セキグチ　アキノリ   関口　暁宣    所属   工学部 機械工学科    職種   専任講師
言語種別	英語
発行・発表の年月	2025/07
形態種別	学術論文
査読	査読あり
標題	Fall Detection Based on Inverted-Pendulum Model as Training Data for Monitoring Elderly People Living Solitarily Using Depth Camera
執筆形態	共著
掲載誌名	Journal of Advanced Computational Intelligence and Intelligent Informatics
掲載区分	国外
出版社・発行元	Fuji Technology Press Ltd.
巻・号・頁	29(4),pp.768-776
担当区分	責任著者
著者・共著者	Eisuke Tomita and Akinori Sekiguchi
概要	This study aims to develop a monitoring system for elderly individuals living solitarily using time-series data generated via simulation as training data. In particular, we focus on classifying three types of motion: falling, static standing, and walking. First, we create a system that calculates body velocity and acceleration using a depth camera. Based on actual measurements of each motion, we identify their distinct characteristics. Subsequently, we implement an inverted-pendulum model, which is commonly used for human-motion analysis, in a dynamics simulator. Simulations of falling, static standing, and walking are conducted, which successfully generated time-series data closely resembling the actual measured motions. Finally, using the simulation-derived time-series data as training data, we perform a machine-learning-based classification of falling, static standing, and walking motions measured using Azure Kinect. Although some misclassifications occurred, the system accurately classified most of the motions.
外部リンクURL	https://doi.org/10.20965/jaciii.2025.p0768