Discovering Group Movement Pattern by Measuring Individual Similarity from GPS Trajectories

• Item type: SIG Technical Reports(1)
• 公開日: 2019-11-16
• タイトル: Discovering Group Movement Pattern by Measuring Individual Similarity from GPS Trajectories
• タイトル / 言語: en
• タイトル: Discovering Group Movement Pattern by Measuring Individual Similarity from GPS Trajectories
• 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 Computer Engineering, Faculty of Engineering, King Mongkut's Institute of Technology Ladkrabang
• 著者所属: Department of Embedded System, Tokai University
• 著者所属: Department of Embedded System, Tokai University
• 著者所属: Department of Computer Engineering, Faculty of Engineering, King Mongkut's Institute of Technology Ladkrabang
• 著者所属(英): en
• 著者所属(英): Department of Computer Engineering, Faculty of Engineering, King Mongkut's Institute of Technology Ladkrabang
• 著者所属(英): en
• 著者所属(英): Department of Embedded System, Tokai University
• 著者所属(英): en
• 著者所属(英): Department of Embedded System, Tokai University
• 著者所属(英): en
• 著者所属(英): Department of Computer Engineering, Faculty of Engineering, King Mongkut's Institute of Technology Ladkrabang
• 著者名: Thi, Thi Shein; Azusa, Yamauchi; Makoto, Imamura; Sutheera, Puntheeranurak
• 著者名(英): Thi, Thi Shein; Azusa, Yamauchi; Makoto, Imamura; Sutheera, Puntheeranurak
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Exploring useful knowledge from moving objects' trajectories can contribute to various application areas such as traffic monitoring, congestion prediction, individual daily activity recognition. Due to a large amount of trajectory data, the main challenge in trajectory pattern mining is to detect the group pattern effectively and efficiently. To address this, our purpose is to discover the group movement pattern from the vehicles' trajectories by comparing different trajectory similarity methods. Group pattern represents a group of moving objects (i.e people, animals, vehicles) that moves together along their trip. Firstly, we extract the similarity matrix to detect the individual's trajectory similarity, by applying trajectory similarity methods. Then, we discover the group movement pattern by using the density-based clustering algorithm. Experimental results are evaluated on real data.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Exploring useful knowledge from moving objects' trajectories can contribute to various application areas such as traffic monitoring, congestion prediction, individual daily activity recognition. Due to a large amount of trajectory data, the main challenge in trajectory pattern mining is to detect the group pattern effectively and efficiently. To address this, our purpose is to discover the group movement pattern from the vehicles' trajectories by comparing different trajectory similarity methods. Group pattern represents a group of moving objects (i.e people, animals, vehicles) that moves together along their trip. Firstly, we extract the similarity matrix to detect the individual's trajectory similarity, by applying trajectory similarity methods. Then, we discover the group movement pattern by using the density-based clustering algorithm. Experimental results are evaluated on real data.
• 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: AA11253943
• 書誌情報: 研究報告情報システムと社会環境（IS）; 巻 2019-IS-150, 号 7, p. 1-2, 発行日 2019-11-16
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8809
• 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