Semi-Supervised Time Series Anomaly Detection Based on Statistics and Deep Learning
Semi-Supervised Time Series Anomaly Detection Based on Statistics and Deep Learning
复制标题
DOI：
10.3390/app11156698
复制
发表时间：
2021-08-01
影响因子：
2.7
通讯作者：
Li, Yu-Lin
中科院分区：
文献类型：
--
作者：
Jiang, Jehn-Ruey;Kao, Jian-Bin;Li, Yu-Lin
由于传感器和物联网(IoT)技术等新技术的进步，随着时间的推移，海量数据被持续收集，产生了各种时间序列。提出了一种单变量时间序列的半监督异常检测框架Tri-CAD。基于皮尔逊积矩相关系数和Dickey-Fuller检验，首先将时间序列分为三类：(I)周期时间序列，(Ii)平稳时间序列，(Iii)非周期和非平稳时间序列。然后，利用统计、小波变换和深度学习自动编码的概念，将不同的机制应用于不同类别的时间序列来检测异常。通过使用三个Numenta异常基准(NAB)数据集的实验对所提出的Tri-CAD框架的性能进行了评估。将Tri-CAD与STL、SARIMA、LSTM、LSTM+STL、ADSAS等相关方法的性能进行了比较。比较结果表明，Tri-CAD在查准率、召回率和F-1得分方面均优于其他两种方法。
Thanks to the advance of novel technologies, such as sensors and Internet of Things (IoT) technologies, big amounts of data are continuously gathered over time, resulting in a variety of time series. A semi-supervised anomaly detection framework, called Tri-CAD, for univariate time series is proposed in this paper. Based on the Pearson product-moment correlation coefficient and Dickey-Fuller test, time series are first categorized into three classes: (i) periodic, (ii) stationary, and (iii) non-periodic and non-stationary time series. Afterwards, different mechanisms using statistics, wavelet transform, and deep learning autoencoder concepts are applied to different classes of time series for detecting anomalies. The performance of the proposed Tri-CAD framework is evaluated by experiments using three Numenta anomaly benchmark (NAB) datasets. The performance of Tri-CAD is compared with those of related methods, such as STL, SARIMA, LSTM, LSTM with STL, and ADSaS. The comparison results show that Tri-CAD outperforms the others in terms of the precision, recall, and F-1-score.