A novel framework of non-parametric for adjusting the window size

• Item type: SIG Technical Reports(1)
• 公開日: 2022-03-03
• タイトル: A novel framework of non-parametric for adjusting the window size
• タイトル / 言語: en
• タイトル: A novel framework of non-parametric for adjusting the window size
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: セッション1
• 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 Informatics, Shizuoka University
• 著者所属: Department of Informatics, Shizuoka University
• 著者所属(英): en
• 著者所属(英): Department of Informatics, Shizuoka University
• 著者所属(英): en
• 著者所属(英): Department of Informatics, Shizuoka University
• 著者名: Thanapiol, Phungtua-eng; Yoshitaka, Yamamoto
• 著者名(英): Thanapiol, Phungtua-eng; Yoshitaka, Yamamoto
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: The data stream may contain irrelevant information due to various factors, such as the huge amount of data volume. The technique for removing irrelevant information is called data binning. The data binning is used to sequence the data stream into smaller bins and each of which captures statistical features in the corresponding sub-sequence. The obtained bins are collected into the window, meaning that the number of bins to be collected is determined by the window size. The window size is required to set in advance, whereas the sufficient value is varied with the target data stream to be captured. This paper proposes a novel framework for automatically adjusting the number of bins in the window with a non-parametric metric. We demonstrate our framework to detect unknown transient patterns with the astronomical data stream.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: The data stream may contain irrelevant information due to various factors, such as the huge amount of data volume. The technique for removing irrelevant information is called data binning. The data binning is used to sequence the data stream into smaller bins and each of which captures statistical features in the corresponding sub-sequence. The obtained bins are collected into the window, meaning that the number of bins to be collected is determined by the window size. The window size is required to set in advance, whereas the sufficient value is varied with the target data stream to be captured. This paper proposes a novel framework for automatically adjusting the number of bins in the window with a non-parametric metric. We demonstrate our framework to detect unknown transient patterns with the astronomical data stream.
• 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: AA11135936
• 書誌情報: 研究報告知能システム（ICS）; 巻 2022-ICS-206, 号 5, p. 1-6, 発行日 2022-03-03
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-885X
• 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