"Multi-level Inference of Human Motions Using Wearable Sensors"

Gregory J. Pottie, EE Department, UCLA

May 28th (Wednesday), 11:00am
Harold Frank Hall (HFH) Rm 4164

Recently, many commercial systems have appeared that claim to track daily activities and estimate energy expenditures. Unfortunately, the simplified approaches based on population models are inadequate for medical purposes such as guidance in rehabilitation, monitoring of chronic disease conditions, or for sports applications such as refinement of athletic form. Moreover, the data and algorithms are generally proprietary. Need exists for open systems that enable analysis at multiple levels of abstraction: environmental context, activity, activity segmentation, and trajectory of limbs. Also needed are systems that provide feedback at the correct level of abstraction to the different actors: experts (doctors/coaches), non-professional caregivers, and the patin/athlete. We describe research conducted at the UCLA Wireless Health Institute in how to do this at low cost and at large scale, while taking into account the extreme variability of motion profiles of various classes of patients. This can potentially revolutionize the provision of medical care, leading to better outcomes at lower cost.

About Gregory J. Pottie:

photo of gregory pottie Gregory J. Pottie was born in Wilmington, DE, and raised in Ottawa, Canada. He received his B.Sc in Engineering Physics from Queen's University, Kingston, Ontario, in 1984, and his M.Eng. and Ph.D. in Electrical Engineering from McMaster University, Hamilton, Ontario, in 1985 and 1988 respectively. From 1989 to 1991, he worked in the transmission research department of Motorola/Codex in Canton, MA, with projects related to voice band modems and digital subscriber lines. Since 1991, he has been a faculty member of the UCLA Electrical Engineering Department, serving in vice-chair roles from 1999-2003. From 2003-2009, he was the Associate Dean for Research and Physical Resources of the Henry Samueli School of Engineering and Applied Science, and from 2002-2012, he was deputy director of the NSF funded center for Embedded Networked Sensing. His research interests include wireless communication systems and sensor networks. His current focus is on modeling, inferences, and experimental design in sensor networks with application to wireless health. From 1997-1999, he was secretary to the board of governors for the IEEE Information Theory Society. In 1998 he received the Allied Signal Award for outstanding faculty research for UCLA engineering. In 2005, he became a Fellow of the IEEE for contributions to the modeling and applications of sensor networks. In 2009, he received a Fullbright Senior Scholar award. Dr. Pottie is a member of the Bruins Master's Swim Club (butterfly) and the St. Alban's Choir (2nd bass).

Hosted by: Jerry Gibson