IPMI 2013 - LNCS 7917

Learning from M/EEG Data with Variable Brain Activation Delays

Wojciech Zaremba^{1, 2}, M. Pawan Kumar^{1, 2, 3}, Alexandre Gramfort^{4, 5}, and Matthew B. Blaschko^{1, 2, 3}

¹Center for Visual Computing, École Centrale Paris, Châtenay-Malabry, France

²INRIA Saclay–Île-de-France, France

³Université Paris-Est, LIGM (UMR CNRS), École des Ponts ParisTech, France

⁴Institut Mines-Télécom, Télécom ParisTech, CNRS LTCI, Paris, France

⁵CEA/Neurospin, bât 145, 91191, Gif-Sur-Yvette, France

Abstract. Magneto- and electroencephalography (M/EEG) measure the electromagnetic signals produced by brain activity. In order to address the issue of limited signal-to-noise ratio (SNR) with raw data, acquisitions consist of multiple repetitions of the same experiment. An important challenge arising from such data is the variability of brain activations over the repetitions. It hinders statistical analysis such as prediction performance in a supervised learning setup. One such confounding variability is the time offset of the peak of the activation, which varies across repetitions. We propose to address this misalignment issue by explicitly modeling time shifts of different brain responses in a classification setup. To this end, we use the latent support vector machine (LSVM) formulation, where the latent shifts are inferred while learning the classifier parameters. The inferred shifts are further used to improve the SNR of the M/EEG data, and to infer the chronometry and the sequence of activations across the brain regions that are involved in the experimental task. Results are validated on a long term memory retrieval task, showing significant improvement using the proposed latent discriminative method.

Keywords: magnetoencephalography (MEG), electroencephalograpy (EEG), Latent SVM, classification, independant component analysis (ICA), functional connectivity, single-trial variability

LNCS 7917, p. 414 ff.

Full article in PDF | BibTeX