Research on Sound-based Context Recognition Methods for User's Surroundings using Smart Devices

• Item type: SIG Technical Reports(1)
• 公開日: 2023-02-21
• タイトル: Research on Sound-based Context Recognition Methods for User's Surroundings using Smart Devices
• タイトル / 言語: en
• タイトル: Research on Sound-based Context Recognition Methods for User's Surroundings using Smart Devices
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 博士論文
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Graduate School of Information Science and Technology, Osaka University
• 著者所属: Graduate School of Information Science and Technology, Osaka University
• 著者所属: Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Graduate School of Information Science and Technology, Osaka University
• 著者名: Thilina, Dissanayake; 前川, 卓也; 原, 隆浩
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: On-body sensors such as accelerometers are used to capture the user's activities, that can be employed to develop context-aware applications. However, the user's surroundings also provide a rich stream of information regarding the user's context. In this study, we focus on capturing contextual information from the user's surroundings using sound sensing techniques and smart devices. Specifically, we propose sound sensing-based methods to capture information regarding (I) the user's interactions with doors, (II) the user's indoor location attributes, and (III) attributes of the obstacles in the user's outdoor surroundings. We further investigate the characteristics of sound sensing that allow us to employ cost-effective, easy-to-maintain methods to sense the user's surroundings with a less number of sensor nodes. Furthermore, our sensing methods do not require any modifications to the device, hence can be implemented on off-the-shelf smart devices that further increase the adaptability of our methods.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: On-body sensors such as accelerometers are used to capture the user's activities, that can be employed to develop context-aware applications. However, the user's surroundings also provide a rich stream of information regarding the user's context. In this study, we focus on capturing contextual information from the user's surroundings using sound sensing techniques and smart devices. Specifically, we propose sound sensing-based methods to capture information regarding (I) the user's interactions with doors, (II) the user's indoor location attributes, and (III) attributes of the obstacles in the user's outdoor surroundings. We further investigate the characteristics of sound sensing that allow us to employ cost-effective, easy-to-maintain methods to sense the user's surroundings with a less number of sensor nodes. Furthermore, our sensing methods do not require any modifications to the device, hence can be implemented on off-the-shelf smart devices that further increase the adaptability of our methods.
• 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: AA11851388
• 書誌情報: 研究報告モバイルコンピューティングと新社会システム（MBL）; 巻 2023-MBL-106, 号 22, p. 1-2, 発行日 2023-02-21
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8817
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会