Adaptive Classification of Arbitrary Activities Through Hidden Markov Modeling with Automated Optimal Initialization

Chris T.M. Baten, Thijs Tromper, Leonie Laura Zeune

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

Abstract

An adaptive method for classification of arbitrary activities is presented that assesses continuously the activity in which a subject is engaged, thus providing contextual information facilitating the interpretation of any continuous data gathered from an (unsupervised) applied wearable robotics device and its bearer. Specifically the effect of a novel adaptive and fully automated initialization method using Potts energy functionals is discussed. Exemplary data suggests that this method very likely improves overall performance equally or better than more traditional methods. This includes state of the art methods based on segmental k-means initialization that do require substantial recurrent manual intervention.
Original languageEnglish
Title of host publicationWearable Robotics: Challenges and Trends
Subtitle of host publicationProceedings of the 2nd International Symposium on Wearable Robotics, WeRob2016, October 18-21, 2016, Segovia, Spain
EditorsJ. González-Vargas, J. Ibáñez , J. Contreras-Vidal , H. van der Kooij, J. Pons
PublisherSpringer
Pages367-371
ISBN (Electronic)978-3-319-46532-6
ISBN (Print)978-3-319-46531-9
DOIs
Publication statusPublished - 2017
Event2nd International Symposium on Wearable Robotics, WeRob 2016 - La Granja, Spain
Duration: 18 Oct 201621 Oct 2016
Conference number: 2
http://werob2016.org/

Publication series

NameBiosystems & Biorobotics
Volume16
ISSN (Print)2195-3562

Conference

Conference2nd International Symposium on Wearable Robotics, WeRob 2016
Abbreviated titleWeRob
CountrySpain
CityLa Granja
Period18/10/1621/10/16
Internet address

Fingerprint Dive into the research topics of 'Adaptive Classification of Arbitrary Activities Through Hidden Markov Modeling with Automated Optimal Initialization'. Together they form a unique fingerprint.

  • Cite this

    Baten, C. T. M., Tromper, T., & Zeune, L. L. (2017). Adaptive Classification of Arbitrary Activities Through Hidden Markov Modeling with Automated Optimal Initialization. In J. González-Vargas, J. Ibáñez , J. Contreras-Vidal , H. van der Kooij, & J. Pons (Eds.), Wearable Robotics: Challenges and Trends: Proceedings of the 2nd International Symposium on Wearable Robotics, WeRob2016, October 18-21, 2016, Segovia, Spain (pp. 367-371). (Biosystems & Biorobotics; Vol. 16). Springer. https://doi.org/10.1007/978-3-319-46532-6_60