Experimental Analysis of the Behavior of Short Time Series Clustering

• Item type: SIG Technical Reports(1)
• 公開日: 2016-06-27
• タイトル: Experimental Analysis of the Behavior of Short Time Series Clustering
• タイトル / 言語: en
• タイトル: Experimental Analysis of the Behavior of Short Time Series Clustering
• 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: Doshisha University
• 著者所属: Doshisha University
• 著者所属: Doshisha University
• 著者所属(英): en
• 著者所属(英): Doshisha University
• 著者所属(英): en
• 著者所属(英): Doshisha University
• 著者所属(英): en
• 著者所属(英): Doshisha University
• 著者名: Marta, Quemada-Lopez; Miho, Ohsaki; Shigeru, Katagiri
• 著者名(英): Marta, Quemada-Lopez; Miho, Ohsaki; Shigeru, Katagiri
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Time series clustering (TSC), which is an important technique to discover groups of time series and their representatives, has wide applications. There are several effective model-based approaches to TSC. However, since time series, especially those of biomedical observations, are often too short to be modeled appropriately, clustering such short time series remains a difficult research issue. To solve this problem, we select two major model-based TSC approaches, deterministic and probabilistic, and analyze their behaviors using simulated short time series. Experimental results suggested that the superiority of these two approaches depended on the inter-cluster distances of the clusters.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Time series clustering (TSC), which is an important technique to discover groups of time series and their representatives, has wide applications. There are several effective model-based approaches to TSC. However, since time series, especially those of biomedical observations, are often too short to be modeled appropriately, clustering such short time series remains a difficult research issue. To solve this problem, we select two major model-based TSC approaches, deterministic and probabilistic, and analyze their behaviors using simulated short time series. Experimental results suggested that the superiority of these two approaches depended on the inter-cluster distances of the clusters.
• 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: AA12055912
• 書誌情報: 研究報告バイオ情報学（BIO）; 巻 2016-BIO-46, 号 35, p. 1-2, 発行日 2016-06-27
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8590
• 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