Traditional Geographic Information Systems (GIS) focus on capturing and analyzing outdoor geographical data. However, there is no corresponding effort for indoor data and indoor GISs remain an open territory for exploration and innovation. In this talk, we show how to automatically construct semantic-rich indoor floorplans tagged with information such as points of interests and the business names or categories. Specifically, we present different crowdsourcing-based systems that leverage the standard cell phone sensors and publicly available information to achieve this goal. Experimental evaluation of these systems in four malls and a large number of transit stations in Egypt and Japan shows that they can achieve a high semantic labeling accuracy in the presence of highly noisy data.
Moustafa Youssef is the Founder & Director of the Wireless Research Center at Egypt-Japan University of Science and Technology (E-JUST). His research interests include mobile computing, location determination technologies, pervasive computing, mobile wireless networks, and network security. He is an associate editor for the ACM TSAS, a previous area editor of the ACM MC2R and served on the organizing and technical committees of numerous prestigious conferences. Prof. Youssef is the recipient of the 2003 University of Maryland Invention of the Year award, the 2010 TWAS-AAS-Microsoft Award for Young Scientists, the 2012 Egyptian State Award, the 2013 and 2014 COMESA Innovation Awards, the 2013 ACM SIGSpatial GIS Conference Best Paper Award, among many others. He is also an ACM Distinguished Speaker and an ACM Distinguished Scientist.
We end the talk by presenting directions for future work and open research challenges.
Prof. Youssef is also available on 3rd May so if you want to have some discussions with him, contact Hong-Linh Truong.
This talk is organized by the Distributed Systems Group at the Institute of Information Systems.