Towards dynamically configurable context recognition systems

Kai Steven Kunze, David Bannach

研究成果: Conference contribution

1 引用 (Scopus)

抄録

General representation, abstraction and exchange definitions are crucial for dynamically configurable context recognition. However, to evaluate potential definitions, suitable standard datasets are needed. This paper presents our effort to create and maintain large scale, multimodal standard datasets for context recognition research. We ourselves used these datasets in previous research to deal with placement effects and presented low-level sensor abstractions in motion based on-body sensing. Researchers, conducting novel data collections, can rely on the toolchain and the the low-level sensor abstractions summarized in this paper. Additionally, they can draw from our experiences developing and conducting context recognition experiments. Our toolchain is already a valuable rapid prototyping tool. Still, we plan to extend it to crowd-based sensing, enabling the general public to gather context data, learn more about their lives and contribute to context recognition research. Applying higher level context reasoning on the gathered context data is a obvious extension to our work.

元の言語English
ホスト出版物のタイトルActivity Context Representation: Techniques and Languages - Papers from the 2012 AAAI Workshop, Technical Report
ページ60-64
ページ数5
WS-12-05
出版物ステータスPublished - 2012
外部発表Yes
イベント2012 AAAI Workshop - Toronto, ON, Canada
継続期間: 2012 7 232012 7 23

Other

Other2012 AAAI Workshop
Canada
Toronto, ON
期間12/7/2312/7/23

Fingerprint

Sensors
Rapid prototyping
Experiments

ASJC Scopus subject areas

  • Engineering(all)

これを引用

Kunze, K. S., & Bannach, D. (2012). Towards dynamically configurable context recognition systems. : Activity Context Representation: Techniques and Languages - Papers from the 2012 AAAI Workshop, Technical Report (巻 WS-12-05, pp. 60-64)

Towards dynamically configurable context recognition systems. / Kunze, Kai Steven; Bannach, David.

Activity Context Representation: Techniques and Languages - Papers from the 2012 AAAI Workshop, Technical Report. 巻 WS-12-05 2012. p. 60-64.

研究成果: Conference contribution

Kunze, KS & Bannach, D 2012, Towards dynamically configurable context recognition systems. : Activity Context Representation: Techniques and Languages - Papers from the 2012 AAAI Workshop, Technical Report. 巻. WS-12-05, pp. 60-64, 2012 AAAI Workshop, Toronto, ON, Canada, 12/7/23.
Kunze KS, Bannach D. Towards dynamically configurable context recognition systems. : Activity Context Representation: Techniques and Languages - Papers from the 2012 AAAI Workshop, Technical Report. 巻 WS-12-05. 2012. p. 60-64
Kunze, Kai Steven ; Bannach, David. / Towards dynamically configurable context recognition systems. Activity Context Representation: Techniques and Languages - Papers from the 2012 AAAI Workshop, Technical Report. 巻 WS-12-05 2012. pp. 60-64
@inproceedings{c8fe3785476849d8893cdb7650f8141a,
title = "Towards dynamically configurable context recognition systems",
abstract = "General representation, abstraction and exchange definitions are crucial for dynamically configurable context recognition. However, to evaluate potential definitions, suitable standard datasets are needed. This paper presents our effort to create and maintain large scale, multimodal standard datasets for context recognition research. We ourselves used these datasets in previous research to deal with placement effects and presented low-level sensor abstractions in motion based on-body sensing. Researchers, conducting novel data collections, can rely on the toolchain and the the low-level sensor abstractions summarized in this paper. Additionally, they can draw from our experiences developing and conducting context recognition experiments. Our toolchain is already a valuable rapid prototyping tool. Still, we plan to extend it to crowd-based sensing, enabling the general public to gather context data, learn more about their lives and contribute to context recognition research. Applying higher level context reasoning on the gathered context data is a obvious extension to our work.",
author = "Kunze, {Kai Steven} and David Bannach",
year = "2012",
language = "English",
isbn = "9781577355700",
volume = "WS-12-05",
pages = "60--64",
booktitle = "Activity Context Representation: Techniques and Languages - Papers from the 2012 AAAI Workshop, Technical Report",

}

TY - GEN

T1 - Towards dynamically configurable context recognition systems

AU - Kunze, Kai Steven

AU - Bannach, David

PY - 2012

Y1 - 2012

N2 - General representation, abstraction and exchange definitions are crucial for dynamically configurable context recognition. However, to evaluate potential definitions, suitable standard datasets are needed. This paper presents our effort to create and maintain large scale, multimodal standard datasets for context recognition research. We ourselves used these datasets in previous research to deal with placement effects and presented low-level sensor abstractions in motion based on-body sensing. Researchers, conducting novel data collections, can rely on the toolchain and the the low-level sensor abstractions summarized in this paper. Additionally, they can draw from our experiences developing and conducting context recognition experiments. Our toolchain is already a valuable rapid prototyping tool. Still, we plan to extend it to crowd-based sensing, enabling the general public to gather context data, learn more about their lives and contribute to context recognition research. Applying higher level context reasoning on the gathered context data is a obvious extension to our work.

AB - General representation, abstraction and exchange definitions are crucial for dynamically configurable context recognition. However, to evaluate potential definitions, suitable standard datasets are needed. This paper presents our effort to create and maintain large scale, multimodal standard datasets for context recognition research. We ourselves used these datasets in previous research to deal with placement effects and presented low-level sensor abstractions in motion based on-body sensing. Researchers, conducting novel data collections, can rely on the toolchain and the the low-level sensor abstractions summarized in this paper. Additionally, they can draw from our experiences developing and conducting context recognition experiments. Our toolchain is already a valuable rapid prototyping tool. Still, we plan to extend it to crowd-based sensing, enabling the general public to gather context data, learn more about their lives and contribute to context recognition research. Applying higher level context reasoning on the gathered context data is a obvious extension to our work.

UR - http://www.scopus.com/inward/record.url?scp=84875591255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875591255&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84875591255

SN - 9781577355700

VL - WS-12-05

SP - 60

EP - 64

BT - Activity Context Representation: Techniques and Languages - Papers from the 2012 AAAI Workshop, Technical Report

ER -