Preliminary Investigation of Using SSL for Complex Work Activity Recognition in Industrial Settings

• Item type: SIG Technical Reports(1)
• 公開日: 2023-05-17
• タイトル: Preliminary Investigation of Using SSL for Complex Work Activity Recognition in Industrial Settings
• タイトル / 言語: en
• タイトル: Preliminary Investigation of Using SSL for Complex Work Activity Recognition in Industrial Settings
• 言語: eng
• 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: Department of Multimedia Engineering, Graduate School of Information Science and Technology, Osaka University
• 著者所属: Department of Multimedia Engineering, Graduate School of Information Science and Technology, Osaka University
• 著者所属: Department of Multimedia Engineering, Graduate School of Information Science and Technology, Osaka University
• 著者所属: Corporate Manufacturing Engineering Center, Toshiba Corporation
• 著者所属: Corporate Manufacturing Engineering Center, Toshiba Corporation
• 著者所属(英): en
• 著者所属(英): Department of Multimedia Engineering, Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Department of Multimedia Engineering, Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Department of Multimedia Engineering, Graduate School of Information Science and Technology, Osaka University
• 著者所属(英): en
• 著者所属(英): Corporate Manufacturing Engineering Center, Toshiba Corporation
• 著者所属(英): en
• 著者所属(英): Corporate Manufacturing Engineering Center, Toshiba Corporation
• 著者名: Qingxin, Xia; Takuya, Maekawa; Takahiro, Hara; Hirotomo, Oshima; Yasuo, Namioka
• 著者名(英): Qingxin, Xia; Takuya, Maekawa; Takahiro, Hara; Hirotomo, Oshima; Yasuo, Namioka
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Activity recognition using sensor data collected by wearable sensors has been actively studied in the ubicomp community. However, in industrial settings, (1) labeled sensor data collection is costly and (2) the activities performed by workers are more complex than those of daily activities such as walking and running. This study presents a new self-supervised learning approach that effectively utilizes unlabeled data to improve complex activity recognition performance in industrial domain. In this study, we focus on characteristic actions in each work activity (i.e., operation). We first select sensor data motifs corresponding to the characteristic actions that uniquely and consistently occur in an operation. Then, we calculate the similarity series of the motifs that indicate the occurrence of the motifs in every operation. We train a neural network so that it outputs the reconstructed similarity series, which is helpful in identifying the operations containing the motifs. The trained feature extractor is applied to the downstream task that uses limited labeled data to recognize complex work activities. The proposed approach was evaluated on real-world work activity data and achieved state-of-the-art results.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Activity recognition using sensor data collected by wearable sensors has been actively studied in the ubicomp community. However, in industrial settings, (1) labeled sensor data collection is costly and (2) the activities performed by workers are more complex than those of daily activities such as walking and running. This study presents a new self-supervised learning approach that effectively utilizes unlabeled data to improve complex activity recognition performance in industrial domain. In this study, we focus on characteristic actions in each work activity (i.e., operation). We first select sensor data motifs corresponding to the characteristic actions that uniquely and consistently occur in an operation. Then, we calculate the similarity series of the motifs that indicate the occurrence of the motifs in every operation. We train a neural network so that it outputs the reconstructed similarity series, which is helpful in identifying the operations containing the motifs. The trained feature extractor is applied to the downstream task that uses limited labeled data to recognize complex work activities. The proposed approach was evaluated on real-world work activity data and achieved state-of-the-art results.
• 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: AA11838947
• 書誌情報: 研究報告ユビキタスコンピューティングシステム（UBI）; 巻 2023-UBI-78, 号 9, p. 1-8, 発行日 2023-05-17
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8698
• 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