An Incremental Approach of Clustering for Human Activity Discovery

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2014/11/01

タイトル(英語): An Incremental Approach of Clustering for Human Activity Discovery

著者名: Wee-Hong Ong (Graduate School of Engineering, The University of Tokyo), Leon Palafox (Department of Radiology, University of California), Takafumi Koseki (Graduate School of Engineering, The University of Tokyo)

著者名(英語): Wee-Hong Ong (Graduate School of Engineering, The University of Tokyo), Leon Palafox (Department of Radiology, University of California), Takafumi Koseki (Graduate School of Engineering, The University of Tokyo)

キーワード: human activity detection，human activity discovery，unsupervised learning，clustering，RGB-D sensor

要約(英語): One of the challenges in human activity recognition is the ability for an intelligent system to discover the activity models by itself. In this paper, we propose an incremental approach to discover human activities from unlabeled data using K-means. The approach does not require prior specification of the number of clusters, or k-value, and has the ability to reject random movements or noise. Simple algorithm is used making the approach easy to implement without requiring any prior knowledge in the data. We evaluated the effectiveness of the approach and the results show more than 30% improvement in precision and 19% improvement in recall when compared to the results obtained using a non-incremental approach with cluster validity index. The achievement in human activity discovery will enable the wide adoption of human activity recognition technologies in the natural human living environment where labeled data are not available.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.134 No.11 （2014） 特集Ⅰ：電気関係学会関西連合大会　特集Ⅱ：国際会議ヒューマナイズド　システム2013

本誌掲載ページ: 1724-1730 p

原稿種別: 論文／英語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/134/11/134_1724/_article/-char/ja/