BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Accelerometer-Based Transportation Mode Detection on Smartphones -
  Petteri Nurmi (University of Helsinki)
DTSTART:20131203T130000Z
DTEND:20131203T140000Z
UID:TALK49200@talks.cam.ac.uk
CONTACT:Ionel Gog
DESCRIPTION:We introduce novel accelerometer-based techniques for accurate
  and fine-grained detection of transportation modes on smartphones. The pr
 imary technical contributions of our work are an improved algorithm for es
 timating the gravity component of accelerometer measurements\, a novel set
  of accelerometer features that are able to capture key characteristics of
  vehicular movement patterns\, and a hierarchical decomposition of the det
 ection task. We evaluate our approach using over 150 hours of transportati
 on data\, which has been collected from 4 different countries and 16 indiv
 iduals. Results of the evaluation demonstrate that our approach is able to
  improve transportation mode detection by over 20% compared to current acc
 elerometer-based systems\, while at the same time improving generalization
  and robustness of the detection\, particularly for different public trans
 portation modalities.\nAs part of the talk\, I will also present an overvi
 ew of the activities of the Ubiquitous Sensing research group at Universit
 y of Helsinki.\n\nBio:\nPetteri Nurmi is a Senior Researcher at University
  of Helsinki and Helsinki Institute for Information Technology HIIT where 
 he is leading the Ubiquitous Sensing research group. He received his PhD i
 n 2009 from the Department of Computer Science in University of Helsinki a
 nd is a Docent of Computer Science since 2012. His research interests incl
 ude mobile sensing\, adaptive interfaces\, and ubiquitous computing in gen
 eral.
LOCATION:Computer Laboratory\, William Gates Building\, Room FW11
END:VEVENT
END:VCALENDAR