A novel confidence-based multiclass boosting algorithm for mobile physical activity monitoring
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
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.
Physical activity monitoring; Activity recognition; Boosting; Multiclass classification; Personalization; Feasibility study
Control Engineering Signal Processing Other Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:liu:diva-112968DOI: 10.1007/s00779-014-0816-xISI: 000347292500012OAI: oai:DiVA.org:liu-112968DiVA: diva2:776056