Classification of independent components of EEG into multiple artifact classes

Authors

  • Laura Frølich,

    Corresponding author
    1. Section for Cognitive Systems, DTU Compute, Technical University of Denmark, Lyngby, Denmark
    • Address correspondence to: Laura Frølich, Section for Cognitive Systems, DTU Compute, Technical University of Denmark, Matematiktorvet, Building 321, 2800 Kgs. Lyngby, Denmark. E-mail: lffr@dtu.dk

    Search for more papers by this author
  • Tobias S. Andersen,

    1. Section for Cognitive Systems, DTU Compute, Technical University of Denmark, Lyngby, Denmark
    Search for more papers by this author
  • Morten Mørup

    1. Section for Cognitive Systems, DTU Compute, Technical University of Denmark, Lyngby, Denmark
    Search for more papers by this author

  • We would like to express our gratitude to Julie Onton, Klaus Gramann, and Thomas Toellner for the use of their data, without which this study would not have been possible. Laura Frølich would also like to thank Scott Makeig for hosting her at the Swartz Center for Computational Neuroscience and for discussions about IC classification, and Christian Kothe for discussions and aid with programming. We would also like to thank two anonymous reviewers for their constructive comments, which have improved the manuscript.

Abstract

In this study, we aim to automatically identify multiple artifact types in EEG. We used multinomial regression to classify independent components of EEG data, selecting from 65 spatial, spectral, and temporal features of independent components using forward selection. The classifier identified neural and five nonneural types of components. Between subjects within studies, high classification performances were obtained. Between studies, however, classification was more difficult. For neural versus nonneural classifications, performance was on par with previous results obtained by others. We found that automatic separation of multiple artifact classes is possible with a small feature set. Our method can reduce manual workload and allow for the selective removal of artifact classes. Identifying artifacts during EEG recording may be used to instruct subjects to refrain from activity causing them.

Ancillary