A computationally light classification method for mobile wellness platforms

Ville Könönen, Mäntyjärvi Jani, Heidi Similä, Juha Pärkkä, Miikka Ermes

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

Abstract

The core of activity recognition in mobile wellness devices is a classification engine which maps observations from sensors to estimated classes. There exists a vast number of different classification algorithms that can be used for this purpose in the machine learning literature. Unfortunately, the computational and space requirements of these methods are often too high for the current mobile devices. In this paper we study a simple linear classifier and find, automatically with SFS and SFFS feature selection methods, a suitable set of features to be used with the classification method. The results show that the simple classifier performs comparable to more complex nonlinear k-Nearest Neighbor Classifier. This depicts great potential in implementing the classifier in small mobile wellness devices.
Original languageEnglish
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages1167-1170
ISBN (Print)978-1-4244-1814-5
DOIs
Publication statusPublished - 2008
MoE publication typeA4 Article in a conference publication
Event30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Personalized Healthcare through Technology - Vancouver, Canada
Duration: 20 Aug 200825 Aug 2008

Conference

Conference30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CountryCanada
CityVancouver
Period20/08/0825/08/08

Fingerprint

Classifiers
Mobile devices
Learning systems
Feature extraction
Engines
Sensors

Keywords

  • Wellness platforms
  • context recognition
  • pattern classification
  • activity recognition

Cite this

Könönen, V., Jani, M., Similä, H., Pärkkä, J., & Ermes, M. (2008). A computationally light classification method for mobile wellness platforms. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008 (pp. 1167-1170). Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/IEMBS.2008.4649369
Könönen, Ville ; Jani, Mäntyjärvi ; Similä, Heidi ; Pärkkä, Juha ; Ermes, Miikka. / A computationally light classification method for mobile wellness platforms. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008. Institute of Electrical and Electronic Engineers IEEE, 2008. pp. 1167-1170
@inproceedings{9b9164402d584993b99ecc0e795e1cb9,
title = "A computationally light classification method for mobile wellness platforms",
abstract = "The core of activity recognition in mobile wellness devices is a classification engine which maps observations from sensors to estimated classes. There exists a vast number of different classification algorithms that can be used for this purpose in the machine learning literature. Unfortunately, the computational and space requirements of these methods are often too high for the current mobile devices. In this paper we study a simple linear classifier and find, automatically with SFS and SFFS feature selection methods, a suitable set of features to be used with the classification method. The results show that the simple classifier performs comparable to more complex nonlinear k-Nearest Neighbor Classifier. This depicts great potential in implementing the classifier in small mobile wellness devices.",
keywords = "Wellness platforms, context recognition, pattern classification, activity recognition",
author = "Ville K{\"o}n{\"o}nen and M{\"a}ntyj{\"a}rvi Jani and Heidi Simil{\"a} and Juha P{\"a}rkk{\"a} and Miikka Ermes",
year = "2008",
doi = "10.1109/IEMBS.2008.4649369",
language = "English",
isbn = "978-1-4244-1814-5",
pages = "1167--1170",
booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - {"}Personalized Healthcare through Technology{"}. Vancouver, BC, Canada, 20 - 25 Aug. 2008",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Könönen, V, Jani, M, Similä, H, Pärkkä, J & Ermes, M 2008, A computationally light classification method for mobile wellness platforms. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008. Institute of Electrical and Electronic Engineers IEEE, pp. 1167-1170, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vancouver, Canada, 20/08/08. https://doi.org/10.1109/IEMBS.2008.4649369

A computationally light classification method for mobile wellness platforms. / Könönen, Ville; Jani, Mäntyjärvi; Similä, Heidi; Pärkkä, Juha; Ermes, Miikka.

Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008. Institute of Electrical and Electronic Engineers IEEE, 2008. p. 1167-1170.

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

TY - GEN

T1 - A computationally light classification method for mobile wellness platforms

AU - Könönen, Ville

AU - Jani, Mäntyjärvi

AU - Similä, Heidi

AU - Pärkkä, Juha

AU - Ermes, Miikka

PY - 2008

Y1 - 2008

N2 - The core of activity recognition in mobile wellness devices is a classification engine which maps observations from sensors to estimated classes. There exists a vast number of different classification algorithms that can be used for this purpose in the machine learning literature. Unfortunately, the computational and space requirements of these methods are often too high for the current mobile devices. In this paper we study a simple linear classifier and find, automatically with SFS and SFFS feature selection methods, a suitable set of features to be used with the classification method. The results show that the simple classifier performs comparable to more complex nonlinear k-Nearest Neighbor Classifier. This depicts great potential in implementing the classifier in small mobile wellness devices.

AB - The core of activity recognition in mobile wellness devices is a classification engine which maps observations from sensors to estimated classes. There exists a vast number of different classification algorithms that can be used for this purpose in the machine learning literature. Unfortunately, the computational and space requirements of these methods are often too high for the current mobile devices. In this paper we study a simple linear classifier and find, automatically with SFS and SFFS feature selection methods, a suitable set of features to be used with the classification method. The results show that the simple classifier performs comparable to more complex nonlinear k-Nearest Neighbor Classifier. This depicts great potential in implementing the classifier in small mobile wellness devices.

KW - Wellness platforms

KW - context recognition

KW - pattern classification

KW - activity recognition

U2 - 10.1109/IEMBS.2008.4649369

DO - 10.1109/IEMBS.2008.4649369

M3 - Conference article in proceedings

SN - 978-1-4244-1814-5

SP - 1167

EP - 1170

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Könönen V, Jani M, Similä H, Pärkkä J, Ermes M. A computationally light classification method for mobile wellness platforms. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". Vancouver, BC, Canada, 20 - 25 Aug. 2008. Institute of Electrical and Electronic Engineers IEEE. 2008. p. 1167-1170 https://doi.org/10.1109/IEMBS.2008.4649369