Univariate Time Series Data Correction Method using LSTM Autoencoder with Temporal Distance

Sohyeon Yun, Han Joon Kim

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

Abstract

High-quality data is essential to increase the reliability of machine learning-based prediction models. For time series data, anomalies significantly reduce the accuracy of prediction models. In this paper, we propose a novel time series data correction method that converts abnormal values of univariate time series data into normal ones. For anomaly detection and correction, we utilize the LSTM Autoencoder model, where we propose a new weight function that considers temporal distance. Through experiments using the open NAB data, we show that our proposed method is superior to the recent conventional methods.

Original languageEnglish
Title of host publication6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages648-652
Number of pages5
ISBN (Electronic)9798350344349
DOIs
StatePublished - 2024
Event6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024 - Osaka, Japan
Duration: 19 Feb 202422 Feb 2024

Publication series

Name6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024

Conference

Conference6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024
Country/TerritoryJapan
CityOsaka
Period19/02/2422/02/24

Keywords

  • anomaly detection
  • data correction
  • data quality
  • deep learning
  • LSTM Autoencoder
  • time series data

Fingerprint

Dive into the research topics of 'Univariate Time Series Data Correction Method using LSTM Autoencoder with Temporal Distance'. Together they form a unique fingerprint.

Cite this