Multi-domain convolutional neural networks for lower-limb motor imagery using dry vs. Wet electrodes

Ji Hyeok Jeong, Junhyuk Choi, Keun Tae Kim, Song Joo Lee, Dong Joo Kim, Hyungmin Kim

Research output: Contribution to journalArticlepeer-review

Abstract

Motor imagery (MI) brain–computer interfaces (BCIs) have been used for a wide variety of applications due to their intuitive matching between the user’s intentions and the performance of tasks. Applying dry electroencephalography (EEG) electrodes to MI BCI applications can resolve many con-straints and achieve practicality. In this study, we propose a multi-domain convolutional neural networks (MD-CNN) model that learns subject-specific and electrode-dependent EEG features using a multi-do-main structure to improve the classification accuracy of dry electrode MI BCIs. The proposed MD-CNN model is composed of learning layers for three domain representations (time, spatial, and phase). We first evaluated the proposed MD-CNN model using a public dataset to confirm 78.96% classification accuracy for multi-class classification (chance level accuracy: 30%). After that, 10 healthy subjects participated and performed three classes of MI tasks related to lower-limb movement (gait, sitting down, and resting) over two sessions (dry and wet electrodes). Consequently, the proposed MD-CNN model achieved the high-est classification accuracy (dry: 58.44%; wet: 58.66%; chance level accuracy: 43.33%) with a three-class classifier and the lowest difference in accuracy between the two electrode types (0.22%, d = 0.0292) com-pared with the conventional classifiers (FBCSP, EEGNet, ShallowConvNet, and DeepConvNet) that used only a single domain. We expect that the proposed MD-CNN model could be applied for developing robust MI BCI systems with dry electrodes.

Original languageEnglish
Article number6672
JournalSensors
Volume21
Issue number19
DOIs
Publication statusPublished - 2021 Oct 1

Keywords

  • Brain–computer interfaces
  • Electrodes
  • Electroencephalography
  • Lower limb
  • Motor imagery
  • Multilayer neural network
  • Neural networks

ASJC Scopus subject areas

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Multi-domain convolutional neural networks for lower-limb motor imagery using dry vs. Wet electrodes'. Together they form a unique fingerprint.

Cite this