基于时间序列相似度的城市功能区识别研究Urban Functional Area Identification Based on Similarity of Time Series
李莹;涂志德;刘艳芳;唐名阳;王楠楠;
摘要(Abstract):
随着城市化的快速发展,城市空间结构愈发复杂,城市功能区的快速有效识别对资源的有效配置和城市规划具有重要意义。传统的功能区识别缺乏对居民这一城市空间活动主体的动态表征,而长时间序列的出租车数据能动态表征居民出行行为,进而反映城市空间结构。动态时间扭曲(DTW)距离比传统的欧氏距离更能有效挖掘高维数据,泛化后的LB_Keogh距离和LB_Hust距离相继克服了DTW距离时间复杂度高和不对称的缺点。为了探究基于时间相似性度量的聚类算法在识别城市功能区方面的可行性,首先基于OpenStreetMap(OSM)路网数据获取研究单元,再通过滴滴订单数据提取上下车点、构建研究单元内的居民出行时间序列,然后利用PAM算法结合4种相似度度量方法进行聚类,最后结合兴趣点(POI)数据识别城市功能区,并对结果进行精度验证。结果表明,基于LB_Hust距离的PAM算法能有效挖掘高维时间序列数据,应用于城市功能区识别的精度高达86%,为应用时间序列数据进行城市研究提供了一种新的方法。
关键词(KeyWords): 城市功能区;DTW;POI数据;时间序列;PAM聚类
基金项目(Foundation): 国家自然科学基金资助项目(41771432)
作者(Author): 李莹;涂志德;刘艳芳;唐名阳;王楠楠;
Email:
DOI:
参考文献(References):
- [1]Batty M. The Size, Scale, and Shape of Cities[J]. Science, 2008,319(5 864):769-771
- [2]颜芳芳.城市功能区发展模式研究[J].经济研究导刊, 2010(12):134-136
- [3]李嘉,林涛.城市信息化与城市功能空间的相关分析[J].上海师范大学学报(自然科学版),2006,35(3):81-87
- [4]柴彦威.城市地理学思想与方法[M].北京:科学出版社, 2012:253-285
- [5]Roesler R, Liebig T. Using Data from Location Based Social Networks for Urban Activity Clustering[C].16th AGILE Conference on Geographic Information Science, New Delhi:Springer, 2013
- [6]SHI L, CHI G, LIU X, et al. Human Mobility Patterns in Different Communities:a Mobile Phone Data-based Social Network Approach[J]. Geographic Information Sciences, 2015,21(1):15-26
- [7]张慧杰,王蓉,陈斌,等.基于轨迹和兴趣点数据的城市功能区动态识别与时变规律可视分析[J].计算机辅助设计与图形学学报,2018(9):1 728-1 740
- [8]韩昊英,于翔,龙瀛.基于北京公交刷卡数据和兴趣点的功能区识别[J].城市规划,2016,40(6):52-60
- [9]荣毅龙,黄晓春,王蓓.基于大数据的城市功能区定量识别方法探究[J].北京规划建设,2017(5):97-101
- [10]陈世莉,陶海燕,李旭亮,等.基于潜在语义信息的城市功能区识别:广州市浮动车GPS时空数据挖掘[J].地理学报,2016, 71(3):471-483
- [11]李苗裔,马妍,孙小明,等.基于多源数据时空熵的城市功能混合度识别评价[J].城市规划,2018,42(2):97-103
- [12]秦萧,甄峰.基于大数据应用的城市空间研究进展与展望[C]//2013中国城市规划年会论文集,北京, 2013:1-14
- [13]冯然,董先敏,梁婷,等.基于logistic回归模型的城市功能区识别[J].测绘与空间地理信息,2018(4):109-112
- [14]Senthilnath J. Hierarchical Clustering Algorithm for Land Cover Mapping Using Satellite Image7[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012, 5(3):762-768
- [15]Salmon B P, Olivier J C, Wessels K J, et al. Unsupervised Land Cover Change Detection:Meaningful Sequential Time Series Analysis[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2011, 4(2):327-335
- [16]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
- [17]杨风召.高维数据挖掘技术研究[M].南京:东南大学出版社,2007
- [18]Petitjean F, Ketterlin A, Gancarski P. A Global Averaging Method for Dynamic Time Warping, with Applications to Clustering[J]. Pattern Recognition, 2011, 44(3):678-693
- [19]FU T. A Review on Time Series Data Mining[J]. Engineering Applications of Artificial Intelligence,2011,24(1):164-181
- [20]Keogh E, Ratanamahatana C A. Exact Indexing of Dynamic Time Warping[J]. Knowledge and Information Systems,2005, 7(3):358-386
- [21]李俊奎,王元珍,李新萍.基于边界距离的时间序列聚类[EB/OL].(2006-05-22)[2020-04-25].中国科技论文在线http://www.paper.edu.cn/releasepaper/content/200605-252
- [22]CHEN Y, LIU X, LI X, et al. Delineating Urban Functional Areas with Building-level Social Media Data:a Dynamic Time Warping(DTW)Distance Based K-medoids Method[J].Landscape and Urban Planning, 2017, 160:48-60
- [23]刘子靖.利用SCD和POI数据研究武汉居民通勤出行与站点分类[D].武汉:武汉大学,2018
- [24]GAO Q, FU J, YU Y, et al. Identification of Urban Regions’Functions in Chengdu, China, Based on Vehicle Trajectory Data[J]. PLoS One, 2019, 14(4):1-17
- [25]郑林江,赵欣,蒋朝辉,等.基于出租车轨迹数据的城市热点出行区域挖掘[J].计算机应用与软件,2018,35(1):1-8
- [26]宁鹏飞,万幼,沈怡然,等.基于签到数据的城市热点功能区识别研究[J].测绘地理信息,2018,43(2):110-114
- [27]LIU Y, WANG F H, XIAO Y, et al. Urban Land Uses and Traffic‘Source-sink Areas’:Evidence from GPS-enabled Taxi Data in Shanghai[J]. Landscape and Urban Planning, 2012, 106(1):75-87
- [28]DING H, Trajcevski G, Scheuermann P, et al. Querying and Mining of Time Series Data[J]. Proceedings of the VLDB Endowment, 2008(2):1 542-1 552
- [29]李海林,郭崇慧.时间序列数据挖掘中特征表示与相似性度量研究综述[J].计算机应用研究,2013,30(5):1 285-1 291
- [30]Popivanov I, Miller R J. Similarity Search over Time-series Data Using Wavelets[C]. IEEE Proceedings 18th International Conference on Data Engineering, 2002:212-221
- [31]Capitani P, Ciaccia P. Warping the Time on Data Streams[J].Data and Knowledge Engineering, 2007, 62(3):438-458
- [32]HAN J W, Kamber M. Data Mining:Concepts and Techniques[J].Data Mining Conce pts Models Methods and Algorithms Second Edition, 2006, 5(4):1-18
- [33]Kaufman L, Rousseeuw P J. Finding Groups in Data:an Introduction to Cluster Analysis[M]. DBLP, 1990:68-125
- [34]Laan M J V D, Pollard K S, Bryan J. A New Partitioning around Medoids Algorithm[J]. Journal of Statistical Computation and Simulation, 2003, 73(8):575-584
- [35]周昭涛.文本聚类分析效果评价及文本表示研究[D].北京:中国科学院大学(中国科学院计算技术研究所),2005
- [36]Peter R J. Silhouettes:a Graphical Aid to the Interpretation and Validation of Cluster Analysis[J]. Journal of Computational and Applied Mathematics, 1999, 20:356-368
- [37]姚尧,张亚涛,关庆锋,等.使用时序出租车轨迹识别多层次城市功能结构[J].武汉大学学报(信息科学版),2019,44(6):875-884
- [38]Verburg P H, Nijs TCMD, Eck J R V, et al. A Method to Analyze Neighborhood Characteristics of Land Use Patterns[J].Computers Environment and Urban Systems, 2004, 28(6):667-690