{"title":"用于多维时间序列异常检测的矩阵剖面图","authors":"Chin-Chia Michael Yeh, Audrey Der, Uday Singh Saini, Vivian Lai, Yan Zheng, Junpeng Wang, Xin Dai, Zhongfang Zhuang, Yujie Fan, Huiyuan Chen, Prince Osei Aboagye, Liang Wang, Wei Zhang, Eamonn Keogh","doi":"arxiv-2409.09298","DOIUrl":null,"url":null,"abstract":"The Matrix Profile (MP), a versatile tool for time series data mining, has\nbeen shown effective in time series anomaly detection (TSAD). This paper delves\ninto the problem of anomaly detection in multidimensional time series, a common\noccurrence in real-world applications. For instance, in a manufacturing\nfactory, multiple sensors installed across the site collect time-varying data\nfor analysis. The Matrix Profile, named for its role in profiling the matrix\nstoring pairwise distance between subsequences of univariate time series,\nbecomes complex in multidimensional scenarios. If the input univariate time\nseries has n subsequences, the pairwise distance matrix is a n x n matrix. In a\nmultidimensional time series with d dimensions, the pairwise distance\ninformation must be stored in a n x n x d tensor. In this paper, we first\nanalyze different strategies for condensing this tensor into a profile vector.\nWe then investigate the potential of extending the MP to efficiently find\nk-nearest neighbors for anomaly detection. Finally, we benchmark the\nmultidimensional MP against 19 baseline methods on 119 multidimensional TSAD\ndatasets. The experiments covers three learning setups: unsupervised,\nsupervised, and semi-supervised. MP is the only method that consistently\ndelivers high performance across all setups.","PeriodicalId":501123,"journal":{"name":"arXiv - CS - Databases","volume":"213 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Matrix Profile for Anomaly Detection on Multidimensional Time Series\",\"authors\":\"Chin-Chia Michael Yeh, Audrey Der, Uday Singh Saini, Vivian Lai, Yan Zheng, Junpeng Wang, Xin Dai, Zhongfang Zhuang, Yujie Fan, Huiyuan Chen, Prince Osei Aboagye, Liang Wang, Wei Zhang, Eamonn Keogh\",\"doi\":\"arxiv-2409.09298\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Matrix Profile (MP), a versatile tool for time series data mining, has\\nbeen shown effective in time series anomaly detection (TSAD). This paper delves\\ninto the problem of anomaly detection in multidimensional time series, a common\\noccurrence in real-world applications. For instance, in a manufacturing\\nfactory, multiple sensors installed across the site collect time-varying data\\nfor analysis. The Matrix Profile, named for its role in profiling the matrix\\nstoring pairwise distance between subsequences of univariate time series,\\nbecomes complex in multidimensional scenarios. If the input univariate time\\nseries has n subsequences, the pairwise distance matrix is a n x n matrix. In a\\nmultidimensional time series with d dimensions, the pairwise distance\\ninformation must be stored in a n x n x d tensor. In this paper, we first\\nanalyze different strategies for condensing this tensor into a profile vector.\\nWe then investigate the potential of extending the MP to efficiently find\\nk-nearest neighbors for anomaly detection. Finally, we benchmark the\\nmultidimensional MP against 19 baseline methods on 119 multidimensional TSAD\\ndatasets. The experiments covers three learning setups: unsupervised,\\nsupervised, and semi-supervised. MP is the only method that consistently\\ndelivers high performance across all setups.\",\"PeriodicalId\":501123,\"journal\":{\"name\":\"arXiv - CS - Databases\",\"volume\":\"213 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Databases\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.09298\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Databases","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.09298","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
矩阵剖面图(MP)是一种用于时间序列数据挖掘的多功能工具,在时间序列异常检测(TSAD)中被证明是有效的。本文深入探讨了多维时间序列中的异常检测问题,这是现实世界应用中的常见问题。例如,在制造工厂中,安装在厂区各处的多个传感器会收集时变数据进行分析。矩阵剖面(Matrix Profile)因其作用是剖析存储单变量时间序列子序列之间成对距离的矩阵而得名,在多维场景中变得复杂。如果输入的单变量时间序列有 n 个子序列,那么成对距离矩阵就是 n x n 矩阵。在具有 d 维的多维时间序列中,成对距离信息必须存储在 n x n x d 张量中。在本文中,我们首先分析了将该张量压缩成轮廓向量的不同策略,然后研究了扩展 MP 以高效查找近邻进行异常检测的潜力。最后,我们在 119 个多维 TSAD 数据集上用 19 种基准方法对多维 MP 进行了基准测试。实验涵盖三种学习设置:无监督、有监督和半监督。MP 是唯一一种在所有设置中都能始终保持高性能的方法。
Matrix Profile for Anomaly Detection on Multidimensional Time Series
The Matrix Profile (MP), a versatile tool for time series data mining, has
been shown effective in time series anomaly detection (TSAD). This paper delves
into the problem of anomaly detection in multidimensional time series, a common
occurrence in real-world applications. For instance, in a manufacturing
factory, multiple sensors installed across the site collect time-varying data
for analysis. The Matrix Profile, named for its role in profiling the matrix
storing pairwise distance between subsequences of univariate time series,
becomes complex in multidimensional scenarios. If the input univariate time
series has n subsequences, the pairwise distance matrix is a n x n matrix. In a
multidimensional time series with d dimensions, the pairwise distance
information must be stored in a n x n x d tensor. In this paper, we first
analyze different strategies for condensing this tensor into a profile vector.
We then investigate the potential of extending the MP to efficiently find
k-nearest neighbors for anomaly detection. Finally, we benchmark the
multidimensional MP against 19 baseline methods on 119 multidimensional TSAD
datasets. The experiments covers three learning setups: unsupervised,
supervised, and semi-supervised. MP is the only method that consistently
delivers high performance across all setups.