Anomalies in time series, also called “discord,” are the abnormal subsequences. The occurrence of anomalies in time series may indicate that some faults or disease will occur soon. Therefore, development of novel computational approaches for anomaly detection (discord search) in time series is of great significance for state monitoring and early warning of real-time system. Previous studies show that many algorithms were successfully developed and were used for anomaly classification, e.g., health monitoring, traffic detection, and intrusion detection. However, the anomaly detection of time series was not well studied. In this paper, we proposed a long short-term memory- (LSTM-) based anomaly detection method (LSTMAD) for discord search from univariate time series data. LSTMAD learns the structural features from normal (nonanomalous) training data and then performs anomaly detection via a statistical strategy based on the prediction error for observed data. In our experimental evaluation using public ECG datasets and real-world datasets, LSTMAD detects anomalies more accurately than other existing approaches in comparison.

中文翻译：

---

一种用于时间序列数据异常检测的新型深度学习方法

时间序列中的异常，也称为“不和谐”，是异常子序列。时间序列异常的出现可能预示着一些故障或疾病即将发生。因此，开发用于时间序列异常检测（不一致搜索）的新计算方法对于实时系统的状态监测和预警具有重要意义。以往的研究表明，许多算法被成功开发并用于异常分类，例如健康监测、流量检测和入侵检测。然而，时间序列的异常检测并没有得到很好的研究。在本文中，我们提出了一种基于长短期记忆（LSTM-）的异常检测方法（LSTMAD），用于从单变量时间序列数据中进行不和谐搜索。LSTMAD 从正常（非异常）训练数据中学习结构特征，然后根据观测数据的预测误差，通过统计策略进行异常检测。在我们使用公共 ECG 数据集和真实世界数据集的实验评估中，相比之下，LSTMAD 比其他现有方法更准确地检测异常。