Change search
ReferencesLink to record
Permanent link

Direct link
A novel confidence-based multiclass boosting algorithm for mobile physical activity monitoring
University of Passau, Passau, Germany.
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology. Swedish Def Res Agcy FOI, Dept Sensor & EW Syst, Linkoping, Sweden.ORCID iD: 0000-0002-1971-4295
German Research Center for Artificial Intelligence, Kaiserslautern, Germany.
2015 (English)In: Personal and Ubiquitous Computing, ISSN 1617-4909, E-ISSN 1617-4917, Vol. 19, no 1, 105-121 p.Article in journal (Refereed) Published
Abstract [en]

This paper addresses one of the main challenges in physical activity monitoring, as indicated by recent benchmark results: The difficulty of the complex classification problems exceeds the potential of existing classifiers. Therefore, this paper proposes the ConfAdaBoost.M1 algorithm. This algorithm is a variant of the AdaBoost.M1 that incorporates well-established ideas for confidence-based boosting. ConfAdaBoost.M1 is compared to the most commonly used boosting methods using benchmark datasets from the UCI machine learning repository.  Moreover, it is evaluated on an activity recognition and an intensity estimation problem, including a large number of physical activities from the recently released PAMAP2 dataset. The presented results indicate that the proposed ConfAdaBoost.M1 algorithm significantly improves the classification performance on most of the evaluated datasets, especially for larger and more complex classification tasks. Finally, two empirical studies are designed and carried out to investigate the feasibility of ConfAdaBoost.M1 for physical activity monitoring applications in mobile systems.

Place, publisher, year, edition, pages
2015. Vol. 19, no 1, 105-121 p.
Keyword [en]
Physical activity monitoring; Activity recognition; Boosting; Multiclass classification; Personalization; Feasibility study
National Category
Control Engineering Signal Processing Other Electrical Engineering, Electronic Engineering, Information Engineering
URN: urn:nbn:se:liu:diva-112968DOI: 10.1007/s00779-014-0816-xISI: 000347292500012OAI: diva2:776056
Available from: 2015-01-06 Created: 2015-01-06 Last updated: 2015-09-22Bibliographically approved

Open Access in DiVA

fulltext(467 kB)61 downloads
File information
File name FULLTEXT01.pdfFile size 467 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Hendeby, Gustaf
By organisation
Automatic ControlThe Institute of Technology
In the same journal
Personal and Ubiquitous Computing
Control EngineeringSignal ProcessingOther Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 61 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 340 hits
ReferencesLink to record
Permanent link

Direct link