3s2sub: A Proposal of Data Segmentation Scheme for Fall Detection by Smartphone built-in Accelerator

• Item type: SIG Technical Reports(1)
• 公開日: 2022-06-30
• タイトル: 3s2sub: A Proposal of Data Segmentation Scheme for Fall Detection by Smartphone built-in Accelerator
• タイトル / 言語: en
• タイトル: 3s2sub: A Proposal of Data Segmentation Scheme for Fall Detection by Smartphone built-in Accelerator
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: LOIS
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: School of Engineering, The University of Tokyo
• 著者所属: Information Technology Center, The University of Tokyo
• 著者所属(英): en
• 著者所属(英): School of Engineering, The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Information Technology Center, The University of Tokyo
• 著者名: Pengyu, Guo; Masaya, Nakayama
• 著者名(英): Pengyu, Guo; Masaya, Nakayama
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: A Fall is defined as an event which results in a person coming to rest inadvertently on the ground or floor or other lower level. While threatening people's lives, it also brings huge economic costs. In this work, data segmentation scheme called 3s2sub is proposed, which is to detect fall with smartphone built-in accelerator. The approach is tested with a public dataset – UniMiB SHAR. The accuracy achieved by KNN and SVM are about 98% in 30-fold evaluation. And Macro Average accuracy are about 97% and 98% in 30-fold evaluation.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: A Fall is defined as an event which results in a person coming to rest inadvertently on the ground or floor or other lower level. While threatening people's lives, it also brings huge economic costs. In this work, data segmentation scheme called 3s2sub is proposed, which is to detect fall with smartphone built-in accelerator. The approach is tested with a public dataset – UniMiB SHAR. The accuracy achieved by KNN and SVM are about 98% in 30-fold evaluation. And Macro Average accuracy are about 97% and 98% in 30-fold evaluation.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10539261
• 書誌情報: 研究報告ドキュメントコミュニケーション（DC）; 巻 2022-DC-125, 号 7, p. 1-6, 発行日 2022-06-30
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8892
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会