Missing Data Imputation Using Data Generated by GAN

Hanan Hammad Alharbi, Masaomi Kimura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Missing data is a common and challenging problem that arises in many research domains and led to the complication of data analysis. Therefore, handling missing data is a necessity as proposed in many previous studies. In this paper, we proposed two methods to impute missing numerical datasets based on generated data by GAN and determine the imputed values using Euclidian distance. In various missing percentages, we evaluated the imputation accuracy of all methods using MAE and RMSE tests. The proposed methods randomGAN and meshGAN produce the best imputation accuracy in 2 out of 4 datasets against three compared methods: SimpleImputer, IterativeImputer, and KNNimputer.

Original languageEnglish
Title of host publicationICCBD 2020 - 2020 3rd International Conference on Computing and Big Data
Subtitle of host publicationWorkshop 2020 2nd International Conference on Computer, Software Engineering and Applications, CSEA 2020
PublisherAssociation for Computing Machinery
Pages73-77
Number of pages5
ISBN (Electronic)9781450387866
DOIs
Publication statusPublished - 2020 Aug 5
Event3rd International Conference on Computing and Big Data, ICCBD 2020 and its Workshop the 2020 2nd International Conference on Computer, Software Engineering and Applications, CSEA 2020 - Virtual, Online, Taiwan, Province of China
Duration: 2020 Aug 52020 Aug 7

Publication series

NameACM International Conference Proceeding Series

Conference

Conference3rd International Conference on Computing and Big Data, ICCBD 2020 and its Workshop the 2020 2nd International Conference on Computer, Software Engineering and Applications, CSEA 2020
Country/TerritoryTaiwan, Province of China
CityVirtual, Online
Period20/8/520/8/7

Keywords

  • GAN
  • KNNimputer
  • Machine learning
  • Missing data imputation

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'Missing Data Imputation Using Data Generated by GAN'. Together they form a unique fingerprint.

Cite this