华东师范大学学报（自然科学版） >

2015 , Vol. 2015 >Issue 5: 162 - 171

DOI: https://doi.org/10.3969/j.issn.1000-5641.2015.05.014

LBS系统及应用

基于手机大数据的城市人口流动分析系统

  • 包婷 ,
  • 章志刚 ,
  • 金澈清
展开
  • 华东师范大学 数据科学与工程研究院 上海市高可信计算重点实验室，上海200062
包婷，女，硕士研究生，研究方向为LBS和大数据处理技术.

收稿日期: 2015-09-16

  网络出版日期: 2015-10-08

基金资助

国家重点基础研究发展计划（973）（2012CB316203）；国家自然科学基金（61370101）；上海市教委科研创新重点项目（14ZZ045）

收起

An urban population flow analysis system based on mobile big data

  • BAO Ting ,
  • ZHANG Zhi-Gang ,
  • JIN Che-Qing
Expand

Received date: 2015-09-16

  Online published: 2015-10-08

Fold

摘要

分析城市人口流动行为有助于合理分配社会资源，有效应对交通压力、维护社会公共治安等.传统的人工分析方法，如问卷调查、座谈访问等，成本高昂且低效率.智能手机的不断发展与普及在为人们日常生活带来极大便利的同时，所产生的用户移动轨迹数据为有效分析城市人口流动行为提供了可能.然而，海量、低质的轨迹数据给查询分析工作带来了诸多挑战.文中提出了一个分布式人口流动分析框架，采用多节点处理任务，从而提升了算法的执行能力和可扩展性.利用手机运营商提供的手机轨迹数据，分析城市人口流动情况，建立了多个模型，包括进出城市的人口流动行为分析模型、市内各区县间的人口流动行为分析模型、居民工作地/居住地人口分析模型.与传统方法相比，本方案的成本更低，效率更高，覆盖人群更广.

关键词： 人口流动; 轨迹数据; 分布式框架

本文引用格式

包婷 , 章志刚 , 金澈清 . 基于手机大数据的城市人口流动分析系统[J]. 华东师范大学学报（自然科学版）, 2015 , 2015(5) : 162 -171 . DOI: 10.3969/j.issn.1000-5641.2015.05.014

Abstract

Analysis on urban population flow can help to make rational distribution of social resources, cope with traffic pressure and maintain public order, etc. The traditional manual analysis methods, such as questionnaire and interview, can not deal with this task efficiently. The continuous development and prevalence of smart phones bring great convenience to people′s daily life and users′ trajectory data generated by the connection between smart phones and base stations, which makes it possible to implement this task. However, trajectory data is massive and has low quality, which brings great challenge to related work. We propose a distributed framework for population flow analysis by using multiple computing nodes, thus greatly enhancing efficiency and scalability. In this paper, we use the massive trajectory data to analyze the behavior of urban population flow. We model flowing behavior among cities and among innercity districts, and decide the work place and living place of each person. Compared with the traditional methods, our method is cheaper and more efficient.

Key words： population flow; trajectory data; distributed framework

参考文献

［1］GONZALEZ M C, HIDALGO C A, BARABASI A L. Understanding individual human mobility patterns［J］. Nature, 2008, 453(7196): 779782.

［2］SONG C, QU Z, BLUMM N, et al. Limits of predictability in human mobility［J］. Science, 2010, 327(5968): 10181021. 

［3］SONG C, KOREN T, WANG P, et al. Modelling the scaling properties of human mobility［J］. Nature Physics, 2010, 6(10): 818823.

［4］LI Z, DING B, HAN J, et al. Mining periodic behaviors for moving objects［C］ Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2010: 10991108.

［5］陈佳, 胡波, 左小清,等. 利用手机定位数据的用户特征挖掘［J］. 武汉大学学报：信息科学版, 2014, 39(6): 734738.

［6］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.

［7］WHITE J, WELLS I. Extracting origin destination information from mobile phone data［C］11th International Conference on Road Transport Information and Control, 2002: 3034.

［8］CACERES N, WIDEBERG J P, BENITEZ F G. Deriving origin destination data from a mobile phone network［J］. Intelligent Transport Systems, IET, 2007, 1(1): 1526.

［9］IQBAL M S, CHOUDHURY C F, WANG P, et al. Development of origindestination matrices using mobile phone call data［J］. Transportation Research Part C Emerging Technologies, 2014, 40(1): 6374.

［10］LIU F, JANSSENS D, CUI J X, et al. Building a validation measure for activitybased transportation models based on mobile phone data［J］. Expert Systems with Applications, 2014, 41(14): 61746189.

［11］PHITHAKKITNUKOON S, HORANONT T, LORENZO G D, et al. Activityaware map: identifying human daily activity pattern using mobile phone data［C］ Proceedings of the First international conference on Human behavior understanding. SpringerVerlag, 2010:1425.

［12］ISAACMAN S, BECKER R, CACERES R, et al. Identifying Important Places in People′s Lives from Cellular Network Data［J］. Lecture Notes in Computer Science, 2011，6696: 133151.

［13］TRAAG V A, BROWET A, CALABRESE F, et al. Social Event Detection in Massive Mobile Phone Data Using Probabilistic Location Inference［C］ Proceedings of the Third IEEE International Conference on Social Computing, 2011: 911.

［14］QUERCIA D, LATHIA N, CALABRESE F, et al. Recommending social events from mobile phone location data［C］Proceedings of the 10th International Conference on Data Mining (ICDM), 2010: 971976.

［15］CALABRESE F, COLONNA M, LOVISOLO P, et al. RealTime Urban Monitoring Using Cell Phones: A Case Study In Rome［J］.IEEE Transactions on Intelligent Transportation Systems, 2011, 12(1): 141151.

［16］SOTO V, FRIASMARTINEZ V, VIRSEDA J, et al. Prediction of Socioeconomic Levels Using Cell Phone Records［J］. Lecture Notes in Computer Science, 2011，6787: 377388.

［17］HONGYAN G, FASHENG L. Estimating freeway traffic measures from mobile phone location data［J］. European Journal of Operational Research, 2013, 229(1): 252260.

［18］陆嘉恒. Hadoop实战［M］.第2版.北京:机械工业出版社， 2012: 85329.

［19］孔扬鑫.手机轨迹数据的人口流动分析［R］.上海：华东师范大学软件工程学院,2015.

［18］章志刚.面向海量手机轨迹数据的重要位置发现［R］.上海：华东师范大学软件工程学院，2015.
Options
文章导航

/

〈 〉