Sensor placement variations in wearable activity recognition

Kai Steven Kunze, Paul Lukowicz

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

This article explores how placement variations in user-carried electronic appliances influence human action recognition and how such influence can be mitigated. The authors categorize possible variations into three classes: placement on different body parts (such as a jacket pocket versus a hip holster versus a trouser pocket), small displacement within a given coarse location (such as a device shifting in a pocket), and different orientations. For each of these variations, they present a systematic evaluation of the impact on human action recognition and give an overview of possible approaches to deal with them. They conclude with a detailed practical example on how to compensate for on-body placements variations that builds on an extension of their previous work. This article is part of a special issue on wearable computing.

Original languageEnglish
Article number6926690
Pages (from-to)32-41
Number of pages10
JournalIEEE Pervasive Computing
Volume13
Issue number4
DOIs
Publication statusPublished - 2014 Oct 1
Externally publishedYes

Fingerprint

Sensors

Keywords

  • activity recognition
  • inertial motion sensors
  • mobile
  • pervasive computing
  • placement variations
  • wearables

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Sensor placement variations in wearable activity recognition. / Kunze, Kai Steven; Lukowicz, Paul.

In: IEEE Pervasive Computing, Vol. 13, No. 4, 6926690, 01.10.2014, p. 32-41.

Research output: Contribution to journalArticle

@article{5b25273776cc4dcd91d9cff12703ba53,
title = "Sensor placement variations in wearable activity recognition",
abstract = "This article explores how placement variations in user-carried electronic appliances influence human action recognition and how such influence can be mitigated. The authors categorize possible variations into three classes: placement on different body parts (such as a jacket pocket versus a hip holster versus a trouser pocket), small displacement within a given coarse location (such as a device shifting in a pocket), and different orientations. For each of these variations, they present a systematic evaluation of the impact on human action recognition and give an overview of possible approaches to deal with them. They conclude with a detailed practical example on how to compensate for on-body placements variations that builds on an extension of their previous work. This article is part of a special issue on wearable computing.",
keywords = "activity recognition, inertial motion sensors, mobile, pervasive computing, placement variations, wearables",
author = "Kunze, {Kai Steven} and Paul Lukowicz",
year = "2014",
month = "10",
day = "1",
doi = "10.1109/MPRV.2014.73",
language = "English",
volume = "13",
pages = "32--41",
journal = "IEEE Pervasive Computing",
issn = "1536-1268",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Sensor placement variations in wearable activity recognition

AU - Kunze, Kai Steven

AU - Lukowicz, Paul

PY - 2014/10/1

Y1 - 2014/10/1

N2 - This article explores how placement variations in user-carried electronic appliances influence human action recognition and how such influence can be mitigated. The authors categorize possible variations into three classes: placement on different body parts (such as a jacket pocket versus a hip holster versus a trouser pocket), small displacement within a given coarse location (such as a device shifting in a pocket), and different orientations. For each of these variations, they present a systematic evaluation of the impact on human action recognition and give an overview of possible approaches to deal with them. They conclude with a detailed practical example on how to compensate for on-body placements variations that builds on an extension of their previous work. This article is part of a special issue on wearable computing.

AB - This article explores how placement variations in user-carried electronic appliances influence human action recognition and how such influence can be mitigated. The authors categorize possible variations into three classes: placement on different body parts (such as a jacket pocket versus a hip holster versus a trouser pocket), small displacement within a given coarse location (such as a device shifting in a pocket), and different orientations. For each of these variations, they present a systematic evaluation of the impact on human action recognition and give an overview of possible approaches to deal with them. They conclude with a detailed practical example on how to compensate for on-body placements variations that builds on an extension of their previous work. This article is part of a special issue on wearable computing.

KW - activity recognition

KW - inertial motion sensors

KW - mobile

KW - pervasive computing

KW - placement variations

KW - wearables

UR - http://www.scopus.com/inward/record.url?scp=84908231186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908231186&partnerID=8YFLogxK

U2 - 10.1109/MPRV.2014.73

DO - 10.1109/MPRV.2014.73

M3 - Article

VL - 13

SP - 32

EP - 41

JO - IEEE Pervasive Computing

JF - IEEE Pervasive Computing

SN - 1536-1268

IS - 4

M1 - 6926690

ER -