Extracting latent brain states - Towards true labels in cognitive neuroscience experiments

Anne K. Porbadnigk, Nico Görnitz, Claudia Sannelli, Alexander Binder, Mikio Braun, Marius Kloft, Klaus Muller

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Neuroscientific data is typically analyzed based on the behavioral response of the participant. However, the errors made may or may not be in line with the neural processing. In particular in experiments with time pressure or studies where the threshold of perception is measured, the error distribution deviates from uniformity due to the structure in the underlying experimental set-up. When we base our analysis on the behavioral labels as usually done, then we ignore this problem of systematic and structured (non-uniform) label noise and are likely to arrive at wrong conclusions in our data analysis. This paper contributes a remedy to this important scenario: we present a novel approach for a) measuring label noise and b) removing structured label noise. We demonstrate its usefulness for EEG data analysis using a standard d2 test for visual attention (N= 20 participants).

Original languageEnglish
Pages (from-to)225-253
Number of pages29
JournalNeuroImage
Volume120
DOIs
Publication statusPublished - 2015

Fingerprint

Noise
Brain
Electroencephalography
Cognitive Neuroscience

Keywords

  • Brain-computer interfaces
  • EEG
  • Systematic label noise
  • Unsupervised learning

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Porbadnigk, A. K., Görnitz, N., Sannelli, C., Binder, A., Braun, M., Kloft, M., & Muller, K. (2015). Extracting latent brain states - Towards true labels in cognitive neuroscience experiments. NeuroImage, 120, 225-253. https://doi.org/10.1016/j.neuroimage.2015.05.078

Extracting latent brain states - Towards true labels in cognitive neuroscience experiments. / Porbadnigk, Anne K.; Görnitz, Nico; Sannelli, Claudia; Binder, Alexander; Braun, Mikio; Kloft, Marius; Muller, Klaus.

In: NeuroImage, Vol. 120, 2015, p. 225-253.

Research output: Contribution to journalArticle

Porbadnigk, AK, Görnitz, N, Sannelli, C, Binder, A, Braun, M, Kloft, M & Muller, K 2015, 'Extracting latent brain states - Towards true labels in cognitive neuroscience experiments', NeuroImage, vol. 120, pp. 225-253. https://doi.org/10.1016/j.neuroimage.2015.05.078
Porbadnigk, Anne K. ; Görnitz, Nico ; Sannelli, Claudia ; Binder, Alexander ; Braun, Mikio ; Kloft, Marius ; Muller, Klaus. / Extracting latent brain states - Towards true labels in cognitive neuroscience experiments. In: NeuroImage. 2015 ; Vol. 120. pp. 225-253.
@article{843fe5096f3b41e7b40c0439fe1a7e7a,
title = "Extracting latent brain states - Towards true labels in cognitive neuroscience experiments",
abstract = "Neuroscientific data is typically analyzed based on the behavioral response of the participant. However, the errors made may or may not be in line with the neural processing. In particular in experiments with time pressure or studies where the threshold of perception is measured, the error distribution deviates from uniformity due to the structure in the underlying experimental set-up. When we base our analysis on the behavioral labels as usually done, then we ignore this problem of systematic and structured (non-uniform) label noise and are likely to arrive at wrong conclusions in our data analysis. This paper contributes a remedy to this important scenario: we present a novel approach for a) measuring label noise and b) removing structured label noise. We demonstrate its usefulness for EEG data analysis using a standard d2 test for visual attention (N= 20 participants).",
keywords = "Brain-computer interfaces, EEG, Systematic label noise, Unsupervised learning",
author = "Porbadnigk, {Anne K.} and Nico G{\"o}rnitz and Claudia Sannelli and Alexander Binder and Mikio Braun and Marius Kloft and Klaus Muller",
year = "2015",
doi = "10.1016/j.neuroimage.2015.05.078",
language = "English",
volume = "120",
pages = "225--253",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Extracting latent brain states - Towards true labels in cognitive neuroscience experiments

AU - Porbadnigk, Anne K.

AU - Görnitz, Nico

AU - Sannelli, Claudia

AU - Binder, Alexander

AU - Braun, Mikio

AU - Kloft, Marius

AU - Muller, Klaus

PY - 2015

Y1 - 2015

N2 - Neuroscientific data is typically analyzed based on the behavioral response of the participant. However, the errors made may or may not be in line with the neural processing. In particular in experiments with time pressure or studies where the threshold of perception is measured, the error distribution deviates from uniformity due to the structure in the underlying experimental set-up. When we base our analysis on the behavioral labels as usually done, then we ignore this problem of systematic and structured (non-uniform) label noise and are likely to arrive at wrong conclusions in our data analysis. This paper contributes a remedy to this important scenario: we present a novel approach for a) measuring label noise and b) removing structured label noise. We demonstrate its usefulness for EEG data analysis using a standard d2 test for visual attention (N= 20 participants).

AB - Neuroscientific data is typically analyzed based on the behavioral response of the participant. However, the errors made may or may not be in line with the neural processing. In particular in experiments with time pressure or studies where the threshold of perception is measured, the error distribution deviates from uniformity due to the structure in the underlying experimental set-up. When we base our analysis on the behavioral labels as usually done, then we ignore this problem of systematic and structured (non-uniform) label noise and are likely to arrive at wrong conclusions in our data analysis. This paper contributes a remedy to this important scenario: we present a novel approach for a) measuring label noise and b) removing structured label noise. We demonstrate its usefulness for EEG data analysis using a standard d2 test for visual attention (N= 20 participants).

KW - Brain-computer interfaces

KW - EEG

KW - Systematic label noise

KW - Unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=84938242792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938242792&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2015.05.078

DO - 10.1016/j.neuroimage.2015.05.078

M3 - Article

C2 - 26067346

AN - SCOPUS:84938242792

VL - 120

SP - 225

EP - 253

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -