3D accelerometer features' differences between young and older people, and between lower back and neck band sensor placements

Juho Merilahti, Miikka Ermes

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

1 Citation (Scopus)

Abstract

In earlier studies, we have developed activity recognition algorithm which are based on features calculated from 3D accelerometer sensor data placed on a hip, close to the centre of mass. In the development subjects have been young adults. Now we study are the input features of the algorithm generalized for older adults and for different sensor placement; in this case worn as a necklace. From the 3D accelerometer resultant magnitude the following features were calculated for each second: spectral entropy, peak frequency, power and range. The frequency domain features behaved in a relatively stable manner in the set-ups but the time domain features differed significantly from statistical and algorithm perspective between the set-ups. By developing time domain features to be more inter-individual independent would be beneficial for activity recognition algorithms
Original languageEnglish
Title of host publicationProceedings
Subtitle of host publicationAnnual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages7885-7887
ISBN (Electronic)978-1-4244-4122-8
ISBN (Print)978-1-4244-4121-1
DOIs
Publication statusPublished - 2011
MoE publication typeA4 Article in a conference publication
Event33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society: EMBC 2011 - Boston, United States
Duration: 30 Aug 20113 Sep 2011

Conference

Conference33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CountryUnited States
CityBoston
Period30/08/113/09/11

Fingerprint

Accelerometers
Sensors
Entropy

Keywords

  • Accelerometer
  • context recognition
  • older people

Cite this

Merilahti, J., & Ermes, M. (2011). 3D accelerometer features' differences between young and older people, and between lower back and neck band sensor placements. In Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 (pp. 7885-7887). Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/IEMBS.2011.6091944
Merilahti, Juho ; Ermes, Miikka. / 3D accelerometer features' differences between young and older people, and between lower back and neck band sensor placements. Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. Institute of Electrical and Electronic Engineers IEEE, 2011. pp. 7885-7887
@inproceedings{c4dd28d68c6248749cc56f1e15af68f4,
title = "3D accelerometer features' differences between young and older people, and between lower back and neck band sensor placements",
abstract = "In earlier studies, we have developed activity recognition algorithm which are based on features calculated from 3D accelerometer sensor data placed on a hip, close to the centre of mass. In the development subjects have been young adults. Now we study are the input features of the algorithm generalized for older adults and for different sensor placement; in this case worn as a necklace. From the 3D accelerometer resultant magnitude the following features were calculated for each second: spectral entropy, peak frequency, power and range. The frequency domain features behaved in a relatively stable manner in the set-ups but the time domain features differed significantly from statistical and algorithm perspective between the set-ups. By developing time domain features to be more inter-individual independent would be beneficial for activity recognition algorithms",
keywords = "Accelerometer, context recognition, older people",
author = "Juho Merilahti and Miikka Ermes",
note = "Project code: 35479",
year = "2011",
doi = "10.1109/IEMBS.2011.6091944",
language = "English",
isbn = "978-1-4244-4121-1",
pages = "7885--7887",
booktitle = "Proceedings",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Merilahti, J & Ermes, M 2011, 3D accelerometer features' differences between young and older people, and between lower back and neck band sensor placements. in Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. Institute of Electrical and Electronic Engineers IEEE, pp. 7885-7887, 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Boston, United States, 30/08/11. https://doi.org/10.1109/IEMBS.2011.6091944

3D accelerometer features' differences between young and older people, and between lower back and neck band sensor placements. / Merilahti, Juho; Ermes, Miikka.

Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. Institute of Electrical and Electronic Engineers IEEE, 2011. p. 7885-7887.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - 3D accelerometer features' differences between young and older people, and between lower back and neck band sensor placements

AU - Merilahti, Juho

AU - Ermes, Miikka

N1 - Project code: 35479

PY - 2011

Y1 - 2011

N2 - In earlier studies, we have developed activity recognition algorithm which are based on features calculated from 3D accelerometer sensor data placed on a hip, close to the centre of mass. In the development subjects have been young adults. Now we study are the input features of the algorithm generalized for older adults and for different sensor placement; in this case worn as a necklace. From the 3D accelerometer resultant magnitude the following features were calculated for each second: spectral entropy, peak frequency, power and range. The frequency domain features behaved in a relatively stable manner in the set-ups but the time domain features differed significantly from statistical and algorithm perspective between the set-ups. By developing time domain features to be more inter-individual independent would be beneficial for activity recognition algorithms

AB - In earlier studies, we have developed activity recognition algorithm which are based on features calculated from 3D accelerometer sensor data placed on a hip, close to the centre of mass. In the development subjects have been young adults. Now we study are the input features of the algorithm generalized for older adults and for different sensor placement; in this case worn as a necklace. From the 3D accelerometer resultant magnitude the following features were calculated for each second: spectral entropy, peak frequency, power and range. The frequency domain features behaved in a relatively stable manner in the set-ups but the time domain features differed significantly from statistical and algorithm perspective between the set-ups. By developing time domain features to be more inter-individual independent would be beneficial for activity recognition algorithms

KW - Accelerometer

KW - context recognition

KW - older people

U2 - 10.1109/IEMBS.2011.6091944

DO - 10.1109/IEMBS.2011.6091944

M3 - Conference article in proceedings

SN - 978-1-4244-4121-1

SP - 7885

EP - 7887

BT - Proceedings

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Merilahti J, Ermes M. 3D accelerometer features' differences between young and older people, and between lower back and neck band sensor placements. In Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011. Institute of Electrical and Electronic Engineers IEEE. 2011. p. 7885-7887 https://doi.org/10.1109/IEMBS.2011.6091944