Multiple time-lag canonical correlation analysis for removing muscular artifacts in EEG

In this work, a new approach for joint blind source separation (BSS) of datasets at multiple time lags using canonical correlation analysis (CCA) is developed for removing muscular artifacts from electroencephalogram (EEG) recordings. The proposed approach jointly extracts sources from each dataset in a decreasing order of between-set source correlations. Muscular artifact sources that typically have lowest between-set correlations can then be removed. It is shown theoretically that the proposed use of CCA on multiple datasets at multiple time lags achieves better BSS under a more relaxed condition and hence offers better performance in removing muscular artifacts than the conventional CCA. This is further demonstrated by experiments on real EEG data.