素来进行路径还原预测. 以宁波市体育中心周围的路网为例, 将出租车服务信息管理平台的GPS轨迹数据作为测试对象, 验证本文方法的适用性. 结果显示, 基于多因素的贝叶斯网络方法在还原精度方面(达到91.4%)优于Logit选择模型. 此外, 新算法尤其适用于出租车轨迹数据缺失率较高的场景, 比如缺失轨迹点跨度在5 min左右. |
| Abstract: | In order to improve the availability of taxi GPS big data, a method based on Bayesian network for sparse taxi GPS path restoration is proposed. Different from the traditional research that is only based on spatiotemporal variables, the algorithm takes into account the weather conditions, driver characteristics, vehicle driving characteristics and taxi load status to calculate path restoration prediction. The applicability of the presented method is verified by taking the road network around Ningbo sports center as an example combined with GPS trajectory data collected from the taxi service information management platform for the testing purposes. The case study results show that the Bayesian network method based on multi factors is superior to the Logit selection model in restoration accuracy (up to 91.4%). In addition, the algorithm is especially suitable for the situation with high missing rate of taxi track data, such as the track points of about 5-minute missing span. |
| 参考文献 /References: | [1] Yuan N J, Zheng Y, Xie X, et al. Discovering urban functional zones using latent activity trajectories[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(3):712-725. [2] Chen M, Liu Y, Yu X. Predicting next locations with object clustering and trajectory clustering[C]//Pacific- Asia Conference on Knowledge Discovery and Data Mining. Springer International Publishing, Singapore, 2015. [3] Mori U, Mendiburu A, ?lvarez M, et al. A review of travel time estimation and forecasting for advanced traveller information systems[J]. Transportmetrica, 2015, 11(2):119-157. [4] Lü L, Chen M, Liu Y, et al. A plane moving average algorithm for short-term traffic flow prediction[C]// Advances in Knowledge Discovery and Data Mining. Springer International Publishing, Singapore, 2015. [5] Bierlaire M, Chen J, Newman J. A probabilistic map matching method for smartphone GPS data[J]. Transportation Research Part C: Emerging Technologies, 2013, 26(1):78-98. [6] Brakatsoulas S, Pfoser D, Salas R, et al. On map-matching vehicle tracking data[C]//Proceedings of the 31st International Conference on Very Large Data Bases. Trondheim, Norway, 2005. [7] 高文超, 李国良, 塔娜. 路网匹配算法综述[J]. 软件学报, 2018, 29(2):225-250. [8] Lou Y, Zhang C Y, Zheng Y, et al. Map-matching for low-sampling-rate GPS trajectories[EB/OL]. [2020-03- 05]. https://www.researchgate.net/publication/221589740. [9] Ozdemir E, Topcu A E, Ozdemir M K. A hybrid HMM model for travel path inference with sparse GPS samples[J]. Transportation, 2016, 45:233-246. [10] Taguchi S, Koide S, Yoshimura T. Online map matching with route prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(1):338-347. [11] 王龙飞, 陈红, 李杨, 等. 车辆出行轨迹调查分析中的丢点轨迹还原[J]. 计算机应用研究, 2014, 31(1):162- 165. [12] Shuaidong Z, Kuilin Z. A distributionally robust optimization approach to reconstructing missing locations and paths using high-frequency trajectory data[J]. Transportation Research Part C: Emerging Technologies, 2019, 102:316-335. [13] Cooper G F, Herskovits E. A Bayesian method for the induction of probabilistic networks from data[J]. Machine Learning, 1992, 9(4):309-347. [14] 肖光年, 隽志才, 张春勤. 基于贝叶斯网络和GPS轨迹数据的出行方式识别[J]. 统计与决策, 2017(6):75- 79. [15] Marcot B G, Steventon J D, Sutherland G D, et al. Guidelines for developing and updating Bayesian belief networks applied to ecological modeling and conservation[J]. Canadian Journal of Forest Research, 2006, 36(12):3063-3074. [16] Pearl J. Fusion, propagation, and structuring in belief networks[J]. Artificial Intelligence, 1986, 29(3):241-288. [17] 韩勇, 樊顺, 周林, 等. 基于聚类算法的出租载客点时空分布特征研究[J]. 中国海洋大学学报(自然科学版), 2019, 49(S1):155-162. [18] 刘康, 仇培元, 刘希亮, 等. 利用词向量模型分析城市道路交通空间相关性[J]. 测绘学报, 2017, 46(12):2032- 2040. [19] 赵晓华, 任贵超, 陈晨, 等. 不良天气下驾驶行为研究综述[J]. 交通信息与安全, 2017, 35(5):70-75; 98. [20] 张卫华, 李梦凡. 不同交通信息诱导下驾驶员路径选择行为研究[J]. 重庆交通大学学报(自然科学版), 2018, 37(10):86-93. |
| 备注/Memo: | 收稿日期: 2020－07－06. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 宁波市自然科学基金（2019A610040）; 国家自然科学基金（51408321）; 浙江省自然科学基金（LY18E080009）. 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/第一作者: 李广耀（1995－）, 男, 山东青岛人, 在读硕士研究生, 主要研究方向: 交通运输规划与管理. E-mail: 1518432988@qq.com *通信作者: 黄正锋（1986－）, 男, 浙江金华人, 博士/副教授, 主要研究方向: 交通运输工程. E-mail: huangzhengfeng@nbu.edu.cn |
