Towards activity recognition of learners by kinect

Takuya Kamizono; Hiromichi Abe; Kensuke Baba; Shigeru Takano; Kazuaki Murakami

doi:10.1109/IIAI-AAI.2014.45

Towards activity recognition of learners by kinect

Takuya Kamizono, Hiromichi Abe, Kensuke Baba, Shigeru Takano, Kazuaki Murakami

Research output: Contribution to conference › Paper › peer-review

5 Citations (Scopus)

Abstract

Understanding the states of learners at a lecture is useful for improving the quality of the lecture. A video camera with an infrared sensor Kinect has been widely studied and proved to be useful for some kinds of activity recognition. However, learners in a lecture usually do not act with large moving. This paper evaluates Kinect for use of activity recognition of learners. The authors considered four activities for detecting states of a learner, and collected the data with the activities by a Kinect. They applied K-nearest neighbor algorithm to the collected data and obtained the accuracy 0.936 of the activity recognition. The result shows that Kinect is applicable also to the activity recognition of learners in a lecture.

Original language	English
Pages	177-180
Number of pages	4
DOIs	https://doi.org/10.1109/IIAI-AAI.2014.45
Publication status	Published - Sep 29 2014
Externally published	Yes
Event	3rd IIAI International Conference on Advanced Applied Informatics, IIAI-AAI 2014 - Kitakyushu, Japan Duration: Aug 31 2014 → Sep 4 2014

Conference

Conference	3rd IIAI International Conference on Advanced Applied Informatics, IIAI-AAI 2014
Country/Territory	Japan
City	Kitakyushu
Period	8/31/14 → 9/4/14

ASJC Scopus subject areas

Information Systems

Access to Document

10.1109/IIAI-AAI.2014.45

Cite this

@conference{bf054cf86318428a9388acaf18d2dff0,

title = "Towards activity recognition of learners by kinect",

abstract = "Understanding the states of learners at a lecture is useful for improving the quality of the lecture. A video camera with an infrared sensor Kinect has been widely studied and proved to be useful for some kinds of activity recognition. However, learners in a lecture usually do not act with large moving. This paper evaluates Kinect for use of activity recognition of learners. The authors considered four activities for detecting states of a learner, and collected the data with the activities by a Kinect. They applied K-nearest neighbor algorithm to the collected data and obtained the accuracy 0.936 of the activity recognition. The result shows that Kinect is applicable also to the activity recognition of learners in a lecture.",

author = "Takuya Kamizono and Hiromichi Abe and Kensuke Baba and Shigeru Takano and Kazuaki Murakami",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 3rd IIAI International Conference on Advanced Applied Informatics, IIAI-AAI 2014 ; Conference date: 31-08-2014 Through 04-09-2014",

year = "2014",

month = sep,

day = "29",

doi = "10.1109/IIAI-AAI.2014.45",

language = "English",

pages = "177--180",

}

TY - CONF

T1 - Towards activity recognition of learners by kinect

AU - Kamizono, Takuya

AU - Abe, Hiromichi

AU - Baba, Kensuke

AU - Takano, Shigeru

AU - Murakami, Kazuaki

PY - 2014/9/29

Y1 - 2014/9/29

N2 - Understanding the states of learners at a lecture is useful for improving the quality of the lecture. A video camera with an infrared sensor Kinect has been widely studied and proved to be useful for some kinds of activity recognition. However, learners in a lecture usually do not act with large moving. This paper evaluates Kinect for use of activity recognition of learners. The authors considered four activities for detecting states of a learner, and collected the data with the activities by a Kinect. They applied K-nearest neighbor algorithm to the collected data and obtained the accuracy 0.936 of the activity recognition. The result shows that Kinect is applicable also to the activity recognition of learners in a lecture.

AB - Understanding the states of learners at a lecture is useful for improving the quality of the lecture. A video camera with an infrared sensor Kinect has been widely studied and proved to be useful for some kinds of activity recognition. However, learners in a lecture usually do not act with large moving. This paper evaluates Kinect for use of activity recognition of learners. The authors considered four activities for detecting states of a learner, and collected the data with the activities by a Kinect. They applied K-nearest neighbor algorithm to the collected data and obtained the accuracy 0.936 of the activity recognition. The result shows that Kinect is applicable also to the activity recognition of learners in a lecture.

UR - http://www.scopus.com/inward/record.url?scp=84918552853&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84918552853&partnerID=8YFLogxK

U2 - 10.1109/IIAI-AAI.2014.45

DO - 10.1109/IIAI-AAI.2014.45

M3 - Paper

AN - SCOPUS:84918552853

SP - 177

EP - 180

T2 - 3rd IIAI International Conference on Advanced Applied Informatics, IIAI-AAI 2014

Y2 - 31 August 2014 through 4 September 2014

ER -

Towards activity recognition of learners by kinect

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this