Detection of eating and drinking arm gestures using inertial body-worn sensors

O.D. Amft; H. Junker; G. Tröster

doi:10.1109/ISWC.2005.17

Detection of eating and drinking arm gestures using inertial body-worn sensors

O.D. Amft
, H. Junker
, G. Tröster

Signal Processing Systems

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

166 Citaten (Scopus)

604 Downloads (Pure)

Samenvatting

We propose a two-stage recognition system for detecting arm gestures related to human meal intake. Information retrieved from such a system can be used for automatic dietary monitoring in the domain of behavioural medicine. We demonstrate that arm gestures can be clustered and detected using inertial sensors. To validate our method, experimental results including 384 gestures from two subjects are presented. Using isolated discrimination based on HMMs an accuracy of 94% can be achieved. When spotting the gestures in continous movement data, an accuracy of up to 87% is reached. © 2005 IEEE.

Originele taal-2	Engels
Titel	Proceedings 9th IEEE International Symposium on Wearable Computers, ISWC 2005, 18 October 2005 through 21 October 2005, Osaka
Plaats van productie	Piscataway
Uitgeverij	Institute of Electrical and Electronics Engineers
Pagina's	160-163
ISBN van geprinte versie	0-7695-2419-2
DOI's	https://doi.org/10.1109/ISWC.2005.17
Status	Gepubliceerd - 2005

Duurzame ontwikkelingsdoelstellingen van de VN

Deze output draagt bij aan de volgende duurzame ontwikkelingsdoelstelling(en)

SDG 3 – Goede gezondheid en welzijn

Toegang tot document

10.1109/ISWC.2005.17

Metis248471Definitieve gepubliceerde versie, 166 KB

Citeer dit

@inproceedings{d630e4b387574ec884306b64ac51acaf,

title = "Detection of eating and drinking arm gestures using inertial body-worn sensors",

abstract = "We propose a two-stage recognition system for detecting arm gestures related to human meal intake. Information retrieved from such a system can be used for automatic dietary monitoring in the domain of behavioural medicine. We demonstrate that arm gestures can be clustered and detected using inertial sensors. To validate our method, experimental results including 384 gestures from two subjects are presented. Using isolated discrimination based on HMMs an accuracy of 94\% can be achieved. When spotting the gestures in continous movement data, an accuracy of up to 87\% is reached. {\textcopyright} 2005 IEEE.",

author = "O.D. Amft and H. Junker and G. Tr{\"o}ster",

year = "2005",

doi = "10.1109/ISWC.2005.17",

language = "English",

isbn = "0-7695-2419-2",

pages = "160--163",

booktitle = "Proceedings 9th IEEE International Symposium on Wearable Computers, ISWC 2005, 18 October 2005 through 21 October 2005, Osaka",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Detection of eating and drinking arm gestures using inertial body-worn sensors. / Amft, O.D.; Junker, H.; Tröster, G.
Proceedings 9th IEEE International Symposium on Wearable Computers, ISWC 2005, 18 October 2005 through 21 October 2005, Osaka. Piscataway: Institute of Electrical and Electronics Engineers, 2005. blz. 160-163.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

TY - GEN

T1 - Detection of eating and drinking arm gestures using inertial body-worn sensors

AU - Amft, O.D.

AU - Junker, H.

AU - Tröster, G.

PY - 2005

Y1 - 2005

N2 - We propose a two-stage recognition system for detecting arm gestures related to human meal intake. Information retrieved from such a system can be used for automatic dietary monitoring in the domain of behavioural medicine. We demonstrate that arm gestures can be clustered and detected using inertial sensors. To validate our method, experimental results including 384 gestures from two subjects are presented. Using isolated discrimination based on HMMs an accuracy of 94% can be achieved. When spotting the gestures in continous movement data, an accuracy of up to 87% is reached. © 2005 IEEE.

AB - We propose a two-stage recognition system for detecting arm gestures related to human meal intake. Information retrieved from such a system can be used for automatic dietary monitoring in the domain of behavioural medicine. We demonstrate that arm gestures can be clustered and detected using inertial sensors. To validate our method, experimental results including 384 gestures from two subjects are presented. Using isolated discrimination based on HMMs an accuracy of 94% can be achieved. When spotting the gestures in continous movement data, an accuracy of up to 87% is reached. © 2005 IEEE.

U2 - 10.1109/ISWC.2005.17

DO - 10.1109/ISWC.2005.17

M3 - Conference contribution

SN - 0-7695-2419-2

SP - 160

EP - 163

BT - Proceedings 9th IEEE International Symposium on Wearable Computers, ISWC 2005, 18 October 2005 through 21 October 2005, Osaka

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Detection of eating and drinking arm gestures using inertial body-worn sensors

Samenvatting

Duurzame ontwikkelingsdoelstellingen van de VN

Toegang tot document

Vingerafdruk

Citeer dit