9:00am - 9:30amRegistration & Breakfast
9:30am - 10:30am
10:30am - 10:45amQ&A
10:45am - 11:00amBreak
11:00am - 12:00pm
12:00pm - 12:15pmQ&A
12:15pm - 1:00pmPoster Sharing & Lunch
Language-agnostic Social Media Signal Processing
Prof Tarek F. Abdelzaher
Professor and Willett Faculty Scholar, Department of Computer Science, University of Illinois
In the last decade, social networks, such as Twitter, emerged as a new information dissemination medium that propagates information regarding the physical world. Viewed from the perspective of an embedded systems researcher, this talk draws an analogy between physical sensing modalities, such as acoustic sensing, magnetic sensing, and seismic sensing on the one hand, and a social sensing modality - the language-agnostic exploitation of social media as sensors - on the other. Much in the way physical targets cause signal propagation through a physical medium, world events cause information propagation on the social medium. Understanding the properties of such propagation allows one to reconstruct properties of both the propagation fabric (people and communities) and the events that caused the propagation in the first place. We model such reconstruction as an estimation problem, drawing on solutions inspired by modeling signal propagation on physical media. We present simple signal processing techniques for the social sensing modality and review experiences using social sensing for event detection, demultiplexing, human bias characterization, veracity analysis, and detection of misinformation campaigns, demonstrating advantages and limitations of the engineering approach.
Tarek Abdelzaher received his B.Sc. and M.Sc. degrees in Electrical and Computer Engineering from Ain Shams University, Cairo, Egypt, in 1990 and 1994 respectively. He received his Ph.D. from the University of Michigan in 1999 on Quality of Service Adaptation in Real-Time Systems. He has been an Assistant Professor at the University of Virginia, where he founded the Software Predictability Group. He is currently a Professor and Willett Faculty Scholar at the Department of Computer Science, the University of Illinois at Urbana Champaign. He has authored/coauthored more than 200 refereed publications in real-time computing, distributed systems, sensor networks, and control. He is an Editor-in-Chief of the Journal of Real-Time Systems, and has served as Associate Editor of the IEEE Transactions on Mobile Computing, IEEE Transactions on Parallel and Distributed Systems, IEEE Embedded Systems Letters, the ACM Transaction on Sensor Networks, and the Ad Hoc Networks Journal. He chaired (as Program or General Chair) several conferences in his area including RTAS, RTSS, IPSN, Sensys, DCoSS, ICDCS, and ICAC. Abdelzaher’s research interests lie broadly in understanding and influencing performance and temporal properties of networked embedded, social and software systems in the face of increasing complexity, distribution, and degree of interaction with an external physical environment. Tarek Abdelzaher is a recipient of the IEEE Outstanding Technical Achievement and Leadership Award in Real-time Systems (2012), the Xerox Award for Faculty Research (2011), as well as several best paper awards. He is a member of IEEE and ACM.
Event Detection and Localization via Time-Varying Sensing on a Graph
Assistant Prof Leman Akolgu
H. John Heinz III College, Carnegie Mellon University
Given time-varying measurements over a graph, how can we detect changes and report when and where they occurred? This problem finds many applications; e.g. event detection in social media, power failure in the power grid, traffic accident detection in road networks, etc. In this talk, I will first introduce an offline approach that employs an unsupervised ensemble of heterogeneous detectors. Then I will present recent work on detecting changes in an online manner via efficient approximations with theoretical guarantees. Besides pinpointing the time of change, both of these techniques can localize the change down to a subset of the nodes in the graph. I will demonstrate effectiveness and scalability on various real world datasets; including Enron email communications, New York Times news corpus, World Cup 2014 Twitter news feed, LA traffic, and Poland power grid.
Leman Akoglu joined the Heinz College faculty as an Assistant Professor in Fall 2016. She also holds a courtesy appointment in the Computer Science Department (CSD) and the Machine Learning Department (MLD) of School of Computer Science (SCS). Prior to this she was an Assistant Professor in the Department of Computer Science at Stony Brook University since receiving her Ph.D. from CSD/SCS of Carnegie Mellon University in 2012.
Dr. Akoglu’s research interests span a wide range of data mining and machine learning topics with a focus on algorithmic problems arising in graph mining, pattern discovery, social and information networks, and especially anomaly mining; outlier, fraud, and event detection. At Heinz, Dr. Akoglu directs the Data Analytics Techniques Algorithms (DATA) Lab.
Dr. Akoglu's research has won 6 publication awards; Best Student Machine Learning Paper Runner-up at ECML PKDD 2018, Best Paper Runner-up at SIAM SDM 2016, Best Paper at SIAM SDM 2015, Best Paper at ADC 2014, Best Paper at PAKDD 2010, and Best Knowledge Discovery Paper at ECML PKDD 2009. She also holds 3 U.S. patents filed by IBM T. J. Watson Research Labs. Dr. Akoglu is a recipient of the National Science Foundation CAREER award (2015) and US Army Research Office Young Investigator award (2013). Her research has been supported by the NSF, US ARO, DARPA, Adobe, Facebook, Northrop Grumman, PNC Bank, and PwC.