Skip Navigation
Search

Lu sU, pHd

Associate Professor
Purdue University

Lu Su is an associate professor in the School of Electrical and Computer Engineering at Purdue University. His research interests are in the general areas of Internet of Things and Cyber- Physical Systems, with a current focus on wireless, mobile, and crowd sensing systems. He received PhD in Computer Science, and MS in Statistics, both from the University of Illinois at Urbana-Champaign, in 2013 and 2012, respectively. He has also worked at IBM T. J. Watson Research Center and National Center for Supercomputing Applications. He has published more than 100 papers in referred journals and conferences, and serves as an associate editor of ACM Transactions on Sensor Networks. He is the recipient of NSF CAREER Award, University at Buffalo Young Investigator Award, ICCPS’17 best paper award, and the ICDCS’17 best student paper award. He is a member of ACM and IEEE.

ABSTRACT

Towards Fine-Grained Wireless Human Perception

The increasing ubiquity of wireless signals (e.g., WiFi, mmWave, Ultrasound) has extended their role of communication tool to contactless sensing platform, as wireless signals usually carry substantial information that can characterize the surrounding objects. Such contactless sensing ability potentially can enable a wide spectrum of applications, especially those related to human perception. By overcoming the technical challenges faced by traditional camera-based human perception solutions, such as occlusion, poor lighting, as well as privacy issues, and eliminating the need for wearable devices which may bring extra burden and discomfort to the monitored subjects, the wireless human perception techniques can enable a new generation of applications capable of supporting more sophisticated interactions between humans and their physical surroundings. In this talk, I will introduce my recent work towards fine-grained wireless human perception, which aims at not only recognizing human activities, which is the task of classifying each monitored activity to a predefined class, but also reconstructing human postures, which are represented as 3D human skeletons composed of the joints on both limbs and torso of the human body.