@article{oai:miyazaki-u.repo.nii.ac.jp:00006429,
 author = {Yamaba, Hisaaki and 山場, 久昭 and 白石, 堅哉 and Aburada, Kentaro and 油田, 健太郎 and Okazaki, Naonobu and 岡崎, 直宣 and Shiraishi, Kenya},
 journal = {宮崎大学工学部紀要, Memoirs of Faculty of Engineering, University of Miyazaki},
 month = {Sep},
 note = {In our present era, mobile devices such as tablet-type personal computers (PCs) and smartphones have penetrated deeply into our daily lives. We report on a new user authentication method for mobile devices that uses surface electromyogram (s-EMG) signals rather than screen-touch operations. These s-EMG signals, which are generated by the electrical activity of muscle fibers during contraction, can be used to identify who generated the signals and which gestures were made. Our method uses a technique called “pass-gesture,” which refers to a series of hand gestures, to achieve s-EMG-based authentication. In this paper, deep learning is introduced to facilitate the identification of gestures from s-EMG signals. Pictures of s-EMG signals were directly used to differentiate gestures in experiments and the performance was evaluated. The results showed that the performance using deep learning was not better than the one using support vector machines that was used in our previous works. However, we expect the results to be used as one of the benchmark indices for the future improvement.},
 pages = {193--197},
 title = {表面筋電位による個人認証システムへの深層学習適用の試み},
 volume = {50},
 year = {2021},
 yomi = {ヤマバ, ヒサアキ and シライシ, ケンヤ and アブラダ, ケンタロウ and オカザキ, ナオノブ}
}