Using acceleration signatures from everyday activities for on-body device location

Kai Steven Kunze, Paul Lukowicz

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

31 Citations (Scopus)

Abstract

This paper is part of an effort to facilitate wearable activity recognition using dynamically changing sets of sensors integrated in everyday appliances such as phones, PDAs, watches, headsets etc. A key issue that such systems have to address is the position of the devices on the body. In general each devices can be in a number of different locations (e.g. headset on the head or in on of many pockets). At the same time most activity recognition algorithms require fixed, known sensor positions. Previously we have shown on a small data set how to recognize a set of on-body locations during a walking motion using an accelerometer signal. We now extend the method to work during arbitrary activity. We verify it on a much larger data set with a total 9 hours from real life activity by three divers users ranging from a 70 year old housewife to a 28 year male student.

Original languageEnglish
Title of host publicationProceedings - Eleventh IEEE International Symposium on Wearable Computers, ISWC 2007
Pages115-116
Number of pages2
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event11th IEEE International Symposium on Wearable Computers, ISWC 2007 - Boston, MA, United States
Duration: 2007 Oct 112007 Oct 13

Other

Other11th IEEE International Symposium on Wearable Computers, ISWC 2007
CountryUnited States
CityBoston, MA
Period07/10/1107/10/13

Fingerprint

Watches
Personal digital assistants
Sensors
Accelerometers
Students

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Kunze, K. S., & Lukowicz, P. (2007). Using acceleration signatures from everyday activities for on-body device location. In Proceedings - Eleventh IEEE International Symposium on Wearable Computers, ISWC 2007 (pp. 115-116). [4373794] https://doi.org/10.1109/ISWC.2007.4373794

Using acceleration signatures from everyday activities for on-body device location. / Kunze, Kai Steven; Lukowicz, Paul.

Proceedings - Eleventh IEEE International Symposium on Wearable Computers, ISWC 2007. 2007. p. 115-116 4373794.

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

Kunze, KS & Lukowicz, P 2007, Using acceleration signatures from everyday activities for on-body device location. in Proceedings - Eleventh IEEE International Symposium on Wearable Computers, ISWC 2007., 4373794, pp. 115-116, 11th IEEE International Symposium on Wearable Computers, ISWC 2007, Boston, MA, United States, 07/10/11. https://doi.org/10.1109/ISWC.2007.4373794
Kunze KS, Lukowicz P. Using acceleration signatures from everyday activities for on-body device location. In Proceedings - Eleventh IEEE International Symposium on Wearable Computers, ISWC 2007. 2007. p. 115-116. 4373794 https://doi.org/10.1109/ISWC.2007.4373794
Kunze, Kai Steven ; Lukowicz, Paul. / Using acceleration signatures from everyday activities for on-body device location. Proceedings - Eleventh IEEE International Symposium on Wearable Computers, ISWC 2007. 2007. pp. 115-116
@inproceedings{3c2365e1dccd4bd8aaca40544f1dd490,
title = "Using acceleration signatures from everyday activities for on-body device location",
abstract = "This paper is part of an effort to facilitate wearable activity recognition using dynamically changing sets of sensors integrated in everyday appliances such as phones, PDAs, watches, headsets etc. A key issue that such systems have to address is the position of the devices on the body. In general each devices can be in a number of different locations (e.g. headset on the head or in on of many pockets). At the same time most activity recognition algorithms require fixed, known sensor positions. Previously we have shown on a small data set how to recognize a set of on-body locations during a walking motion using an accelerometer signal. We now extend the method to work during arbitrary activity. We verify it on a much larger data set with a total 9 hours from real life activity by three divers users ranging from a 70 year old housewife to a 28 year male student.",
author = "Kunze, {Kai Steven} and Paul Lukowicz",
year = "2007",
doi = "10.1109/ISWC.2007.4373794",
language = "English",
isbn = "9781424414536",
pages = "115--116",
booktitle = "Proceedings - Eleventh IEEE International Symposium on Wearable Computers, ISWC 2007",

}

TY - GEN

T1 - Using acceleration signatures from everyday activities for on-body device location

AU - Kunze, Kai Steven

AU - Lukowicz, Paul

PY - 2007

Y1 - 2007

N2 - This paper is part of an effort to facilitate wearable activity recognition using dynamically changing sets of sensors integrated in everyday appliances such as phones, PDAs, watches, headsets etc. A key issue that such systems have to address is the position of the devices on the body. In general each devices can be in a number of different locations (e.g. headset on the head or in on of many pockets). At the same time most activity recognition algorithms require fixed, known sensor positions. Previously we have shown on a small data set how to recognize a set of on-body locations during a walking motion using an accelerometer signal. We now extend the method to work during arbitrary activity. We verify it on a much larger data set with a total 9 hours from real life activity by three divers users ranging from a 70 year old housewife to a 28 year male student.

AB - This paper is part of an effort to facilitate wearable activity recognition using dynamically changing sets of sensors integrated in everyday appliances such as phones, PDAs, watches, headsets etc. A key issue that such systems have to address is the position of the devices on the body. In general each devices can be in a number of different locations (e.g. headset on the head or in on of many pockets). At the same time most activity recognition algorithms require fixed, known sensor positions. Previously we have shown on a small data set how to recognize a set of on-body locations during a walking motion using an accelerometer signal. We now extend the method to work during arbitrary activity. We verify it on a much larger data set with a total 9 hours from real life activity by three divers users ranging from a 70 year old housewife to a 28 year male student.

UR - http://www.scopus.com/inward/record.url?scp=41149120116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41149120116&partnerID=8YFLogxK

U2 - 10.1109/ISWC.2007.4373794

DO - 10.1109/ISWC.2007.4373794

M3 - Conference contribution

AN - SCOPUS:41149120116

SN - 9781424414536

SP - 115

EP - 116

BT - Proceedings - Eleventh IEEE International Symposium on Wearable Computers, ISWC 2007

ER -