2022 Fiscal Year Final Research Report

Time-series Anomaly Detection based on Difference Subspace between Signal Subspaces

Research Project

PDF

Project/Area Number	19H04129
Research Category	Grant-in-Aid for Scientific Research (B)
Allocation Type	Single-year Grants
Section	一般
Review Section	Basic Section 61010:Perceptual information processing-related
Research Institution	University of Tsukuba
Principal Investigator	Fukui Kazuhiro 筑波大学, システム情報系, 教授 (40375423)
Co-Investigator(Kenkyū-buntansha)	小林匠国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (30443188) 飯塚里志筑波大学, システム情報系, 准教授 (30755153)
Project Period (FY)	2019-04-01 – 2022-03-31
Keywords	時系列解析 / 変化検知 / 特異スペクトル解析 / 部分空間表現 / 差分部分空間
Outline of Final Research Achievements	We proposed a new method for anomaly detection in time-series data by incorporating the concept of difference subspace into the singular spectrum analysis (SSA). The key idea is to monitor slight temporal variations of the difference subspace between two signal subspaces corresponding to the past and present time-series data, as anomaly score. It is a natural generalization of the conventional SSA-based method which measures the minimum angle between the two signal subspaces as the degree of changes. By replacing the minimum angle with the difference subspace, our method boosted the performance while using the SSA-based framework as it can capture the whole structural difference between the two subspaces in its magnitude and direction. We demonstrated our method's effectiveness through performance evaluations on public time-series datasets.
Free Research Field	機械学習
Academic Significance and Societal Importance of the Research Achievements	近年，工場の生産ラインや社会インフラなどの複雑システムには，多種多様なセンサ群が配置されており，システム内部状態を反映した膨大な時系列データを得ることが可能となっている．しかしながら，データ量の増大と供にオペレーターの作業負担が増しており，これを軽減することは社会的なニーズが高い．本研究で取り組んだ時系列からの変化・異常検知は，データから通常と異なる僅かな時間変動を異常として自動検知することを可能とする．これによりオペレータの作業負担を大きく減らすと期待できる．