Riemannian classification of EEG signals with missing values

Alexandre Hippert-Ferrer (1) , Ammar Mian (2) , Florent Bouchard (1) , Frédéric Pascal (1)

1 L2S - Laboratoire des signaux et systèmes
2 LISTIC - Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance

This paper proposes a strategy to handle missing data for the classification of electroencephalograms using covariance matrices. It relies on the observed-data likelihood within an expectation-maximization algorithm. This approach is compared to two existing state-of-the-art methods: (i) covariance matrices computed with imputed data; (ii) Riemannian averages of partially observed covariance matrix. All approaches are combined with the minimum distance to Riemannian mean classifier and applied to a classification task of two widely known paradigms of brain-computer interfaces. In addition to be applicable for a wider range of missing data scenarios, the proposed strategy generally performs better than other methods on the considered real EEG data.

Mots clés: Missing data; Electroencephalography; Brain-computer interfaces; Covariance estimation; Riemannian geometry

Domaines: Machine Learning [stat.ML]; Traitement du signal et de l'image [eess.SP]

Alexandre Hippert-Ferrer, Ammar Mian, Florent Bouchard, Frédéric Pascal. Riemannian classification of EEG signals with missing values. 30th European Signal Processing Conference (EUSIPCO 2022), Aug 2022, Belgrade, Serbia. ⟨10.23919/eusipco55093.2022.9909703⟩. ⟨hal-03856816⟩