Presentation 2011-05-19
A Study on the Walking States Classification Method using Cycles of Acceleration Data
Hiroki KASAHARA, Tomonori ITO, Hideki YOSHII, Kazuhiro TSURUMARU, Naohisa KOMATSU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a method that classifies walking condition into three states, walking on the flat ground, going up stairs and going down, using a three dimensional acceleration sensor in a smart phone. In our approach, we focused on periodicity of a walking step and investigated statistical particularity of walking condition, such as average and dispersion, based on this periodicity. Also, we applied the LPC cepstrum into this classification and evaluated with typical statistical values.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) acceleration sensor / walking states / pattern recognition / LPC cepstrum
Paper # LOIS2011-3
Date of Issue

Conference Information
Committee LOIS
Conference Date 2011/5/12(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 Life Intelligence and Office Information Systems (LOIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on the Walking States Classification Method using Cycles of Acceleration Data
Sub Title (in English)
Keyword(1) acceleration sensor
Keyword(2) walking states
Keyword(3) pattern recognition
Keyword(4) LPC cepstrum
1st Author's Name Hiroki KASAHARA
1st Author's Affiliation Faculty of Science and Engineering, Waseda University()
2nd Author's Name Tomonori ITO
2nd Author's Affiliation Faculty of Science and Engineering, Waseda University
3rd Author's Name Hideki YOSHII
3rd Author's Affiliation SOFTBANK TELECOM Corporation
4th Author's Name Kazuhiro TSURUMARU
4th Author's Affiliation Faculty of Science and Engineering, Waseda University
5th Author's Name Naohisa KOMATSU
5th Author's Affiliation Advanced Research Institute For Science And Engineering, Waseda University
Date 2011-05-19
Paper # LOIS2011-3
Volume (vol) vol.111
Number (no) 50
Page pp.pp.-
#Pages 6
Date of Issue