BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Learning for WLAN Positioning - Teemu Roos\, Helsinki Inst
 itute for Information Technology HIIT
DTSTART:20110322T100000Z
DTEND:20110322T110000Z
UID:TALK30245@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:The need for special-purpose indoor positioning systems arises
  from the failure of established technologies\, such as GPS\, in indoor sc
 enarios. Recently\, the interest in positioning based on WLAN networks has
  grown. We discuss the basics of WLAN positioning\, focusing on machine le
 arning approaches where signal strength measurements are associated to geo
 graphic coordinates by applying classification and regression techniques. 
 We also present recent work on semi-supervised learning for WLAN positioni
 ng where the costly training phase is simplified by exploiting easily obta
 inable unlabeled signal strength measurements whose position needs not be 
 recorded.
LOCATION:Small lecture theatre\, Microsoft Research Ltd\, 7 J J Thomson Av
 enue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR