Nonstationary Brain Source Separation for Multiclass Motor Imagery

• Published in: IEEE transactions on biomedical engineering 2010-02, Vol.57 (2), p.469-478
• Main Authors: Gouy-Pailler, CÉdric, Congedo, Marco, Brunner, Clemens, Jutten, Christian, Pfurtscheller, Gert
• Format: Article
• Language: English
• Subjects: Algorithms; Analysis of Variance; Biological and medical sciences; Blind source separation; Brain; Brain - physiology; Brain > computer interfaces (BCIs); Bridges; Electroencephalography; Electroencephalography - methods; Filtering; Fundamental and applied biological sciences. Psychology; Humans; Imagination - physiology; joint approximate diagonalization (JAD); Laboratories; Man-Machine Systems; Motor Activity; Motor control and motor pathways. Reflexes. Control centers of vegetative functions. Vestibular system and equilibration; multiclass motor imagery (MI); Psychomotor Performance; Reproducibility of Results; Sensor arrays; Signal Processing, Computer-Assisted; Source separation; Speech; Vertebrates: nervous system and sense organs
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2009.2032162

This paper describes a method to recover task-related brain sources in the context of multiclass brain--computer interfaces (BCIs) based on noninvasive EEG. We extend the method joint approximate diagonalization (JAD) for spatial filtering using a maximum likelihood framework. This generic formulation: 1) bridges the gap between the common spatial patterns (CSPs) and blind source separation of nonstationary sources; and 2) leads to a neurophysiologically adapted version of JAD, accounting for the successive activations/deactivations of brain sources during motor imagery (MI) trials. Using dataset 2a of BCI Competition IV (2008) in which nine subjects were involved in a four-class two-session MI-based BCI experiment, a quantitative evaluation of our extension is provided by comparing its performance against JAD and CSP in the case of cross-validation, as well as session-to-session transfer. While JAD, as already proposed in other works, does not prove to be significantly better than classical one-versus-rest CSP, our extension is shown to perform significantly better than CSP for cross-validated and session-to-session performance. The extension of JAD introduced in this paper yields among the best session-to-session transfer results presented so far for this particular dataset; thus, it appears to be of great interest for real-life BCIs.