Xiaofan (Fred) Jiang (Columbia University)
Shahriar Nirjon (University of North Carolina, Chapel Hill)
Nirupam Roy (University of Maryland, College Park)
Mi Zhang (Ohio State University)
Shijia Pan (University of California, Merced)
Jagmohan Chauhan (University of Southampton)
Local Time: Central Daylight Time(UTC-5)
| 9:00 am - 10:00 am |
Keynote 1: Pei Zhang (University of Michigan, Ann Arbor) Title: Listening to Structures: Leveraging Building Vibrations to Understand People Abstract: This talk introduces sensing people using structural vibrations. Occupants and Environments induces vibrations on structures. These induced vibrations range from large vibrations like foot-steps to small vibrations like heartbeats. Measuring these vibrations should allow us to learn information about these persons. However, building vibration is also a mixture of these signals convoluted with the building response that makes this problem especially challenging and often impossible. This talk introduces a combination of techniques that incorporate physical models and hardware characteristics to enable learning in from highly convoluted signal to enable learning with “small data”. We 1) improve sensed data through actuation of the sensing system, 2) incorporate physical characteristics to guide learning, and 3) combine and transfer data from other domains using the physical understanding. This talk illustrates these approaches through our work on Structures-as-Sensors, where a building acts as the physical elements of the sensor; and the structural response is interpreted to obtain information about the occupants. I will present our results through a range of applications through a range of real-world deployments from pristine hospitals and not-so-pristine pig farms. Bio: Pei Zhang is an Associate Professor in Department of Electrical Engineering and Computer Science at the University of Michigan, Ann Arbor. He received his bachelor's degree from California Institute of Technology in 2002, and his Ph.D. degree in Electrical Engineering from Princeton University in 2008. His early work ZebraNet is considered one of the seminal works in sensor networks, for which he received the SenSys Test-of-Time Award in 2017. His recent work focuses on Cyber-Physical systems that utilizes the physical properties of vehicles and structures to discover surrounding physical information. His work combines machine learning-based data models, physics-based models, as well as heuristic models to improve learning using a small amount of labeled sensor data. His work is applied to the field of medicine, farming, smart retail, and is part of multiple startups. His work has been featured in popular media including CNN, CBS, NBC, Science Channel, Discovery Channel, Scientific American, etc. In addition, he has received various best paper awards, the NSF CAREER award (2012), SenSys Test of Time Award (2017), Google faculty award (2013, 2016), and was a member of the Department of Defense Computer Science Studies Panel. |
|---|---|
| 10:30 am - 12:00 pm |
Session 1: Robust Acoustic Sensing 1. A Cognitive Scaling Mixer for Concurrent Ultrasound Sensing and Music Playback in Smart Devices Yin Li (Cornell Tech), Rajalakshmi Nandakumar (Cornell Tech)2. CaNRun: Non-Contact, Acoustic-based Cadence Estimation on Treadmills using Smartphones Ziyi Xuan (Columbia University), Ming Liu (Columbia University), Jingping Nie (Columbia University), Minghui Zhao (Columbia University), Stephen Xia (Columbia University), Xiaofan Jiang (Columbia University)3. Spatial Audio Empowered Smart speakers with Xblock - A Pose-Adaptive Crosstalk Cancellation Algorithm for Free-moving Users Frank Liu (Arizona State University), Anish Narsipur (Arizona State University), Andrew Kemeklis (Arizona State University), Lucy Song (Arizona State University), Robert LiKamWa (Arizona State University) |
| 1:30 pm - 3:30 pm |
Session 2: Augmentation Acoustic 1. [Invited Paper] Augmenting Vibration-Based Customer-Product Interaction Recognition with Sparse Load Sensing Yue Zhang (University of California Merced), Shiwei Fang (University of Massachusetts Amherst), Carlos Ruiz (Aifi Inc.), Zhizhang Hu (University of California Merced), Shubham Rohal (University of California Merced), Shijia Pan (University of California Merced)2. [Invited Paper] Structure Assisted Spectrum Sensing for Low-power Acoustic Event Detection Nakul Garg (University of Maryland, College Park, Harshvardhan Takawale (University of Maryland, College Park), Yang Bai (University of Maryland College Park), Irtaza Shahid (University of Maryland, College Park), Nirupam Roy (University of Maryland, College Park) |
