ECE Colloquium - Dr. Jorge Ortiz, IBM Research

Wed, 10/25/2017 - 10:00am
Add to Calendar
Location: 
CoRE Building, Lecture Hall

Title:
Adding Intelligence to the Internet-of-Things
 
Abstract:
The Internet-of-Things (IoT) has seen explosive growth in recent years.  The number of IoT devices in use has doubled in the last three years -- over 8 Billion devices in use today -- and is expected to double again by 2020.  The potential impact IoT will have on society is massive, with growth in such areas as intelligent buildings, smart infrastructure, and healthcare.  However, the true value of these deployments cannot be realized without intelligent tools that automate or help end users deal with scale effectively -- both in the number and diversity of devices.  In this talk, I will discuss a set of technical challenges in several IoT application domains, including smart buildings and commercial IoT device management.  More specifically, I will describe the challenges with metadata management in the built environment and how transfer learning and active learning can help address them.  I will also present results from  a study that aims to identify IoT devices in the wild by analyzing and classifying their network traffic.  In addition, since much of IoT data is time series in nature, I will briefly describe techniques for extracting useful knowledge from IoT-based time series sensor data.  Throughout the talk, I will mention some open research questions and will go over future directions of my work at the end.
 
Bio:
Dr. Jorge Ortiz is a Research Staff Member in the IBM Research AI division at TJ Watson Labs in Yorktown Heights, NY.  He works on systems and algorithms for physical analytics in buildings and IoT and deploying machine learning on resource constrained devices.  Broadly he is interested in sensing and building informatics, machine learning and systems.  He has been at IBM Research since 2013, after obtaining a Ph.D. in Computer Science from the University of California at Berkeley (2013). He also has an M.S. in Computer Science from UC Berkeley (2010) and a B.S. in Electrical Engineering and Computer Science from M.I.T. (2003).