Show simple item record

dc.contributor.authorChowdhury, AK
dc.contributor.authorTjondronegoro, D
dc.contributor.authorChandran, V
dc.contributor.authorTrost, SG
dc.date.accessioned2020-01-14T05:15:36Z
dc.date.available2020-01-14T05:15:36Z
dc.date.issued2017
dc.identifier.issn0195-9131
dc.identifier.doi10.1249/MSS.0000000000001291
dc.identifier.urihttp://hdl.handle.net/10072/390244
dc.description.abstractPurpose To investigate whether the use of ensemble learning algorithms improve physical activity recognition accuracy compared to the single classifier algorithms, and to compare the classification accuracy achieved by three conventional ensemble machine learning methods (bagging, boosting, random forest) and a custom ensemble model comprising four algorithms commonly used for activity recognition (binary decision tree, k nearest neighbor, support vector machine, and neural network). Methods The study used three independent data sets that included wrist-worn accelerometer data. For each data set, a four-step classification framework consisting of data preprocessing, feature extraction, normalization and feature selection, and classifier training and testing was implemented. For the custom ensemble, decisions from the single classifiers were aggregated using three decision fusion methods: weighted majority vote, naïve Bayes combination, and behavior knowledge space combination. Classifiers were cross-validated using leave-one subject out cross-validation and compared on the basis of average F1 scores. Results In all three data sets, ensemble learning methods consistently outperformed the individual classifiers. Among the conventional ensemble methods, random forest models provided consistently high activity recognition; however, the custom ensemble model using weighted majority voting demonstrated the highest classification accuracy in two of the three data sets. Conclusions Combining multiple individual classifiers using conventional or custom ensemble learning methods can improve activity recognition accuracy from wrist-worn accelerometer data.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherLippincott Williams & Wilkins (LWW)
dc.relation.ispartofpagefrom1965
dc.relation.ispartofpageto1973
dc.relation.ispartofissue9
dc.relation.ispartofjournalMedicine and Science in Sports and Exercise
dc.relation.ispartofvolume49
dc.subject.fieldofresearchSports science and exercise
dc.subject.fieldofresearchMedical physiology
dc.subject.fieldofresearchHealth services and systems
dc.subject.fieldofresearchPublic health
dc.subject.fieldofresearchClinical sciences
dc.subject.fieldofresearchcode4207
dc.subject.fieldofresearchcode3208
dc.subject.fieldofresearchcode4203
dc.subject.fieldofresearchcode4206
dc.subject.fieldofresearchcode3202
dc.titleEnsemble Methods for Classification of Physical Activities from Wrist Accelerometry
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationChowdhury, AK; Tjondronegoro, D; Chandran, V; Trost, SG, Ensemble Methods for Classification of Physical Activities from Wrist Accelerometry, Medicine and Science in Sports and Exercise, 2017, 49 (9), pp. 1965-1973
dc.date.updated2020-01-14T05:12:47Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© 2017 LWW. This is a non-final version of an article published in final form in Medicine and Science in Sports and Exercise, 2017, Volume 49, Issue 9, p 1965–1973. Reproduced in accordance with the copyright policy of the publisher. Please refer to the journal link for access to the definitive, published version.
gro.hasfulltextFull Text
gro.griffith.authorTjondronegoro, Dian W.
gro.griffith.authorChandran, Vinod


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record