Select a calendar:
Filter November Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for November 30, 2015
-
CS Seminar: Dr. Gita Sukthankar (University of Central Florida) - Data-driven Social Informatics
Mon, Nov 30, 2015 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Gita Sukthankar, University of Central Florida
Talk Title: Data-driven Social Informatics
Series: Teamcore Seminar
Abstract: Data-driven social informatics unites models derived from social science with data-driven approaches in order to model and predict population behavior patterns. It can be used to advance our understanding of human behavior, guide public policy decisions, and improve user experience with social media platforms. In this talk, I'll describe work done at UCF's Intelligent Agents Lab (http://ial.eecs.ucf.edu/) in which we use a combination of agent-based modeling, machine learning, and crowdsourcing to model human social systems. The benefits of this approach will be illustrated using three case studies: 1) predicting the influence of social norms on smoking cessation behavior, 2) tracking campus parking usage using crowdsourcing and transportation modeling, 3) learning collaboration patterns from co-authorship networks. We believe that the combination of techniques yields a more nuanced view that relying on data alone.
Biography: Dr. Gita Sukthankar is an Associate Professor and Charles N. Millican Faculty Fellow in the Department of Computer Science at the University of Central Florida, and an affiliate faculty member at UCF's Institute for Simulation and Training. She received her Ph.D. from the Robotics Institute at Carnegie Mellon and an A.B. in psychology from Princeton University. In 2009, Dr. Sukthankar was selected for the Air Force Young Investigator award, the DARPA Computer Science Study Panel, and an NSF CAREER award. Gita Sukthankar's research focuses on multi-agent systems and computational social models. She is the lead editor of the book: Plan, Activity, and Intent Recognition: Theory and Practice and currently serves on DARPA's Information Science and Technology advisory group.
Host: Teamcore Group
Location: 107
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
PhD Defense - Saima Aman
Mon, Nov 30, 2015 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science, Ming Hsieh Department of Electrical and Computer Engineering
University Calendar
PhD Defense - Saima Aman
Title: Prediction Models for Dynamic Decision Making in Smart Grid
Committee: Viktor Prasanna (chair), Cauligi Raghavendra, Cyrus Shahabi
Abstract:
The widespread use of smart meters and sensors in the Smart Grid is generating large volumes of data, also designated as big data. Predictive modeling can be used to learn from this data about when peak demand periods occur to make dynamic decisions about when, by how much, and how to reduce consumption, by means of demand response (DR). While day-ahead predictions have long been used for DR, we propose dynamic demand response (D2R) that requires performing DR at a few hours- advance notice whenever necessitated by dynamic conditions such as intermittent generation from renewable energy sources. D2R is a prime example of dynamic decision making in smart grids that involves balancing supply and demand in real-time and adapting to dynamically changing conditions by automating and transforming the DR planning process.
We focus on the challenges of prediction modeling and evaluation to enable D2R. First, we address the partial data problem that arises when real-time data from sensors is only partially available at the utilities. Our proposed model learns the dependencies among time series collected from a set of sensors, and uses data from a small subset of -"influential" sensors to make accurate predictions for all sensors. The second problem we address is that of predicting reduced consumption during DR. We leverage big data on reduced consumption to learn a single ensemble model to predict reduced consumption for diverse customers over different time intervals, thus achieving high cost efficiency. Finally, we identify the limitations of existing measures for evaluating the performance of prediction models in smart grid and propose a suite of performance measures that address accuracy, reliability, and cost. We use the USC microgrid data in our experiments, and our proposed models are being used for D2R on the USC campus.
Biography:
Saima Aman is currently a Ph.D. candidate in the Computer Science Department at the University of Southern California. Her research interests are in Data Science and Artificial Intelligence. She has a M.S. in Computer Science from the University of Ottawa, Canada, and a B.Tech. in Computer Engineering from Aligarh Muslim University, India.Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Kathy Kassar
