標本部分列を用いた時系列データ異常検知方式

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2016/03/01

タイトル(英語): An Anomaly Detection Method with Exemplar Subsequence for Time Series Data

著者名: 中村　隆顕（三菱電機（株）情報技術総合研究所），今村　誠（三菱電機（株）情報技術総合研究所），立床　雅司（三菱電機（株）情報技術総合研究所），平井　規郎（三菱電機（株）情報技術総合研究所）

著者名(英語): Takaaki Nakamura (Information Technology R&D Center, Mitsubishi Electric Corporation), Makoto Imamura (Information Technology R&D Center, Mitsubishi Electric Corporation), Masashi Tatedoko (Information Technology R&D Center, Mitsubishi Electric Corporation), Norio Hirai (Information Technology R&D Center, Mitsubishi Electric Corporation)

キーワード: 異常検知，ディスコード，時系列クラスタリング，標本部分列　　Anomaly Detection，Discord，Time Series Clustering，Exemplar Subsequence

要約(英語): “Discord” is useful method of detecting anomaly from time series data such as equipment sensor data. The discord method detects anomaly by calculating brute-force nearest neighbor distance between two subsequence of the time series. Hence there is a problem of increasing detection time with the increase in data length. In this paper, we propose an algorithm that, at first, clusters subsequences of the input time series and selects centroid from each clusters (called as “exemplar subsequence”), then detect anomaly by calculating nearest neighbor distance between input subsequence and exemplar subsequence. We also show that our proposed method is more faster detection speed than the discord method and have equivalent detection ability as the discord method by an experiment with two time series data.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.136 No.3 （2016） 特集：機械学習が拓くシステムイノベーション

本誌掲載ページ: 363-372 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/136/3/136_363/_article/-char/ja/