Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (6): 1553-1564.DOI: 10.11772/j.issn.1001-9081.2019101805

Special Issue: 综述

• Artificial intelligence •     Next Articles

Review of anomaly detection algorithms for multidimensional time series

HU Min1,2, BAI Xue1,2, XU Wei1,2, WU Bingjian1,2   

  1. 1. SILC Business School, Shanghai University, Shanghai 201800, China
    2. SHU-SUCG Research Centre for Building Industrialization, Shanghai University, Shanghai 200072, China
  • Received:2019-10-24 Revised:2019-12-21 Online:2020-06-18 Published:2020-06-10
  • Contact: BAI Xue, born in 1995, M. S. candidate. Her research interest includes anomaly detection algorithm for multidimensional time series
  • About author:HU Min, born in 1970, Ph. D., associate professor. Her research interests include intelligent information processing, urban infrastructure construction anomaly detection and prediction.BAI Xue, born in 1995, M. S. candidate. Her research interest includes anomaly detection algorithm for multidimensional time series.XU Wei, born in 1990, M. S. , teaching assistant. His research interests include data mining, intelligent information processing.WU Bingjian,born in 1995, M. S. His research interests include data mining, intelligent control.


胡珉1,2, 白雪1,2, 徐伟1,2, 吴秉键1,2   

  1. 1.上海大学 悉尼工商学院,上海 201800
    2.上海大学—上海城建建筑产业化研究中心,上海 200072
  • 通讯作者: 白雪(1995—)
  • 作者简介:胡珉(1970—),女,浙江上虞人,副教授,博士,主要研究方向:智能信息处理、城市基础设施施工异常检测和预测。白雪(1995—),女,河南焦作人,硕士研究生,主要研究方向:多维时间序列异常监测算法。徐伟(1990—),男,江苏南通人,助教,硕士,主要研究方向:数据挖掘、智能信息处理。吴秉键(1995—),男,安徽宿州人,硕士,主要研究方向:数据挖掘、智能控制。


With the continuous development of information technology, the scale of time series data has grown exponentially, which provides opportunities and challenges for the development of time series anomaly detection algorithm, making the algorithm in this field gradually become a new research hotspot in the field of data analysis. However, the research in this area is still in the initial stage and the research work is not systematic. Therefore, by sorting out and analyzing the domestic and foreign literature, this paper divides the research content of multidimensional time series anomaly detection into three aspects: dimension reduction, time series pattern representation and anomaly pattern detection in logical order, and summarizes the mainstream algorithms to comprehensively show the current research status and characteristics of anomaly detection. On this basis, the research difficulties and trends of multi-dimensional time series anomaly detection algorithms were summarized in order to provide useful reference for related theory and application research.

Key words: multidimensional time series, anomaly detection, dimension reduction, time series pattern representation, anomaly pattern detection



关键词: 多维时间序列, 异常检测, 维数约简, 时间序列的模式表示, 异常模式发现

CLC Number: