3軸加速度センサーによる歩行特徴量を用いた中・高齢者の身体的虚弱状態検出

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: 2022/12/01

タイトル(英語): Detection of Physical Frailty Status of Middle-Aged and Elderly People Using Gait Features Based on 3-Axis Acceleration Sensors

著者名: 中村　早希（名古屋工業大学大学院工学研究科），増尾　明（名古屋工業大学大学院工学研究科），竹尾　淳（名古屋国際工科専門職大学工科学部／名古屋工業大学 NITech AI 研究センター／名古屋市立大学大学院医学研究科），佐久間　拓人（名古屋工業大学大学院工学研究科），加藤　昇平（名古屋工業大学大学院工学研究科／名古屋工業大学 NITech AI 研究センター），渡邊　航平（中京大学スポーツ科学部），川出　義浩（名古屋市立大学大学院薬学研究科），間辺　利江（名古屋市立大学大学院医学研究科），赤津　裕康（名古屋

著者名(英語): Saki Nakamura (Graduate School of Engineering, Nagoya Institute of Technology), Akira Masuo (Graduate School of Engineering, Nagoya Institute of Technology), Jun Takeo (Faculty of Technology, International Professional University of Technology in Nagoya/NITech Artificial Intelligence Research Center, Nagoya Institute of Technology/Graduate School of Medical Sciences, Nagoya City University), Takuto Sakuma (Graduate School of Engineering, Nagoya Institute of Technology), Shohei Kato (Graduate School of Engineering, Nagoya Institute of Technology/NITech Artificial Intelligence Research Center, Nagoya Institute of Technology), Kohei Watanabe (School of Health and Sport Sciences, Chukyo University), Yoshihiro Kawade (Graduate School of Pharmaceutical Sciences, Nagoya City University), Toshie Manabe (Graduate School of Medical Sciences, Nagoya City University), Hiroyasu Akatsu (Graduate School of Medical Sciences, Nagoya City University)

キーワード: 加速度，中・高齢者，SVM，重錘負荷歩行，フレイル，サルコペニア_x000D_　　acceleration，middle-aged elderly people，SVM，limb-loaded walking，frailty，sarcopenia

要約(英語): In Japan's super-aged society, it is important to prolong independent daily living. This paper, we focus on walking, which is indispensable for daily living, to diagnose frailty. This study included acceleration data during limb-loaded walking to increase muscle strength in the analysis. Also, we classified and identified whether middle-aged and elderly persons are in a frail state or not were conducted following the Cardiovascular Health Study. After selecting useful features by random forest, a Support Vector Machine was used to identify the frailty state. As a result, we reported that we could identify frailty with an accuracy rate of 82%, suggesting the possibility of detecting low grip strength from the features extracted from gait data.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.142 No.12 （2022） 特集：電気・電子・情報関係学会東海支部連合大会

本誌掲載ページ: 1262-1268 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/142/12/142_1262/_article/-char/ja/