Person Identification Based on Accelerations Sensed in Smartphones with LSTM (Preprint)

• Item type: Trans(1)
• 公開日: 2021-09-30
• タイトル: Person Identification Based on Accelerations Sensed in Smartphones with LSTM (Preprint)
• タイトル / 言語: en
• タイトル: Person Identification Based on Accelerations Sensed in Smartphones with LSTM (Preprint)
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [研究論文] accelerometer, machine learning, LSTM, personal identification
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Kogakuin University
• 著者所属: Kogakuin University
• 著者所属: Nagasaki University
• 著者所属: Ochanomizu University
• 著者所属: Kogakuin University
• 著者所属(英): en
• 著者所属(英): Kogakuin University
• 著者所属(英): en
• 著者所属(英): Kogakuin University
• 著者所属(英): en
• 著者所属(英): Nagasaki University
• 著者所属(英): en
• 著者所属(英): Ochanomizu University
• 著者所属(英): en
• 著者所属(英): Kogakuin University
• 著者名: Yoshihaya, Takahashi; Kosuke, Nakamura; Takeshi, Kamiyama; Masato, Oguchi; Saneyasu, Yamaguchi
• 著者名(英): Yoshihaya, Takahashi; Kosuke, Nakamura; Takeshi, Kamiyama; Masato, Oguchi; Saneyasu, Yamaguchi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: User identification is an important task for a variety of purposes such as authentication or providing personalized advice for improving user experience. In this paper, we propose a method for identifying a user who is holding a smartphone out of previously given target users from acceleration data obtained from the accelerometer in the smartphone using a deep neural network. This proposed method preliminary creates the model from the acceleration data of each user while walking in its training phase. This method identifies the user from acceleration data for identification based on this model in the classification phase. We evaluated the proposed method with the acceleration obtained from the actual eight and twelve users in two aspects, which were identifications including no-decision choice and that without no-decision choice. Our evaluation showed that the proposed method achieved accuracies higher than 95% for two- to five-class identification without no-decision. The proposed method identified the user with no or little false positive in evaluations with “no-decision.”; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.29(2021) (online); ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: User identification is an important task for a variety of purposes such as authentication or providing personalized advice for improving user experience. In this paper, we propose a method for identifying a user who is holding a smartphone out of previously given target users from acceleration data obtained from the accelerometer in the smartphone using a deep neural network. This proposed method preliminary creates the model from the acceleration data of each user while walking in its training phase. This method identifies the user from acceleration data for identification based on this model in the classification phase. We evaluated the proposed method with the acceleration obtained from the actual eight and twelve users in two aspects, which were identifications including no-decision choice and that without no-decision choice. Our evaluation showed that the proposed method achieved accuracies higher than 95% for two- to five-class identification without no-decision. The proposed method identified the user with no or little false positive in evaluations with “no-decision.”; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.29(2021) (online); ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12628043
• 書誌情報: 情報処理学会論文誌コンシューマ・デバイス＆システム（CDS）; 巻 11, 号 3, 発行日 2021-09-30
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2186-5728
• 出版者 / 言語: ja
• 出版者: 情報処理学会