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

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

doi:10.1007/978-3-319-46532-6_60

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

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

Medical Cell Biophysics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Downloads (Pure)

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 language	English
Title of host publication	Wearable Robotics: Challenges and Trends
Subtitle of host publication	Proceedings of the 2nd International Symposium on Wearable Robotics, WeRob2016, October 18-21, 2016, Segovia, Spain
Editors	J. González-Vargas, J. Ibáñez , J. Contreras-Vidal , H. van der Kooij, J. Pons
Publisher	Springer
Pages	367-371
ISBN (Electronic)	978-3-319-46532-6
ISBN (Print)	978-3-319-46531-9
DOIs	https://doi.org/10.1007/978-3-319-46532-6_60
Publication status	Published - 2017
Event	2nd International Symposium on Wearable Robotics, WeRob 2016 - La Granja, Spain Duration: 18 Oct 2016 → 21 Oct 2016 Conference number: 2 http://werob2016.org/

Publication series

Name	Biosystems & Biorobotics
Volume	16
ISSN (Print)	2195-3562

Conference

Conference	2nd International Symposium on Wearable Robotics, WeRob 2016
Abbreviated title	WeRob
Country/Territory	Spain
City	La Granja
Period	18/10/16 → 21/10/16
Internet address	http://werob2016.org/

Access to Document

10.1007/978-3-319-46532-6_60

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

Baten, Chris T.M. ; Tromper, Thijs ; Zeune, Leonie Laura. / Adaptive Classification of Arbitrary Activities Through Hidden Markov Modeling with Automated Optimal Initialization. Wearable Robotics: Challenges and Trends: Proceedings of the 2nd International Symposium on Wearable Robotics, WeRob2016, October 18-21, 2016, Segovia, Spain. editor / J. González-Vargas ; J. Ibáñez ; J. Contreras-Vidal ; H. van der Kooij ; J. Pons. Springer, 2017. pp. 367-371 (Biosystems & Biorobotics).

@inproceedings{3bfb9e30ff1e466b95341b6d6ea4727e,

title = "Adaptive Classification of Arbitrary Activities Through Hidden Markov Modeling with Automated Optimal Initialization",

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.",

author = "Baten, {Chris T.M.} and Thijs Tromper and Zeune, {Leonie Laura}",

year = "2017",

doi = "10.1007/978-3-319-46532-6_60",

language = "English",

isbn = "978-3-319-46531-9",

series = "Biosystems & Biorobotics",

publisher = "Springer",

pages = "367--371",

editor = "J. Gonz{\'a}lez-Vargas and {Ib{\'a}{\~n}ez }, J. and {Contreras-Vidal }, J. and {van der Kooij}, H. and J. Pons",

booktitle = "Wearable Robotics: Challenges and Trends",

address = "Germany",

note = "2nd International Symposium on Wearable Robotics, WeRob 2016, WeRob ; Conference date: 18-10-2016 Through 21-10-2016",

url = "http://werob2016.org/",

}

Baten, CTM, Tromper, T & Zeune, LL 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. Biosystems & Biorobotics, vol. 16, Springer, pp. 367-371, 2nd International Symposium on Wearable Robotics, WeRob 2016, La Granja, Spain, 18/10/16. https://doi.org/10.1007/978-3-319-46532-6_60

Adaptive Classification of Arbitrary Activities Through Hidden Markov Modeling with Automated Optimal Initialization. / Baten, Chris T.M.; Tromper, Thijs; Zeune, Leonie Laura.
Wearable Robotics: Challenges and Trends: Proceedings of the 2nd International Symposium on Wearable Robotics, WeRob2016, October 18-21, 2016, Segovia, Spain. ed. / J. González-Vargas; J. Ibáñez ; J. Contreras-Vidal ; H. van der Kooij; J. Pons. Springer, 2017. p. 367-371 (Biosystems & Biorobotics; Vol. 16).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Adaptive Classification of Arbitrary Activities Through Hidden Markov Modeling with Automated Optimal Initialization

AU - Baten, Chris T.M.

AU - Tromper, Thijs

AU - Zeune, Leonie Laura

N1 - Conference code: 2

PY - 2017

Y1 - 2017

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-319-46532-6_60

DO - 10.1007/978-3-319-46532-6_60

M3 - Conference contribution

SN - 978-3-319-46531-9

T3 - Biosystems & Biorobotics

SP - 367

EP - 371

BT - Wearable Robotics: Challenges and Trends

A2 - González-Vargas, J.

A2 - Ibáñez , J.

A2 - Contreras-Vidal , J.

A2 - van der Kooij, H.

A2 - Pons, J.

PB - Springer

T2 - 2nd International Symposium on Wearable Robotics, WeRob 2016

Y2 - 18 October 2016 through 21 October 2016

ER -

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

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

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this