電気学会 電子図書館
 HOME > 同研究会の論文誌(論文単位) > 文献詳細
Extended Summaryはついていません。

・会員価格 ¥550
・一般価格 ¥770
こちらはBookPark「電気学会 電子図書館(IEEJ Electronic Library)」による文献紹介ページです。
非会員の方はログインの必要はありません。このまま お進みください。
■ページ数 8ページ



Development of Evaluation System for VIMS by Machine Learning of Eye Movement Data

■著者名 藤掛 和広(中京大学心理学部),板津 佳希(福井大学工学部),高田 宗樹(福井大学工学部)
■著者名(英語) Kazuhiro Fujikake (School of Psychology, Chukyo University), Yoshiyuki Itada (Faculty of Engineering, University of Fukui), Hiroki Takada (Faculty of Engineering, University of Fukui)
■価格 会員 ¥550 一般 ¥770
■書籍種類 論文誌(論文単位)
■グループ名 【C】電子・情報・システム部門
■本誌 電気学会論文誌C(電子・情報・システム部門誌) Vol.142 No.10 (2022) 特集:電子材料関連技術の最近の進展
■本誌掲載ページ 1107-1114ページ
■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/142/10/142_1107/_article/-char/ja/
■キーワード 映像酔い,視線データ,高齢者,ドライビングシミュレータ   visually induced motion sickness (VIMS),gaze data,elderly people,driving simulator (DS)
■要約(英語) The prevention of traffic accidents involving elderly drivers is an important issue. Research on elderly drivers often uses the driving simulator (DS). Visually induced motion sickness (VIMS) has been pointed out as a problem in DS experiments. Although there are many methods to evaluate VIMS, reducing the burden on the experimental collaborators is an issue. As a method of measuring physiological indices that is less burdensome to the participants and has many applications, the use of noncontact eye-tracking device has been mentioned. This study developed a VIMS evaluation system using data collected with a noncontact eye-tracking device for DS experiments. The participants included eight elderly people with visual and balance functions that did not interfere with their daily life. The participants' gaze data were measured, and they answered the simulator sickness questionnaire (SSQ) before and after experiment. Gaze measurements were taken at rest. The participants were divided into two groups on the basis of their SSQ results. One group experienced VIMS during the DS trial (four people; average age, 79.0 years), whereas the other group did not experience it (four people; average age, 72.0 years). Machine learning analysis was performed on the gaze data from the 1st and 5th DS trials. we used the leave one out method for the verification of training and test data in machine learning; in this method, verification is repeated so that the data of all experimental participants become test cases. The results of the learning model's validation showed a high rate of correct answers. The results suggested that the learning model obtained using machine learning was an effective evaluation system for VIMS.
■版 型 A4
©Contents Works Inc.