A Deep Autoencoder based Outlier Detection for Time Series

摘要：

　　Time series outlier detection is an important topic in data mining,having significant applications in reality.Due to the complexity and dynamics of time series,it is quite difficult to detect outlier in time series.Particularly,influenced by outside factors,time series are usually unpredictable,accompanied with concept drift.Recently,recurrent neural network has been used to identify time series outlier,and demonstrated great potential.However,RNN usually uses deterministic state transition structure,which cannot characterize the variability of high-dimensional time series.This paper proposes to incorporate latent variables into RNN,aiming to catch the time series variability as much as possible.In particular,our method combines RNN and variation auto-encoder framework.We evaluate our method with several real datasets,and demonstrate that our method has superior detecting performance.

关键词： outlier detection time series variation auto-encoder machine learning virtual assets

作者: Jin Wang Fang Miao Lei You Wenjie Fan

作者单位: School of Information Science & Technology,Chengdu University,2025 Chengluo Rd.,Chengdu,Sichuan,Chin Institute of Big Data,Chengdu University,2025 Chengluo Rd.,Chengdu,Sichuan,China

会议类型: 国际会议

会议名称: 2018 3rd International Conference on Computer Science and Information Engineering (ICCSIE 2018) 2018第三届计算机科学与信息工程国际会议(ICCSIE 2018)

会议地点: 西安

会议语种:英文

页码: 294-298

在线出版日期: 2018-09-21（万方平台首次上网日期，不代表论文的发表时间）