<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EN-US link="#0563C1" vlink="#954F72"><div class=WordSection1><p class=MsoNormal><span style='color:black'>Seminar Speaker<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Dr. Shijia Pan from Carnegie Mellon University<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Thursday, September 27, 2018 - 12:30pm<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Computer Science - Room 402<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Host: Margaret Martonosi<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'> <o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>“Indoor Human Information Acquisition from Physical Vibrations”<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'> <o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Abstract:<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>The number of everyday smart devices (such as smart TV, Samsung SmartThings, Nest, Google<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Home) is projected to grow to the billions in the coming decade. The Cyber-Physical Systems or Internet<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>of Things systems that consist of these devices are used to obtain human information for various smart<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>building applications. Different sensing approaches have been explored, including vision-, sound-, RF-,<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>mobile-, and load-based methods, to obtain various indoor human information. From the system<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>perspective, general problems faced by these existing technologies are their sensing requirements (e.g.,<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>line-of-sight, high deployment density, carrying a device) and intrusiveness (e.g., privacy concerns).<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'><o:p> </o:p></span></p><p class=MsoNormal><span style='color:black'>My research focuses on non-intrusive indoor human information acquisition through ambient<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>structural vibration, which is referred to as ’structures as sensors’. People’s interaction with structures in<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>the ambient environment (e.g., floor, table, door) induces those structures to vibrate. By capturing and<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>analyzing the vibration response of structures, we can indirectly infer information about the people and<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>their actions that cause it. However, challenges remain. Due to the complexity of the physical world (in<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>this case, both structures and people), sensing data distributions can change significantly under different<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>sensing conditions. Therefore, from the data perspective, accurate information learning through a pure<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>data-driven approach requires a large amount of labeled data, which is costly and difficult if not<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>impossible to obtain in real-world sensing applications. My research addresses these challenges by<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>combining physical knowledge and data-driven approaches. Specifically, my system can robustly learn<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>human information from limited labeled data distributions by iteratively expanding the labeled dataset.<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>With insights into the relationship between changes of sensing data distributions and measurable physical<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>attributes, the iterative algorithm guides the expansion order by measured physical attributes to ensure a<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>high learning accuracy in each iteration.<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'> <o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Bio:<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Dr. Shijia Pan is a postdoctoral researcher at Carnegie Mellon University. She received her Bachelor's<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>degree in Computer Science and Technology from University of Science and Technology of China and<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>her Ph.D. degree in Electrical and Computer Engineering at Carnegie Mellon University. Her research<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>interests include cyber-physical systems, Internet-of-Things (IoT), and ubiquitous computing. She worked<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>in multiple disciplines and focused on indoor human information acquisition through ambient sensing.<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>She has published in both top-tier Computer Science ACM/IEEE conferences (IPSN, UbiComp) and<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>high-impact Civil Engineering journals (Journal of Sound and Vibration, Frontiers Built Environment).<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>She is the recipient of numerous awards and fellowships, including Rising Stars in EECS, Nick G.<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Vlahakis Graduate Fellowship, Google Anita Borg Scholarship, Best Poster Awards (SenSys, IPSN), Best<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Demo Award (Ubicomp), Best Presentation Award (SenSys Doctoral Colloquium), and Audience Choice<o:p></o:p></span></p><p class=MsoNormal><span style='color:black'>Award (BuildSys) from ACM/IEEE conferences.</span><o:p></o:p></p></div></body></html>