Shijia Pan
Carnegie Mellon University
shijiapan@cmu.edu
Bio
Shijia Pan is a postdoctoral researcher at Carnegie Mellon. She received a bachelor’s degree in computer science and technology from University of Science and Technology of China and a PhD degree in electrical and computer engineering from Carnegie Mellon. Her research interests include cyber-physical systems, Internet-of-Things (IoT), and ubiquitous computing. She worked in multiple disciplines and focused on indoor human information acquisition through ambient sensing. She published in both top-tier computer science ACM/IEEE conferences (IPSN UbiComp) and high-impact civil engineering journals (Journal of Sound and Vibration, Frontiers in Built Environment). Awards include a Nick G. Vlahakis Graduate Fellowship, a Google Anita Borg Memorial Scholarship, best poster awards (SenSys, IPSN), a best demo and presentation award (Ubicomp, SenSys Doctoral Colloquium), and audience-choice award (BuildSys) from ACM/IEEE conferences.
Indoor Human Information Acquisition from Physical Vibrations
Indoor Human Information Acquisition from Physical Vibrations
The number of everyday smart devices (such as smart TV, Samsung SmartThings, Nest, Google Home, etc.) is projected to grow to the billions in the coming decade. The Cyber-Physical Systems or Internet of Things (IoT) systems that consist of these devices are used to obtain human information for various smart building applications. Different sensing approaches have been explored, including vision-, sound-, RF-, mobile-, and load-based methods to obtain various indoor human information. From the system perspective, general problems faced by these existing technologies are their sensing requirements (e.g., line-of-sight, high deployment density, carrying a device) and intrusiveness (e.g., privacy concerns). My research focuses on non-intrusive indoor human information acquisition through ambient structural vibration, which I call “structures as sensors.” People’s interaction with structures in the ambient environment (e.g., floor, table, door) induces those structures to vibrate. By capturing and analyzing the vibration response of structures, we can indirectly infer information about the people causing it. However, challenges remain. Due to the complexity of the physical world (in this case, structures and people), sensing data distributions can change significantly under different sensing conditions. Therefore, from the data perspective, accurate information learning through a pure data-driven approach requires a large amount of labeled data, which is costly and difficult if not impossible to obtain in sensing applications. My research addresses these challenges by using physical insights to guide the sensing process. My system can robustly learn human information from limited labeled data distributions by iteratively expanding the labeled dataset. With insights into the relationship between changes of sensing data distributions and measurable physical attributes, the expansion order is guided by measured physical attributes to ensure a high learning accuracy in each iteration.