Automated rejection and repair of bad trials in MEG/EEG - Archive ouverte HAL Access content directly
Conference Papers Year :

Automated rejection and repair of bad trials in MEG/EEG


We present an automated solution for detecting bad trials in magneto-/electroencephalography (M/EEG). Bad trials are commonly identified using peak-to-peak rejection thresholds that are set manually. This work proposes a solution to determine them automatically using cross-validation. We show that automatically selected rejection thresholds perform at par with manual thresholds, which can save hours of visual data inspection. We then use this automated approach to learn a sensor-specific rejection threshold. Finally, we use this approach to remove trials with finer precision and/or partially repair them using interpolation. We illustrate the performance on three public datasets. The method clearly performs better than a competitive benchmark on a 19-subject Faces dataset.
Fichier principal
Vignette du fichier
automated-rejection-repair.pdf (725.17 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01313458 , version 1 (10-05-2016)


  • HAL Id : hal-01313458 , version 1


Mainak Jas, Denis Engemann, Federico Raimondo, Yousra Bekhti, Alexandre Gramfort. Automated rejection and repair of bad trials in MEG/EEG. 6th International Workshop on Pattern Recognition in Neuroimaging (PRNI), Jun 2016, Trento, Italy. ⟨hal-01313458⟩
341 View
1962 Download


Gmail Facebook Twitter LinkedIn More