TALK: Recent Advances in Traffic Prediction Using Deep Learning Techniques

SERIES OVERVIEW: This series of talks highlights research results from leaders in the field who are focused on theory and applications involving spatial data. The lecture series is organized by Hanan Samet and Leila De Floriani from the University of Maryland, with Yunting Song managing the web services. To view video recordings of each talk, go to tinyurl.com/MLrecordings.

SPEAKER: Jianzhong Qi, University of Melbourne

DATE: Thursday, April 22

TIME: 7 p.m.–8:15 p.m. EDT

ZOOM LINK: https://umd.zoom.us/j/93125652090?pwd=RUVHTTRKSGxVQ2p4czFhR1JUTUJ2Zz09

ABSTRACT: Traffic prediction plays an essential role in intelligent transportation systems. Accurate traffic prediction can assist traffic management, route planning and assignment, and congestion mitigation. This problem is challenging due to the complex and dynamic spatio-temporal dependencies between different regions of the road network. Extensive studies have been done in this area, proposing techniques ranging from classical statistical methods to modern machine learning, especially deep learning models. In this lecture, we will discuss recent developments in this area, with a focus on deep learning models for traffic prediction.

SPEAKER BIO: Jianzhong Qi is a senior lecturer in the School of Computing and Information Systems at the University of Melbourne. His research interests include machine learning and data management and analytics, with a focus on spatial, temporal, and textual data. Qi obtained his Ph.D. from the University of Melbourne in 2014. He was an intern at Microsoft Redmond in 2014 and a visiting scholar at Northwestern University in 2017. Qi publishes in leading venues in database management and machine learning such as TPAMI, TODS, VLDBJ, ICML, NeurIPS, and PVLDB. He won the "Best Vision Paper" award at ACM SIGSPATIAL 2017. Qi was the PC co-chair for the Australasian Database Conference 2020.