[Eeglablist] New P300 BCI dataset (multi-session and multi-subject)

[Marco Simões]

Dear colleagues,

I would like to share with you the BCIAUT-P300 dataset, that we have just
published in Frontiers in Neuroscience:
https://urldefense.com/v3/__https://www.frontiersin.org/articles/10.3389/fnins.2020.568104/full__;!!Mih3wA!SiwAgbwLG3S_54NAcfOIowD-d7akDgYHaBdDcdiOdrhstfjWFRvRDp5u7uvDhyz7TvjErw$ 

It is composed by EEG data from 15 participants with Autism Spectrum
Disorder performing 7 sessions of a P300-based Brain-Computer Interface
(BCI) intervention specifically designed for joint attention training.

The article provides benchmark results from 9 teams which competed to
achieve the best possible decoding accuracy during the recent IFMBE
Scientific Challenge <https://urldefense.com/v3/__https://www.medicon2019.org/scientific-challenge/__;!!Mih3wA!SiwAgbwLG3S_54NAcfOIowD-d7akDgYHaBdDcdiOdrhstfjWFRvRDp5u7uvDhyxCkTqv9Q$ >,
with the winning team obtaining about 92% accuracy.

We hope this can help the research community to target the challenges
related to inter-session and inter-subject variability in P300-based BCIs,
reducing calibration times or developing calibration-free systems.

You can access the data in https://urldefense.com/v3/__https://www.kaggle.com/disbeat/bciaut-p300__;!!Mih3wA!SiwAgbwLG3S_54NAcfOIowD-d7akDgYHaBdDcdiOdrhstfjWFRvRDp5u7uvDhywT35bIGQ$ . Any
doubt or question you might have please feel free to contact me.

Best regards,

Marco Simões
Assistant Professor
Department of Informatics Engineering
University of Coimbra, Portugal