Human activity recognition for an intelligent knee orthosis

Diliana Rebelo; Christoph Amma; Hugo Gamboa; Tanja Schultz

Human activity recognition for an intelligent knee orthosis

Diliana Rebelo, Christoph Amma, Hugo Gamboa, Tanja Schultz

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

Abstract

This paper investigates the possibility to classify isolated human activities from biosignal sensors integrated into a knee orthosis. An intelligent orthosis that is capable to recognize its wearers activity would be able to adapt itself to the users situation for enhanced comfort. We use a setup with three modalities: accelerometry, electromyography and goniometry to measure leg motion and muscle activity of the wearer. We segment signals in motion primitives and apply Hidden Markov Models to classify these isolated motion primitives. We discriminate between seven activities like for example walking stairs and ascend or descend a hill. In a small user study we reach an average person-dependent accuracy of 98% and a person-independent accuracy of 79%.

Original language	English
Title of host publication	BIOSIGNALS 2013 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing
Pages	368-371
Number of pages	4
Publication status	Published - 2013
Event	International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2013 - Barcelona, Spain Duration: 11 Feb 2013 → 14 Feb 2013

Conference

Conference	International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2013
Country	Spain
City	Barcelona
Period	11/02/13 → 14/02/13

Keywords

Biosignals
Hidden Markov models
Human activity recognition
Signal-processing

Fingerprint Dive into the research topics of 'Human activity recognition for an intelligent knee orthosis'. Together they form a unique fingerprint.

Cite this

@inproceedings{3d3a91395729490daa75557812a0f71e,

title = "Human activity recognition for an intelligent knee orthosis",

abstract = "This paper investigates the possibility to classify isolated human activities from biosignal sensors integrated into a knee orthosis. An intelligent orthosis that is capable to recognize its wearers activity would be able to adapt itself to the users situation for enhanced comfort. We use a setup with three modalities: accelerometry, electromyography and goniometry to measure leg motion and muscle activity of the wearer. We segment signals in motion primitives and apply Hidden Markov Models to classify these isolated motion primitives. We discriminate between seven activities like for example walking stairs and ascend or descend a hill. In a small user study we reach an average person-dependent accuracy of 98% and a person-independent accuracy of 79%.",

keywords = "Biosignals, Hidden Markov models, Human activity recognition, Signal-processing",

author = "Diliana Rebelo and Christoph Amma and Hugo Gamboa and Tanja Schultz",

year = "2013",

language = "English",

isbn = "978-989856536-5",

pages = "368--371",

booktitle = "BIOSIGNALS 2013 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing",

note = "International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2013 ; Conference date: 11-02-2013 Through 14-02-2013",

}

TY - GEN

T1 - Human activity recognition for an intelligent knee orthosis

AU - Rebelo, Diliana

AU - Amma, Christoph

AU - Gamboa, Hugo

AU - Schultz, Tanja

PY - 2013

Y1 - 2013

N2 - This paper investigates the possibility to classify isolated human activities from biosignal sensors integrated into a knee orthosis. An intelligent orthosis that is capable to recognize its wearers activity would be able to adapt itself to the users situation for enhanced comfort. We use a setup with three modalities: accelerometry, electromyography and goniometry to measure leg motion and muscle activity of the wearer. We segment signals in motion primitives and apply Hidden Markov Models to classify these isolated motion primitives. We discriminate between seven activities like for example walking stairs and ascend or descend a hill. In a small user study we reach an average person-dependent accuracy of 98% and a person-independent accuracy of 79%.

AB - This paper investigates the possibility to classify isolated human activities from biosignal sensors integrated into a knee orthosis. An intelligent orthosis that is capable to recognize its wearers activity would be able to adapt itself to the users situation for enhanced comfort. We use a setup with three modalities: accelerometry, electromyography and goniometry to measure leg motion and muscle activity of the wearer. We segment signals in motion primitives and apply Hidden Markov Models to classify these isolated motion primitives. We discriminate between seven activities like for example walking stairs and ascend or descend a hill. In a small user study we reach an average person-dependent accuracy of 98% and a person-independent accuracy of 79%.

KW - Biosignals

KW - Hidden Markov models

KW - Human activity recognition

KW - Signal-processing

UR - http://www.scopus.com/inward/record.url?scp=84877964940&partnerID=8YFLogxK

UR - http://www.plux.info/files/ftp/docs/RebeloAmmaGamboaSchultz_Biosignals2013.pdf

M3 - Conference contribution

AN - SCOPUS:84877964940

SN - 978-989856536-5

SP - 368

EP - 371

BT - BIOSIGNALS 2013 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing

T2 - International Conference on Bio-Inspired Systems and Signal Processing, BIOSIGNALS 2013

Y2 - 11 February 2013 through 14 February 2013

ER -

Human activity recognition for an intelligent knee orthosis

Abstract

Conference

Keywords

Other files and links

Cite this