Accurate activity recognition in a home setting

Tim van Kasteren; Athanasios Noulas; Gwenn Englebienne; Ben Kröse

doi:10.1145/1409635.1409637

Accurate activity recognition in a home setting

Tim van Kasteren
, Athanasios Noulas
, Gwenn Englebienne
, Ben Kröse

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

752 Citations (Scopus)

Abstract

A sensor system capable of automatically recognizing activities would allow many potential ubiquitous applications. In this paper, we present an easy to install sensor network and an accurate but inexpensive annotation method. A recorded dataset consisting of 28 days of sensor data and its annotation is described and made available to the community. Through a number of experiments we show how the hidden Markov model and conditional random fields perform in recognizing activities. We achieve a timeslice accuracy of 95.6% and a class accuracy of 79.4%.

Original language	English
Title of host publication	UbiComp08
Subtitle of host publication	Proceedings of the 10th International Conference on Ubiquitous Computing, Seoul, Korea, September 21-24, 2008
Publisher	ACM Publishing
Pages	1-9
ISBN (Print)	978-1-60558-136-1
DOIs	https://doi.org/10.1145/1409635.1409637
Publication status	Published - Nov 2008
Externally published	Yes
Event	10th International Conference on Ubiquitous Computing 2008 - Seoul, Korea, Republic of Duration: 21 Sept 2008 → 24 Sept 2008 Conference number: 10

Conference

Conference	10th International Conference on Ubiquitous Computing 2008
Country/Territory	Korea, Republic of
City	Seoul
Period	21/09/08 → 24/09/08

Keywords

n/a OA procedure

Access to Document

10.1145/1409635.1409637

Cite this

@inproceedings{49728d6b7e2f49879d84fc76e96120dc,

title = "Accurate activity recognition in a home setting",

abstract = "A sensor system capable of automatically recognizing activities would allow many potential ubiquitous applications. In this paper, we present an easy to install sensor network and an accurate but inexpensive annotation method. A recorded dataset consisting of 28 days of sensor data and its annotation is described and made available to the community. Through a number of experiments we show how the hidden Markov model and conditional random fields perform in recognizing activities. We achieve a timeslice accuracy of 95.6\% and a class accuracy of 79.4\%.",

keywords = "n/a OA procedure",

author = "\{van Kasteren\}, Tim and Athanasios Noulas and Gwenn Englebienne and Ben Kr{\"o}se",

year = "2008",

month = nov,

doi = "10.1145/1409635.1409637",

language = "English",

isbn = "978-1-60558-136-1",

pages = "1--9",

booktitle = "UbiComp08",

publisher = "ACM Publishing",

note = "10th International Conference on Ubiquitous Computing 2008 ; Conference date: 21-09-2008 Through 24-09-2008",

}

van Kasteren, T, Noulas, A, Englebienne, G & Kröse, B 2008, Accurate activity recognition in a home setting. in UbiComp08: Proceedings of the 10th International Conference on Ubiquitous Computing, Seoul, Korea, September 21-24, 2008. ACM Publishing, pp. 1-9, 10th International Conference on Ubiquitous Computing 2008, Seoul, Korea, Republic of, 21/09/08. https://doi.org/10.1145/1409635.1409637

Accurate activity recognition in a home setting. / van Kasteren, Tim; Noulas, Athanasios; Englebienne, Gwenn et al.
UbiComp08: Proceedings of the 10th International Conference on Ubiquitous Computing, Seoul, Korea, September 21-24, 2008. ACM Publishing, 2008. p. 1-9.

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

TY - GEN

T1 - Accurate activity recognition in a home setting

AU - van Kasteren, Tim

AU - Noulas, Athanasios

AU - Englebienne, Gwenn

AU - Kröse, Ben

N1 - Conference code: 10

PY - 2008/11

Y1 - 2008/11

N2 - A sensor system capable of automatically recognizing activities would allow many potential ubiquitous applications. In this paper, we present an easy to install sensor network and an accurate but inexpensive annotation method. A recorded dataset consisting of 28 days of sensor data and its annotation is described and made available to the community. Through a number of experiments we show how the hidden Markov model and conditional random fields perform in recognizing activities. We achieve a timeslice accuracy of 95.6% and a class accuracy of 79.4%.

AB - A sensor system capable of automatically recognizing activities would allow many potential ubiquitous applications. In this paper, we present an easy to install sensor network and an accurate but inexpensive annotation method. A recorded dataset consisting of 28 days of sensor data and its annotation is described and made available to the community. Through a number of experiments we show how the hidden Markov model and conditional random fields perform in recognizing activities. We achieve a timeslice accuracy of 95.6% and a class accuracy of 79.4%.

KW - n/a OA procedure

U2 - 10.1145/1409635.1409637

DO - 10.1145/1409635.1409637

M3 - Conference contribution

SN - 978-1-60558-136-1

SP - 1

EP - 9

BT - UbiComp08

PB - ACM Publishing

T2 - 10th International Conference on Ubiquitous Computing 2008

Y2 - 21 September 2008 through 24 September 2008

ER -

Accurate activity recognition in a home setting

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this