基于深度表示模型的移动模式挖掘

doi:10.11772/j.issn.1001-9081.2016.01.0033

计算机应用 ›› 2016, Vol. 36 ›› Issue (1): 33-38.DOI: 10.11772/j.issn.1001-9081.2016.01.0033

• 第32届中国数据库学术会议(NDBC 2015) • 上一篇下一篇

基于深度表示模型的移动模式挖掘

陈勐, 禹晓辉, 刘洋

山东大学计算机科学与技术学院, 济南 250101

收稿日期:2015-07-10 修回日期:2015-08-04 出版日期:2016-01-10 发布日期:2016-01-09
通讯作者: 刘洋(1977-),女,山东济南人,副教授,博士,CCF会员,主要研究方向:情感分析、文本挖掘
作者简介:陈勐(1990-),男,山东滕州人,博士研究生,主要研究方向:轨迹挖掘、城市计算;禹晓辉(1977-),男,山东济南人,教授,博士生导师,博士,CCF会员,主要研究方向:大数据管理、数据挖掘。
基金资助:
国家自然科学基金资助项目(61272092);山东省自然科学基金资助项目(ZR2012FZ004);山东省科技发展计划基金资助项目(2014GGE27178);国家973计划项目(2015CB352500);泰山学者计划基金资助项目。

Mining mobility patterns based on deep representation model

CHEN Meng, YU Xiaohui, LIU Yang

College of Computer Science and Technology, Shandong University, Jinan Shandong 250101, China

Received:2015-07-10 Revised:2015-08-04 Online:2016-01-10 Published:2016-01-09
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61272092), the Natural Science Foundation of Shandong Province (ZR2012FZ004), the Science and Technology Development Program of Shandong Province (2014GGE27178), the National Basic Research Program (973 Program) of China (2015CB352500) and the Research Fund for the Taishan Scholar Project of Shandong Province.

摘要/Abstract

摘要： 针对时空轨迹中位置顺序和时间对于理解用户移动模式的重要性,提出了一种新的用户轨迹深度表示模型。该模型考虑到时空轨迹的特点:1)不同的位置顺序表示不同的移动模式;2)轨迹有周期性并且在不同的时间段有变化。首先,将两个连续的位置点组合成位置序列;然后,将位置序列和对应的时间块组合成时间位置序列,作为描述轨迹特征的基本单位;最后,利用深度表示模型为每个序列训练特征向量。为了验证深度表示模型的有效性,设计实验将时间位置序列向量应用到用户移动模式发现中,并利用Gowalla签到数据集进行了实验评测。实验结果显示提出的模型能够发现"上班""购物"等明确的模式,而Word2Vec很难发现有意义的移动模式。

关键词: 时空轨迹挖掘, 用户移动模式, 深度表示模型, 时间位置序列向量, 哈夫曼编码

Abstract: Focusing on the fact that the order of locations and time play a pivotal role in understanding user mobility patterns for spatio-temporal trajectories, a novel deep representation model for trajectories was proposed. The model considered the characteristics of spatio-temporal trajectories: 1) different orders of locations indicate different user mobility patterns; 2) trajectories tend to be cyclical and change over time. First, two time-ordered locations were combined in location sequence; second, the sequence and its corresponding time bin were combined in the temporal location sequence, which was the basic unit of describing the features of a trajectory; finally, the deep representation model was utilized to train the feature vector for each sequence. To verify the effectiveness of the deep representation model, experiments were designed to apply the temporal location sequence vectors to user mobility patterns mining, and empirical studies were performed on a real check-in dataset of Gowalla. The experimental results confirm that the proposed method is able to discover explicit movement patterns (e.g., working, shopping) and Word2Vec is difficult to discover the valuable patterns.

Key words: spatio-temporal trajectory mining, user mobility pattern, deep representation model, temporal location sequence vector, Huffman coding

中图分类号:

TP311.13

陈勐, 禹晓辉, 刘洋. 基于深度表示模型的移动模式挖掘[J]. 计算机应用, 2016, 36(1): 33-38.

CHEN Meng, YU Xiaohui, LIU Yang. Mining mobility patterns based on deep representation model[J]. Journal of Computer Applications, 2016, 36(1): 33-38.

参考文献

[1] COOK D. How smart is your home? [J]. Science, 2012, 335(6076): 1579-1581.
[2] GRADY M, HARE G. How smart is your city? [J]. Science, 2012, 335(6076): 1581-1582.
[3] CHEN Z, SHEN H, ZHOU X. Discovering popular routes from trajectories [C]// ICDE 2011: Proceedings of the 27th International Conference on Data Engineering. Piscataway, NJ: IEEE, 2011: 900-911.
[4] YUAN N, ZHENG Y, ZHANG L, et al. T-Finder: a recommender system for finding passengers and vacant taxis [J]. IEEE transactions on knowledge and data engineering, 2013, 25(10): 2390-2403.
[5] ZHENG Y, LIU Y, YUAN J, et al. Urban computing with taxicabs [C]// UbiComp 2011: Proceedings of the 13th International Conference on Ubiquitous Computing. New York: ACM, 2011: 89-98.
[6] BAO J, ZHENG Y, MOKBEL M. Location-based and preference-aware recommendation using sparse geo-social networking data [C]// GIS 2012: Proceedings of the 20th International Conference on Advances in Geographic Information Systems. New York: ACM, 2012: 199-208.
[7] SON J, KIM A, PARK S. A location-based news article recommendation with explicit localized semantic analysis [C]// SIGIR 2013: Proceedings of the 36th International Conference on Research and Development in Information Retrieval. New York: ACM, 2013: 293-302.
[8] HSIEH H, LI C, LIN S. Exploiting large-scale check-in data to recommend time-sensitive routes [C]// UrbComp 2012: Proceedings of the ACM SIGKDD International Workshop on Urban Computing. New York: ACM, 2012: 55-62.
[9] KURASHIMA T, IWATA T, HOSHIDE T, et al. Geo topic model: joint modeling of user's activity area and interests for location recommendation [C]// WSDM 2013: Proceedings of the Sixth ACM International Conference on Web Search and Data Mining. New York: ACM, 2013: 375-384.
[10] YIN Z, CAO L, HAN J, et al. Diversified trajectory pattern ranking in geo-tagged social media [C]// SDM 2011: Proceedings of the SIAM International Conference on Data Mining. Berlin: Springer, 2011: 980-991.
[11] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space [EB/OL]. [2015-04-20]. http://arxiv.org/pdf/1301.3781v3.pdf.
[12] CAO Z, LI S, LIU Y, et al. A novel neural topic model and its supervised extension [C]// AAAI 2015: Proceedings of the 29th AAAI Conference on Artificial Intelligence. Menlo Park, CA: AAAI Press, 2015: 2210-2216.
[13] CHEN M, LIU Y, YU X. NLPMM: a next location predictor with Markov modeling [C]// PAKDD 2014: Proceedings of the 18th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining. Berlin: Springer, 2014: 186-197.
[14] FARRAHI K, GATICA-PEREZ D. Discovering routines from large-scale human locations using probabilistic topic models [J]. ACM transactions on intelligent systems and technology, 2011, 2(1): Article No. 3.
[15] YU Z, FENG Y, XU H, et al. Recommending travel packages based on mobile crowdsourced data [J]. IEEE communications magazine, 2014, 52(8): 56-62.
[16] YUAN J, ZHENG Y, ZHANG L, et al. Where to find my next passenger [C]// UbiComp 2011: Proceedings of the 13th International Conference on Ubiquitous Computing. New York: ACM, 2011: 109-118.
[17] PANG L, CHAWLA S, LIU W, et al. On mining anomalous patterns in road traffic streams [C]// ADMA 2011: Proceedings of the 7th International Conference on Advanced Data Mining and Applications. Berlin: Springer, 2011: 237-251.
[18] PAN G, QI G, WU Z, et al. Land-use classification using taxi GPS traces [J]. IEEE transactions on intelligent transportation systems, 2013, 14(1): 113-123.
[19] LI X, PAN G, WU Z, et al. Prediction of urban human mobility using large-scale taxi traces and its applications [J]. Frontiers of computer science, 2012, 6(1): 111-121.
[20] CASTRO P, ZHANG D, CHEN C, et al. From taxi GPS traces to social and community dynamics: a survey [J]. ACM computing surveys, 2013, 46(2): Article No. 17.
[21] HASAN S, ZHAN X, UKKUSURI S. Understanding urban human activity and mobility patterns using large-scale location-based data from online social media [C]// UrbComp 2013: Proceedings of the 2nd ACM SIGKDD International Workshop on Urban Computing. New York: ACM, 2013: Article No. 6.
[22] XUE G, LI Z, ZHU H, et al. Traffic-known urban vehicular route prediction based on partial mobility patterns [C]// ICPADS 2009: Proceedings of the 15th International Conference on Parallel and Distributed Systems. Piscataway, NJ: IEEE, 2009: 369-375.
[23] MONREALE A, PINELLI F, TRAARTI R, et al. WhereNext: a location predictor on trajectory pattern mining [C]// SIGKDD 2009: Proceedings of the 15th International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2009: 637-646.
[24] BLEI D, NG A, JORDAN M. Latent Dirichlet allocation [J]. Journal of machine learning research, 2003, 3: 993-1022.
[25] CHANG J, SUN E. Location 3: how users share and respond to location-based data on social networking sites [C]// AAAI 2011: Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media. Menlo Park, CA: AAAI Press, 2011: 74-80.
[26] CRANSHAW J, YANO T. Seeing a home away from the home: distilling proto-neighborhoods from incidental data with latent topic modeling [C]// NIPS 2010: Proceedings of the Twenty-Fourth Annual Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates, Inc., 2010: 10.
[27] YUAN J, ZHENG Y, XIE X. Discovering regions of different functions in a city using human mobility and POIs [C]// SIGKDD 2012: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2012: 186-194.

基于深度表示模型的移动模式挖掘

Mining mobility patterns based on deep representation model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	赵全, 汤小春, 朱紫钰, 毛安琪, 李战怀. 大规模短时间任务的低延迟集群调度框架[J]. 计算机应用, 2021, 41(8): 2396-2405.
[2]	冯钧王秉发陆佳民. 分布式资源描述框架数据管理系统查询性能评价[J]. 计算机应用, 0, (): 0-0.
[3]	李国荣, 冶继民, 甄远婷. 基于新的鲁棒相似性度量的时间序列聚类[J]. 计算机应用, 2021, 41(5): 1343-1347.
[4]	林定康颜嘉麒巴·楠登符朕皓姜皓晨. 门罗币匿名及追踪技术综述[J]. 计算机应用, 0, (): 0-0.
[5]	沈忱, 邰凌翔, 彭煜玮. 面向自动参数调优的动态负载匹配方法[J]. 计算机应用, 2021, 41(3): 657-661.
[6]	杨程, 陆佳民, 冯钧. 分布式环境下大规模资源描述框架数据划分方法综述[J]. 计算机应用, 2020, 40(11): 3184-3191.
[7]	兰海, 韩珂, 申砾, 崔秋, 彭煜玮. TiDB的多索引访问优化[J]. 计算机应用, 2020, 40(2): 410-415.
[8]	崔艺馨, 陈晓东. Spark框架优化的大规模谱聚类并行算法[J]. 计算机应用, 2020, 40(1): 168-172.
[9]	万静, 郑龙君, 何云斌, 李松. 高维不确定数据的子空间聚类算法[J]. 计算机应用, 2019, 39(11): 3280-3287.
[10]	李博, 张晓, 颜靖艺, 李可威, 李恒, 凌玉龙, 张勇. 基于值差度量和聚类优化的K最近邻算法在银行客户行为预测中的应用[J]. 计算机应用, 2019, 39(9): 2784-2788.
[11]	李耘书, 滕飞, 李天瑞. 基于微操作的Hadoop参数自动调优方法[J]. 计算机应用, 2019, 39(6): 1589-1594.
[12]	霍峥, 张坤, 贺萍, 武彦斌. 满足本地化差分隐私的众包位置数据采集[J]. 计算机应用, 2019, 39(3): 763-768.
[13]	朱跃龙, 朱晓晓, 王继民. 基于子序列全连接和最大团的时间序列模体发现算法[J]. 计算机应用, 2019, 39(2): 414-420.
[14]	尹远, 张昌, 文凯, 郑云俊. 基于DiffNodeset结构的最大频繁项集挖掘算法[J]. 计算机应用, 2018, 38(12): 3438-3443.
[15]	曲立平, 吴家喜. 基于评分可靠性的跨域个性化推荐方法[J]. 计算机应用, 2018, 38(11): 3081-3083.