留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

顾及相似用户特征的个人位置预测算法

张宇,  吴升,  赵志远,  杨喜平,  方志祥

downloadPDF
文章导航 > 武汉大学学报 ● 信息科学版  > 优先出版
张宇, 吴升, 赵志远, 杨喜平, 方志祥. 顾及相似用户特征的个人位置预测算法[J]. 武汉大学学报 ● 信息科学版. doi: 10.13203/j.whugis20200609
引用本文: 张宇, 吴升, 赵志远, 杨喜平, 方志祥. 顾及相似用户特征的个人位置预测算法[J]. 武汉大学学报 ● 信息科学版. doi: 10.13203/j.whugis20200609
shu
ZHANG Yu, ZHAO Zhiyuan, WU Sheng, YANG Xiping, FANG Zhixiang. Personal location prediction algorithm taking into account similar user characteristics[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20200609
Citation: ZHANG Yu, ZHAO Zhiyuan, WU Sheng, YANG Xiping, FANG Zhixiang. Personal location prediction algorithm taking into account similar user characteristics[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20200609
shu

顾及相似用户特征的个人位置预测算法

doi: 10.13203/j.whugis20200609

  • 1 福州大学数字中国研究院(福建);

  • 2 空间数据挖掘与信息共享教育部重点实验室;

  • 3 海西政务大数据应用协同创新中心;

  • 4 陕西师范大学地理与旅游学院;

  • 5 测绘遥感信息工程国家重点实验室, 武汉大学

基金项目: 

国家重点研发计划项目（2017YFB0503500）；国家自然科学基金（41801373）；中国博士后科学基金（2019M652244）。

详细信息
    作者简介:

    张宇,男,硕士研究生,从事地理信息服务与时空数据挖掘研究,E-mail:752403543@qq.com

Personal location prediction algorithm taking into account similar user characteristics

  • 1 Academy of Digital China(Fujian), Fuzhou University;

  • 2 Key Laboratory of Spatial Data Mining and Information Sharing,;

  • 3 Ministry of Education Fujian Collaborative Innovation Center for Big Data Applications in Governments;

  • 4 School of Geography and Tourism, Shaanxi Normal University;

  • 5 State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University

Funds: 

National Key R&D Program of China (No.2017YFB0503500)

  • 摘要: 个体位置预测在传染病精准防控、公共设施科学规划等应用中具有重要意义。既有位置预测算法主要侧重对个体纵向历史轨迹特征进行挖掘建模，并实现位置预测，对横向相似性用户的规律特性考虑较少。为此，本文基于图卷积（Graph Convolution Network，GCN）和长短期记忆模型（Long Short-Term Memory，LSTM）框架，提出顾及横向相似用户轨迹特征以及纵向历史规律性特征的个体位置预测算法。首先构建用户轨迹相似性算法并筛选高相似度用户，然后利用图卷积模型提取待预测用户相似高的用户轨迹特征，最后利用长短期记忆模型框架，提取历史轨迹特征，并集成相似用户轨迹特征，从而实现个体位置预测。基于某市8万多用户连续4个工作日的数据进行实验，结果表明：本文提出方法的准确率随预测时间步长增加而下降，而夜间预测准确率明显高于白天，但相比于既有模型均有10%以上提高，以15分钟为预测时间步长时，模型准确率达80.45%。
    Abstract: Individual location prediction is of great significance in applications such as precise prevention and control of infectious diseases and scientific planning of public facilities. Existing location prediction algorithms mainly focus on mining and modeling individual longitudinal historical trajectory characteristics, and realize location prediction, and less consider the regular characteristics of users with horizontal similarity. For this reason, based on the framework of Graph Convolution Network (GCN) and Long Short-Term Memory (LSTM) model, this paper proposes an individual location prediction algorithm that takes into account the characteristics of horizontally similar user trajectories and the characteristics of vertical historical regularity. First, construct a user trajectory similarity algorithm and screen users with high similarity, then use the graph convolution model to extract user trajectory features with high similarity of users to be predicted, and finally use the long and short-term memory model framework to extract historical trajectory features and integrate similar user trajectory features, So as to achieve individual location prediction. Based on the data of more than 80,000 users in a city for 4 consecutive working days, the results show that the accuracy of the method proposed in this paper decreases with the increase of the prediction time step, and the accuracy of night prediction is significantly higher than that of the day, but compared to the previous All models have an improvement of more than 10%. When 15 minutes is used as the prediction time step, the model accuracy rate reaches 80.45%.
  • [1] Zheng Y. Trajectory Data Mining:An Overview[J]. ACM Transactions on Intelligent Systems and Technology, 2015, 6(3):1-41.
    [2] Cuttone A, Lehmann S, González M C. Understanding predictability and exploration in human mobility[J]. Epj Data Science, 2018, 7(1):2.
    [3] Smith G, Wieser R, Goulding J, et al. A refined limit on the predictability of human mobility[C]. IEEE International Conference on Pervasive Computing & Communications(PerCom), Budapest, 2014:88-94.
    [4] Song C, Qu Z, Blumm N, et al. Limits of predictability in human mobility[J]. Science, 2010, 327(5968):1018-1021.
    [5] Jeung H, Liu Q, Shen H T, et al. A Hybrid Prediction Model for Moving Objects[C]. 2008 IEEE 24th International Conference on Data Engineering, Cancun, 2018:70-79.
    [6] Morzy M. Mining Frequent Trajectories of Moving Objects for Location Prediction[C]. International Conference on Machine Learning & Data Mining in Pattern Recognition, Leipaig, 2007:667-680.
    [7] Montoliu R, Blom J, Gatica-Perez D. Discovering places of interest in everyday life from smartphone data[J]. Multimedia Tools & Applications, 2013, 62(1):179-207.
    [8] Liao D, Liu W, Zhong Y, et al. Predicting Activity and Location with Multi-task Context Aware Recurrent Neural Network[C]. Twenty-Seventh International Joint Conference on Artificial Intelligence IJCAI-18, Stockholm, 2018:3435-3441.
    [9] Liu L, Zhang S, Zhou W. Mobility Predictability of College Students via Full Lifecycle Campus Consuming Logs[C]. 2018 IEEE International Conference on Communications (ICC 2018), Kansas City, 2018:1-6.
    [10] Liu Q, Wu S, Wang L, et al. Predicting the Next Location:A Recurrent Model with Spatial and Temporal Contexts[C]. Thirtieth Aaai Conference on Artificial Intelligence, Phoenix, 2016:194-200.
    [11] Alahi A, Goel K, Ramanathan V, et al. Social LSTM:Human Trajectory Prediction in Crowded Spaces[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016:961-971.
    [12] Altche F, Fortelle A D L. An LSTM network for highway trajectory prediction[C]. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), Yokohama, 2017:353-359.
    [13] Ashbrook D, Starner T. Using GPS to learn significant locations and predict movement across multiple users[J]. Personal and Ubiquitous computing, 2003, 7(5):275-286.
    [14] Gambs S, Killijian M-O, Del Prado Cortez M N. Next place prediction using mobility markov chains[C]. Proceedings of the First Workshop on Measurement, Privacy, and Mobility:Association for Computing Machinery, Bern, 2012:1-6.
    [15] Mathew W, Raposo R, Martins B. Predicting future locations with hidden Markov models[C]. ACM Conference on Ubiquitous Computing, Pittsburgh, 20 Predicting next location using a variabl 12:911-918.
    [16] Sun S,Zhao J,Gao Q. Modeling and Recognizing Human Trajectories with Beta Process Hidden Markov Models[J]. Pattern Recogn, 2015, 48(8):2407-2417.
    [17] Yang J, Xu J, Xu M, et al. Predicting next location using a variable order Markov model[C]. Acm Sigspatial International Workshop on Geostreaming, Dallas, 2014:37-42.
    [18] Begleiter R, El-Yaniv R, Yona G. On Prediction Using Variable Order Markov Models[J]. Journal of Artificial Intelligence Research, Pittsburgh, 2004:911-918.
    [19] Li F, Li Q, Li Z, et al. A Personal Location Prediction Method to Solve the Problem of Sparse Trajectory Data[C]. 2019 20th IEEE International Conference on Mobile Data Management (MDM), Hong Kong, 2019:329-336.
    [20] Li F, Gui Z, Zhang Z, et al. A hierarchical temporal attention-based LSTM encoder-decoder model for individual mobility prediction[J]. Neurocomputing, 2020, 403:153-166.
    [21] Dai Y. A Collaborative Filtering Recommendation Algorithm Based on Time Weight[J]. Advanced Materials Research, 2010, 159(1):667-670.
    [22] Gao Z, Lu Z, Deng N, et al. A novel collaborative filtering recommendation algorithm based on user location[C]. 2016 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), Nantou, 2016:1-2.
    [23] A D K H, B P V, C R G. Wavelets on graphs via spectral graph theory[J]. Applied and Computational Harmonic Analysis, 2011, 30(2):129-150.
    [24] Geng X, Li Y, Wang L, et al. Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33:3656-3663.
    [25] Jia T, Yan P. Predicting Citywide Road Traffic Flow Using Deep Spatiotemporal Neural Networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2020.
    [26] Defferrard M,Bresson X,Vandergheynst P. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering[C].Proceedings of the 30th International Conference on Neural Information Processing Systems:Curran Associates Inc., Barcelona, 2016:3844-3852.
    [27] Zhao L, Song Y, Zhang C, et al. T-GCN:A Temporal Graph Convolutional Network for Traffic Prediction[J]. IEEE Transactions on Intelligent Transportation Systems,21(9):3848-3858.
    [28] Bruna J,Zaremba W,Szlam A, et al. Spectral Networks and Locally Connected Networks on Graphs[J]. Paper presented at 2nd International Conference on Learning Representations, ICLR 2014, Banff, Canada, 2014.
    [29] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation, 1997, 9(8):1735-1780.
    [30] Zhao Z, Shaw S-L, Yin L, et al. The effect of temporal sampling intervals on typical human mobility indicators obtained from mobile phone location data[J]. International Journal of Geographical Information Science, 2019, 33(7):1471-1495.
    [31] Yuan F, Xia G S, Sahbi H, et al. Mid-level features and spatio-temporal context for activity recognition[J]. Pattern Recognition, 2012, 45(12):4182-4191.
  • [1] 桂志鹏, 杨乐, 丁劲宸, 王锦添, 孙云增, 吴华意.  顾及路口转移偏好和当前移动模式的个体驾驶目的地预测方法 . 武汉大学学报 ● 信息科学版, doi: 10.13203/J.whugis20210555
    [2] 刘万科, 陶贤露, 张传明, 姚宜斌, 王甫红, 贾海禄, 楼益栋.  云-端协同的智能手机行人室内外无缝定位技术及其原型系统验证 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20210310
    [3] 王颖喆, 陶贤露, 朱锋, 刘万科, 张小红, 吴明魁.  利用智能手机实现GNSS原始观测值的高精度差分定位 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20210280
    [4] 郭斐, 吴维旺, 张小红, 刘万科.  Android智能手机实时精密单点定位软件实现及精度分析 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20200527
    [5] 罗欢, 翁多杰, 陈武.  一种改进的手机阴影匹配定位方法 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20210275
    [6] 方志祥, 倪雅倩, 黄守倩.  融合Markov与多类机器学习模型的个体出行位置预测模型 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20190404
    [7] 王米琪, 艾廷华, 晏雄锋, 肖屹.  图卷积网络模型识别道路正交网格模式 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20200022
    [8] 冯明翔, 方志祥, 路雄博, 谢泽丰, 熊盛武, 郑猛, 黄守倩.  交通分析区尺度上的COVID-19时空扩散推估方法：以武汉市为例 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20200141
    [9] 马威, 熊汉江, 郑先伟, 龚健雅.  室内三维场景纹理手机图片的自动更新方法 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20170109
    [10] 付兵杰, 赵双明, 喻国荣, 赵帅华.  一种无需控制信息的智能手机自检校方法 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20160432
    [11] 刘耀林, 方飞国, 王一恒.  基于手机数据的城市内部就业人口流动特征及形成机制分析——以武汉市为例 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20180140
    [12] 彭正洪, 孙志豪, 程青, 焦洪赞, 陈伟.  利用时序手机通话数据识别城市用地功能 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20170329
    [13] 康朝贵, 刘瑜, 邬伦.  城市手机用户移动轨迹时空熵特征分析 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20160203
    [14] 杨喜平, 方志祥, 赵志远, 萧世伦, 尹凌.  顾及手机基站分布的核密度估计城市人群时空停留分布 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20150646
    [15] 吴华意, 李锐, 周振, 蒋捷, 桂志鹏.  公共地图服务的群体用户访问行为时序特征模型及预测 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20150283
    [16] 许宁, 尹凌, 胡金星.  从大规模短期规则采样的手机定位数据中识别居民职住地 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20140085
    [17] 陈佳, 胡波, 左小清, 乐阳.  利用手机定位数据的用户特征挖掘 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20130066
    [18] 邱国利, 蒋国平, 宋玉蓉.  一种带节点移动的手机蓝牙病毒传播模型 . 武汉大学学报 ● 信息科学版,
    [19] 李鲁群, 李明禄.  面向Java手机GPS数据采集与无线网络传输系统的研究 . 武汉大学学报 ● 信息科学版,
    [20] 毕京学, 甄杰, 姚国标, 桑文刚, 宁一鹏, 郭秋英.  面向智能手机的改进有限状态机步态探测算法 . 武汉大学学报 ● 信息科学版, doi: 10.13203/j.whugis20200186
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  345
  • HTML全文浏览量:  54
  • PDF下载量:  24
  • 被引次数: 0
出版历程
  • 网络出版日期:  2021-05-07

顾及相似用户特征的个人位置预测算法

doi: 10.13203/j.whugis20200609
  • 1 福州大学数字中国研究院(福建);
  • 2 空间数据挖掘与信息共享教育部重点实验室;
  • 3 海西政务大数据应用协同创新中心;
  • 4 陕西师范大学地理与旅游学院;
  • 5 测绘遥感信息工程国家重点实验室, 武汉大学
    • 基金项目:

    国家重点研发计划项目（2017YFB0503500）；国家自然科学基金（41801373）；中国博士后科学基金（2019M652244）。

    作者简介:

    张宇,男,硕士研究生,从事地理信息服务与时空数据挖掘研究,E-mail:752403543@qq.com

  • 网络出版日期: 2021-05-07

摘要: 个体位置预测在传染病精准防控、公共设施科学规划等应用中具有重要意义。既有位置预测算法主要侧重对个体纵向历史轨迹特征进行挖掘建模，并实现位置预测，对横向相似性用户的规律特性考虑较少。为此，本文基于图卷积（Graph Convolution Network，GCN）和长短期记忆模型（Long Short-Term Memory，LSTM）框架，提出顾及横向相似用户轨迹特征以及纵向历史规律性特征的个体位置预测算法。首先构建用户轨迹相似性算法并筛选高相似度用户，然后利用图卷积模型提取待预测用户相似高的用户轨迹特征，最后利用长短期记忆模型框架，提取历史轨迹特征，并集成相似用户轨迹特征，从而实现个体位置预测。基于某市8万多用户连续4个工作日的数据进行实验，结果表明：本文提出方法的准确率随预测时间步长增加而下降，而夜间预测准确率明显高于白天，但相比于既有模型均有10%以上提高，以15分钟为预测时间步长时，模型准确率达80.45%。

English Abstract

张宇, 吴升, 赵志远, 杨喜平, 方志祥. 顾及相似用户特征的个人位置预测算法[J]. 武汉大学学报 ● 信息科学版. doi: 10.13203/j.whugis20200609
引用本文: 张宇, 吴升, 赵志远, 杨喜平, 方志祥. 顾及相似用户特征的个人位置预测算法[J]. 武汉大学学报 ● 信息科学版. doi: 10.13203/j.whugis20200609
shu
ZHANG Yu, ZHAO Zhiyuan, WU Sheng, YANG Xiping, FANG Zhixiang. Personal location prediction algorithm taking into account similar user characteristics[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20200609
Citation: ZHANG Yu, ZHAO Zhiyuan, WU Sheng, YANG Xiping, FANG Zhixiang. Personal location prediction algorithm taking into account similar user characteristics[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20200609
shu

    全文HTML

参考文献 (31)

目录

    /

    返回文章
    返回

    我要投稿

    投稿攻略

    联系我们

    二维码

    版权所有 © 2013 《武汉大学学报·信息科学版》编辑部

    地址：武汉大学文理学部本科生院楼北5楼邮政编码：430072

    电话：027-68778465,68778045E-mail:whuxxb@vip.163.com

    本系统由 北京仁和汇智信息技术有限公司 开发    百度统计