moabb.datasets.Huebner2018#

class moabb.datasets.Huebner2018(interval=None, raw_slice_offset=None, use_blocks_as_sessions=True)[source]#

Mixture of LLP and EM for a visual matrix speller (ERP) dataset from Hübner et al 2018 [1].

PapersWithCode leaderboard: https://paperswithcode.com/dataset/huebner2018-moabb

Dataset summary

#Subj

#Chan

#Trials / class

Trials length

Sampling rate

#Sessions

12

31

364 NT / 112 T

0.9s

1000Hz

3

Dataset description

Within a single session, a subject was asked to spell the beginning of a sentence in each of three blocks.The text consists of the 35 symbols “Franzy jagt im Taxi quer durch das ”. Each block, one of the three decoding algorithms (EM, LLP, MIX) was used in order to guess the attended symbol. The order of the blocks was pseudo-randomized over subjects, such that each possible order of the three decoding algorithms was used twice. This randomization should reduce systematic biases by order effects or temporal effects, e.g., due to fatigue or task-learning.

A trial describes the process of spelling one character. Each of the 35 trials per block contained 68 highlighting events. The stimulus onset asynchrony (SOA) was 250 ms and the stimulus duration was 100 ms leading to an interstimulus interval (ISI) of 150 ms.

Parameters

  • interval (array_like) – range/interval in milliseconds in which the brain response/activity relative to an event/stimulus onset lies in. Default is set to [-.2, .7].

  • raw_slice_offset (int, None) – defines the crop offset in milliseconds before the first and after the last event (target or non-targeet) onset. Default None which crops with an offset 2,000 ms.

References

1

Huebner, D., Verhoeven, T., Mueller, K. R., Kindermans, P. J., & Tangermann, M. (2018). Unsupervised learning for brain-computer interfaces based on event-related potentials: Review and online comparison [research frontier]. IEEE Computational Intelligence Magazine, 13(2), 66-77. https://doi.org/10.1109/MCI.2018.2807039

New in version 0.4.5.