Presentation 2009-01-15
User's Commute Prediction for Use in a Wearable Learning System Using GPS and an Accelerometer
Tomohiro NISHIKAWA, Tomohiro MASHITA, Kiyoshi KIYOKAWA, Haruo TAKEMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we have investigated a user's commute prediction mechanism for a wearable system that provides a context-based uninterrupted learning environment. We use acceleration data of thigh motion and GPS data to recognize user's motion and location. The support vector machine predicts user's context based on the power spectrum of acceleration data. User's location and moving speed is measured by GPS data. And we predict user's commute by using location of landscapes and timetable of every station or train. We have conducted a series of experiments to evaluate our system. Our system was able to predict highly accurate commute when user uses trains, but not when user walks on commute path.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Wearable Learning System / Commute Prediction / Context Recognition / GPS / Accelerometer
Paper # MVE2008-98
Date of Issue

Conference Information
Committee MVE
Conference Date 2009/1/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) User's Commute Prediction for Use in a Wearable Learning System Using GPS and an Accelerometer
Sub Title (in English)
Keyword(1) Wearable Learning System
Keyword(2) Commute Prediction
Keyword(3) Context Recognition
Keyword(4) GPS
Keyword(5) Accelerometer
1st Author's Name Tomohiro NISHIKAWA
1st Author's Affiliation Graduate School of Information Science and Technology, Osaka University()
2nd Author's Name Tomohiro MASHITA
2nd Author's Affiliation Graduate School of Information Science and Technology, Osaka University:Cybermedia Center, Osaka University
3rd Author's Name Kiyoshi KIYOKAWA
3rd Author's Affiliation Graduate School of Information Science and Technology, Osaka University:Cybermedia Center, Osaka University
4th Author's Name Haruo TAKEMURA
4th Author's Affiliation Graduate School of Information Science and Technology, Osaka University:Cybermedia Center, Osaka University
Date 2009-01-15
Paper # MVE2008-98
Volume (vol) vol.108
Number (no) 379
Page pp.pp.-
#Pages 6
Date of Issue