Gait analyzer based on a cell phone with a single three-axis accelerometer

Toshiki Iso, Kenichi Yamazaki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

75 Citations (Scopus)

Abstract

We propose a fuss-free gait analyzer based on a single three-axis accelerometer mounted on a cell phone for health care and presence services. It is not necessary for users not to wear sensors on any part of their bodies; all they need to do is to carry the cell phone. Our algorithm has two main functions; one is to extract feature vectors by analyzing sensor data in detail using wavelet packet decomposition. The other is to flexibly cluster personal gaits by combining a self-organizing algorithm with Bayesian theory. Not only does the three-axis accelerometer realize low cost personal devices, but we can track aging or situation changes through on-line learning. A prototype that implements the algorithm is constructed. Experiments on the prototype show that the algorithm can identify gaits such as walking, running, going up/down stairs, and walking fast with an accuracy of about 80[%].

Original languageEnglish
Title of host publicationACM International Conference Proceeding Series
Pages141-144
Number of pages4
Volume159
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event8th International Conference on Human-Computer Interaction with Mobile Devices and Services, MobileHCI 2006 - Espoo
Duration: 2006 Sep 122006 Sep 15

Other

Other8th International Conference on Human-Computer Interaction with Mobile Devices and Services, MobileHCI 2006
CityEspoo
Period06/9/1206/9/15

Fingerprint

Accelerometers
Stairs
Sensors
Health care
Aging of materials
Wear of materials
Decomposition
Costs
Experiments

Keywords

  • Accelerometer
  • Cell phone
  • Context
  • Gait analysis
  • Self-organizing map
  • Sensor
  • Ubiquitous service
  • Wavelet packet

ASJC Scopus subject areas

  • Human-Computer Interaction

Cite this

Iso, T., & Yamazaki, K. (2006). Gait analyzer based on a cell phone with a single three-axis accelerometer. In ACM International Conference Proceeding Series (Vol. 159, pp. 141-144) https://doi.org/10.1145/1152215.1152244

Gait analyzer based on a cell phone with a single three-axis accelerometer. / Iso, Toshiki; Yamazaki, Kenichi.

ACM International Conference Proceeding Series. Vol. 159 2006. p. 141-144.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Iso, T & Yamazaki, K 2006, Gait analyzer based on a cell phone with a single three-axis accelerometer. in ACM International Conference Proceeding Series. vol. 159, pp. 141-144, 8th International Conference on Human-Computer Interaction with Mobile Devices and Services, MobileHCI 2006, Espoo, 06/9/12. https://doi.org/10.1145/1152215.1152244
Iso T, Yamazaki K. Gait analyzer based on a cell phone with a single three-axis accelerometer. In ACM International Conference Proceeding Series. Vol. 159. 2006. p. 141-144 https://doi.org/10.1145/1152215.1152244
Iso, Toshiki ; Yamazaki, Kenichi. / Gait analyzer based on a cell phone with a single three-axis accelerometer. ACM International Conference Proceeding Series. Vol. 159 2006. pp. 141-144
@inproceedings{903e985ee1ae410bb9bdffc0a86cebdc,
title = "Gait analyzer based on a cell phone with a single three-axis accelerometer",
abstract = "We propose a fuss-free gait analyzer based on a single three-axis accelerometer mounted on a cell phone for health care and presence services. It is not necessary for users not to wear sensors on any part of their bodies; all they need to do is to carry the cell phone. Our algorithm has two main functions; one is to extract feature vectors by analyzing sensor data in detail using wavelet packet decomposition. The other is to flexibly cluster personal gaits by combining a self-organizing algorithm with Bayesian theory. Not only does the three-axis accelerometer realize low cost personal devices, but we can track aging or situation changes through on-line learning. A prototype that implements the algorithm is constructed. Experiments on the prototype show that the algorithm can identify gaits such as walking, running, going up/down stairs, and walking fast with an accuracy of about 80[{\%}].",
keywords = "Accelerometer, Cell phone, Context, Gait analysis, Self-organizing map, Sensor, Ubiquitous service, Wavelet packet",
author = "Toshiki Iso and Kenichi Yamazaki",
year = "2006",
doi = "10.1145/1152215.1152244",
language = "English",
isbn = "1595933905",
volume = "159",
pages = "141--144",
booktitle = "ACM International Conference Proceeding Series",

}

TY - GEN

T1 - Gait analyzer based on a cell phone with a single three-axis accelerometer

AU - Iso, Toshiki

AU - Yamazaki, Kenichi

PY - 2006

Y1 - 2006

N2 - We propose a fuss-free gait analyzer based on a single three-axis accelerometer mounted on a cell phone for health care and presence services. It is not necessary for users not to wear sensors on any part of their bodies; all they need to do is to carry the cell phone. Our algorithm has two main functions; one is to extract feature vectors by analyzing sensor data in detail using wavelet packet decomposition. The other is to flexibly cluster personal gaits by combining a self-organizing algorithm with Bayesian theory. Not only does the three-axis accelerometer realize low cost personal devices, but we can track aging or situation changes through on-line learning. A prototype that implements the algorithm is constructed. Experiments on the prototype show that the algorithm can identify gaits such as walking, running, going up/down stairs, and walking fast with an accuracy of about 80[%].

AB - We propose a fuss-free gait analyzer based on a single three-axis accelerometer mounted on a cell phone for health care and presence services. It is not necessary for users not to wear sensors on any part of their bodies; all they need to do is to carry the cell phone. Our algorithm has two main functions; one is to extract feature vectors by analyzing sensor data in detail using wavelet packet decomposition. The other is to flexibly cluster personal gaits by combining a self-organizing algorithm with Bayesian theory. Not only does the three-axis accelerometer realize low cost personal devices, but we can track aging or situation changes through on-line learning. A prototype that implements the algorithm is constructed. Experiments on the prototype show that the algorithm can identify gaits such as walking, running, going up/down stairs, and walking fast with an accuracy of about 80[%].

KW - Accelerometer

KW - Cell phone

KW - Context

KW - Gait analysis

KW - Self-organizing map

KW - Sensor

KW - Ubiquitous service

KW - Wavelet packet

UR - http://www.scopus.com/inward/record.url?scp=34547358090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547358090&partnerID=8YFLogxK

U2 - 10.1145/1152215.1152244

DO - 10.1145/1152215.1152244

M3 - Conference contribution

SN - 1595933905

SN - 9781595933904

VL - 159

SP - 141

EP - 144

BT - ACM International Conference Proceeding Series

ER -