@article{oai:ipsj.ixsq.nii.ac.jp:00183691,
 author = {松原, 靖子 and 櫻井, 保志 and Christos, Faloutsos and Yasuko, Matsubara and Yasushi, Sakurai and Christos, Faloutsos},
 issue = {3},
 journal = {情報処理学会論文誌データベース(TOD)},
 month = {Oct},
 note = {本論文では,大規模オンライン活動データのための特徴自動抽出手法であるCompCubeについて述べる.CompCubeは,(activity, location, time)の三つ組で構成される様々なオンライン活動データに対し,重要な時系列パターンや外れ値を統合的に解析,要約し,将来の長期的なイベント予測を実現する.たとえば,“Nokia/Nexus/Kindle”あるいは“CNN/BBC”等のオンライン検索キーワードの各地域(国)における2004年から2015年にかけての出現件数に関する時系列データが与えられたとき,提案手法は,(a)基本的な非線形動的パターン,(b)各アクティビティ間の潜在的な関連性や競合性(Nokia vs. Nexus等),(c)クリスマスや旧正月等の各地域における季節性,(d)単発的なイベントや外れ値等の重要なパターンを自動的に抽出する.本論文ではさらに,重要な特徴を自動的かつ高速に抽出するためのアルゴリズムとしてCompCube-Fitを提案する.実データを用いた実験では,CompCubeが様々なオンライン活動データの中から有用なパターンを正確に発見することを確認し,さらに,最新の既存手法と比較し提案手法が大幅な精度,性能向上を達成していることを明らかにした., Given a large collection of time-evolving activities, such as Google search queries, which consist of d keywords/activities for m locations of duration n, how can we analyze temporal patterns and relationships among all these activities and find location-specific trends? How do we go about capturing non-linear evolutions of local activities and forecasting future patterns? For example, assume that we have the online search volume for multiple keywords, e.g., “Nokia/Nexus/Kindle” or “CNN/BBC” for 236 countries/territories, from 2004 to 2015. We present CompCube, a unifying non-linear model, which provides a compact and powerful representation of co-evolving activities; and also a novel fitting algorithm, CompCube-Fit, which is parameter-free and scalable. Our method captures the following important patterns: (B), i.e., non-linear dynamics of co-evolving activities, signs of (C) and latent interaction, e.g., Nokia vs. Nexus, (S), e.g., a Christmas spike for iPod in the U.S. and Europe, and (D), e.g., unrepeated local events such as the U.S. election in 2008. Thanks to its concise but effective summarization, CompCube can also forecast long-range future activities. Extensive experiments on real datasets demonstrate that CompCube consistently outperforms the best state-of-the-art methods in terms of both accuracy and execution speed.},
 pages = {1--15},
 title = {大規模オンライン活動データの特徴自動抽出},
 volume = {10},
 year = {2017}
}