講演抄録/キーワード |
講演名 |
2022-07-07 14:55
3s2sub:スマートフォン内蔵型加速度計による転倒検知ためのデータ分割方式提案 ○郭 鵬宇・中山雅哉(東大) LOIS2022-7 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
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. |
キーワード |
(和) |
行動認識 / 転倒検出 / スマートホン内蔵センサー / 加速度計 / / / / |
(英) |
Activity Recognition / Fall Detection / Smartphone built-in Sensor / Accelerometer / / / / |
文献情報 |
信学技報, vol. 122, no. 97, LOIS2022-7, pp. 18-23, 2022年7月. |
資料番号 |
LOIS2022-7 |
発行日 |
2022-06-30 (LOIS) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
LOIS2022-7 |