• Understanding Urban Vibrancy: A Data Driven Perspective
  • Modeling and Analysis of Heterogeneous Human Mobility Data

Understanding Urban Vibrancy: A Data Driven Perspective

Understanding Urban Vibrancy: A Data Driven Perspective

NVESTIGATORS
Yanjie Fu


FUNDING SOURCE
University of Missouri Research Board


PROJECT DESCRIPTION
It is traditionally challenging to develop vibrant urban communities. With the pervasiveness of sensing and mobile technologies, the increasing availability of crowd-sourced geo-tagged data such as urban geography data and human mobility data have attracted efforts building analytic methods to discover insights of sustainable urban vibrancy from the data. One important finding is that urban vibrancy is usually related with unique geographic and mobility patterns, e.g., walkable, compact, connected, mixed-use, multi-use, intensive social interactions, and strong willingness to rent and visit. It is critical to exploit the relatedness of these patterns for understanding and sustaining urban vibrancy. This project will develop effective and efficient analytic algorithms to discover complex urban geography and human motility patterns and model their inter-connections with urban vibrancy. The algorithms developed in this project will directly impact urban planning and smart growth as they will be used in city governance.

 

PUBLICATIONS 

  1. "Modeling of Geographical Dependencies for Real Estate Ranking," Yanjie Fu, Hui Xiong, Yong Ge, Yu Zheng, Zijun Yao, Zhi-Hua Zhou, ACM Transactions on Knowledge Discovery from Data (TKDD), 11(1):1-27, 2016.
  2. "Real Estate Ranking via Mixed Land-use Latent Models," Yanjie Fu, Guannan Liu, Spiros Papadimitriou, Hui Xiong, Yong Ge, Hengshu Zhu, Chen Zhu, In Proceedings of the 21st SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'15), Sydney, Australia, 2015.
  3. "Sparse Real Estate Ranking with Online User Reviews and Offline Moving Behaviors," Yanjie Fu, Yong Ge, Yu Zheng, Zijun Yao, Yanchi Liu, Hui Xiong, Nicholas Jing Yuan, In Proceedings of the 14th IEEE Conference on Data Mining (ICDM'14), Shenzhen, China, 2014.
  4. "Exploiting Geographic Dependencies for Real Estate Appraisal," Yanjie Fu, Hui Xiong, Yong Ge, Zijun Yao, Yu Zheng, Zhi-Hua Zhou, In Proceedings of the 20th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'14), New York, USA, 2014.

 

Modeling and Analysis of Heterogeneous Human Mobility Data

Modeling and Analysis of Heterogeneous Human Mobility Data

INVESTIGATORS
Yanjie Fu


FUNDING SOURCE
Missouri S&T


PROJECT DESCRIPTION
With the development of Internet, mobile, and sensing technologies, a variety of human mobility data, such as vehicle GPS trajectories and check-ins, have been accumulated. These Heterogeneous Human Mobility Data (HHMD) represent an invaluable source of intelligence for providing data-driven decision making supports in smart growth. Knowledge discovered from HHMD can be useful for many applications, e.g., improving city planning and governance, supporting transportation engineering, enhancing public safety, understanding social interaction. While it is very promising to mine HHMD, there are many practical challenges for modeling and mining HHMD. Given the inherent heterogeneous and complex nature of human mobility data, it highly necessitate innovative data driven approaches to unleash the power of HHMD. This project will develop novel, systematical, and effective analytic techniques to significantly advance critical problems in modeling, augmenting, and mining HHMD.

 

PUBLICATIONS

  1. "Spotting Trip Purposes from Taxi Trajectories: A General Probabilistic Model," Pengfei Wang, Guannan Liu, Yanjie Fu, Haoyi Xiong, Yuanchun Zhou, ACM Transactions on Intelligent Systems and Technology (TIST), 2017.
  2. "Exploiting Heterogeneous Human Mobility Patterns for Intelligent Bus Routing," Yanchi Liu, Chuanren Liu, Jing Yuan, Lian Duan, Yanjie Fu, Hui Xiong, Songhua Xu, Junjie Wu, In Proceedings of the 14th IEEE Conference on Data Mining (ICDM'14), Shenzhen, China, 2014. (Best Paper Candidate)