Yang Xu

yang.ls.xu@polyu.edu.hk
181 Chatham Road South, Hung Hom, Kowloon, Hong Kong

I am an Assistant Professor in the Department of Land Surveying and Geo-Informatics (LSGI) at The Hong Kong Polytechnic University. My research lies at the intersection of GIScience, Transportation, and Urban Informatics. Leveraging big data, my work focuses on the quatification and modeling of human activities in cities, aiming to reveal their linkage with urban and technological developments, and their impact on future economic, social and transportation systems. Before joining PolyU, I worked as a joint postdoctoral associate at the MIT Senseable City Lab and the Singapore-MIT Alliance for Research and Technology (SMART), where I focused on human mobility mining and modeling based on large scale urban datasets. (CVGoogle ScholarResearchGateORCIDTwitter)



I am currently seeking exceptional candidates to compete for the Hong Kong PhD Fellowship Sceheme (HKPFS) for 2021/22. The awardee will be admitted to the full-time PhD program at PolyU, and the fellowship will provide a monthly stipend of HK$26,000, plus conference and research related travel allowance. The application closes on December 1st, 2020. More information can be found here and here.



PROFESSIONAL POSITIONS


Assistant Professor, Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University (2017/10 - Present)

Postdoctoral Associate, MIT Senseable City Lab & SMART Centre, Singapore (2016/06 - 2017/09)

Research Assistant, Oak Ridge National Laboratory (ORNL), USA (2013 - 2015)




EDUCATION


Ph.D., Geographic Information Science, University of Tennessee, Knoxville, US (2011 - 2015)

M.S., Geographic Information Science, Wuhan University, China (2009 - 2011)

B.S., Remote Sensing and Photogrammetry, Wuhan University, China (2005 - 2009)




WHAT'S NEW


July 2020: Our paper "Effects of Data Preprocessing Methods on Addressing Location Uncertainty in Mobile Signaling Data" is published in Annals of the American Association of Geographers.


July 2020: Our paper "Characterizing destination networks through mobility traces of international tourists — A case study using a nationwide mobile positioning dataset" is published in Tourism Management.


Nov 2019: Our paper "Quantifying segregation in an integrated urban physical-social space" is published in Journal of the Royal Society Interface.


Nov 2018: The kickoff video of our project, Shared Bikes, is released!




Have problem accessing YouTube? Use this channel: https://v.qq.com/x/page/a0798qotoie.html


Big Data for Smart Tourism

A collaborative research project with the PolyU School of Hotel and Tourism Management (SHTM). The project aims to characterize and model travel behavior of interntaional tourists to South Korea, with the hope to further reveal their linkage with spatial and socioeconomic orgnizations of cities. Through data analysis and visualization, the project will provide insights that are beneficial to government sectors and local stakeholders, and pave the way for sustainable tourism development.

Conducted at: The Hong Kong Polytechnic University

Project Video: Travel Movement in Jeonju City (2019); Travel Patterns of Visitors to Jeju Island (2020)

Publications: Tourism Management (2020); Annals of Tourism Research (2020)






Big Data Veracity: A Mobile Phone Data Perspective

Mobile phone data are valuable resources for mobility research. However, observations in the data are usually associated with positional inaccuracy, which hinders accurate estimations of phone users' mobility characteristics. In this project, we examine different forms of location uncertainty in mobile phone data, and discuss how they would impact and giude the ways we process and analyze the data. Our research calls for more attention to the "veracity" issue in data driven mobility research, and broader implications to urban and geographic knowledge discovery.

Conducted at: The Hong Kong Polytechnic University

Publications: Annals of the American Association of Geographers (2020)






Spatial and Social Network Segregation in Cities

We put forward a computational framework based on coupling large scale information on human mobility, social network connections, and people’s socioeconomic status, to provide a breakthrough in our understanding of the dynamics of spatiotemporal and social-network segregation in cities. The framework can be used to depict segregation dynamics down to the individual level, and meanwhile, provide aggregate measurements at the scale of places and cities, and their evolution over time.

Conducted at: The Hong Kong Polytechnic University; MIT Senseable City Lab

Project Website: http://senseable.mit.edu/singapore-calling

Publications: Journal of The Royal Society Interface (2019); BBVA OpenMind (2019)





Shared Bikes

What will a city look like if shared bikes are unleashed from docking stations? Dockless bike-sharing represents a new urban phenomena that will affect the future use and design of our transportation systems. This project aims to conduct empirical studies to understand the usage of this new mobility service in cities and its linkage with urban built environment. Meanwhile, new approaches will be developed to support travel demand forecast and fleet size management.

Conducted at: The Hong Kong Polytechnic University

Project Video: YouTube, 腾讯视频, bilibili

Publications: Computers, Environment and Urban Systems (2019)




Comparative Urban Analytics

The explosion of massive mobility datasets (e.g., taxi trajectories, smart card transactions, mobile phone data) has generated new opportunities for urban research. Yet, there are increasing concerns about data representativeness and whether the knowledge and insights can be genenalized across cities. To this end, the project aims to perform intra- and inter-city comparisons to discover universal mechanisms and social-cultural differences that shape human behaviour in cities.

Conducted at: The Hong Kong Polytechnic University; SMART

Publications: Journal of Transport Geography (2018)





Human Mobility and Socioeconomic Status

How do people belonging to different social classes move around in a city, and whether they use urban spaces in different ways? In this research, we propose an analytical framework, by coupling large scale mobile phone and urban socioeconomic datasets ( e.g., housing price, travel survey, census data), to better understand human mobility patterns and their relationships with travelers' socioeconomic status.

Conducted at: MIT Senseable City Lab

Publications: Computers, Environment and Urban Systems (2018)





Friendly Cities: Quantifying the Social Roles of Urban Space

Using a mobile phone dataset collected in Singapore, we propose a framework to understand the spatiotemporal characteristics of friends' use of urban space as well as that of the strangers in the city. We derive two metrics, namely bonding and bridging capability, to identify places in the city that bring together friends versus those that facilitate chance encounters among strangers.

Conducted at: MIT Senseable City Lab

Project Website: http://senseable.mit.edu/friendly-cities

Publications: Transactions in GIS (2017)





A Bite of China

How are different cooking traditions featured in a city's restaurants? Do people always favor local food? To what extent do cities' culinary scenes align with their socioeconomic development? Using a dataset captured from a large online review site in China (www.dianping.com), we demonstrate how geo-referenced social review data can be leveraged to uncover the geographic prevalence and mix of regional cuisines in Chinese cities.

Conducted at: Wuhan University

Publications: IJGI (2017)





Travel Demand Estimation Through Mobile Phone Data

By leveraging actively tracked mobile phone data, we propose an anchor-point based trajectory segmentation method to estimate potential demand of bicycle trips in a city (Shenzhen, China). The travel demand generated at the cellphone tower level is further used to support planning of bike sharing systems (e.g., location recommendation of bike sharing stations).

Conducted at: University of Tennessee, Knoxville

Publications: IJGI (2016)






Deriving Mobility Signatures From Mobile Phone Data

By using actively tracked mobile phone data in two big cities in China, we introduce three mobility indicators (daily activity range, number of activity anchor points, frequency of movements) to represent the major determinants of individual activity space, and demonstrate how these indicators can be combined with each other to gain insights into human mobility patterns in cities.

Conducted at: University of Tennessee, Knoxville

Publications: Annals of the American Association of Geographers (2016)






Mapping The Spatial Extent of Human Activity Space

How do people's daily activities take place around where they live? Do people living in different parts of a city exhibit different activity space sizes? By leveraging mobile call detail records (CDRs), we propose a home-based approach to quantifying the spatial extent of human activity space, and investigate how they are related to the socio-economic characteristics of the built environment.

Conducted at: University of Tennessee, Knoxville

Publications: Transportation (2015)







Visual-Analytic System For Complex Environmental Models

I develop a web-based visual analytic system to help environmental scientists better understand the software structures of large-scale environmetal models. The framework integrates data management, software structure analysis, and web-based visualizations.

Conducted at: Oak Ridge National Laboratory (ORNL)

Website: http://cem-base.ornl.gov/CLM_Web/CLM_Web.html

Publications: SERP (2014); EMS (2017); Procedia Computer Science (2017)

2020


[37]. Xu, Y., Li, X., Shaw, S. L., Lu, F., Yin, L. and Chen, B. Effects of data preprocessing methods on addressing location uncertainty in mobile signaling data. Annals of the American Association of Geographers [PDF]


[36]. Xu, Y., Li, J., Belyi, A. and Park, S. Characterizing destination networks through mobility traces of international tourists — A case study using a nationwide mobile positioning dataset. Tourism Management, 82, p.104195 [PDF]


[35]. Xu, Y., Li, J., Xue, J., Park, S. and Li, Q. Tourism geography through the lens of time use — A computational framework using fine-grained mobile phone data. Annals of the American Association of Geographers (accepted). [PDF]


[34]. Luo, Y., Xiang, L., Xu, Y. and Gui, Z. Road Network Extraction from GPS Trajectories — A Tensor Voting Based Algorithm. Proceedings of the GISRUK 2020, London.


[33]. Park, S., Xu, Y., Jiang, L., Chen, Z. and Huang, S. Spatial structures of tourism destinations: A trajectory data mining approach leveraging mobile big data. Annals of Tourism Research, 84, p. 102973 [PDF]


[32]. Tu, W., Mai, K., Zhang, Y., Xu, Y., Huang, J., Deng, M., Chen, L. and Li, Q. Real-time Route Recommendations for E-Taxies Leveraging GPS Trajectories. IEEE Transactions on Industrial Informatics. [PDF]


[31]. Zhao, P., Xu, Y., Liu, X. and Kwan, M.P. Space-time dynamics of cab drivers' stay behaviors and their relationships with built environment characteristics. Cities, 101, p.102689. [PDF]


2019


[30]. Xu, Y., Belyi, A., Santi, P. and Ratti, C. Quantifying segregation in an integrated urban physical-social space. Journal of The Royal Society Interface, 16: 20190536. [PDF]


[29]. Yu, H., Fang, Z., Lu, F., Murray, A.T., Zhao, Z., Xu, Y. and Yang, X. Massive Automatic Identification System Sensor Trajectory Data-Based Multi-Layer Linkage Network Dynamics of Maritime Transport along 21st-Century Maritime Silk Road. Sensors, 19(19), p.4197. [PDF]


[28]. Jia, T., Yu, X., Shi, W., Liu, X., Li, X. and Xu, Y. Detecting the regional delineation from a network of social media user interactions with spatial constraint: A case study of Shenzhen, China. Physica A: Statistical Mechanics and its Applications, p.121719. [PDF]


[27]. Yang, X., Fang, Z., Xu, Y., Yin, L., Li, J. and Lu, S. Spatial heterogeneity in spatial interaction of human movements—Insights from large-scale mobile positioning data. Journal of Transport Geography, 78, 29-40. [PDF]


[26]. Xu, Y. and Ratti, C. Conquer the Divided Cities. Towards a New Enlightenment: A Transcendent Decade, pp.366-380, BBVA OpenMind, Spain. [PDF]


[25]. Xu, Y., Chen, D., Zhang, X., Tu, W., Chen, Y., Shen, Y. and Ratti, C. Unravel the landscape and pulses of cycling activities from a dockless bike-sharing system. Computers, Environment and Urban Systems, 75, 184-203. [PDF]


[24]. Liu, X., Xu, Y. and Ye, X. Outlook and Next Steps: Integrating Social Network and Spatial Analyses for Urban Research in the New Data Environment. Cities as Spatial and Social Networks, pp. 227-238. Springer, Cham. [PDF]


2018


[23]. Zhang, X., Xu, Y., Tu, W. and Ratti, C. Do different datasets tell the same story about urban fmobility — A comparative study of public transit and taxi usage. Journal of Transport Geography, 70, 78-90. [PDF]


[22]. Zhu, J., Xu, Y., Shaw, S. L., Fang, Z. and Liu, X. Geographic Prevalence and Mix of Regional Cuisines in Chinese Cities. ISPRS International Journal of Geo-Information, 7(5), 183. [PDF]


[21]. Xu, Y., Belyi, A., Bojic, I. and Ratti, C. Human Mobility and Socioeconomic Status: Analysis of Singapore and Boston. Computers, Environment and Urban Systems, 72, 51-67. [PDF]


[20]. Xu, Y., Shaw, S. L., Lu, F., Chen, J., and Li, Q. Uncovering the relationships between phone communication activities and spatiotemporal distribution of mobile phone users. In Human Dynamics Research in Smart and Connected Communities, pp. 41-65, Springer, Cham. [PDF]



2017


[19]. Tu, W., Cao, J., Yue, Y., Shaw, S.L., Zhou, M., Wang, Z., Chang, X., Xu, Y. and Li, Q. Coupling mobile phone and social media data: a new approach to understanding urban functions and diurnal patterns. International Journal of Geographical Information Science, 31(12), 2331-2358. [PDF]


[18]. Fang, Z., Yang, X., Xu, Y., Shaw, S.L. and Yin, L. Spatiotemporal model for assessing the stability of urban human convergence and divergence patterns. International Journal of Geographical Information Science, 31(11), 2119-2141. [PDF]


[17]. Xu, Y., Belyi, A., Bojic, I. and Ratti C. How friends share urban space: An exploratory spatiotemporal analysis using mobile phone data. Transactions in GIS, 21, 468-487. [PDF]


[16]. Xu, Y., Wang, D., Janjusic, T., Wu, W., Pei, Y. and Yao, Z. A Web-based Visual Analytic Framework for Understanding Large-scale Environmental Models: A Use Case for The Community Land Model. Procedia Computer Science, 108, 1731-1740. [PDF]


[15]. Xu, Y., Wang, D., Iverson, C., Walker, A. and Warren, J. Building a Virtual Ecosystem Dynamic Model for Root Research. Environmental Modelling & Software, 89, 97-105. [PDF]



2016


[14]. Yang, X., Fang, Z., Xu, Y., Shaw, S-L., Zhao Z., Yin, L., Zhang, T. and Lin, Y. Understanding Spatiotemporal Patterns of Human Convergence and Divergence Using Mobile Phone Location Data. ISPRS International Journal of Geo-Information, 5(10), 177. [PDF]


[13]. Xu, Y., Shaw, S-L., Fang, Z. and Yin, L. Estimating Potential Demand of Bicycle Trips from Mobile Phone Data - An Anchor Point Based Approach. ISPRS International Journal of Geo-Information, 5(8), 131. [PDF]


[12]. He, H., Wang, D., Xu, Y. and Tan, J. Data synthesis in the Community Land Model for ecosystem simulation. Journal of Computational Science, 13, 83-95. [PDF]


[11]. Xu, Y., Shaw, S-L., Zhao, Z., Yin, L., Lu, F., Chen, J., Fang, Z. and Li, Q. Another Tale of Two Cities — Understanding Human Activity Space Using Actively Tracked Cellphone Location Data. Annals of the American Association of Geographers, 106(2), 489-502. [PDF]


[10]. Zhao, Z., Shaw, S-L., Xu, Y., Lu, F., Chen, J. and Yin, L. Understanding the Bias of Call Detail Records in Human Mobility Research. International Journal of Geographical Information Science, 30(9), 1738-1762. [PDF]



2015


[9]. Xu, Y., Shaw, S-L., Zhao, Z., Yin, L., Fang, Z. and Li. Q. Understanding aggregate human mobility patterns using passive mobile phone location data: a home-based approach. Transportation, 42(4), 625-646. [PDF]


[8]. Xu, Y., Shaw, S-L., Zhao, Z., Yin, L., Fang, Z. and Li. Q. Understanding Individual Daily Activity Spaces Based on Large Scale Mobile Phone Location Data. Proceedings of The 13th International Conference on GeoComputation. Dallas, Texas, USA.



2014


[7]. Wang, D., Xu, Y., Thornton, P., King, A., Steed, C., Gu, L. and Schuchart A functional test platform for the Community Land Model. Environmental Modelling & Software, 55, 25-31. [PDF]


[6]. Xu, Y., Wang, D., Janjusic, T. and Xu, X. A Web-based Visual Analytic System for Understanding the Structure of Community Land Model. Proceedings of The 13th International Conference on Software Engineering Research and Practice. Las Vegas, NV. USA.


[5]. Wang, D., Schuchart, T., Janjusic, T., Winkler, F., Xu, Y. and Kartsaklis. Toward Better Understanding of the Community Land Model within the Earth System Modeling Framework. Procedia Computer Science, 29, 1515-1524. [PDF]


[4]. Wang, D. and Xu, Y.. Software Engineering for Scientific Application: Effort Report on The Community Land Model within the Earth System Modeling Framework. Proceedings of The 7th International Congress on Environmental Modelling and Software. San Diego, CA, USA.



2012


[3]. Xu, Y., Shaw, S-L., Chen, J., Li, Q., Fang, Z. and Li, Y. Uncover Repeated Spatio-temporal Behavioral Patterns Embedded in GPS-based Taxi Tracking Data. Proceedings of The 7th International Conference on Geographic Information Science. (Extended abstract). Columbus, OH, USA.


[2]. Chen, J., Shaw, S-L., Xu, Y., Li, Q., Fang, Z. and Li, Y. Where and When Taxi Drivers Deviate from the Shortest Path in Their Route Choices: A Case Study of Wuhan, China. Proceedings of The 7th International Conference on Geographic Information Science. (Extended abstract). Columbus, OH, USA.



2011


[1]. Xu, Y., Li, Q. and Tang, L. Road Damage Detection from Remote Sensing Imagery Based on Road Network Vector Data (in Chinese). Bulletin of Surveying and Mapping, 4, 004. [PDF]

Research Assistant / Postdoctoral Fellow in Urban Analytics



I always welcome outstanding candidates to fill RA & Postdoctoral positions in the broad field of urban informatics and big data analytics. For interested applicants, please refer to the job description for more details.








Funded Ph.D. in Urban Informatics



I am currently seeking exceptional candidates to fill funded Ph.D. positions starting in Fall 2021. Applicants must hold an undergradate degree or higher in GIS & geo-informatics, computer science, urban planning, or related fields. Language requirements should be fullfilled (TOEFL & IELTS). For interested applicants, please contact yang.ls.xu@polyu.edu.hk.








Hong Kong Ph.D. Fellowship



I am always keen to work with outstanding applicants to compete for the Hong Kong Ph.D. fellowship. The awardee will be admitted to the full-time PhD program at PolyU, and the fellowship will provide a monthly stipend of HK$26,000, plus conference and research related travel allowance. The application closes on December 1st every year. More information can be found here.








PhD Students


• Xinyu Li, 2018/09 - Present

• Yan Luo, 2019/09 - Present

• Jingyi Cheng, 2019/09 - Present

• Mengyao Ren, 2020/01 - Present





Research Asisstants

• Jingyan Li, 2019/09 - Present

• Jiaying Xue, 2019/10 - Present





Master Students

• Zhelin Chen, 2018/09 - Present

• Wei Liu, 2018/09 - Present

• Lin Zhong, 2018/09 - Present

• Hongdan Chen, 2018/09 - Present





Past Researchers & Students

• Dachi Chen (research asistant); Current: Facebook

• Liu Jiang (research asistant); Current: MSc, Stanford University

• Yuanyang Chen (master student and research assistant)