Research on Big Data-Driven Human Mobility Patterns and Models
Ya-Jing Xu
Associate Professor of Beijing University of Posts and Telecommunications (BUPT) in China
DEIB - PT1 Room
February 3rd, 2016
3.00 pm
Contact:
Guido Maier
Research line:
Networking
Associate Professor of Beijing University of Posts and Telecommunications (BUPT) in China
DEIB - PT1 Room
February 3rd, 2016
3.00 pm
Contact:
Guido Maier
Research line:
Networking
Abstract
Human mobility has received much attention in many research fields such as geography, sociology, physics, epidemiology, urban planning and management in recent years. On the one hand, trajectory datasets characterized by a large scale, long time series and fine spatial-temporal granularity become more and more available with rapid development of mobile positioning, wireless communication and mobile internet technologies. On the other hand, quantitative studies of human mobility are strongly supported by interdisciplinary research among geographic information science, statistical physics, complex networks and computer science. In this talk, I will show some recent results on region function discovering based on affinity model and Non-negative Matrix Factorization (NMF). In addition, I also will show how to use trajectories to measure the attraction force between regions based on above outputs.
Short Bio
Ya-Jing Xu, female, born in 1977, Associate Professor of Beijing University of Posts and Telecommunications (BUPT) in China. She got her Ph.D on Signals and Systems from BUPT at 2007. Then at 2008 she went to Montana State University of USA as a visiting scholar. After six months she joined in Pattern Recognition and Intelligent Systems Laboratory (PRIS) of BUPT until now. Her current main research areas: Pattern Recognition, machine learning and data mining. She has participated in many projects funded by national 863 high-tech and national natural science foundation of China. She has also published more than 20 academic papers on international journals and conferences, and received 5 authorized patents.