Transform based feature construction utilizing magnitude and phase for convolutional neural network in EEG signal classification

Jeonghyun Kim, Yongkoo Park, Wonzoo Chung

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

Abstract

Extracting relevant feature and classification are significant in brain-computer interface (BCI) systems. Deep learning have achieved remarkable growth in many fields like speech recognition and computer vision. However, deep learning in biomedical field is yet to be fully utilized. In this paper, We propose a novel methodology for convolutional neural network (CNN) based motor imagery (MI) classification using new form of input. Continuous Wavelet Transform (CWT) is applied to the input Electroencephalography (EEG) signal to extract the features of MI. After transformation, we consider the real part and imaginary part of the transformed signal to exploit magnitude and phase information at the same time. This feature is fed to the CNN having one convolution layer, one max-pooling layer and one fully connected layer. The classification accuracy is tested on two public BCI datasets: BCI competition IV dataset IIb and BCI competition II dataset III. The proposed method shows increase in classification accuracy compared to other MI classification methods. The results show that the method using CNN with magnitude and phase based features can be better than other state-of-the-art approaches.

Original languageEnglish
Title of host publication8th International Winter Conference on Brain-Computer Interface, BCI 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728147079
DOIs
Publication statusPublished - 2020 Feb
Event8th International Winter Conference on Brain-Computer Interface, BCI 2020 - Gangwon, Korea, Republic of
Duration: 2020 Feb 262020 Feb 28

Publication series

Name8th International Winter Conference on Brain-Computer Interface, BCI 2020

Conference

Conference8th International Winter Conference on Brain-Computer Interface, BCI 2020
CountryKorea, Republic of
CityGangwon
Period20/2/2620/2/28

Keywords

  • brain-computer interface (BCI)
  • convolutional neural network (CNN)
  • electroencephalography (EEG)
  • motor imagery (MI)

ASJC Scopus subject areas

  • Behavioral Neuroscience
  • Cognitive Neuroscience
  • Artificial Intelligence
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Transform based feature construction utilizing magnitude and phase for convolutional neural network in EEG signal classification'. Together they form a unique fingerprint.

  • Cite this

    Kim, J., Park, Y., & Chung, W. (2020). Transform based feature construction utilizing magnitude and phase for convolutional neural network in EEG signal classification. In 8th International Winter Conference on Brain-Computer Interface, BCI 2020 [9061635] (8th International Winter Conference on Brain-Computer Interface, BCI 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BCI48061.2020.9061635