Classification of independent components of EEG into multiple artifact classes

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