Monitoring of human activities using a trainable system based on Hidden Markov modelling technology

R.G.V. Wassink; Christian T.M. Baten; Petrus H. Veltink; Raymond N.J. Veldhuis; Jan Hindrik Smeding

doi:10.1016/j.gaitpost.2006.11.076

Monitoring of human activities using a trainable system based on Hidden Markov modelling technology

R.G.V. Wassink, Christian T.M. Baten, Petrus H. Veltink, Raymond N.J. Veldhuis, Jan Hindrik Smeding

Research output: Contribution to journal › Article › Academic › peer-review

6 Downloads (Pure)

Abstract

In order to facilitate proper interpretation of long measurements involving large data sets a novel data classifier was implemented and tested. The method is based on Hidden Markov modelling technique, the basic tool in speech recognition. Tests performed used motion data and yielded a activity recognition score of up to 95.5 ± 1.9% on a set of 8 different human activities.

Original language	Undefined
Pages (from-to)	S109-S110
Number of pages	2
Journal	Gait & posture
Volume	24
Issue number	Suppl.
DOIs	https://doi.org/10.1016/j.gaitpost.2006.11.076
Publication status	Published - Dec 2006

Keywords

EWI-19915
human activity monitoring
IR-61429
HMM
SCS-Safety

Access to Document

10.1016/j.gaitpost.2006.11.076

http://eprints.eemcs.utwente.nl/secure2/19915/01/Wassink06_Monitoring_of_human_activities_using_a_trainable_system_based_on_Hidden_Markov_modelling_technology.pdf

Cite this

@article{ce3cf95cd7684789835177d250a03c0b,

title = "Monitoring of human activities using a trainable system based on Hidden Markov modelling technology",

abstract = "In order to facilitate proper interpretation of long measurements involving large data sets a novel data classifier was implemented and tested. The method is based on Hidden Markov modelling technique, the basic tool in speech recognition. Tests performed used motion data and yielded a activity recognition score of up to 95.5 ± 1.9% on a set of 8 different human activities.",

keywords = "EWI-19915, human activity monitoring, IR-61429, HMM, SCS-Safety",

author = "R.G.V. Wassink and Baten, {Christian T.M.} and Veltink, {Petrus H.} and Veldhuis, {Raymond N.J.} and Smeding, {Jan Hindrik}",

year = "2006",

month = dec,

doi = "10.1016/j.gaitpost.2006.11.076",

language = "Undefined",

volume = "24",

pages = "S109--S110",

journal = "Gait & posture",

issn = "0966-6362",

publisher = "Elsevier",

number = "Suppl.",

}

TY - JOUR

T1 - Monitoring of human activities using a trainable system based on Hidden Markov modelling technology

AU - Wassink, R.G.V.

AU - Baten, Christian T.M.

AU - Veltink, Petrus H.

AU - Veldhuis, Raymond N.J.

AU - Smeding, Jan Hindrik

PY - 2006/12

Y1 - 2006/12

N2 - In order to facilitate proper interpretation of long measurements involving large data sets a novel data classifier was implemented and tested. The method is based on Hidden Markov modelling technique, the basic tool in speech recognition. Tests performed used motion data and yielded a activity recognition score of up to 95.5 ± 1.9% on a set of 8 different human activities.

AB - In order to facilitate proper interpretation of long measurements involving large data sets a novel data classifier was implemented and tested. The method is based on Hidden Markov modelling technique, the basic tool in speech recognition. Tests performed used motion data and yielded a activity recognition score of up to 95.5 ± 1.9% on a set of 8 different human activities.

KW - EWI-19915

KW - human activity monitoring

KW - IR-61429

KW - HMM

KW - SCS-Safety

U2 - 10.1016/j.gaitpost.2006.11.076

DO - 10.1016/j.gaitpost.2006.11.076

M3 - Article

SN - 0966-6362

VL - 24

SP - S109-S110

JO - Gait & posture

JF - Gait & posture

IS - Suppl.

ER -