【摘要】 多元时间序列问题广泛存在于社会生产和生活中,异常检测已经在金融、水文、气象、地震、视频监控医疗以及其他领域给人们提供了很多有价值的信息。为了快速高效地发现时间序列中的异常,使之以直观的方式呈现在人们面前,本文以滑动窗口为基础,用协方差矩阵作为时间序列的描述子,将黎曼流形与统计过程控制图相结合,来实现多元时间序列的异常检测及其可视化。以MA模拟数据流和MIT-BIH的心电失常数据作为实验对象,对异常检测方法进行了验证,结果表明该方法是合理有效的。更多还原

【Abstract】 Multivariate time series problems widely exist in production and life in the society.Anomaly detection has provided people with a lot of valuable information in financial,hydrological,meteorological fields,and the research areas of earthquake,video surveillance,medicine and others.In order to quickly and efficiently find exceptions in time sequence so that it can be presented in front of people in an intuitive way,we in this study combined the Riemannian manifold with statistical process control charts,based on sliding window,with a description of the covariance matrix as the time sequence,to achieve the multivariate time series of anomaly detection and its visualization.We made MA analog data flow and abnormal electrocardiogram data from MIT-BIH as experimental objects,and verified the anomaly detection method.The results showed that the method was reasonable and effective.更多还原