Predicting_Crowds

PREDICTING CROWDS ON PUBLIC TRANSPORT

If you'd been able to predict how crowded the metro was going to be, you might have decided to go get a latte and read your email before heading underground! To empower passengers to make such decisions, we used data analytics on extensive Shanghai passenger metro card data to build a model to predict crowd density on station platforms and in the train cars, for any given day and time. In this presentation, we'll discuss the data, the techniques we used to build the model, the quality of the resulting predictions, and the lessons we learned. We will also demonstrate the phone app we built that embodies the model. We'll follow the presentation with a discussion on other situations where this approach can be applied, and the requirements and considerations if you want to use this approach.

About the Speakers
Marianne Winslett has been a professor in the Department of Computer Science at the University of Illinois since 1987. She returned to the US in 2013 after four years as the director of Illinois's research center in Singapore, the Advanced Digital Sciences Center. She is an ACM Fellow and the recipient of a Presidential Young Investigator Award from the US National Science Foundation. She is the former vice-chair of ACM SIGMOD and the co-editor-in-chief of ACM Transactions on the Web, and has served on the editorial boards of ACM Transactions on Database Systems, IEEE Transactions on Knowledge and Data Engineering, ACM Transactions on Information and Systems Security, the Very Large Data Bases Journal, and ACM Transactions on the Web. She has received two best paper awards for research on managing regulatory compliance data (VLDB, SSS), one best paper award for research on analyzing browser extensions to detect security vulnerabilities (USENIX Security), and one for keyword search (ICDE). Her PhD is from Stanford University.

Zhenjie Zhang is a Senior Research Scientist at the Advanced Digital Sciences Center, Singapore. He received his Ph.D. in computer science from the School of Computing, National University of Singapore, in 2010. Before that, he graduated with a B.S. degree from the Department of Computer Science and Engineering, Fudan University, in 2004. He was visiting student at the Hong Kong University of Science and Technology in 2008 and a visiting student at AT&T Shannon Lab in 2009. Before joining the Advanced Digital Sciences Center in October 2010, he worked as a Research Assistant and Research Fellow at the National University of Singapore from 2008 to 2010. His research interests cover a variety of different topics, including clustering analysis, non-metric indexing, game theory, and data privacy. He has published more than 20 research papers in database and data mining venues, including SIGMOD, VLDB, and ICML. He has served as a Program Committee member for WWW 2010, VLDB 2010, KDD 2010, and APWeb 2011. He was the recipient of a President's Graduate Fellowship of Singapore in 2007.

Date/Time

Venue

Type of Event

EVENT MATERIALS

Here are the presentation slides in pdf format. Download here.

Here are the videos of the presentation. Part 1 covers the Shanghai public transport case study. Part 2 covers the Sentosa Island case study.

ISKO Singapore is registered in Singapore. Society registration number T15SS0160B
By continuing to use the ISKO Singapore website you are agreeing that ISKO Singapore may collect, use and disclose your personal data obtained by ISKO Singapore as a result of your use of the ISKO Singapore website. Please consult our data protection policy, including how you may access and correct your personal data or withdraw consent to the collection, use or disclosure of your personal data.