异常检测
计算机科学
模式识别(心理学)
多元统计
代表(政治)
变压器
系列(地层学)
嵌入
人工智能
时间序列
时频分析
数据挖掘
机器学习
工程类
计算机视觉
电压
电气工程
滤波器(信号处理)
古生物学
政治
生物
法学
政治学
作者
Shuxin Qin,Jing Zhu,Dan Wang,Liang Ou,Hongxin Gui,Gaofeng Tao
标识
DOI:10.1109/bigdata55660.2022.10021063
摘要
Unsupervised anomaly detection for multivariate time series has been an active area of research due to its enormous potential for industrial applications. Existing works have made extraordinary progress in time series representation, reconstruction and forecasting. However, the intricate temporal patterns of individual signals and the relationships between different signals are rarely explicitly considered, which limits the performance. To this end, we propose a novel approach based on Transformer and signal decomposition for time series anomaly detection. Specifically, we provide a multi-view embedding method to capture temporal and correlational features of signals. To take full advantage of temporal patterns, we design a frequency attention module to extract periodic oscillation features. Then, the signals are decomposed into seasonal, trend and remainder components for further representation separately. Additionally, we employ a optimization strategy to improve feature representation. Extensive experiments on various public benchmarks demonstrate that our method has achieved the state-of-the-art performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI