Seminars

back Back to all Seminars

EE Seminar: Learning from Distributed Data - Theory and Applications

Start Date: April 22, 2018
End Date: April 22, 2018

By Professor Usman Khan (Tufts University, Medford, MA, USA)
 
 
In today's high-tech world, inexpensive sensors are ubiquitous, instrumenting our surrounding infrastructure and carried by users in their phones, clothing, or vehicles. The data collected by these, possibly mobile, devices is diverse and may include audio and visual signals, environmental measurements, physiological indices, or measurements on one's automobile. With fifth generation (5G) technologies looming on the horizon, there is potential for networking vast numbers of such devices, enabling many distinct tasks through information exchange and cooperation. The resulting integration of sensing, autonomy, and networking is giving rise to fundamentally new classes of distributed learning problems that are essential to many emerging applications on the Internet of Mobile Things (IoMTs), indoor robotics, fleets of driverless vehicles, and smart-and-connected cities. In this talk, I will describe our ongoing work on an IoMT setup built completely in our lab that includes a network of stationary cameras, ground vehicles, and aerial robots. With the help of this setup, I will cast two distributed learning problems: GPS-free localization, and optimization over directed graphs. I will conclude by discussing an overarching theme that unifies the research activity in my lab, which is to design and analyze learning algorithms over a network of diverse, autonomous, mobile agents.
 
Biography: Dr. Usman Khan has been an Associate Professor of Electrical and Computer Engineering (ECE) at Tufts University, Medford, MA, USA, since September 2017, where he is the Director of Signal Processing and Robotic Networks laboratory. His research interests include statistical signal processing, network science, and distributed optimization over autonomous multi-agent systems. He has published extensively in these topics with more than 75 articles in journals and conference proceedings and holds multiple patents. Recognition of his work includes the prestigious National Science Foundation (NSF) Career award, several NSF REU awards, an IEEE journal cover, three best student paper awards in IEEE conferences, and several news articles including one on IEEE spectrum. Dr. Khan joined Tufts as an Assistant Professor in 2011 and held a Visiting Professor position at KTH, Sweden, in Spring 2015. Prior to joining Tufts, he was a postdoc in the GRASP lab at the University of Pennsylvania. He received his B.S. degree in 2002 from University of Engineering and Technology, Pakistan, M.S. degree in 2004 from University of Wisconsin-Madison, USA, and Ph.D. degree in 2009 from Carnegie Mellon University, USA, all in ECE. Dr. Khan is an IEEE senior member and has been an associate member of the Sensor Array and Multichannel Technical Committee with the IEEE Signal Processing Society since 2010. He is an elected member of the IEEE Big Data special interest group and has served on the IEEE Young Professionals Committee and on IEEE Technical Activities Board. He was an editor of the IEEE Transactions on Smart Grid from 2014 to 2017, and is currently an associate editor of the IEEE Control System Letters. He has served on the Technical Program Committees of several IEEE conferences and has organized and chaired several IEEE workshops and sessions.
 

More Information:

For more info contact: Professor Jeff Shamma: email: jeff.shamma@kaust.edu.sa
 
Date: Sunday 22nd Apr 2018
Time:11:00 AM - 12:00 PM
Location: Building 1 level 3 Room 3119
Refreshment will be available at 10:45 AM