BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Computer Laboratory Systems Research Group Seminar
SUMMARY:The Quest for Zero-Effort Indoor Localization - Ve
 nkat Padmanabhan (MSR)
DTSTART;TZID=Europe/London:20120607T110000
DTEND;TZID=Europe/London:20120607T120000
UID:TALK38305AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/38305
DESCRIPTION:WiFi-based indoor localization has emerged as perh
 aps the most promising approach to indoor localiza
 tion because it holds the possibility of  pretty g
 ood localization at a low cost\, by leveraging the
  near-ubiquitous coverage of WiFi in indoor spaces
  of interest such as office buildings and malls. H
 owever\, widespread deployment has been stymied by
  the need for significant calibration effort.\n\nI
 n this talk\, I will trace through our research at
  MSR\, moving towards the goal of zero-effort indo
 or localization. I will start with the Radar syste
 m\, which pioneered the idea of piggybacking on an
  existing RF-based wireless LAN to perform indoor 
 localization. Radar introduced two approaches to i
 ndoor localization: (a) RF fingerprinting through 
 empirical measurements made at known locations\, a
 nd (b) RF computation using mathematical modeling.
  While these techniques offer good localization ac
 curacy and there has been much follow-on work on f
 urther improving accuracy\, making empirical measu
 rements in a new environment is expensive and cust
 omizing the mathematical model to such an environm
 ent is challenging. To overcome these difficulties
 \, we advocate a crowdsourcing-based approach\, wh
 erein smartphones carried by users in normal cours
 e are used to make measurements and construct mode
 ls\, without any explicit effort on the part of us
 ers. The key is to use the radios and sensors on t
 hese smartphones\, such as WiFi\, GPS\, accelerome
 ter\, and compass\, in unison to (i) track users a
 nd thereby enable empirical measurement of trainin
 g data\, using a system called Zee\, and (ii) cons
 truct an RF model with patchy information\, using 
 a system called EZ.\n\n[EZ is joint work with Kris
 hna Chintalapudi and Anand Iyer\, and Zee with Kri
 shna\, Anshul Rai\, and Riju Sen.]\n\nBio:Venkat P
 admanabhan is a Principal Researcher and Research 
 Manager at Microsoft Research India in Bangalore\,
  where he founded and now leads the Mobility\, Net
 works\, and Systems group. Venkat was previously w
 ith Microsoft Research Redmond for almost 9 years.
  His research interests are broadly in networked a
 nd mobile systems\, and his current/recent work is
 /has been on indoor localization\, efficient mobil
 e communication\, network diagnostics\, and green 
 computing. He is serving as program co-chair for A
 CM Sigcomm 2012\, and has served as an affiliate f
 aculty member at the University of Washington\, wh
 ere he has taught and served on student thesis com
 mittees. Venkat holds a B.Tech. from IIT Delhi and
  an M.S. and a Ph.D. from UC Berkeley\, all in Com
 puter Science. He is a Fellow of the IEEE and a Di
 stinguished Scientist of the ACM. He can be reache
 d on the web athttp://research.microsoft.com/~padm
 anab/.\n
LOCATION:FW26\, Computer Laboratory\, William Gates Builidi
 ng
CONTACT:Eiko Yoneki
END:VEVENT
END:VCALENDAR