Anomaly Detection for Univariate Time Series with Statistics and Deep Learning

Jian Bin Kao, Jehn Ruey Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

This paper proposes an anomaly detection framework for univariate time series data. Based on the Dickey-Fuller test, fast Fourier transform (FFT), and Pearson product-moment correlation coefficient, data are classified into three classes, namely (1) stationary, (2) periodic and (3) non-stationary and non-periodic time series. Different schemes using statistics and gated recurrent unit (GRU) deep learning concepts are applied to different class of time series for performing anomaly detection. The proposed framework outperforms related methods, namely STL, SARIMA, LSTM, LSTM with STL, and ADSaS, in almost all measurements for five Numenta Anomaly Benchmark(NAB) datasets.

Original languageEnglish
Title of host publication2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages404-407
Number of pages4
ISBN (Electronic)9781728125015
DOIs
StatePublished - Oct 2019
Event2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019 - Yunlin, Taiwan
Duration: 3 Oct 20196 Oct 2019

Publication series

Name2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019

Conference

Conference2019 IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2019
Country/TerritoryTaiwan
CityYunlin
Period3/10/196/10/19

Keywords

  • anomaly detection
  • deep learning
  • gated recurrent unit neural network
  • time series

Fingerprint

Dive into the research topics of 'Anomaly Detection for Univariate Time Series with Statistics and Deep Learning'. Together they form a unique fingerprint.

Cite this