Collective Representation Learning in Spatial and Temporal Data Environments: Techniques and Applications


报告题目:Collective Representation Learning in Spatial and Temporal Data Environments: Techniques and Applications

报告人:傅衍杰(Fu Yanjie) 教授






The pervasiveness of mobile and sensing technologies have accumulated large-scale spatial temporal activity data of individual users in real time and at different locations from mobile devices and App services. Such socio-spatio-temporal data have unprecedented and unique complexity. For instance, they are mostly spatially-autocorrelated, temporally-dependent, dynamically-networked, cross-domain, and semantically-rich. As a result, it is difficult to make sense of spatiotemporal data.

In this talk, we first introduce why representation learning can help. We then focus on (1) spatial representation learning; (2) spatiotemporal representation learning; (3) their applications to smart site selection for urban planning and driving behavior analysis for transportation safety. Finally, we conclude the talk and present the big picture on developing close-looped intelligent and trustworthy data science systems.


报告人简介: Dr. Yanjie Fu received his Ph.D. degree from Rutgers University in 2016, the B.E. degree in Computer Science from University of Science and Technology of China in 2008, and the M.E. degree in Computer Engineering from Chinese Academy of Sciences in 2011. He is currently an Assistant Professor at Missouri S&T (University of Missouri-Rolla). His general interests include data mining and big data analytics. His recent research focuses on collective machine learning, heterogeneous information fusion, and spatio-temporal socio-textual mining, with application to big data problems including urban computing, social computing, wireless intelligence, recommender systems, and health care. He has research experience in industry research labs, such as Microsoft Research Asia and IBM Thomas J. Watson Research Center. He has published prolifically in refereed journals and conference proceedings, such as IEEE Transactions on KDE, ACM Transactions on KDD, IEEE Transactions on MC, ACM Transactions on IST, SIGKDD Conference, AAAI Conference, IJCAI Conference.