A multi-task learning approach for the extraction of single-trial evoked potentials

作者：D' Avanzo Costanza; Goljahani Anahita; Pillonetto Gianluigi; De Nicolao Giuseppe; Sparacino Giovanni^*

来源：Computer Methods and Programs in Biomedicine, 2013, 110(2): 125-136.

DOI：10.1016/j.cmpb.2012.11.001

• Bayesian estimation
• Population approach
• P300
• Single-trial
• Mixed effect models
• Multilevel models

Evoked potentials (EPs) are of great interest in neuroscience, but their measurement is difficult as they are embedded in background spontaneous electroencephalogaphic (EEG) activity which has a much larger amplitude. The widely used averaging technique requires the delivery of a large number of identical stimuli and yields only an %26quot;average%26quot; EP which does not allow the investigation of the possible variability of single-trial EPs. In the present paper, we propose the use of a multi-task learning method (MTL) for the simultaneous extraction of both the average and the N single-trial EPs from N recorded sweeps. The technique is developed within a Bayesian estimation framework and uses flexible stochastic models to describe the average response and the N shifts between the single-trial EPs and this average. Differently from other single-trial estimation approaches proposed in the literature, MTL can provide estimates of both the average and the N single-trial EPs in a single stage. In the present paper, MTL is successfully assessed on both synthetic (100 simulated recording sessions with N = 20 sweeps) and real data (11 subjects with N = 20 sweeps) relative to a cognitive task carried out for the investigation of the P300 component of the EP.

• 出版日期2013-5