Multiclass Classification of EEG Motor Imagery Signals Based on Transfer Learning

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

2 Scopus citations

Abstract

Multiclass Classification of EEG signal is essential for brain computer interface (BCI) applications but extremely time consuming. We proposed a subject-weighted adaptive transfer learning method in conjunction with MLP and CNN classifiers for fast classification of multiclass EEG dataset.Analytic results show that CNN generally outperforms MLP in this multi-class classification. The use of transfer learning is efficient for building the predictive model without decreasing the accuracy and 2D CNN is more robust to between-subject variabilities.

Original languageEnglish
Title of host publicationProceedings of the 2022 8th International Conference on Applied System Innovation, ICASI 2022
EditorsShoou-Jinn Chang, Sheng-Joue Young, Artde Donald Kin-Tak Lam, Liang-Wen Ji, Stephen D. Prior
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages140-143
Number of pages4
ISBN (Electronic)9781665496506
DOIs
StatePublished - 2022
Event8th International Conference on Applied System Innovation, ICASI 2022 - Nantou, Taiwan
Duration: 21 Apr 202223 Apr 2022

Publication series

NameProceedings of the 2022 8th International Conference on Applied System Innovation, ICASI 2022

Conference

Conference8th International Conference on Applied System Innovation, ICASI 2022
Country/TerritoryTaiwan
CityNantou
Period21/04/2223/04/22

Keywords

  • Deep Learning
  • EEG
  • Transfer Learning
  • multi-category classification

Fingerprint

Dive into the research topics of 'Multiclass Classification of EEG Motor Imagery Signals Based on Transfer Learning'. Together they form a unique fingerprint.

Cite this